Bioinformatics and Medicine

A special issue of Journal of Personalized Medicine (ISSN 2075-4426). This special issue belongs to the section "Omics/Informatics".

Deadline for manuscript submissions: 5 June 2024 | Viewed by 16801

Special Issue Editors

Department of Radiological Informatics and Statistics, Medical University of Gdańsk, 80-210 Gdańsk, Poland
Interests: bioinformatics; graphical representations of biological sequences; biophysics; mathematical modeling in biomedical and social sciences; health and biomedical informatics
Special Issues, Collections and Topics in MDPI journals
Faculty of Health Sciences, Medical University of Gdańsk, 80-210 Gdańsk, Poland
Interests: bioinformatics; graphical representations of biological sequences; computational statistics; mathematical modeling in medicine, physics, astronomy; computational pharmacology
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues, 

We are launching a Special Issue entitled Bioinformatics and Medicine and are looking to publish original research, reviews, and combined original–review papers. This Special Issue is mainly devoted to a branch of bioinformatics known as “alignment-free bioinformatics methods”. This branch of bioinformatics, developed over the last two decades, is one of the most promising directions in the development of this area of science. In particular, articles on graphical representation methods, aimed at both the graphical and numerical analysis of the similarity/dissimilarity of biological sequences (DNA, RNA, and protein), are welcome. The submitted articles may contain descriptions of new algorithms. Papers dealing with different aspects of the graphical or numerical comparisons of the considered objects or focused on discussing a variety of applications of the methods already published in the biomedical sciences are also welcome. We will also accept papers related to standard bioinformatics methods and medical informatics.

Prof. Dr. Dorota Bielińska-Wąż
Prof. Dr. Piotr Wąż
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Journal of Personalized Medicine is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • bioinformatics
  • alignment-free bioinformatics methods
  • graphical bioinformatics
  • biomedical informatics
  • data analysis
  • mathematical modeling

Published Papers (12 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

20 pages, 5039 KiB  
Article
Integrating Optical Genome Mapping and Whole Genome Sequencing in Somatic Structural Variant Detection
by Laura Budurlean, Diwakar Bastihalli Tukaramrao, Lijun Zhang, Sinisa Dovat and James Broach
J. Pers. Med. 2024, 14(3), 291; https://doi.org/10.3390/jpm14030291 - 09 Mar 2024
Viewed by 685
Abstract
Structural variants drive tumorigenesis by disrupting normal gene function through insertions, inversions, translocations, and copy number changes, including deletions and duplications. Detecting structural variants is crucial for revealing their roles in tumor development, clinical outcomes, and personalized therapy. Presently, most studies rely on [...] Read more.
Structural variants drive tumorigenesis by disrupting normal gene function through insertions, inversions, translocations, and copy number changes, including deletions and duplications. Detecting structural variants is crucial for revealing their roles in tumor development, clinical outcomes, and personalized therapy. Presently, most studies rely on short-read data from next-generation sequencing that aligns back to a reference genome to determine if and, if so, where a structural variant occurs. However, structural variant discovery by short-read sequencing is challenging, primarily because of the difficulty in mapping regions of repetitive sequences. Optical genome mapping (OGM) is a recent technology used for imaging and assembling long DNA strands to detect structural variations. To capture the structural variant landscape more thoroughly in the human genome, we developed an integrated pipeline that combines Bionano OGM and Illumina whole-genome sequencing and applied it to samples from 29 pediatric B-ALL patients. The addition of OGM allowed us to identify 511 deletions, 506 insertions, 93 duplications/gains, and 145 translocations that were otherwise missed in the short-read data. Moreover, we identified several novel gene fusions, the expression of which was confirmed by RNA sequencing. Our results highlight the benefit of integrating OGM and short-read detection methods to obtain a comprehensive analysis of genetic variation that can aid in clinical diagnosis, provide new therapeutic targets, and improve personalized medicine in cancers driven by structural variation. Full article
(This article belongs to the Special Issue Bioinformatics and Medicine)
Show Figures

Figure 1

19 pages, 11875 KiB  
Article
Identifying Proteins and Amino Acids Associated with Liver Cancer Risk: A Study Utilizing Mendelian Randomization and Bulk RNA Sequencing Analysis
by Chi Ma, Ling Tang, Jiaqi Yao and Guang Tan
J. Pers. Med. 2024, 14(3), 262; https://doi.org/10.3390/jpm14030262 - 28 Feb 2024
Viewed by 716
Abstract
Background: Primary liver cancer (PLC) ranks third in terms of fatality rate among all malignant tumors worldwide. Proteomics and metabolomics have become widely utilized in identifying causes and diagnostic indicators of PLC. Nevertheless, in studies aiming to identify proteins/metabolites that experienced significant changes [...] Read more.
Background: Primary liver cancer (PLC) ranks third in terms of fatality rate among all malignant tumors worldwide. Proteomics and metabolomics have become widely utilized in identifying causes and diagnostic indicators of PLC. Nevertheless, in studies aiming to identify proteins/metabolites that experienced significant changes before PLC, the potential impact of reverse causation and confounding variables still needs to be fully addressed. Methods: This study thoroughly investigated the causal relationship between 4719 blood proteins, 21 amino acids, and the risk of PLC using the Mendelian randomization (MR) method. In addition, through a comprehensive analysis of the TCGA-LIHC cohort and GEO databases, we evaluated the differentially expressed genes (DEGs) related to serine metabolism in diagnosing and predicting the prognosis of patients with PLC. Results: A total of 63 proteins have been identified as connected to the risk of PLC. Additionally, there has been confirmation of a positive cause–effect between PLC and the concentration of serine. The integration of findings from both MR analyses determined that the protein associated with PLC risk exhibited a significant correlation with serine metabolism. Upon careful analysis of the TCGA-LIHC cohort, it was found that eight DEGs are linked to serine metabolism. After thoroughly validating the GEO database, two DEGs, TDO2 and MICB, emerged as potential biomarkers for diagnosing PLC. Conclusions: Two proteins involved in serine metabolism, MICB and TDO2, are causally linked to the risk of PLC and could potentially be used as diagnostic indicators. Full article
(This article belongs to the Special Issue Bioinformatics and Medicine)
Show Figures

Figure 1

11 pages, 2296 KiB  
Article
Multi-Omics Reveals the Role of Osteopontin/Secreted Phosphoprotein 1 in Regulating Ovarian Aging
by Li-Chuan Hsu, Chia-Jung Li, Li-Te Lin, Li-Fei Pan, Zhi-Hong Wen, Jim Jinn-Chyuan Sheu and Kuan-Hao Tsui
J. Pers. Med. 2024, 14(1), 78; https://doi.org/10.3390/jpm14010078 - 09 Jan 2024
Viewed by 1019
Abstract
Secreted phosphoprotein 1 (SPP1), also known as osteopontin (OPN), is located on chromosome 4q22.1. This multifunctional secreted acidic glycoprotein is expressed intracellularly and extracellularly in various tissues, where it interacts with regulatory proteins and pro-inflammatory immune chemokines, contributing to the pathogenesis of multiple [...] Read more.
Secreted phosphoprotein 1 (SPP1), also known as osteopontin (OPN), is located on chromosome 4q22.1. This multifunctional secreted acidic glycoprotein is expressed intracellularly and extracellularly in various tissues, where it interacts with regulatory proteins and pro-inflammatory immune chemokines, contributing to the pathogenesis of multiple diseases. Nevertheless, the intricate genetic connections between SPP1 and ovarian aging remain largely unexplored. This study aims to bridge this knowledge gap by delving into ovarian aging and its associations with SPP1 using multi-omics data analysis. Our findings indicate that SPP1 is a potential gene related to ovarian aging. To comprehend the role of SPP1, we conducted spatial transcriptomic analyses on young and aged female mouse ovaries, revealing a significant decline in SPP1 expression in the aging group compared to the young group. Similarly, a significantly low level of SPP1 was found in the 73-year-old sample. Additionally, in-depth single-cell RNA-sequencing analysis identified associations between SPP1 and ITGAV, ITGB1, CD44, MMP3, and FN1. Notably, co-expression analysis highlighted a strong correlation between SPP1 and ITGB1. In summary, this study pioneers the identification of SPP1 as a gene implicated in ovarian aging. Further research into the role of SPP1 has the potential to advance precision medicine and improve treatment strategies for ovarian aging-related conditions. Full article
(This article belongs to the Special Issue Bioinformatics and Medicine)
Show Figures

Figure 1

12 pages, 3327 KiB  
Article
Association between the Number of Days/Week of Different Levels of Physical Activity and Chronic Pain in People of Different Races: A Mendelian Randomization Study
by Sumei Luo, Minjing Yang, Haojun Yang, Qulian Guo, Yunjiao Wang and E Wang
J. Pers. Med. 2024, 14(1), 50; https://doi.org/10.3390/jpm14010050 - 29 Dec 2023
Viewed by 808
Abstract
Objective: Regular physical activity is beneficial for health, but the effect of the number of days/week of physical activity on chronic pain (CP) remains unclear, so we used a two-sample Mendelian randomization (MR) analysis to explore the relationship between the number of days/weeks [...] Read more.
Objective: Regular physical activity is beneficial for health, but the effect of the number of days/week of physical activity on chronic pain (CP) remains unclear, so we used a two-sample Mendelian randomization (MR) analysis to explore the relationship between the number of days/weeks of different levels of physical activity and chronic pain in people of different races. Methods: We obtained summary data from genome-wide association studies (GWASs) on the number of days/week of physical activity and multisite chronic pain in European, South Asian, East Asian, Middle Eastern, and African American populations. The single-nucleotide polymorphisms (SNPs) of the exposed data were visualized with a Manhattan plot via the R program. MR analysis was performed by the MR-Base platform. Results: The results indicated that a higher number of days/week with ≥10 min of walking protects against CP in African American and Afro-Caribbean populations (inverse-variance weighting, IVW p < 0.05) but has little effect on people of different races (IVW p > 0.05). A higher number of days/week with ≥10 min of moderate physical activity increased the risk of CP in European and South Asia (IVW p < 0.05) but had little effect on people of different races (IVW p > 0.05). The number of days/week of ≥10 min of vigorous physical activity increased the risk of CP in Europeans (IVW p < 0.05) and protected against CP in African Americans and Afro-Caribbeans (IVW p < 0.05). Conclusions: A higher number of days/week of moderate and vigorous physical activity increased the risk of CP in Europeans; however, a higher number of days/week of walking and vigorous physical activity may protect against CP in African American and Afro-Caribbean individuals. Full article
(This article belongs to the Special Issue Bioinformatics and Medicine)
Show Figures

Figure 1

17 pages, 1569 KiB  
Article
Classification Maps: A New Mathematical Tool Supporting the Diagnosis of Age-Related Macular Degeneration
by Piotr Wąż, Katarzyna Zorena, Anna Murawska and Dorota Bielińska-Wąż
J. Pers. Med. 2023, 13(7), 1074; https://doi.org/10.3390/jpm13071074 - 29 Jun 2023
Viewed by 815
Abstract
Objective: A new diagnostic graphical tool—classification maps—supporting the detection of Age-Related Macular Degeneration (AMD) has been constructed. Methods: The classification maps are constructed using the ordinal regression model. In the ordinal regression model, the ordinal variable (the dependent variable) is the degree of [...] Read more.
Objective: A new diagnostic graphical tool—classification maps—supporting the detection of Age-Related Macular Degeneration (AMD) has been constructed. Methods: The classification maps are constructed using the ordinal regression model. In the ordinal regression model, the ordinal variable (the dependent variable) is the degree of the advancement of AMD. The other variables, such as CRT (Central Retinal Thickness), GCC (Ganglion Cell Complex), MPOD (Macular Pigment Optical Density), ETDRS (Early Treatment Diabetic Retinopathy Study), Snellen and Age have also been used in the analysis and are represented on the axes of the maps. Results: Here, 132 eyes were examined and classified to the AMD advancement level according to the four-point Age-Related Eye Disease Scale (AREDS): AREDS 1, AREDS 2, AREDS 3 and AREDS 4. These data were used for the creation of two-dimensional classification maps for each of the four stages of AMD. Conclusions: The maps allow us to perform the classification of the patient’s eyes to particular stages of AMD. The pairs of the variables represented on the axes of the maps can be treated as diagnostic identifiers necessary for the classification to particular stages of AMD. Full article
(This article belongs to the Special Issue Bioinformatics and Medicine)
Show Figures

Figure 1

22 pages, 6449 KiB  
Article
Integrated Bioinformatics Investigation of Novel Biomarkers of Uterine Leiomyosarcoma Diagnosis and Outcome
by Aleksandar Rakic, Radomir Anicic, Marija Rakic and Lazar Nejkovic
J. Pers. Med. 2023, 13(6), 985; https://doi.org/10.3390/jpm13060985 - 13 Jun 2023
Viewed by 1499
Abstract
Uterine leiomyosarcomas (uLMS) have a poor prognosis and a high percentage of recurrent disease. Bioinformatics has become an integral element in rare cancer studies by overcoming the inability to collect a large enough study population. This study aimed to investigate and highlight crucial [...] Read more.
Uterine leiomyosarcomas (uLMS) have a poor prognosis and a high percentage of recurrent disease. Bioinformatics has become an integral element in rare cancer studies by overcoming the inability to collect a large enough study population. This study aimed to investigate and highlight crucial genes, pathways, miRNAs, and transcriptional factors (TF) on uLMS samples from five Gene Expression Omnibus datasets and The Cancer Genome Atlas Sarcoma study. Forty-one common differentially expressed genes (DEGs) were enriched and annotated by the DAVID software. With protein–protein interaction (PPI) network analysis, we selected ten hub genes that were validated with the TNMplotter web tool. We used the USCS Xena browser for survival analysis. We also predicted TF-gene and miRNA-gene regulatory networks along with potential drug molecules. TYMS and TK1 correlated with overall survival in uLMS patients. Finally, our results propose further validation of hub genes (TYMS and TK1), miR-26b-5p, and Sp1 as biomarkers of pathogenesis, prognosis, and differentiation of uLMS. Regarding the aggressive behavior and poor prognosis of uLMS, with the lack of standard therapeutic regimens, in our opinion, the results of our study provide enough evidence for further investigation of the molecular basis of uLMS occurrence and its implication in the diagnosis and therapy of this rare gynecological malignancy. Full article
(This article belongs to the Special Issue Bioinformatics and Medicine)
Show Figures

Figure 1

12 pages, 715 KiB  
Article
Susceptibility to Colorectal Cancer Based on HSD17B4 rs721673 and rs721675 Polymorphisms and Alcohol Intake among Taiwan Biobank Participants: A Retrospective Case Control Study Using the Nationwide Claims Data
by Tzu-Chiao Lin, Min-Hua Chuang, Chia-Ni Hsiung, Pi-Kai Chang, Chien-An Sun, Tsan Yang, Yu-Ching Chou, Je-Ming Hu and Chih-Hsiung Hsu
J. Pers. Med. 2023, 13(4), 576; https://doi.org/10.3390/jpm13040576 - 24 Mar 2023
Viewed by 1196
Abstract
Colorectal cancer (CRC) is a major public health issue, and there are limited studies on the association between 17β-hydroxysteroid dehydrogenase type 4 (HSD17B4) polymorphism and CRC. We used two national databases from Taiwan to examine whether HSD17B4 rs721673, rs721675, and alcohol intake were [...] Read more.
Colorectal cancer (CRC) is a major public health issue, and there are limited studies on the association between 17β-hydroxysteroid dehydrogenase type 4 (HSD17B4) polymorphism and CRC. We used two national databases from Taiwan to examine whether HSD17B4 rs721673, rs721675, and alcohol intake were independently and interactively correlated with CRC development. We linked the Taiwan Biobank (TWB) participants’ health and lifestyle information and genotypic data from 2012 to 2018 to the National Health Insurance Database (NHIRD) to confirm their medical records. We performed a genome-wide association study (GWAS) using data from 145 new incident CRC cases and matched 1316 healthy, non-CRC individuals. We calculated the odds ratios (OR) and 95% confidence intervals (CI) for CRC based on multiple logistic regression analyses. HSD17B4 rs721673 and rs721675 on chromosome 5 were significantly and positively correlated with CRC (rs721673 A > G, aOR = 2.62, p = 2.90 × 10−8; rs721675 A > T, aOR = 2.61, p = 1.01 × 10−6). Within the high-risk genotypes, significantly higher ORs were observed among the alcohol intake group. Our results demonstrated that the rs721673 and rs721675 risk genotypes of HSD17B4 might increase the risk of CRC development in Taiwanese adults, especially those with alcohol consumption habits. Full article
(This article belongs to the Special Issue Bioinformatics and Medicine)
Show Figures

Figure 1

16 pages, 6919 KiB  
Article
High-Throughput Sequencing Reveals That Rotundine Inhibits Colorectal Cancer by Regulating Prognosis-Related Genes
by Lingyu Huang, Tongxiang Zou, Wenken Liang, Chune Mo, Jianfen Wei, Yecheng Deng and Minglin Ou
J. Pers. Med. 2023, 13(3), 550; https://doi.org/10.3390/jpm13030550 - 20 Mar 2023
Viewed by 1450
Abstract
Background: Rotundine is an herbal medicine with anti-cancer effects. However, little is known about the anti-cancer effect of rotundine on colorectal cancer. Therefore, our study aimed to investigate the specific molecular mechanism of rotundine inhibition of colorectal cancer. Methods: MTT and cell scratch [...] Read more.
Background: Rotundine is an herbal medicine with anti-cancer effects. However, little is known about the anti-cancer effect of rotundine on colorectal cancer. Therefore, our study aimed to investigate the specific molecular mechanism of rotundine inhibition of colorectal cancer. Methods: MTT and cell scratch assay were performed to investigate the effects of rotundine on the viability, migration, and invasion ability of SW480 cells. Changes in cell apoptosis were analyzed by flow cytometry. DEGs were detected by high-throughput sequencing after the action of rotundine on SW480 cells, and the DEGs were subjected to function enrichment analysis. Bioinformatics analyses were performed to screen out prognosis-related DEGs of COAD. Followed by enrichment analysis of prognosis-related DEGs. Furthermore, prognostic models were constructed, including ROC analysis, risk curve analysis, PCA and t-SNE, Nomo analysis, and Kaplan–Meier prognostic analysis. Results: In this study, we showed that rotundine concentrations of 50 μM, 100 μM, 150 μM, and 200 μM inhibited the proliferation, migration, and invasion of SW480 cells in a time- and concentration-dependent manner. Rotundine does not induce SW480 cell apoptosis. Compared to the control group, high-throughput results showed that there were 385 DEGs in the SW480 group. And DEGs were associated with the Hippo signaling pathway. In addition, 16 of the DEGs were significantly associated with poorer prognosis in COAD, with MEF2B, CCDC187, PSD2, RGS16, PLXDC1, HELB, ASIC3, PLCH2, IGF2BP3, CLHC1, DNHD1, SACS, H1-4, ANKRD36, and ZNF117 being highly expressed in COAD and ARV1 being lowly expressed. Prognosis-related DEGs were mainly enriched in cancer-related pathways and biological functions, such as inositol phosphate metabolism, enterobactin transmembrane transporter activity, and enterobactin transport. Prognostic modeling also showed that these 16 DEGs could be used as predictors of overall survival prognosis in COAD patients. Conclusions: Rotundine inhibits the development and progression of colorectal cancer by regulating the expression of these prognosis-related genes. Our findings could further provide new directions for the treatment of colorectal cancer. Full article
(This article belongs to the Special Issue Bioinformatics and Medicine)
Show Figures

Figure 1

22 pages, 6259 KiB  
Article
Identification of Five Tumor Antigens for Development and Two Immune Subtypes for Personalized Medicine of mRNA Vaccines in Papillary Renal Cell Carcinoma
by Jianpei Hu, Zhongze Yuan, Yifen Jiang and Zengnan Mo
J. Pers. Med. 2023, 13(2), 359; https://doi.org/10.3390/jpm13020359 - 18 Feb 2023
Viewed by 1598
Abstract
Increasing evidence has revealed the promise of mRNA-type cancer vaccines as a new direction for cancer immune treatment in several solid tumors, however, its application in papillary renal cell carcinoma (PRCC) remains unclear. The purpose of this study was to identify potential tumor [...] Read more.
Increasing evidence has revealed the promise of mRNA-type cancer vaccines as a new direction for cancer immune treatment in several solid tumors, however, its application in papillary renal cell carcinoma (PRCC) remains unclear. The purpose of this study was to identify potential tumor antigens and robust immune subtypes for the development and appropriate use of anti-PRCC mRNA vaccines, respectively. Raw sequencing data and clinical information of PRCC patients were downloaded from The Cancer Genome Atlas (TCGA) database. The cBioPortal was utilized for the visualization and comparison of genetic alterations. The TIMER was used to assess the correlation between preliminary tumor antigens and the abundance of infiltrated antigen presenting cells (APCs). Immune subtypes were determined by the consensus clustering algorithm, and clinical and molecular discrepancies were further explored for a deeper understanding of immune subtypes. Five tumor antigens, including ALOX15B, HS3ST2, PIGR, ZMYND15 and LIMK1, were identified for PRCC, which were correlated with patients’ prognoses and infiltration levels of APCs. Two immune subtypes (IS1 and IS2) were disclosed with obviously distinct clinical and molecular characteristics. Compared with IS2, IS1 exhibited a significantly immune-suppressive phenotype, which largely weakened the efficacy of the mRNA vaccine. Overall, our study provides some insights for the design of anti-PRCC mRNA vaccines and, more importantly, the selection of suitable patients to be vaccinated. Full article
(This article belongs to the Special Issue Bioinformatics and Medicine)
Show Figures

Figure 1

12 pages, 1124 KiB  
Article
Progression of Selected Parameters of the Clinical Profile of Patients with Periodontitis Using Kohonen’s Self-Organizing Maps
by Agata Ossowska, Aida Kusiak and Dariusz Świetlik
J. Pers. Med. 2023, 13(2), 346; https://doi.org/10.3390/jpm13020346 - 16 Feb 2023
Viewed by 1127
Abstract
(1) Background: Periodontitis is an inflammatory condition that affects the tissues surrounding the tooth and causes clinical attachment loss, which is the loss of periodontal attachment (CAL). Periodontitis can advance in various ways, with some patients experiencing severe periodontitis in a short period [...] Read more.
(1) Background: Periodontitis is an inflammatory condition that affects the tissues surrounding the tooth and causes clinical attachment loss, which is the loss of periodontal attachment (CAL). Periodontitis can advance in various ways, with some patients experiencing severe periodontitis in a short period of time while others may experience mild periodontitis for the rest of their lives. In this study, we have used an alternative methodology to conventional statistics, self-organizing maps (SOM), to group the clinical profiles of patients with periodontitis. (2) Methods: To predict the periodontitis progression and to choose the best treatment plan, we can use artificial intelligence, more precisely Kohonen’s self-organizing maps (SOM). In this study, 110 patients, both genders, between the ages of 30 and 60, were included in this retrospective analysis. (3) Results: To discover the pattern of patients according to the periodontitis grade and stage, we grouped the neurons together to form three clusters: Group 1 was made up of neurons 12 and 16 that represented a percentage of slow progression of almost 75%; Group 2 was made up of neurons 3, 4, 6, 7, 11, and 14 in which the percentage of moderate progression was almost 65%; and Group 3 was made up of neurons 1, 2, 5, 8, 9, 10, 13, and 15 that represented a percentage of rapid progression of almost 60%. There were statistically significant differences in the approximate plaque index (API), and bleeding on probing (BoP) versus groups (p < 0.0001). The post-hoc tests showed that API, BoP, pocket depth (PD), and CAL values were significantly lower in Group 1 relative to Group 2 (p < 0.05) and Group 3 (p < 0.05). A detailed statistical analysis showed that the PD value was significantly lower in Group 1 relative to Group 2 (p = 0.0001). Furthermore, the PD was significantly higher in Group 3 relative to Group 2 (p = 0.0068). There was a statistically significant CAL difference between Group 1 relative to Group 2 (p = 0.0370). (4) Conclusions: Self-organizing maps, in contrast to conventional statistics, allow us to view the issue of periodontitis advancement by illuminating how the variables are organized in one or the other of the various suppositions. Full article
(This article belongs to the Special Issue Bioinformatics and Medicine)
Show Figures

Figure 1

12 pages, 1729 KiB  
Article
Construction of Tongue Image-Based Machine Learning Model for Screening Patients with Gastric Precancerous Lesions
by Changzheng Ma, Peng Zhang, Shiyu Du, Yan Li and Shao Li
J. Pers. Med. 2023, 13(2), 271; https://doi.org/10.3390/jpm13020271 - 31 Jan 2023
Cited by 7 | Viewed by 1899
Abstract
Screening patients with precancerous lesions of gastric cancer (PLGC) is important for gastric cancer prevention. The accuracy and convenience of PLGC screening could be improved with the use of machine learning methodologies to uncover and integrate valuable characteristics of noninvasive medical images related [...] Read more.
Screening patients with precancerous lesions of gastric cancer (PLGC) is important for gastric cancer prevention. The accuracy and convenience of PLGC screening could be improved with the use of machine learning methodologies to uncover and integrate valuable characteristics of noninvasive medical images related to PLGC. In this study, we therefore focused on tongue images and for the first time constructed a tongue image-based PLGC screening deep learning model (AITongue). The AITongue model uncovered potential associations between tongue image characteristics and PLGC, and integrated canonical risk factors, including age, sex, and Hp infection. Five-fold cross validation analysis on an independent cohort of 1995 patients revealed the AITongue model could screen PLGC individuals with an AUC of 0.75, 10.3% higher than that of the model with only including canonical risk factors. Of note, we investigated the value of the AITongue model in predicting PLGC risk by establishing a prospective PLGC follow-up cohort, reaching an AUC of 0.71. In addition, we developed a smartphone-based app screening system to enhance the application convenience of the AITongue model in the natural population from high-risk areas of gastric cancer in China. Collectively, our study has demonstrated the value of tongue image characteristics in PLGC screening and risk prediction. Full article
(This article belongs to the Special Issue Bioinformatics and Medicine)
Show Figures

Figure 1

17 pages, 6551 KiB  
Article
Three-Dimensional Semantic Segmentation of Diabetic Retinopathy Lesions and Grading Using Transfer Learning
by Natasha Shaukat, Javeria Amin, Muhammad Sharif, Faisal Azam, Seifedine Kadry and Sujatha Krishnamoorthy
J. Pers. Med. 2022, 12(9), 1454; https://doi.org/10.3390/jpm12091454 - 05 Sep 2022
Cited by 12 | Viewed by 1846
Abstract
Diabetic retinopathy (DR) is a drastic disease. DR embarks on vision impairment when it is left undetected. In this article, learning-based techniques are presented for the segmentation and classification of DR lesions. The pre-trained Xception model is utilized for deep feature extraction in [...] Read more.
Diabetic retinopathy (DR) is a drastic disease. DR embarks on vision impairment when it is left undetected. In this article, learning-based techniques are presented for the segmentation and classification of DR lesions. The pre-trained Xception model is utilized for deep feature extraction in the segmentation phase. The extracted features are fed to Deeplabv3 for semantic segmentation. For the training of the segmentation model, an experiment is performed for the selection of the optimal hyperparameters that provided effective segmentation results in the testing phase. The multi-classification model is developed for feature extraction using the fully connected (FC) MatMul layer of efficient-net-b0 and pool-10 of the squeeze-net. The extracted features from both models are fused serially, having the dimension of N × 2020, amidst the best N × 1032 features chosen by applying the marine predictor algorithm (MPA). The multi-classification of the DR lesions into grades 0, 1, 2, and 3 is performed using neural network and KNN classifiers. The proposed method performance is validated on open access datasets such as DIARETDB1, e-ophtha-EX, IDRiD, and Messidor. The obtained results are better compared to those of the latest published works. Full article
(This article belongs to the Special Issue Bioinformatics and Medicine)
Show Figures

Figure 1

Back to TopTop