Big Data in Healthcare, Bioinformatics and Precision Medicine

Each individual has a unique and interacting set of genetic, lifestyle, and environmental factors that are reflected in their physical exam and laboratory biomarkers and significantly impact their experience of health. Patterns of nutrient deficiency signs and biomarker levels below health-promoting thresholds have been identified in national nutrition surveys. However, identifying these patterns remains a challenge in clinical medicine for many reasons, including clinician training and education, clinical time restraints, and the belief that these signs are both rare and recognizable only in cases of severe nutritional deficiencies. With an increased interest in prevention and limited resources for comprehensive diagnostic evaluations, a functional nutrition evaluation may augment patient-centered screening evaluations and personalized wellness programs. During LIFEHOUSE, we have documented physical exam, anthropometric, and biomarker findings that may increase the recognition of these wellness-challenging patterns in a population of 369 adult employees working in two occupational areas: administrative/sales and manufacturing/warehouse. Distinct and significant physical exam differences and constellations of biomarker abnormalities were identified. We present these patterns of physical exam findings, anthropometrics, and advanced biomarkers to assist clinicians in diagnostic and therapeutic interventions that may stem the loss of function that precedes the development of the non-communicable chronic diseases of aging. Full article

Sub-maximal physical load (sub-max) training is optimal for athletes. However, few methods can directly assess whether training is sub-max. Therefore, this study aimed to identify metrics that could assess sub-max training by predicting maximal physical load, helping athletes to avoid the risks associated with maximal training. Physiological data were collected from 30 participants in a bicycle incremental exercise experiment, including the R-R interval (RR), stroke volume (SV), breath-to-breath interval (BB), and breathing rate (BR). Sample Entropy (SampEn) analysis was used to assess the complexity of the physiological data. BR increased with exercise time but could not be used to identify the sub-max stage; however, SampEn BB could effectively identify the sub-max stage (p < 0.05), as could the novel indicators SampEn SV and cardiac output (p < 0.01). This study also identified the threshold value of each SampEn value in sub-max, which can be used as a sports science indicator to assess the load of athletes. The results suggest that SampEn-based indicators can be used to assess sub-max and maximal physical load. These findings can be used as a guide for quantitative exercise healthcare. Full article

Ena-VASP-like (EVL), a member of the Enabled/vasodilator stimulated phosphoprotein family, is functionally expressed in various cancers. This study explored the prognostic value and potential mechanism of EVL in pancreatic cancer (PC). RNA-seq obtained from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) databases were used to evaluate EVL expression differences, and clinical samples were collected for validation. The prognostic value of EVL was evaluated by survival data obtained from TCGA and clinical samples. The biological pathways involved in EVL were evaluated by functional enrichment analysis such as GO, KEGG, and GSEA. We used immune infiltration analysis to estimate the correlation between EVL and tumor-infiltrating immune cells (TICs). The expression of EVL is down-regulated in PC tissues, which is an independent factor affecting survival time. Survival analysis suggested EVL-high expression was associated with good prognosis in PC patients. The results of the enrichment analysis suggested that the biological function of EVL was closely related to the immune mechanism. Tumor immune infiltration analysis showed that high expression of EVL was accompanied by high levels of immune infiltration. Furthermore, EVL was strongly correlated with the content of immune cells such as CD8+ T cells, B cells, regulatory T cells, CD4+ Tem cells, and follicular Th cells. EVL is a potential independent prognostic marker and immunotherapy target for PC. Mechanistically, EVL may affect the prognosis by extensively promoting immune cell infiltration, including strengthening the anti-tumor immune response of CD8+ T cells. Full article

We evaluated the clinical features of patients admitted to the ED with acute vertigo, verifying symptoms after one month and one year to establish epidemiological factors and predictors of resolution. We reviewed 233 records of patients admitted to ED for acute vertigo (125 F and 85 M, mean age 56.12 years). We analyzed the correlation between time of resolution (at one month and one year) and symptoms duration (subjective and/or objective vertigo, instability, cervical pain, audiological, neurological, and neurovegetative symptoms), comorbidities, and therapies, the result of the clinical and instrumental vestibular examination. Resolution of acute vertigo occurred in 81.1%, while persistence of vertigo one year after ED access was reported in 18.8%. There were 135 patients who recovered in one month. The presence of instability, auditory and neurovegetative symptoms, and neck pain represents a significant factor for recovery within one year. Age over 65 and a history of hypertension are associated with a worst recovery. Patients with spontaneous Nystagmus or positive HIT showed a significant difference in symptoms recovery within one month and one year. Presence of positional Nystagmus represents a positive prognostic factor. Our findings emphasize the importance of clinical evaluation of the acute vertigo, helping the clinicians to define central or peripheral diagnosis and predict the resolution of vertigo. Full article

Purpose: Due to poor prognosis and immunotherapy failure of skin cutaneous melanoma (SKCM), this study sought to find necroptosis-related biomarkers to predict prognosis and improve the situation with predicted immunotherapy drugs. Experimental Design: The Cancer Genome Atlas (TCGA) and The Genotype-Tissue Expression Program (GTEx) database were utilized to recognize the differential necroptosis-related genes (NRGs). Univariate Cox (uni-Cox) and least absolute shrinkage and selection operator (LASSO) Cox analysis were utilized for prognostic signature establishment. The signature was verified in the internal cohort. To assess the signature’s prediction performance, the area under the curve (AUC) of receiver operating characteristic (ROC) curves, Kaplan-Meier (K-M) analyses, multivariate Cox (multi-Cox) regression, nomogram, and calibration curves were performed. The molecular and immunological aspects were also reviewed using single-sample gene set enrichment analysis (ssGSEA). Cluster analysis was performed to identify the different types of SKCM. Finally, the expression of the signature gene was verified by immunohistochemical staining. Results: On basis of the 67 NRGs, 4 necroptosis-related genes (FASLG, PLK1, EGFR, and TNFRSF21) were constructed to predict SKCM prognosis. The area’s 1-, 3-, and 5-year OS under the AUC curve was 0.673, 0.649, and 0.677, respectively. High-risk individuals had significantly lower overall survival (OS) compared to low-risk patients. Immunological status and tumor cell infiltration in high-risk groups were significantly lower, indicating an immune system that was suppressed. In addition, hot and cold tumors could be obtained by cluster analysis, which is helpful for accurate treatment. Cluster 1 was considered a hot tumor and more susceptible to immunotherapy. Immunohistochemical results were consistent with positive and negative regulation of coefficients in signature. Conclusion: The results of this finding supported that NRGs could predict prognosis and help make a distinction between the cold and hot tumors for improving personalized therapy for SKCM. Full article

A small number of robust studies have explored the association between cognitive tests and marital status levels of mild cognitive impairment (MCI) patients using the TADPOLE dataset. Rey Auditory Verbal Learning Test (RAVLT) cognition performance combined with marital status levels is associated with increased odds of MCI than either RAVLT in isolation. The cross-sectional association between RAVLT performance in immediate response, learning, forgetting, and perception of forgetting with marital status and MCI was evaluated using TADPOLE data. We included participants with MCI and normal cognition in our study. Based on our logistic regression model, four RAVLT subgroups are associated with MCI (low and high response performance, immediate response with learning, immediate response with learning and forgetting, immediate response with learning, forgetting, and perception of forgetting). We adjusted models for sex, age, race, marital status, education, ethnicity, APOE4 genotype, hippocampus, whole brain, ventricles, and ICV. A mean age of 77/67 years was observed in the sample (n = 6560), 44% of participants were females, and 58% had mild cognitive impairment. Subgroups whose ages are 61 to 70 (OR 0.26, 95% CI 0.15–0.45) and older (OR 0.07, 95% CI 0.04–0.12), as well as race: black/African American (OR 0.13, 95% CI 0.03–0.52), multiple races (OR 0.05, 95% CI 0.01–0.24), and never married (OR 0.2, 95% CI 0.12–0.34) were negatively associated with immediate response and forgetting subgroup tests. There is a need for studies that evaluate other cognitive tests in the TADPOLE dataset with missing data as a predictive tool that aligns with the factors associated with MCI. Full article

Gut microbes play a prominent role in many aspects of human health, as seen through the increasing number of related studies. The accumulation of intestinal-flora-related studies enables us to better understand the various relationships between human gut microbes and other factors that affect the human body. However, the existing database does not meet the requirements of scientists to browse or retrieve the latest and most comprehensive published data. Thus, a knowledge base containing data related to gut microbes with updates occurring in real time would be highly valuable. We present a knowledge base of consistently curated relationships between human gut microbes and disease. By continuously and automatically collecting papers published in mainstream journals and using deep learning and NLP methods for entity relationship identification, GDReBase has now integrated 3674 diseases, 687 microbes, 7068 relationships, and 13,553 pieces of evidence from 518,286 papers, a figure that will continue to grow. GDReBase is a convenient and comprehensive resource for gut microbiology research and can be accessed free of charge. Full article

Background: Previous studies have examined the link between blood metabolic biomarkers and risk of thyroid cancer, with inconclusive results. We performed a cohort study based on the Swedish Apolipoprotein-Related Mortality Risk (AMORIS) Cohort, including 561,388 individuals undergoing health examinations during 1985–1996 with a follow-up of >30 years. Methods: Newly diagnosed cases of thyroid cancer were identified from the Swedish Cancer Register. We assessed the associations of nine blood biomarkers of carbohydrate, lipid, and apolipoprotein metabolism measured at the time of health examinations with the subsequent risk of thyroid cancer and demonstrated the temporal trend of these biomarkers during the 30 years before diagnosis of thyroid cancer. Results: After multivariable adjustment, there was a lower risk of thyroid cancer, per standard deviation increase in total cholesterol (TC; HR 0.91; 95%CI 0.82–0.99) and HDL-C (HR 0.86; 95%CI 0.75–0.99). During the 20 to 30 years before diagnosis, patients with thyroid cancer, as a group, demonstrated constantly lower levels of TC and HDL-C, compared to controls. Further, patients with thyroid cancer demonstrated declining levels of these biomarkers during the ten years before diagnosis, whereas controls demonstrated stable or increasing levels. Conclusions: Taken together, we found blood levels of TC and HDL-C to be associated with the risk of thyroid cancer and that there was a declining level of metabolic biomarkers during the 10 years before diagnosis of thyroid cancer. Full article

The summary-data-based Mendelian randomization (SMR) method is gaining popularity in estimating the causal effect of an exposure on an outcome. In practice, the instrument SNP is often selected from the genome-wide association study (GWAS) on the exposure but no correction is made for such selection in downstream analysis, leading to a biased estimate of the effect size and invalid inference. We address this issue by using the likelihood derived from the sampling distribution of the estimated SNP effects in the exposure GWAS and the outcome GWAS. This likelihood takes into account how the instrument SNPs are selected. Since the effective sample size is 1, the asymptotic theory does not apply. We use a support for a profile likelihood as an interval estimate of the causal effect. Simulation studies indicate that this support has robust coverage while the confidence interval implied by the SMR method has lower-than-nominal coverage. Furthermore, the variance of the two-stage least squares estimate of the causal effect is shown to be the same as the variance used for SMR for one-sample data when there is no selection. Full article

Cuproptosis is a copper-induced form of mitochondrial cell death which is engaged in the proliferation and migration of a variety of tumors. Nevertheless, the role of cuproptosis in tumor microenvironment (TME) remodeling and antitumor therapy is still poorly understood. We characterized two diverse cuproptosis-associated molecular isoforms in CRC which exhibit distinct prognostic and TME characteristics. Subsequently, we constructed a cuproptosis-associated prognostic model containing five genes and divided the patients into a high CPS-score group and a low CPS-score group. Univariate and multivariate Cox analyses showed that the CPS score could be used as an independent prognostic factor. The nomogram, and its consequent calibration curves, indicated that this prognostic signature had good predictive power for CRC. The analysis of single-cell sequencing data showed the significant expression of HES4 and SPHK1 in various immune and stromal (including fibroblasts) cells. Further studies showed that tumor mutational burden (TMB), high microsatellite instability (MSI-H) ratio, immune checkpoint blockade (ICB), and human leukocyte antigen (HLA) gene expression all positively correlated with the CPS score, predicting a better reaction to immunotherapy in high CPS-core patients. The CPS score constructed from cuproptosis subtypes can be used as a predictive tool to evaluate the prognosis of CRC patients and their response to immunotherapy. Full article

Retinal vascular occlusions are a common cause of visual loss. The association between oral health and the risk of retinal vascular occlusions remains unknown. We investigated whether oral health was associated with the risk of retinal vascular occlusions. We conducted a retrospective cohort study including 138,484 participants who completed a national health screening program with an oral health examination from the National Health Insurance Service-National Health Screening Cohort (NHIS-HEALS) 2002–2015. Oral health markers, such as the presence of periodontitis, tooth loss, and dental caries, and the frequency of daily tooth brushing, were evaluated. The primary outcome was the occurrence of retinal vascular occlusions up to December 2015. In total, 2533 participants developed retinal vascular occlusions (215 with retinal artery occlusion, 1686 with retinal vein occlusion, 632 with unspecified retinal vascular occlusion). In the multivariable Cox regression analysis, periodontitis was an independent risk factor for retinal vascular occlusions (adjusted hazard ratio: 1.18; 95% confidence interval: 1.02–1.36; p = 0.024). Frequent tooth brushing was negatively associated with the risk of retinal vascular occlusions (adjusted hazard ratio: 0.89; 95% confidence interval: 0.80–0.98; p = 0.022). Improving oral hygiene may contribute to the attenuation of the risk of retinal vascular occlusions. Full article

Background: 60–70% of patients who die from breast cancer have lung metastases. However, there is a lack of readily available tools for accurate risk stratification in patients with breast cancer lung metastases (BCLM). Therefore, a web-based dynamic nomogram was developed for BCLM to quickly, accurately, and intuitively assess overall and cancer-specific survival rates. Methods: Patients diagnosed with BCLM between 2004 and 2016 were extracted from the Surveillance, Epidemiology, and Final Results (SEER) database. After excluding incomplete data, all patients were randomly assigned to training and validation cohorts (2:1). Patients’ basic clinical information, detailed pathological staging and treatment information, and sociological information were included in further analysis. Nomograms were constructed following the evaluations of the Cox regression model and verified using the concordance index (C-index), calibration curves, time-dependent receiver operating characteristic (ROC) curves, and decision curve analysis (DCA). Web-based dynamic nomograms were published online. Results: 3916 breast cancer patients with lung metastases were identified from the SEER database. Based on multivariate Cox regression analysis, overall survival (OS) and cancer-specific survival (CSS) are significantly correlated with 13 variables: age, marital status, race, grade, T stage, surgery, chemotherapy, bone metastatic, brain metastatic, liver metastatic, estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor-2 (HER2). These are included in the construction of the nomogram of OS and CSS. The time-dependent receiver operating characteristic curve, decision curve analysis, consistency index, and calibration curve prove the distinct advantages of the nomogram. Conclusions: Our web-based dynamic nomogram effectively integrates patient molecular subtype and sociodemographic characteristics with clinical characteristics and guidance and can be easily used. ER-Negative should receive attention in diagnosing and treating BCLM. Full article

Background: Non-small cell lung cancer (NSCLC) is still one of the types of cancer with the highest death rates. MicroRNAs (miRNAs) play essential roles in NSCLC development. This study evaluates miRNA expression patterns and specific mechanisms in male patients with NSCLC. Methods: We report an integrated microarray analysis of miRNAs for eight matched samples of males with NSCLC compared to the study of public datasets of males with NSCLC from TCGA, followed by qRT-PCR validation. Results: For the TCGA dataset, we identified 385 overexpressed and 75 underexpressed miRNAs. Our cohort identified 54 overexpressed and 77 underexpressed miRNAs, considering a fold-change (FC) of ±1.5 and p < 0.05 as the cutoff value. The common miRNA signature consisted of eight overexpressed and nine underexpressed miRNAs. Validation was performed using qRT-PCR on the tissue samples for miR-183-3p and miR-34c-5p and on plasma samples for miR-34c-5p. We also created mRNA-miRNA regulatory networks to identify critical molecules, revealing NSCLC signaling pathways related to underexpressed and overexpressed transcripts. The genes targeted by these transcripts were correlated with overall survival. Conclusions: miRNAs and some of their target genes could play essential roles in investigating the mechanisms involved in NSCLC evolution and provide opportunities to identify potential therapeutic targets. Full article

A body shape index (ABSI) is an abdominal obesity index developed based on epidemiological statistics and designed to correlate minimally with body mass index (BMI). We examined the approximation between ABSI and other abdominal obesity indices based on biophysical concepts. The cross-sectional data from 62,514 Japanese urban residents were analyzed. Body adiposity indices comprising BMI, waist circumference (WC), ABSI, conicity index (CI), waist-to-height ratio (WHtR), and WC/BMI ratio were examined. ABSI and CI more strongly correlated with age and arterial stiffness assessed by cardio-ankle vascular index (CAVI) compared to the other indices. The discriminative power for high CAVI (≥9.0) was the strongest for ABSI followed by CI and other indices, in that order. The range and distribution of WC corresponding to the cutoff of ABSI (0.0801), or CI (1.23) seemed reasonable. The correlation between ABSI and CI was the strongest compared to any other combination of indices. CI correlated moderately with BMI, whereas ABSI correlated minimally with BMI. ABSI correlates strongly and approximates closely with CI. Hence, ABSI may be considered to reflect the degree of body shape change from cylindricity to conicity and is currently the only abdominal obesity index not affected by the obesity paradox. Full article

The association between acute pancreatitis (AP) and gastrointestinal cancers in diabetic patients is currently not well understood. The study aim was to investigate the association between AP and gastrointestinal cancers in diabetic patients. Data from the Korean National Health Insurance Service database were analyzed. Participants with diabetes who underwent a health examination between 2009 and 2012 were followed up till December 2018. The primary outcome was the occurrence of gastrointestinal cancer. A total of 2,263,184 patients were included in the final analysis. Patients with a history of AP (n = 2390) were found to have a significantly higher risk of gastrointestinal cancer, except for esophageal cancer, as follows: gastric cancer (aHR = 1.637, 95% CI: 1.323–2.025), colorectal cancer (aHR = 2.183, 95% CI: 1.899–2.51), liver cancer (aHR = 2.216, 95% CI: 1.874–2.621), pancreatic cancer (aHR = 4.558, 95% CI: 4.078–5.095), bile duct cancer (aHR = 3.996, 95% CI: 3.091–5.269), and gallbladder cancer (aHR = 2.445, 95% CI: 1.459–4.099). The history of AP is associated with the increased risk of gastrointestinal cancer in diabetic patients. It is necessary to investigate the history of AP and more actively recommend screening for gastrointestinal cancers in such patients. Full article

Background: Up frameshift protein 1 (UPF1) is a key component of nonsense-mediated mRNA decay (NMD) of mRNA containing premature termination codons (PTCs). The dysregulation of UPF1 has been reported in various cancers. However, the expression profile of UPF1 and its clinical significance in clear cell renal cell carcinoma (ccRCC) remains unclear. Methods: In order to detect UPF1 expression in ccRCC and its relationship with the clinical features of ccRCC, bulk RNA sequencing data were analyzed from The Cancer Genome Atlas (TCGA), Gene Expression Omnibus (GEO) and ArrayExpress databases. The impact of UPF1 on the immune microenvironment of ccRCC was evaluated by multiple immune scoring algorithms to identify the cell groups that typically express UPF1 using ccRCC single cell sequencing (scRNA) data. In addition, genes co-expressed with UPF1 were identified by the weighted gene correlation network analysis (WGCNA), followed by KEGG and Reactome enrichment analysis. A series of functional experiments were performed to assess the roles of UPF1 in renal cancer cells. Finally, pan-cancer analysis of UPF1 was also performed. Results: Compared with normal tissues, the expression levels of UPF1 mRNA and protein in tumor tissues of ccRCC patients decreased significantly. In addition, patients with low expression of UPF1 had a worse prognosis. Analysis of the immune microenvironment indicated that UPF1 immune cell infiltration was closely related and the ccRCC scRNA-seq data identified that UPF1 was mainly expressed in macrophages. WGCNA analysis suggested that the functions of co-expressed genes are mainly enriched in cell proliferation and cellular processes. Experimental tests showed that knockdown of UPF1 can promote the invasion, migration and proliferation of ccRCC cells. Lastly, pan-cancer analysis revealed that UPF1 disorders were closely associated with various cancer outcomes. Conclusions: UPF1 may play a tumor suppressive role in ccRCC and modulate the immune microenvironment. The loss of UPF1 can predict the prognosis of ccRCC, making it a promising biomarker and providing a new reference for prevention and treatment. Full article

To determine the efficacy of glucose control in type 2 diabetes patients who switch from dipeptidyl peptidase-4 (DPP-4) inhibitors use or non-use to GLP-1 receptor agonists (GLP-1 RAs). We conducted a cohort study using data from the Chang Gung Research Database. Patients aged ≥18 years using newly initiated GLP-1 RAs between 1 January 2009, and 31 December 2016, were included. Cox proportional hazards models were used to adjust for treatment selection bias. The primary outcome was changes in the glycated hemoglobin (HbA1c) level. The HbA1c level fell substantially after initiating GLP-1 RAs in DPP-4 inhibitor users and nonusers. A mean HbA1c reduction of −0.42% was found in patients who received DPP-4 inhibitors. Those who were DPP-4 inhibitor nonusers had a reduction in HbA1c of −0.99%. The degree of reduction in HbA1c was significantly greater in patients who were DPP-4 inhibitor nonusers (p value < 0.01), compared to the DPP-4 inhibitor users. In routine care, DPP-4 inhibitor nonusers had better efficacy in glucose control than DPP-4 inhibitor users after switching to a GLP-1 agonist. Full article

Ehlers-Danlos syndromes (EDS) are a heterogeneous group of genetically transmitted connective tissue disorders that directly affect collagen synthesis, with a broad range of symptoms. Case presentation: This study presents a clinical case of a Colombian woman with myopathic EDS and multiple comorbidities taking 40 years of medical history to make the right diagnosis. This article also presents a review of the current literature on EDS, not only to remind the syndrome but also to help the clinician correctly identify symptoms of this diverse syndrome. Conclusion: A multidisciplinary approach to the diagnosis of the patient, including clinical and molecular analysis, and neuropsychological and psychological assessment, is important to improve the treatment choice and the outcome prediction of the patients. Full article

Although several biclustering algorithms have been studied, few are used for cross-pattern identification across species using multi-omics data mining. A fast empirical Bayesian biclustering (Bi-EB) algorithm is developed to detect the patterns shared from both integrated omics data and between species. The Bi-EB algorithm addresses the clinical critical translational question using the bioinformatics strategy, which addresses how modules of genotype variation associated with phenotype from cancer cell screening data can be identified and how these findings can be directly translated to a cancer patient subpopulation. Empirical Bayesian probabilistic interpretation and ratio strategy are proposed in Bi-EB for the first time to detect the pairwise regulation patterns among species and variations in multiple omics on a gene level, such as proteins and mRNA. An expectation–maximization (EM) optimal algorithm is used to extract the foreground co-current variations out of its background noise data by adjusting parameters with bicluster membership probability threshold Ac; and the bicluster average probability p. Three simulation experiments and two real biology mRNA and protein data analyses conducted on the well-known Cancer Genomics Atlas (TCGA) and The Cancer Cell Line Encyclopedia (CCLE) verify that the proposed Bi-EB algorithm can significantly improve the clustering recovery and relevance accuracy, outperforming the other seven biclustering methods—Cheng and Church (CC), xMOTIFs, BiMax, Plaid, Spectral, FABIA, and QUBIC—with a recovery score of 0.98 and a relevance score of 0.99. At the same time, the Bi-EB algorithm is used to determine shared the causality patterns of mRNA to the protein between patients and cancer cells in TCGA and CCLE breast cancer. The clinically well-known treatment target protein module estrogen receptor (ER), ER (p118), AR, BCL2, cyclin E1, and IGFBP2 are identified in accordance with their mRNA expression variations in the luminal-like subtype. Ten genes, including CCNB1, CDH1, KDR, RAB25, PRKCA, etc., found which can maintain the high accordance of mRNA–protein for both breast cancer patients and cell lines in basal-like subtypes for the first time. Bi-EB provides a useful biclustering analysis tool to discover the cross patterns hidden both in multiple data matrixes (omics) and species. The implementation of the Bi-EB method in the clinical setting will have a direct impact on administrating translational research based on the cancer cell screening guidance. Full article

Gastric cancer (GC) molecular heterogeneity represents a major determinant for clinical outcomes, and although new molecular classifications have been introduced, they are not easy to translate from bench to bedside. We explored the data from GC public databases by performing differential gene expression analysis (DEGs) and gene network reconstruction to identify master regulators (MRs), as well as a gene set analysis (GSA) to reveal their biological features. Moreover, we evaluated the association of MRs with clinicopathological parameters. According to the GSA, the Diffuse group was characterized by an epithelial-mesenchymal transition (EMT) and inflammatory response, while the Intestinal group was associated with a cell cycle and drug resistance pathways. In particular, the regulons of Diffuse MRs, such as Vgll3 and Ciita, overlapped with the EMT and interferon-gamma response, while the regulons Top2a and Foxm1 were shared with the cell cycle pathways in the Intestinal group. We also found a strict association between MR activity and several clinicopathological features, such as survival. Our approach led to the identification of genes and pathways differentially regulated in the Intestinal and Diffuse GC histotypes, highlighting biologically interesting MRs and subnetworks associated with clinical features and prognosis, suggesting putative actionable candidates. Full article

Background: Gastric cancer remains the most prevalent and highly lethal disease worldwide. MAP4K4, a member of Ste20, plays an important role in various pathologies, including cancer. However, its role in gastric cancer is not yet fully elucidated. Therefore, this study aims to determine the tumor-promoting role of MAP4K4 in gastric cancer and whether it can be used as a new and reliable biomarker to predict the prognosis of gastric cancer. For this purpose, we divide the samples into high- and low-expression groups according to the expression level of MAP4K4. The association of MAP4K4 expression with prognosis is assessed using the Kaplan–Meier survival analysis. Furthermore, immune infiltration analysis using ESTIMATE is conducted to evaluate the tumor immune scores of the samples. Results: The findings reveal a significantly higher expression of MAP4K4 in tumor samples than in adjacent samples. The high-expression group was significantly enriched in tumor-related pathways, such as the PI3K-Akt signaling pathway. In addition, immune infiltration analysis revealed a positive correlation between immune scores and MAP4K4 expression. We also observed that miRNAs, such as miR-192-3p (R = −0.317, p-value 3.111 × 10⁻⁹), miR-33b-5p (R= −0.238, p-value 1.166 × 10⁻⁵), and miR-582-3p (R = −0.214, p-value 8.430 × 10⁻⁵), had potential negative regulatory effects on MAP4K4. Moreover, we identified several transcription factors, ubiquitinated proteins, and interacting proteins that might regulate MAP4K4. The relationship between MAP4K4 and DNA methylation was also identified. Finally, we verified the high expression of MAP4K4 and its effect on promoting cancer. Conclusion: MAP4K4 might be closely related to gastric cancer’s progression, invasion, and metastasis. Its high expression negatively impacts the prognosis of gastric cancer patients. This suggests MAP4K4 as an important prognostic factor for gastric cancer and could be regarded as a new potential prognostic detection and therapeutic target. Full article

Large-scale Asian studies on this topic are lacking. We evaluated the CRC risk associated with family history in the Korean population. We analyzed the data of participants aged ≥40 years who underwent national cancer screening between 2013 and 2014. During a mean follow-up of 4.7 ± 0.8 years, 0.43% of the 292,467 participants with family history and 0.28% of the 1,169,868 participants without family history developed CRC. Participants with a family history in any FDR, parents only, and siblings only had a higher risk of CRC than those without family history; adjusted hazard ratios (HRs) were 1.53, 1.46, and 1.61, respectively. Participants with a family history comprising both parents and siblings had an even higher risk of CRC than those without a family history (HR, 2.34). The HRs for CRC in the 40–49, 50–59, 60–69, 70–79, and ≥80 age groups with family history were 1.72, 1.74, 1.50, 1.30, and 0.78, respectively (p < 0.001). A family history of CRC in any FDR and both parents and siblings was associated with an approximately 1.5- and 2.3-fold increased risk of CRC. The effect of family history was relatively greater in the younger than the older age group. Full article

Background: Psoriasis can present different phenotypes and could affect diverse body areas. In contrast to the high effectiveness of biological drugs in the treatment of trunk and extremities plaque psoriasis, in palmoplantar phenotypes and in plaque scalp psoriasis, these same drugs usually have reduced efficacy. Anti-TNF drugs could induce the appearance of palmoplantar pustulosis (PPP) in patients with other inflammatory diseases. The objective of this study is to identify if there are DNA Copy Number Variations (CNVs) associated with these different clinical phenotypes, which could justify the differences found in clinical practice. Moreover, we intend to elucidate if anti-TNF-induced PPP has a similar genetic background to idiopathic PPP. Methods: Skin samples were collected from 39 patients with different patterns of psoriasis and six patients with anti-TNF-induced PPP. The CNVs were obtained from methylation array data (Illumina Infinium Human Methylation) using the conumee R package. Results: No significant CNVs were found between the different phenotypes and the locations of psoriasis compared. Nevertheless, we found two significant bins harboring five different genes associated with anti-TNF-induced PPP in patients with a different background other than psoriasis. Conclusions: Our results may help to predict which patients could develop anti-TNF-induced PPP. Full article

Both the annotation and identification of genes in pathogenic parasites are still challenging. Although, as a survival factor, nitric oxide (NO) has been proven to be synthesized in Trichomonas vaginalis (TV), nitric oxide synthase (NOS) has not yet been annotated in the TV genome. We developed a witness-to-suspect strategy to identify incorrectly annotated genes in TV via the Smith–Waterman and Needleman–Wunsch algorithms through in-depth and repeated alignment of whole coding sequences of TV against thousands of sequences of known proteins from other organisms. A novel NOS of TV (TV NOS), which was annotated as hydrogenase in the NCBI database, was successfully identified; this TV NOS had a high witness-to-suspect ratio and contained all the NOS cofactor-binding motifs (NADPH, tetrahydrobiopterin (BH4), heme and flavin adenine dinucleotide (FAD) motifs). To confirm this identification, we performed in silico modeling of the protein structure and cofactor docking, cloned the gene, expressed and purified the protein, performed mass spectrometry analysis, and ultimately performed an assay to measure enzymatic activity. Our data showed that although the predicted structure of the TV NOS protein was not similar to the structure of NOSs of other species, all cofactor-binding motifs could interact with their ligands with high affinities. We clearly showed that the purified protein had high enzymatic activity for generating NO in vitro. This study provides an innovative approach to identify incorrectly annotated genes in TV and highlights a novel NOS that might serve as a virulence factor of TV. Full article

Maintaining a social environment that enables going out freely is important for older people and aids the prevention of frailty syndrome. However, losing a driver’s license can increase the long-term care needs of older people. Therefore, outing support systems are important. However, the utilization rate of these systems is currently relatively low. We conducted a demonstration experiment among older people aged 70 years and over, living in Iruma City, Saitama Japan, by implementing the Choisoko outing support system developed by Aisin Co., Ltd., in conjunction with an approach for improving motivation. Using this system, elderly people were able to go shopping freely whenever they chose, without a driver’s license. Participants in the demonstration experiment exhibited higher Functional Independence Measure scores after the intervention, irrespective of whether or not they used the Choisoko system. The number of uses per person increased over time, and the subjective well-being of Choisoko users improved. However, few male participants engaged with the system. Although improving motivation is important for inducing positive behaviors and enabling the elderly to go out, motivation-improving factors differ between men and women. Full article

Background: In chronic obstructive pulmonary disease (COPD), inhaled corticosteroids (ICSs) are recommended for use by patients with frequent exacerbations and blood eosinophilia. However, ICSs are often inappropriately prescribed and overused. COPD studies have reported an increased risk of tuberculosis among ICS users. This study aimed to compare the risk of tuberculosis according to the different ICS components. Methods: This study was conducted using a nationwide, population-based cohort. Patients newly diagnosed with COPD between 2005 and 2018, and treated with either fluticasone propionate or budesonide, were selected. The patients were followed up until the development of tuberculosis. Results: After propensity score matching, 16,514 fluticasone propionate and 16,514 budesonide users were identified. The incidence rate of tuberculosis per 100,000 person-years was 274.73 for fluticasone propionate and 214.18 for budesonide. The hazard ratio of tuberculosis in fluticasone propionate compared with budesonide was 1.28 (95% confidence interval 1.05–1.60). The risk of tuberculosis for fluticasone propionate increased with higher ICS cumulative doses: 1.01 (0.69–1.48), 1.16 (0.74–1.81), 1.25 (0.79–1.97), and 1.82 (1.27–2.62) from the lowest to highest quartiles, respectively. Conclusion: Fluticasone propionate is associated with a higher risk of tuberculosis than budesonide. ICS components can differently affect the risk of tuberculosis in patients with COPD. Full article

A stem cell theory of cancer considers genetic makeup in the proper cellular context. It is a unified theory of cancer that unites the genome with the epigenome, links the intracellular with the extracellular, and connects the cellular constituents and compartments with the microenvironment. Although it allies with genomic medicine, it is better aligned with integrated medicine. In this perspective, we focus on translational research in cancer care. We expose some intrinsic fallacies in translational research when it relates to the basic principles of the scientific method in the care of patients with genomic medicine versus integrated medicine. We postulate that genomic medicine may be at the root of many failed efforts in drug development and data reproducibility. We propose an alternate heuristic approach that may expedite the development of safe and effective treatments and minimize the generation of unproductive pharmaceutical products and nonreproducible experimental results. Importantly, a heuristic approach emphasizes the role of a pertinent scientific theory and distinguishes therapy development from drug development, such that we discover not only useful drugs but also better ways to use them in order to optimize patient care and maximize clinical outcomes. Full article

Endometriosis is a condition characterized by implants of endometrial tissues into extrauterine sites, mostly within the pelvic peritoneum. The prevalence of endometriosis is under-diagnosed and is estimated to account for 5–10% of all women of reproductive age. The goal of this study was to develop a model for endometriosis based on the UK-biobank (UKB) and re-assess the contribution of known risk factors to endometriosis. We partitioned the data into those diagnosed with endometriosis (5924; ICD-10: N80) and a control group (142,723). We included over 1000 variables from the UKB covering personal information about female health, lifestyle, self-reported data, genetic variants, and medical history prior to endometriosis diagnosis. We applied machine learning algorithms to train an endometriosis prediction model. The optimal prediction was achieved with the gradient boosting algorithms of CatBoost for the data-combined model with an area under the ROC curve (ROC-AUC) of 0.81. The same results were obtained for women from a mixed ethnicity population of the UKB (7112; ICD-10: N80). We discovered that, prior to being diagnosed with endometriosis, affected women had significantly more ICD-10 diagnoses than the average unaffected woman. We used SHAP, an explainable AI tool, to estimate the marginal impact of a feature, given all other features. The informative features ranked by SHAP values included irritable bowel syndrome (IBS) and the length of the menstrual cycle. We conclude that the rich population-based retrospective data from the UKB are valuable for developing unified machine learning endometriosis models despite the limitations of missing data, noisy medical input, and participant age. The informative features of the model may improve clinical utility for endometriosis diagnosis. Full article

Background and purpose: to investigate the frequency of cervical–cranial vascular complications soon after radiation therapy (RT) and identify differences among patients with various types of head and neck cancer (HNC). Methods: We enrolled 496 patients with HNC who had received their final RT dose in our hospital. These patients underwent carotid duplex ultrasound (CDU) for monitoring significant carotid artery stenosis (CAS). Brain imaging were reviewed to detect vertebral, intracranial artery stenosis, or preexisted CAS before RT. Primary outcome was significant CAS at the internal or common carotid artery within first 5 years after RT. We categorized the patients into nasopharyngeal carcinoma (NPC) and non-NPC groups and compared the cumulative occurrence of significant CAS between the groups using Kaplan–Meier and Cox-regression analyses. Results: Compared to the NPC group, the non-NPC group had a higher frequency of significant CAS (12.7% vs. 2.0%) and were more commonly associated with significant CAS after adjusting the covariates (Adjusted hazard ratio: 0.17, 95% confident interval: 0.05–0.57) during the follow-up period. All the non-NPC subtypes (oral cancer/oropharyngeal, hypopharyngeal, and laryngeal cancers) were associated with higher risks of significant CAS than the NPC group (p < 0.001 respectively). Conclusion: Significant CAS was more frequently noted within 5 years of RT among the patients with non-NPC HNC than among the patients with NPC. Scheduled carotid artery surveillance and vascular risk monitoring should be commenced earlier for patients with non-NPC HNC. By contrast, vascular surveillance could be deferred to 5 years after RT completion in NPC patients. Full article

Lung adenocarcinoma (LUAD) is a common type of lung cancer. Although the diagnosis and treatment of LUAD have significantly improved in recent decades, the survival for advanced LUAD is still poor. It is necessary to identify more targets for developing potential agents against LUAD. This study explored the dysregulation of translation initiation factors, specifically eukaryotic initiation factors 4A1 (EIF4A1) and EIF4A2, in developing LUAD, as well as their underlying mechanisms. We found that the expression of EIF4A1, but not EIF4A2, was higher in tumor tissue and associated with poor clinical outcomes in LUAD patients. Elevated expression of EIF4H with poor prognosis may potentiate the oncogenic role of EIF4A1. Functional enrichment analysis revealed that upregulation of EIF4A1 was related to cell cycle regulation and DNA repair. The oncogenic effect of EIF4A1 was further elucidated by Gene Set Variation Analysis (GSVA). The GSVA score of the gene set positively correlated with EIF4A1 was higher in tumors and significantly associated with worse survival. In the meantime, gene set enrichment analysis (GSEA) also indicated that elevated EIF4A1 expression in LUAD patients was associated with a decreased infiltration score for immune cells by reducing anticancer immune cell types and recruiting immunosuppressive cells. Consistent with the results, the GSVA score of genes whose expression was negatively correlated with EIF4A1 was lower in the tumor tissue of LUAD cases with worse clinical outcomes and was strongly associated with the disequilibrium of anti-cancer immunity by recruiting anticancer immune cells. Based on the results from the present study, we hypothesize that the dysregulation of EIF4A1 might be involved in the pathophysiology of LUAD development by promoting cancer growth and changing the tumor immune microenvironment. This can be used to develop potential diagnostic biomarkers or therapeutic targets for LUAD. Full article

The incidence of major hemorrhage and transfusion during liver transplantation has decreased significantly over the past decade, but major bleeding remains a common expectation. Massive intraoperative hemorrhage during liver transplantation can lead to mortality or reoperation. This study aimed to develop machine learning models for the prediction of massive hemorrhage and a scoring system which is applicable to new patients. Data were retrospectively collected from patients aged >18 years who had undergone liver transplantation. These data included emergency information, donor information, demographic data, preoperative laboratory data, the etiology of hepatic failure, the Model for End-stage Liver Disease (MELD) score, surgical history, antiplatelet therapy, continuous renal replacement therapy (CRRT), the preoperative dose of vasopressor, and the estimated blood loss (EBL) during surgery. The logistic regression model was one of the best-performing machine learning models. The most important factors for the prediction of massive hemorrhage were the disease etiology, activated partial thromboplastin time (aPTT), operation duration, body temperature, MELD score, mean arterial pressure, serum creatinine, and pulse pressure. The risk-scoring system was developed using the odds ratios of these factors from the logistic model. The risk-scoring system showed good prediction performance and calibration (AUROC: 0.775, AUPR: 0.753). Full article

Prostate adenocarcinoma (PRAD), also named prostate cancer, the most common visceral malignancy, is diagnosed in male individuals. Herein, in order to obtain immune-based subtypes, we performed an integrative analysis to characterize molecular subtypes based on immune-related genes, and further discuss the potential features and differences between identified subtypes. Simultaneously, we also construct an immune-based risk model to assess cancer prognosis. Our findings showed that the two subtypes, C1 and C2, could be characterized, and the two subtypes showed different characteristics that could clearly describe the heterogeneity of immune microenvironments. The C2 subtype presented a better survival rate than that in the C1 subtype. Further, we constructed an immune-based prognostic model based on four screened abnormally expressed genes, and they were selected as predictors of the robust prognostic model (AUC = 0.968). Our studies provide reference for characterization of molecular subtypes and immunotherapeutic agents against prostate cancer, and the developed robust and useful immune-based prognostic model can contribute to cancer prognosis and provide reference for the individualized treatment plan and health resource utilization. These findings further promote the development and application of precision medicine in prostate cancer. Full article

The potential link between rheumatoid arthritis (RA) and cancer incidence needs to be validated due to inconsistent results between Asian and Western countries. We explored the long-term association of RA with the overall and organ-specific cancer incidence using nationwide population data. This longitudinal follow-up study (2002–2015) included 3070 patients with RA and 12,280 controls (1:4 propensity score-matched for sex, age, residence, and income) from the Korean National Health Insurance Service-Health Screening Cohort database. A Cox proportional hazard model estimated the hazard ratio for malignancy following adjusting for covariates. Despite the similar overall cancer incidence between RA and control groups, differences in the incidence of organ-specific cancers were noted: the RA group had a 1.63-fold greater likelihood for lung cancer (95% confidence interval 1.11–2.40). In the sex-stratified subgroup analyses, the male RA patients exhibited higher odds of lung and thyroid cancer but a lower probability for colorectal cancer; no such associations were detected in either female patients with RA or age subgroups. In summary, the higher likelihood for lung cancer in Korean RA patients, especially thyroid and lung cancer in male RA patients, seems to be characteristic, which needs to be carefully monitored. Full article

Background: Primary open-angle glaucoma (POAG) is the most prevalent glaucoma subtype, but its exact etiology is still unknown. In this study, we aimed to prioritize the most likely ‘causal’ genes and identify functional characteristics and underlying biological pathways of POAG candidate genes. Methods: We used the results of a large POAG genome-wide association analysis study from GERA and UK Biobank cohorts. First, we performed systematic gene-prioritization analyses based on: (i) nearest genes; (ii) nonsynonymous single-nucleotide polymorphisms; (iii) co-regulation analysis; (iv) transcriptome-wide association studies; and (v) epigenomic data. Next, we performed functional enrichment analyses to find overrepresented functional pathways and tissues. Results: We identified 142 prioritized genes, of which 64 were novel for POAG. BICC1, AFAP1, and ABCA1 were the most highly prioritized genes based on four or more lines of evidence. The most significant pathways were related to extracellular matrix turnover, transforming growth factor-β, blood vessel development, and retinoic acid receptor signaling. Ocular tissues such as sclera and trabecular meshwork showed enrichment in prioritized gene expression (>1.5 fold). We found pleiotropy of POAG with intraocular pressure and optic-disc parameters, as well as genetic correlation with hypertension and diabetes-related eye disease. Conclusions: Our findings contribute to a better understanding of the molecular mechanisms underlying glaucoma pathogenesis and have prioritized many novel candidate genes for functional follow-up studies. Full article

Ischemic cardiomyopathy (ICM) caused by coronary artery disease always leads to myocardial infarction and heart failure. Identification of novel transcriptional regulators in ICM is an effective method to establish new diagnostic and therapeutic strategies. In this study, we used two RNA-seq datasets and one microarray dataset from different studies, including 25 ICM and 21 non-failing control (NF) samples of human left ventricle tissues for further analysis. In total, 208 differentially expressed genes (DEGs) were found by combining two RNA-seq datasets with batch effects removed. GO and KEGG analyses of DEGs indicated that the response to wounding, positive regulation of smooth muscle contraction, chromatin, PI3K-Akt signaling pathway, and transporters pathways are involved in ICM. Simple Enrichment Analysis found that NFIC-binding motifs are enriched in promoter regions of downregulated genes. The Gene Importance Calculator further proved that NFIC is vital. NFIC and its downstream genes were verified in the validating microarray dataset. Meanwhile, in rat cardiomyocyte cell line H9C2 cells, two genes (Tspan1 and Hopx) were confirmed, which decreased significantly along with knocking down Nfic expression. In conclusion, NFIC participates in the ICM process by regulating TSPAN1 and HOPX. NFIC and its downstream genes may be marker genes and potential diagnostic and therapeutic targets for ICM. Full article

Precision medicine has been revolutionized by the advent of high-throughput next-generation sequencing (NGS) technology and development of various bioinformatic analysis tools for large-scale NGS big data. At the population level, biomedical studies have identified human diseases and phenotype-associated genetic variations using NGS technology, such as whole-genome sequencing, exome sequencing, and gene panel sequencing. Furthermore, patients’ genetic variations related to a specific phenotype can also be identified by analyzing their genomic information. These breakthroughs paved the way for the clinical diagnosis and precise treatment of patients’ diseases. Although many bioinformatics tools have been developed to analyze the genetic variations from the individual patient’s NGS data, it is still challenging to develop user-friendly programs for clinical physicians who do not have bioinformatics programing skills to diagnose a patient’s disease using the genomic data. In response to this demand, we developed a Phenotype to Genotype Variation program (PhenGenVar), which is a user-friendly interface for monitoring the variations in a gene of interest for molecular diagnosis. This allows for flexible filtering and browsing of variants of the disease and phenotype-associated genes. To test this program, we analyzed the whole-genome sequencing data of an anonymous person from the 1000 human genome project data. As a result, we were able to identify several genomic variations, including single-nucleotide polymorphism, insertions, and deletions in specific gene regions. Therefore, PhenGenVar can be used to diagnose a patient’s disease. PhenGenVar is freely accessible and is available at our website. Full article

Almost half of patients show no primary or secondary response to monoclonal anti-tumor necrosis factor α (anti-TNF) antibody treatment for inflammatory bowel disease (IBD). Thus, the exact mechanisms of a non-durable response (NDR) remain inadequately defined. We used our genome-wide genotype data to impute expression values as features in training machine learning models to predict a NDR. Blood samples from various IBD cohorts were used for genotyping with the Korea Biobank Array. A total of 234 patients with Crohn’s disease (CD) who received their first anti-TNF therapy were enrolled. The expression profiles of 6294 genes in whole-blood tissue imputed from the genotype data were combined with clinical parameters to train a logistic model to predict the NDR. The top two and three most significant features were genetic features (DPY19L3, GSTT1, and NUCB1), not clinical features. The logistic regression of the NDR vs. DR status in our cohort by the imputed expression levels showed that the β coefficients were positive for DPY19L3 and GSTT1, and negative for NUCB1, concordant with the known eQTL information. Machine learning models using imputed gene expression features effectively predicted NDR to anti-TNF agents in patients with CD. Full article

Obstructive sleep apnea (OSA) yields intermittent hypoxia, hypercapnia, and sleep fragmentation. OSA is associated with chronic medical conditions such as cardiovascular diseases, metabolic syndrome, and neurocognitive dysfunction. However, the risk of infertility in OSA remains unclear due to limited data and lack of long-term population-based studies. The study aims to assess the risk of infertility in obstructive sleep apnea (OSA) by means of a population-based cohort study. The data was utilized from the Taiwan National Health Insurance Research Database (NHIRD) to conduct a population-based cohort study (1997–2013). Compared with the Non-OSA group, the male with OSA and surgery group has the OR (odds ratio) of infertility of 2.70 (95% CI, 1.46–4.98, p = 0.0015), but no significance exists in females with OSA. When the data was stratified according to age and gender, some associations in the specific subgroups were significant. Respectively, males aged 20–35 years old and aged 35–50 years old with a history of OSA and surgery both had a positive association with infertility. (aOR: 3.19; 95% CI, 1.18–8.66, p = 0.0227; aOR: 2.57; 95% CI, 1.18–5.62 p = 0.0176). Male patients with OSA suffer from reduced fertility, but no significant difference was noted in females with OSA. The identification of OSA as a risk factor for male infertility will aid clinicians to optimize long-term medical care. Furthermore, more studies will be encouraged to clarify the effect of OSA on female fertility. Full article

Lung cancer is well known for its high mortality worldwide. The treatment for advanced lung cancer needs more attention to improve its survival time. A disintegrin and metallopeptidase with thrombospondin motifs 8 (ADAMTS8) has been linked to several cancer types. However, its role in lung cancer is worthy of deep investigation to promote novel drug development. This study took advantage of RNA-seq and bioinformatics to verify the role that ADAMTS8 plays in lung cancer. The functional assays suggested that ADAMTS8 mediates invasion and metastasis when expressed at a low level, contributing to poor overall survival (OS). The expression of ADAMTS8 was under the regulation of GATA Binding Protein 1 (GATA1) and executed its pathologic role through Thrombospondin Type 1 Domain Containing 1 (THSD1) and ADAMTS Like 2 (ADAMTSL2). To define the impact of ADAMTS8 in the lung cancer treatment strategy, this study further grouped lung cancer patients in the TCGA database into mutated epidermal growth factor receptor (EGFR)/wild-type EGFR and programmed death ligand 1 (PD-L1) high/low groups. Importantly, the expression of ADAMTS8 was correlated positively with the recruitment of anticancer NKT cells and negatively with the infiltration of immunosuppressive Treg and exhausted T cells. The results indicated that lung cancer patients with higher ADAMTS8 levels among wild-type EGFR or low PD-L1 groups survive longer than those with lower levels do. This study indicates that ADAMTS8 might be a treatment option for patients with lung adenocarcinoma who lack efficient targeted or immunotherapies. Full article

MicroRNAs (miRNAs) have drawn enormous attention owing to their significant roles in various biological processes, as well as in the pathogenesis of human diseases. Therefore, predicting miRNA–disease associations is a pivotal task for the early diagnosis and better understanding of disease pathogenesis. To date, numerous computational frameworks have been proposed to identify potential miRNA–disease associations without escalating the costs and time required for clinical experiments. In this regard, I propose a novel computational framework (MDMF) for identifying potential miRNA–disease associations using matrix factorization with a disease similarity constraint. To evaluate the performance of MDMF, I calculated the area under the ROC curve (AUCs) in the framework of global and local leave-one-out cross-validation (LOOCV). In conclusion, MDMF achieved reliable AUC values of 0.9147 and 0.8905 for global and local LOOCV, respectively, which was a significant improvement upon the previous methods. Additionally, case studies were conducted on two major human cancers (breast cancer and lung cancer) to validate the effectiveness of MDMF. Comprehensive experimental results demonstrate that MDMF not only discovers miRNA–disease associations efficiently but also deciphers the underlying roles of miRNAs in the pathogenesis of diseases at a system level. Full article

Relapsed and refractory (R/r) disease in paediatric acute leukaemia remains the first reason for treatment failure. Advances in molecular characterisation can ameliorate the identification of genetic biomarkers treatment strategies for this disease, especially in high-risk patients. The purpose of this study was to analyse a cohort of R/r children diagnosed with acute lymphoblastic (ALL) or myeloid (AML) leukaemia in order to offer them a targeted treatment if available. Advanced molecular characterisation of 26 patients diagnosed with R/r disease was performed using NGS, MLPA, and RT-qPCR. The clinical relevance of the identified alterations was discussed in a multidisciplinary molecular tumour board (MTB). A total of 18 (69.2%) patients were diagnosed with B-ALL, 4 (15.4%) with T-ALL, 3 (11.5%) with AML and 1 patient (3.8%) with a mixed-phenotype acute leukaemia (MPL). Most of the patients had relapsed disease (88%) at the time of sample collection. A total of 17 patients (65.4%) were found to be carriers of a druggable molecular alteration, 8 of whom (47%) received targeted therapy, 7 (87.5%) of them in addition to hematopoietic stem cell transplantation (HSCT). Treatment response and disease control were achieved in 4 patients (50%). In conclusion, advanced molecular characterisation and MTB can improve treatment and outcome in paediatric R/r acute leukaemias. Full article

Background: Breast cancer (BC) is the most frequent cancer and the leading cause of cancer-related death in women. The French National Cancer Institute has created a national cancer cohort to promote cancer research and improve our understanding of cancer using the National Health Data System (SNDS) and amalgamating all cancer sites. So far, no detailed separate data are available for early BC. Objectives: To describe the creation of the French Early Breast Cancer Cohort (FRESH). Methods: All French women aged 18 years or over, with early-stage BC newly diagnosed between 1 January 2011 and 31 December 2017, treated by surgery, and registered in the general health insurance coverage plan were included in the cohort. Patients with suspected locoregional or distant metastases at diagnosis were excluded. BC treatments (surgery, chemotherapy, targeted therapy, radiotherapy, and endocrine therapy), and diagnostic procedures (biopsy, cytology, and imaging) were extracted from hospital discharge reports, outpatient care notes, or pharmacy drug delivery data. The BC subtype was inferred from the treatments received. Results: We included 235,368 patients with early BC in the cohort (median age: 60 years). The BC subtype distribution was as follows: luminal (80.2%), triple-negative (TNBC, 9.5%); HER2⁺ (10.3%), or unidentifiable (n = 44,388, 18.9% of the cohort). Most patients underwent radiotherapy (n = 200,685, 85.3%) and endocrine therapy (n = 165,655, 70.4%), and 38.3% (n = 90,252) received chemotherapy. Treatments and care pathways are described. Conclusions: The FRESH Cohort is an unprecedented population-based resource facilitating future large-scale real-life studies aiming to improve care pathways and quality of care for BC patients. Full article

Background. The incidence of colorectal cancers has been constantly increasing. Although the mortality has slightly decreased, it is far from satisfaction. Precise early diagnosis for colorectal cancer has been a great challenge in order to improve patient survival. Patients and Methods. We started with searching for protein biomarkers based on our colorectal cancer biomarker database (CBD), finding differential expressed genes (GEGs) and non-DEGs from RNA sequencing (RNA-seq) data, and further predicted new biomarkers of protein–protein interaction (PPI) networks by machine learning (ML) methods. The best-selected biomarker was further verified by a receiver operating characteristic (ROC) test from microarray and RNA-seq data, biological network, and functional analysis, and immunohistochemistry in the tissue arrays from 198 specimens. Results. There were twelve proteins (MYO5A, CHGA, MAPK13, VDAC1, CCNA2, YWHAZ, CDK5, GNB3, CAMK2G, MAPK10, SDC2, and ADCY5) which were predicted by ML as colon cancer candidate diagnosis biomarkers. These predicted biomarkers showed close relationships with reported biomarkers of the PPI network and shared some pathways. An ROC test showed the CHGA protein with the best diagnostic accuracy (AUC = 0.9 in microarray data and 0.995 in RNA-seq data) among these candidate protein biomarkers. Furthermore, immunohistochemistry examination on our colon cancer tissue microarray samples further confirmed our bioinformatical prediction, indicating that CHGA may be used as a potential biomarker for early diagnosis of colon cancer patients. Conclusions. CHGA could be a potential candidate biomarker for diagnosing earlier colon cancer in the patients. Full article

Background: Lung cancer is among the most dangerous malignant tumors to human health. Lung adenocarcinoma (LUAD) accounts for about 40% of all lung cancers. Accumulating evidence suggests that the tumor microenvironment (TME) is a crucial regulator of carcinogenesis and therapeutic efficacy in LUAD. However, the impact of tumor microenvironment-related signatures (TMERSs) representing the TME characteristics on the prognosis and therapeutic outcome of LUAD patients remains to be further explored. Materials and methods: Gene expression files and clinical information of 1630 LUAD samples and 275 samples with immunotherapy information from different databases such as The Cancer Genome Atlas (TCGA), Gene Expression Omnibus (GEO) and Cancer Research Institute (CRI) iAtlas were downloaded and analyzed. Three hundred tumor microenvironment-related signatures (TMERS) based on a comprehensive collection of marker genes were quantified by single sample gene set enrichment analysis (ssGSEA), and then eight significant signatures were selected to construct the tumor microenvironment-related signature score (TMERSscore) by performing Least Absolute Shrinkage and Selection Operator (LASSO)-Cox analysis. Results: In this study, we constructed a TME-based prognostic stratification model for patients with LUAD and validated it in several external datasets. Furthermore, the TMERSscore was found to be positively correlated with tumor malignancy and a high TMERSscore predicted a poor prognosis. Moreover, the TMERSscore of responders treated with Immune Checkpoint Inhibitor (ICI) therapies was significantly lower than that of non-responders, and the TMERSscore was positively correlated with the tumor immune dysfunction and exclusion (TIDE) score, implying that a low TMERSscore predicts a better response to ICI treatment and may provide independent and incremental predictive value over current biomarkers. Conclusions: Overall, we constructed a TMERSscore that can be used for LUAD patient prognosis stratification as well as ICI therapeutic efficacy evaluation, supportive results from independent external validation sets showed its robustness and effectiveness. Full article

The molecular genetic mechanism of Turner syndrome (TS) still leaves much to be discovered. Methods: TS (45X0) patients and age-matched controls (46XX and 46XY) were selected. The nanopore sequencing combined with trio-whole exome sequencing (trio-WES) were used for the first time to investigate TS. Results: Thirteen TS (45X0) patients and eight controls were enrolled. Trio-WES analysis did not find any pathogenetic or likely pathogenic variants except X chromosome (chrX) deletion. The average methylation levels and patterns of chrX in 45X0 and 46XY were similar, and significantly higher than in 46XX (p = 2.22 × 10⁻¹⁶). Both hyper-methylation and hypo-methylation were detected in the CpG island (CGI), CGI_shore, promoter, genebody, and PAR1-region, while in the transposon element inactivation regions of the chrX and hypermethylation were predominant. A total of 125 differentially methylated genes were identified in 45X0 compared to 46XX, including 8 and 117 hypermethylated and hypomethylated genes, respectively, with the enrichment terms of mitophagy, regulation of DNA-binding transcription factor activity, etc. Conclusions: The results suggest that the methylation profile in patients with TS might be determined by the number of X chromosomes; the patterns of methylation in TS were precisely associated with the maintenance of genomic stability and improvement of gene expression. Differentially methylated genes/pathways might reveal the potential epigenetic modulation and lead to better understanding of TS. Full article

Background: There have been concerns regarding increased perioperative mortality, length of hospital stay, and rates of graft loss in kidney transplant recipients with functional limitations. The application of machine learning consensus clustering approach may provide a novel understanding of unique phenotypes of functionally limited kidney transplant recipients with distinct outcomes in order to identify strategies to improve outcomes. Methods: Consensus cluster analysis was performed based on recipient-, donor-, and transplant-related characteristics in 3205 functionally limited kidney transplant recipients (Karnofsky Performance Scale (KPS) < 40% at transplant) in the OPTN/UNOS database from 2010 to 2019. Each cluster’s key characteristics were identified using the standardized mean difference. Posttransplant outcomes, including death-censored graft failure, patient death, and acute allograft rejection were compared among the clusters Results: Consensus cluster analysis identified two distinct clusters that best represented the clinical characteristics of kidney transplant recipients with limited functional status prior to transplant. Cluster 1 patients were older in age and were more likely to receive deceased donor kidney transplant with a higher number of HLA mismatches. In contrast, cluster 2 patients were younger, had shorter dialysis duration, were more likely to be retransplants, and were more likely to receive living donor kidney transplants from HLA mismatched donors. As such, cluster 2 recipients had a higher PRA, less cold ischemia time, and lower proportion of machine-perfused kidneys. Despite having a low KPS, 5-year patient survival was 79.1 and 83.9% for clusters 1 and 2; 5-year death-censored graft survival was 86.9 and 91.9%. Cluster 1 had lower death-censored graft survival and patient survival but higher acute rejection, compared to cluster 2. Conclusion: Our study used an unsupervised machine learning approach to characterize kidney transplant recipients with limited functional status into two clinically distinct clusters with differing posttransplant outcomes. Full article

Background: Patients with non-cystic fibrosis bronchiectasis have an increased risk of lung cancer, followed by higher mortality in this population. Because the risk factors of lung cancer have not been well identified, this study aimed to investigate the risk factors of lung cancer in individuals with newly diagnosed bronchiectasis. Methods: This cohort study using the Korean National Health Insurance Service database identified 7425 individuals with incident bronchiectasis among those who participated in the health screening exam in 2009. The cohort was followed from baseline to the date of incident: lung cancer, death, or until the end of the study period. We investigated the risk factors of lung cancer in participants with bronchiectasis using the Cox–proportional hazard models. Results: During median 8.3 years of follow-up duration, 1.9% (138/7425) developed lung cancer. In multivariable analyses, significant factors associated with increased risk of incident lung cancer included: males (adjusted hazard ratio [HR] = 3.54, 95% confidence interval [CI] = 2.17–5.79) than females, the overweight (adjusted HR = 1.55, 95% CI = 1.03–2.35) than the normal weight, current smokers (adjusted HR = 3.10, 95% CI = 2.00–4.79) than never smokers, participants living in the rural area (adjusted HR = 2.54, 95% CI = 1.68–3.85) than those living in the metropolitan area. Among comorbidities, chronic obstructive pulmonary disease was associated with an increased risk of lung cancer (adjusted HR = 1.46, 95% CI = 1.01–2.13) in participants with bronchiectasis. In contrast, mild alcohol consumption was associated with reduced risk of lung cancer (adjusted HR = 0.47, 95% CI = 0.29–0.74) in those with bronchiectasis. Conclusion: This Korean population-based study showed that males, current smoking, overweight, living in rural areas, and comorbid chronic obstructive pulmonary disease are associated with increased risk of lung cancer in individuals with bronchiectasis. Full article

Triple-negative breast cancer (TNBC) is a heterogeneous disease with diverse, often poor prognoses and treatment responses. In order to identify targetable biomarkers and guide personalized care, scientists have developed multiple molecular classification systems for TNBC based on transcriptomic profiling. However, there is no consensus on the molecular subtypes of TNBC, likely due to discrepancies in technical and computational methods used by different research groups. Here, we reassessed the major steps for TNBC subtyping, validated the reproducibility of established TNBC subtypes, and identified two more subtypes with a larger sample size. By comparing results from different workflows, we demonstrated the limitations of formalin-fixed, paraffin-embedded samples, as well as batch effect removal across microarray platforms. We also refined the usage of computational tools for TNBC subtyping. Furthermore, we integrated high-quality multi-institutional TNBC datasets (discovery set: n = 457; validation set: n = 165). Performing unsupervised clustering on the discovery and validation sets independently, we validated four previously discovered subtypes: luminal androgen receptor, mesenchymal, immunomodulatory, and basal-like immunosuppressed. Additionally, we identified two potential intermediate states of TNBC tumors based on their resemblance with more than one well-characterized subtype. In summary, we addressed the issues and limitations of previous TNBC subtyping through comprehensive analyses. Our results promote the rational design of future subtyping studies and provide new insights into TNBC patient stratification. Full article

Despite advancements in molecular classification, tumor stage and grade still remain the most relevant prognosticators used by clinicians to decide on patient management. Here, we leverage publicly available data to characterize bladder cancer (BLCA)’s stage biology based on increased sample sizes, identify potential therapeutic targets, and extract putative biomarkers. A total of 1135 primary BLCA transcriptomes from 12 microarray studies were compiled in a meta-cohort and analyzed for monotonal alterations in pathway activities, gene expression, and co-expression patterns with increasing stage (Ta–T1–T2–T3–T4), starting from the non-malignant tumor-adjacent urothelium. The TCGA-2017 and IMvigor-210 RNA-Seq data were used to validate our findings. Wnt, MTORC1 signaling, and MYC activity were monotonically increased with increasing stage, while an opposite trend was detected for the catabolism of fatty acids, circadian clock genes, and the metabolism of heme. Co-expression network analysis highlighted stage- and cell-type-specific genes of potentially synergistic therapeutic value. An eight-gene signature, consisting of the genes AKAP7, ANLN, CBX7, CDC14B, ENO1, GTPBP4, MED19, and ZFP2, had independent prognostic value in both the discovery and validation sets. This novel eight-gene signature may increase the granularity of current risk-to-progression estimators. Full article

Background: Descriptive epidemiologists have repeatedly reported that males are more susceptible to head and neck cancers. However, most published data are those of cross-sectional studies, and no population-based cohort study has yet been published. The aim of this study was to compare the prevalence of head and neck cancers in healthy males with females. Methods: A retrospective cohort study using the Korean National Health Insurance Service database on 9,598,085 individuals who underwent regular health checkups from 1 January to 31 December 2009. We sought head and neck cancers developed during the 10-year follow-up. Results: A total of 10,732 (incidence rate (IR) per 1000 person-years 0.25) individuals were newly diagnosed with head and neck cancer among the 9,598,085 individuals during the 10-year follow-up. The IR was 0.19 in males (8500 affected) and 0.06 in females (2232 affected). Notably, the male–female ratio increased with age below 70 years but decreased thereafter. The male–female difference was most apparent for laryngeal cancer; the male IR was 11-fold higher in the 40 s and 20-fold higher in the 60 s, followed by hypopharyngeal cancer (6.8- and 24.2-fold). Males smoked more and drank more alcohol than females (p < 0.0001 *, p < 0.0001 *). When never-smokers/-drinkers (only) were compared, males remained at a 2.9-fold higher risk of head and neck cancer than females. The hazard ratios for head and neck cancers in males tended to increase in the lower part of the upper aerodigestive tract: larynx (13.9) > hypopharynx (10.9) > oropharynx (4.4) > nasopharynx (2.9) > sinonasal region (1.8) > oral (1.6). Only the salivary gland cancer incidence did not differ between the sexes; the gland is not in the upper aerodigestive tract. Conclusion: Males are much more susceptible to head and neck cancers than females regardless of whether they drink alcohol or smoke tobacco. Sex differences in the incidence of head and neck cancer are most evident in the 60 s in the lower part of the upper aerodigestive tract, such as the larynx and hypopharynx. Full article

Many living organisms have DNA in their cells that is responsible for their biological features. DNA is an organic molecule of two complementary strands of four different nucleotides wound up in a double helix. These nucleotides are adenine (A), thymine (T), guanine (G), and cytosine (C). Genes are DNA sequences containing the information to synthesize proteins. The genes of higher eukaryotic organisms contain coding sequences, known as exons and non-coding sequences, known as introns, which are removed on splice sites after the DNA is transcribed into RNA. Genome annotation is the process of identifying the location of coding regions and determining their function. This process is fundamental for understanding gene structure; however, it is time-consuming and expensive when done by biochemical methods. With technological advances, splice site detection can be done computationally. Although various software tools have been developed to predict splice sites, they need to improve accuracy and reduce false-positive rates. The main goal of this research was to generate Deep Splicer, a deep learning model to identify splice sites in the genomes of humans and other species. This model has good performance metrics and a lower false-positive rate than the currently existing tools. Deep Splicer achieved an accuracy between 93.55% and 99.66% on the genetic sequences of different organisms, while Splice2Deep, another splice site detection tool, had an accuracy between 90.52% and 98.08%. Splice2Deep surpassed Deep Splicer on the accuracy obtained after evaluating C. elegans genomic sequences (97.88% vs. 93.62%) and A. thaliana (95.40% vs. 94.93%); however, Deep Splicer’s accuracy was better for H. sapiens (98.94% vs. 97.15%) and D. melanogaster (97.14% vs. 92.30%). The rate of false positives was 0.11% for human genetic sequences and 0.25% for other species’ genetic sequences. Another splice prediction tool, Splice Finder, had between 1% and 3% of false positives for human sequences, while other species’ sequences had around 4% and 10%. Full article

(1) Background: The study aimed to investigate the association between radioactive iodine (RAI) treatment and long-term gastrointestinal disorders including ulcers, atrophic gastritis, and secondary malignant neoplasm of the stomach in patients with thyroid cancer. (2) Methods: The data of the study were extracted from the National Health Insurance Database (NHIRD) of Taiwan between 2000 to 2015. Patients of ages older than 20 with thyroid cancer after thyroidectomy were included and divided into groups with RAI (study cohort) and without RAI (comparison cohort). Multivariate Cox proportional hazards regression analysis and the Kaplan–Meier method were used for statistical analysis. (3) Results: A total of 7250 (with RAI: 5800, without RAI: 1450) patients were included. The Kaplan-Meier analysis revealed a significantly higher cumulative risk for overall gastrointestinal disorders in the group with RAI (log-rank p = 0.034). The risk for gastrointestinal disorders was higher when receiving a cumulative RAI dose higher than 1.11 GBq in the Cox regression analysis. In the subgroup analysis, the risks of gastric and duodenal ulcers are significantly higher in the group with RAI treatment. (4) Conclusions: This study revealed that RAI was associated with an increased risk for long-term gastrointestinal disorders, specifically gastric and duodenal ulcers, in thyroid cancer, especially when the cumulative dose exceeds 1.11 GBq. Full article

Malaria is a severe parasite infectious disease with high fatality. As one of the approved treatments of this disease, hydroxychloroquine (HCQ) lacks clinical administration guidelines for patients with special health conditions and co-morbidities. This may result in improper dosing for different populations and lead them to suffer from severe side effects. One of the most important toxicities of HCQ overdose is cardiotoxicity. In this study, we built and validated a physiologically based pharmacokinetic modeling (PBPK) model for HCQ. With the full-PBPK model, we predicted the pharmacokinetic (PK) profile for malaria patients without other co-morbidities under the HCQ dosing regimen suggested by Food and Drug Administration (FDA) guidance. The PK profiles for different special populations were also predicted and compared to the normal population. Moreover, we proposed a series of adjusted dosing regimens for different populations with special health conditions and predicted the concentration-time (C-T) curve of the drug plasma concentration in these populations which include the pregnant population, elderly population, RA patients, and renal impairment populations. The recommended special population-dependent dosage regimens can maintain the similar drug levels observed in the virtual healthy population under the original dosing regimen provided by FDA. Last, we developed mathematic formulas for predicting dosage based on a patient’s body measurements and two indexes of renal function (glomerular filtration rate and serum creatine level) for the pediatric and morbidly obese populations. Those formulas can facilitate personalized treatment of this disease. We hope to provide some advice to clinical practice when taking HCQ as a treatment for malaria patients with special health conditions or co-morbidities so that they will not suffer from severe side effects due to higher drug plasma concentration, especially cardiotoxicity. Full article

Sex determination in forensic dentistry is a major step towards postmortem profiling. The most widely recognized method is DNA, yet its application in the dental field of forensic sciences is still impractical. Depending on the conditions of the remains, teeth are often the only surviving organ. Some systematic reviews (SRs) have been recently produced; hence this umbrella review critically assesses their level of evidence and provides an overall comprehensive view. An electronic database search was conducted in four databases (PubMed, Cochrane, Web of Science, and LILACS) and three grey search engines up to December 2021, focusing on SRs of sex determination through forensic dentistry procedures. The methodological quality of the SRs was analyzed using the measurement tool to assess SRs criteria (AMSTAR2). Five SRs were included, two of critically low quality and three of low quality. The SRs posited that canines are the most dimorphic teeth; oral tissue remnants are a rich source for sex determination by DNA tracing; and artificial intelligence tools demonstrate high potential in forensic dentistry. The quality of evidence on sex determination using dental approaches was rated as low. Well-designed clinical trials and high standard systematic reviews are essential to corroborate the accuracy of the different procedures of sex determination in forensic dentistry. Full article

Clear cell renal cell carcinoma (ccRCC) is the most prevalent subtype of renal cell carcinoma, which is characterized by metabolic reprogramming. Cuproptosis, a novel form of cell death, is highly linked to mitochondrial metabolism and mediated by protein lipoylation. However, the clinical impacts of cuproptosis-related genes (CRGs) in ccRCC largely remain unclear. In the current study, we systematically evaluated the genetic alterations of cuproptosis-related genes in ccRCC. Our results revealed that CDKN2A, DLAT, DLD, FDX1, GLS, PDHA1 and PDHB exhibited differential expression between ccRCC and normal tissues (|log₂(fold change)| > 2/3 and p < 0.05). Utilizing an iterative sure independence screening (SIS) method, we separately constructed the prognostic signature of CRGs for predicting the overall survival (OS) and progression-free survival (PFS) in ccRCC patients. The prognostic score of CRGs yielded an area under the curve (AUC) of 0.658 and 0.682 for the prediction of 5-year OS and PFS, respectively. In the Kaplan−Meier survival analysis of OS, a higher risk score of cuproptosis-related gene signature was significantly correlated with worse overall survival (HR = 2.72 (2.01–3.68), log-rank p = 1.76 × 10⁻⁷). Patients with a higher risk had a significantly shorter PFS (HR = 2.83 (2.08–3.85), log-rank p = 3.66 × 10⁻⁷). Two independent validation datasets (GSE40435 (N = 101), GSE53757 (N = 72)) were collected for meta-analysis, suggesting that CDKN2A (log₂(fold change) = 1.46, 95%CI: 1.75–2.35) showed significantly higher expression in ccRCC tissues while DLAT (log₂(fold change) = −0.54, 95%CI: −0.93–−0.15) and FDX1 (log₂(fold change) = −1.01, 95%CI: −1.61–−0.42) were lowly expressed. The expression of CDKN2A and FDX1 in ccRCC was also significantly associated with immune infiltration levels and programmed cell death protein 1 (PD-1) expression (CDKN2A: r = 0.24, p = 2.14 × 10⁻⁸; FDX1: r = −0.17, p = 1.37 × 10⁻⁴). In conclusion, the cuproptosis-related gene signature could serve as a potential prognostic predictor for ccRCC patients and may offer novel insights into the cancer treatment. Full article

Precision medicine can be defined as the comparison of a new patient with existing patients that have similar characteristics and can be referred to as patient similarity. Several deep learning models have been used to build and apply patient similarity networks (PSNs). However, the challenges related to data heterogeneity and dimensionality make it difficult to use a single model to reduce data dimensionality and capture the features of diverse data types. In this paper, we propose a multi-model PSN that considers heterogeneous static and dynamic data. The combination of deep learning models and PSN allows ample clinical evidence and information extraction against which similar patients can be compared. We use the bidirectional encoder representations from transformers (BERT) to analyze the contextual data and generate word embedding, where semantic features are captured using a convolutional neural network (CNN). Dynamic data are analyzed using a long-short-term-memory (LSTM)-based autoencoder, which reduces data dimensionality and preserves the temporal features of the data. We propose a data fusion approach combining temporal and clinical narrative data to estimate patient similarity. The experiments we conducted proved that our model provides a higher classification accuracy in determining various patient health outcomes when compared with other traditional classification algorithms. Full article