Next Article in Journal
Real-Time Jaundice Detection in Neonates Based on Machine Learning Models
Next Article in Special Issue
The Development and Usability Assessment of an Augmented Reality Decision Support System to Address Burn Patient Management
Previous Article in Journal
Development and Practical Applications of Computational Intelligence Technology
Previous Article in Special Issue
Depleted-MLH1 Expression Predicts Prognosis and Immunotherapeutic Efficacy in Uterine Corpus Endometrial Cancer: An In Silico Approach
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
BioMedInformatics
Volume 4
Issue 1
10.3390/biomedinformatics4010033
biomedinformatics-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles thumb_up
...
Endorse textsms
...
Comment
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Machine Learning Approach to Identify Case-Control Studies on ApoE Gene Mutations Linked to Alzheimer’s Disease in Italy

by
Giorgia Francesca Saraceno
1,
Diana Marisol Abrego-Guandique
2,
Roberto Cannataro
3,4,
Maria Cristina Caroleo
2,3 and
Erika Cione
1,3,*
1
Department of Pharmacy, Health and Nutritional Sciences, University of Calabria, 87036 Rende, Italy
2
Department of Health Sciences, University of Magna Graecia Catanzaro, 88100 Catanzaro, Italy
3
Galascreen Laboratories, University of Calabria, 87036 Rende (CS), Italy
4
Research Division, Dynamical Business & Science Society—DBSS International SAS, Bogotá 110311, Colombia
*
Author to whom correspondence should be addressed.
BioMedInformatics 2024, 4(1), 600-622; https://doi.org/10.3390/biomedinformatics4010033
Submission received: 17 January 2024 / Revised: 14 February 2024 / Accepted: 21 February 2024 / Published: 23 February 2024
(This article belongs to the Special Issue Feature Papers in Computational Biology and Medicine)
Browse Figures
Versions Notes

Abstract

:
Background: An application of artificial intelligence is machine learning, which allows computer programs to learn and create data. Methods: In this work, we aimed to evaluate the performance of the MySLR machine learning platform, which implements the Latent Dirichlet Allocation (LDA) algorithm in the identification and screening of papers present in the literature that focus on mutations of the apolipoprotein E (ApoE) gene in Italian Alzheimer’s Disease patients. Results: MySLR excludes duplicates and creates topics. MySLR was applied to analyze a set of 164 scientific publications. After duplicate removal, the results allowed us to identify 92 papers divided into two relevant topics characterizing the investigated research area. Topic 1 contains 70 papers, and topic 2 contains the remaining 22. Despite the current limitations, the available evidence suggests that articles containing studies on Italian Alzheimer’s Disease (AD) patients were 65.22% (n = 60). Furthermore, the presence of papers about mutations, including single nucleotide polymorphisms (SNPs) ApoE gene, the primary genetic risk factor of AD, for the Italian population was 5.4% (n = 5). Conclusion: The results show that the machine learning platform helped to identify case-control studies on ApoE gene mutations, including SNPs, but not only conducted in Italy.

Graphical Abstract

1. Introduction

Alzheimer’s disease (AD) is the most common cause of dementia, accounting for approximately 60–80% of all dementia cases [1]. Numerous susceptibility genes and coding variants associated with the risk of developing AD have been identified so far [2,3]. The apolipoprotein E (ApoE) gene is the primary risk factor [4]. ApoE gene has three variant alleles (epsilon 2, epsilon 3, and epsilon 4), with differences in amino acid residues 112 and 158, which generate six genotypes (ε2/ε2, ε2/ε3, ε2/ε4, ε3/ε3, ε3/ε4, and ε4/ε4) and lead to three isoforms, E2, E3, E4 [4]. It is worth noting that ApoE is a 299-amino-acid glycoprotein with a molecular mass of ~34 kDa. Individuals possessing at least one copy of the ε4 allele in their genetic makeup are more susceptible to AD than those with ε3 [5]. Conversely, ε2 is suggested to have a protective effect [6]. Mutations, including Single Nucleotide Polymorphisms (SNPs) in the ApoE gene, were associated with the prevalence of AD [7,8,9]. SNPs on ApoE were linked to ethnicity [10]. Artificial intelligence (AI) represents a contemporary technological discipline dedicated to exploring and formulating hypotheses, strategies, technologies, and application systems aimed at emulating and expanding upon the facets of human intelligence [11]. Arthur Samuel coined the term “Machine Learning” in 1959 to refer to a set of algorithms and the development of classifiers. The algorithm automatically learns from input data and constructs a model to anticipate new data [12] accurately. Today, with advances in artificial intelligence, machine learning is concerned with the development and application of computer algorithms that improve with experience [13]; traditionally, the management of extensive collections of paper has been organized and treated by topic using spreadsheets [14], dictionaries or supervised methods [15]; these types of approaches are very laborious and expensive and require good knowledge of the research field in which one wishes to operate. Thanks to the refinement of machine learning techniques, many of the steps in the literature review process have been simplified and automated, reducing workload for researchers and the time needed to evaluate the literature [16]. The digitization of healthcare data and the exponential spread of technology and new machine learning technologies are driving progress in the development and use of artificial intelligence in the healthcare sector [17,18]. AI is used to improve the precision medicine approach to treating neurodegeneration [19]. This work aimed to evaluate whether the MySLR platform based on machine learning can help extract scientific works focusing on SNPs on the ApoE gene in the Italian AD population.

2. Materials and Methods

A machine learning methodology was used to conduct a thorough analysis of a substantial volume of the scientific literature, extracting knowledge essential for the objectives of this research. While traditional algorithms are typically delineated for numerical and structured data, the content found in the scientific literature comprises unstructured documents, such as papers. To handle this unstructured textual data, the Latent Dirichlet Allocation (LDA) algorithm was selected to extend machine learning applications, particularly in extracting information from scientific journal articles [20]. The MySLR platform, using the LDA algorithm, emulates the behavior of “human-like intelligence” as accurately as possible. It can efficiently process substantial volumes of data, interpret texts, comprehend their content, extract necessary information, and reveal disguised connections among papers. This methodology involves establishing a model that individually identifies a set of “topics” (or themes) within texts, discerns the specific topic addressed by each, and subsequently recognizes the presence of these identified topics within various papers [21]. The platform is accessible at https://myslr.unical.it following registration (accessed on 10 November 2023).

2.1. Paper Location and Selection

We conducted specific research on three databases (Scopus, Web of Science, and Pubmed) to provide a comprehensive overview of scientific research concerning the presence of SNPs on the ApoE gene in the Italian population. The methodological approach involves three key steps: paper location and selection, paper analysis, and results presentation, aligning with the framework proposed by Denyer and Tranfield [22]. Three investigators (G.F.A.S, D.M.A.G., and E.C.) independently searched the PubMed, Scopus, and Web of Science databases to identify publications in peer-reviewed journals published before 10 November 2023. The search was conducted using the Boolean operators “AND” and “OR” to combine the following terms:(“snps” OR “single nucleotide polymorphism” OR “Single-nucleotide polymorphism”) AND (“ApoE” OR “apoliprotein E” AND (“Alzheimer disease” OR “alzheimer’s disease” OR “AD” OR “LOAD”) AND (italian OR italy)”. By identifying primary topics within a collection of documents, topic modeling can generate succinct summaries that encapsulate the core content. The search conducted through Boolean operators allowed us to identify one hundred and sixty-four papers (n = 41 from Scopus, n = 61 from Web of Science, n = 62 from Pubmed), Figure 1. After duplicate removal assisted by the MySLR platform, ninety-two papers resulted from the three databases.

2.2. Paper Analysis

We applied a text-mining approach to the ultimate set of ninety-two papers to spotlight the primary research themes related to SNPs in the ApoE gene only in the Italian population. This approach relies on LDA, a statistical method that divides topics into each document. The model treats documents as probability distributions of topics and topics as distributions of words. In Natural Language Processing, a topic model is a statistical framework designed to identify abstract “topics” or themes within a collection of documents. These topics are not predetermined but are autonomously identified by the algorithm based on the frequency and occurrence of words in the texts. Leveraging such statistical principles, the employed algorithm identified two primary overarching topics (referred to as topics) linked to the keywords generated by the LDA procedure in the texts. It accurately assigned each text its corresponding semantic topic. The output of this procedure includes:
  • k sets of relevant keywords (each set representing a topic).
  • The document-term matrix depicts the statistical relationship between each paper and a specific topic (namely, the topic proportion).
This step aims to clearly articulate and explore the findings of the LDA procedure through an in-depth, human-based examination of significant papers clustered around the two identified topics. To assess the capability of the MySLR machine learning tool, we opted to retain all the papers retrieved using the specified search string. Following the recommendations of Blei [20], we set the value of k (number of topics to be extracted) to two. This choice resulted in a satisfactory topic coherence value (−1.15) [23], aligning with the ease of interpreting results for human readers. Topic coherence assesses the level of semantic similarity among highly scored words within a topic. This coefficient is a metric to gauge the quality of topic modeling, differentiating between semantically coherent arguments and mere statistical inference artifacts [24].

2.3. Results Presentation

The final stage of our methodological approach is explained in the “Results and Discussion” section. The objective at this stage is to provide a clear description and discuss the outcomes derived from the LDA procedure through a comprehensive human-based review of noteworthy papers clustered around the two identified topics by MySLR. The three steps of the machine learning process are illustrated in Figure 2.
After these steps, with a dropdown menu, the MySLR allow us to identify studies classified as article, journal article, conference paper, proceeding paper, reviews. In our case, we did not find editorial articles, meta-analyses, letters to the editors, short communications, erratum, book chapters, notes, opinions, and personal comments, or retracted publications. Since our aim was to assess platform functionality, we did not exclude reviews from our tests. The flowchart, reported in Figure 3, depicts the selection algorithm.

3. Results

The initial literature search retrieved data from the MySLR platform, which loaded an overall published paper and ninety-two unique studies.
Utilizing the LDA procedure, we identified pertinent keywords linked to the two topics. Figure 4 illustrates the most significant keywords for each topic, visually represented through a “word cloud”.
Topic 1 counts 70 papers and Topic 2 counts 22, as shown in Figure 5. From the analysis of the keywords, it was possible to identify the central theme of the two topics based on their relative weight. The weight of each keyword is calculated based on how often that keyword is repeated within the topic, also considering word associations. The MySLR platform can graph the final weight of the two topics (Figure 5), considering the weight of each keyword, the frequency with which the keyword is repeated, and the associations between keywords. Documents for topic one weigh 70,393, and documents for topic two weigh 21,607.
The platform can produce a graph showing the number of articles published per year, as shown in Figure 6. Interest in the topic grew significantly from 2002 onwards, especially in 2008 and 2010.
Machine Learning also provides a way to show the trend of the topics over time. It also allows us to show the trend of topics over time. As shown in Figure 7, the interest in the two topics has a different trend over time: topic 1 generated much more interest in the scientific community, especially in the 2008–2010 period, where it reached the maximum interest. Even in 2016, interest was high, despite not exceeding the 2008–2010 threshold. For topic 2, the highest interest was reached in 2006 and 2012.

3.1. Topic 1: Gene Polymorphisms Risk Factor for Alzheimer’s Disease

Examining the top 30 most relevant terms and their frequency within papers grouped around the chosen topic, “load” (late-onset late-onset alzheimer’s disease) reached the highest value (Figure 8). Analyzing the seventy papers clustered around this topic, it became apparent that the focal point of the topic was the influence of gene polymorphism on the progression and manifestation of AD, but not what we were searching for.
To gain insight into the papers generated by the machine learning algorithm under our query, we constructed a table delineating the main characteristics of each study, Table 1. Of the seventy papers in topic 1, 11.4% (n = 8) were not carried out in Italy, and we indicated it as “Not in Italy”. The 1.4% (n = 1) were not carried only in Italy (in this case, we only considered the Italian population for studies that involved clustering the sample based on the state of origin. We left the wording “Not only in Italy” only for studies that did not include this clustering, while the studies that had the Italian population clustered were indicated as “Italy”); 2.85% (n = 2) were reviews or systematic reviews. Although there is a function to choose not to include it in the paper selection, we left it as such at this stage. The 8.57% (n = 6) were not considered as they were not conducted in Alzheimer’s patients and therefore did not answer the search query. It is worth to mention here that AD is the most frequent type of dementia associated with genetic mutations [25,26].

3.2. Topic 2: The Enigma of Alzheimer’s: Investigating Genetic Patterns, Genotypes as a Future Biomarker

The top 30 most relevant terms of this topic (i.e., the most frequent terms within papers grouped in this topic, Figure 9) indicate a research “biomarker”, focusing on evaluating SNPs’ translation research. Indeed, the twenty-two analyzed articles aimed to elucidate the relationship of SNPs expressed pathological clinical data and evaluate SNPs’ potential as biomarkers in AD.
For the second topic, we built Table 2, which included the main characteristics of interest to us, intending to evaluate MySLR ability to help us to select papers. Of the twenty-two papers included in topic 2, 13.6% (n = 3) were not carried out in Italy, and we indicated it as “Not in Italy”, 4.5% (n = 1) do not specify the origin of the patients and controls, 13.6% (n = 3) are reviews or systematic reviews. The 27.2% (n = 6) were not considered, as they were not conducted in Alzheimer’s patients and therefore did not answer the search query. A total of 4.5% (n = 1) of the studies included in topic two concern SNP on ApoE in the Italian population.
Therefore, MySLR, after duplicate removal, allowed us to identify 92 papers divided into two relevant topics characterizing the investigated research area. Despite the current limitations, the available evidence suggests that articles containing studies on AD patients were the 65.22% (n = 60) but the presence of papers about mutations, including SNPs on ApoE gene, for the Italian population was only 5.4% (n = 5)—four of them present in topic 1 and one in topic 2. Therefore, the machine learning used here pointed out five papers work that met our criteria and that we listed in Table 3 specifically.
This approach, which features human-like intelligence, helped us to examine the scientific literature as effectively and rapidly as possible. The machine learning approach allowed us to obtain numerous graphical representations of the data to orient us in choosing the scientific purpose we want. The t-distributed Stochastic Neighbor Embedding (t-SNE) algorithm is shown in Figure 10.
The graph’s points symbolize documents (scientific sources), reflecting their similarity concerning a specific topic, each topic is clustered and corresponds to a color (blue and red).

4. Discussion

Alzheimer’s disease (AD) is a form of dementia and is considered the most frequent type [25]. Genome-wide association studies (GWAS) identified genetic AD mutations [26].
The main objective of this assessment was to evaluate the usefulness of using MySLR machine learning in identifying papers that evaluated the presence of mutations on the ApoE gene in Italian Alzheimer’s patients. We did not consider the assessment of mutation on ApoE systematic reviews and reviews; the latter are indicated in Table 1 as “review” or “systematic review.” Several studies were not considered, as they were not conducted in Alzheimer’s patients and therefore did not answer the search query; 10% (n = 7) of the studies included in topic 1 concern SNPs on ApoE in the Italian Alzheimer’s population. A total of 4.28% (n = 3) did not report the provenience of cases and controls. Many studies, as seen in Table 1, do not specify the SNPs through their nomenclature but indicate the position of the mutation and the consequent amino acid substitution. This phenomenon is probably attributable to the percentage of single nucleotide variation instead of polymorphism, which usually is present in less than 1% of the population harboring variation. The studies that perfectly fit our query have been highlighted in bold in Table 1, along with their reference literature [27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96]. Topic 1 has seventy articles. Several of them contain information on the query made; only six works are not linked to AD [35,44,49,72,82,92]. The majority (four) focus on longevity and APoE [35,49,72,82,92]. In the first, a genome-wide association study (GWAS) was performed for longevity in the Cohorts for Heart and Aging Research in Genomic Epidemiology (CHARGE) consortium that confirmed APoE and FOXO3 candidacy in this direction [35]. In the second, the genome-wide scan assessment identifies loci for exceptional human longevity [49]. The third paper provides evidence that APoE haplotypes are associated with human longevity in the Central Italy population [72]. The last is to explore genes in lipid and Alzheimer’s disease associated with healthy aging and longevity in healthy older populations [92]. In the other two papers, one describes age-related white matter changes [82], and one analyses the cognitive performance and polymorphisms of several genes, including ApoE, in patients with mild cognitive impairment and cognitively healthy controls [44].
Several studies, shown in Table 2, do not specify the SNPs through their nomenclature but indicate the position of the mutation and the consequent amino acid substitution. Studies that perfectly fit our query, even in this case, have been highlighted in bold, which also applies to references [97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117]. Even in this topic, machine learning identified six papers in which AD is not the focus [97,98,105,108,111,118]. In particular, one is related to the epidemiology and genetics factor of frontotemporal dementia assessed by a survey in southern Italy [97], and one is a 7-year follow-up study in subjective cognitive decline and mild cognitive impairment focusing on diverse genes than ApoE [108]. Two works relate to laboratory techniques to assess APoE and study lipid metabolism [98,111]. One correlates ApoE with glaucoma [105] and one is unrelated [118].
The machine learning approach used here helped remove duplicate papers, identify the topic(s), and focus on selecting the papers that interest us. Of the ninety-two papers, only five met our criteria listed in Table 3 [33,38,59,94,115].
In particular, the study of Bizzarro et al. confirmed the role of ApoEε4, harboring the mutation as a Single Nucleotide Polymorphism (SNP) rs449647 A/A genotype, as a risk factor for AD in Italy [33]. In the paper of Capurso et al., the APOE SNPs reported were rs4925 and rs1804834, although they correlate it with other mutations in the glutathione S-transferase omega-1 gene [38].
Lescai and coworkers addressed the relationship between ApoEɛ4, and five SNPs, the rs449647, rs769446, rs405509 in the promoter of the APOE gene, and in ε4 rs429358 and rs7412. Confirming the association between the SNP rs405509 and the AD [59]. Valenza et al., pointed out that APoEɛ4 allele represents the only established genetic risk factor for AD; identified that patients hiding the −491 AA genotype had poorer cognitive performances than the −491 AT ones in the tests of visual attention in AD. This indicates that this mutation has a biological effect more exerted on APOE transcription, and the −491 A/T polymorphism could be considered a disease modifier more than a risk factor for sporadic AD [94]. The last paper is a multicenter study conducted in Denmark, Finland, Germany, Greece, Portugal, Spain, the Netherlands, and Italy. It is the only one of this type, in which ApoEɛ4 allele harbors the SNP rs769449 and rs429358. Therefore, MySLR, with its LDA algorithms, made it possible for us to identify what we were looking for. It is worth noting here that machine learning is widely used in the medical field [119,120] to identify systematic reviews and meta-analyses or to evaluate the state of the art of a given topic, as it is a helpful tool for simplifying the steps necessary for re-elaboration of complex data contained in the papers. The MySLR platform has already been used to give convincing results previously [121,122]. There are strengths and limitations in our assessment. On the MySRL platform, only key decisions are made transparently and held by humans [21]. The LDA algorithm has been applied in various fields such as medicine, biology, and computer science to extract topics and identify patterns within the literature [121,122]. The use of MySRL offers several strengths, including its ability to reduce the workload involved in the screening phase of a systematic review, making the process more efficient and manageable to analyze large datasets, enabling researchers to identify emerging trends and conduct in-depth topic modeling, and in addition, it allows for the identification of key topics within the literature, which is essential for conducting comprehensive systematic reviews [123,124,125]. MySLR provides a boost for realizing systematic literature reviews among scientific community members using the LDA algorithm. However, by discarding word order, the LDA algorithm loses specific local context information on semantic relations between words, which might otherwise help interpret deeper meanings and solve ambiguities [126]. A limitation is that LDA assumes that the topics are independent of each other. This is particularly true with topic 2, in our case, in which one paper is unrelated [118] to the context of our research [127,128]. Thus, the analysis did not include correlations between topics or hierarchical structures regarding sub-topics. When applying LDA, it is important to note that the model results are not deterministic. Instead, the results are affected by the researcher’s choices regarding the input parameters and built-in stochastic processes. Lastly, an interesting representation coming from MySLR is the t-distributed Stochastic Neighbor Embedding (t-SNE) algorithm. The graph’s points symbolize documents (scientific sources), reflecting their similarity concerning a specific topic. These points are grouped into clusters (each topic corresponds to a color—blue and red), highlighting the cohesive thematic relationships among the documents [119]. The t-SNE algorithm is an unsupervised dimensionality reduction technique. This means that the algorithm tries to represent high-dimensional data in a lower-dimensional space, preserving the similarity relations between the original examples without assuming that these relations are linearly distributed.

5. Conclusions

We believe that introducing machine learning, MySLR, will facilitate epidemiologists, physicians, and health professionals’ more precise assessment through systematic review and meta-analysis, even following Cochrane’s dictates. The semi-automated machine learning platform was able to identify studies related to the query performed on the database with a low percentage of bias. MySLR performed excellently in eliminating duplications and good performance in recognizing keywords linked, in our case, to ApoE mutations in AD.

Author Contributions

Conceptualization, G.F.S.; methodology, G.F.S.; validation, D.M.A.-G. and G.F.S.; formal analysis, G.F.S.; resources, E.C.; writing—original draft preparation, G.F.S. and D.M.A.-G.; writing—review and editing, E.C.; supervision, M.C.C. and R.C.; funding acquisition, E.C. All authors have read and agreed to the published version of the manuscript.

Funding

This research was supported by PNRR Project: H23C22000370006-T4Y S5G4PP1 to E.C.

Institutional Review Board Statement

Not applicable.

Informed Consent Statement

Not applicable.

Data Availability Statement

The data presented in this study are available on request from the corresponding author.

Acknowledgments

G.F.S. thank Salvatore Ammirato and Marilena De Simone for the course on “How to Conduct a systematic literature review”, with MySLR. The course was held at University of Calabria, Rende, 87036, the period was November 2023–December 2023.

Conflicts of Interest

The authors declare no conflicts of interest.

References

  1. Blennow, K.; de Leon, M.J.; Zetterberg, H. Alzheimer’s disease. Lancet 2006, 368, 387–403. [Google Scholar] [CrossRef]
  2. Karch, C.M.; Goate, A.M. Alzheimer’s Disease Risk Genes and Mechanisms of Disease Pathogenesis. Biol. Psychiatry 2015, 77, 43–51. [Google Scholar] [CrossRef]
  3. Carmona, S.; Hardy, J.; Guerreiro, R. The genetic landscape of Alzheimer disease. Handb. Clin. Neurol. 2018, 148, 395–408. [Google Scholar] [CrossRef]
  4. Liu, C.-C.; Kanekiyo, T.; Xu, H.; Bu, G. Apolipoprotein E and Alzheimer disease: Risk, mechanisms and therapy. Nat. Rev. Neurol. 2013, 9, 106–118. [Google Scholar] [CrossRef]
  5. Farrer, L.A.; Cupples, L.A.; Haines, J.L.; Hyman, B.; Kukull, W.A.; Mayeux, R.; Myers, R.H.; Pericak-Vance, M.A.; Risch, N.; van Duijn, C.M. Effects of Age, Sex, and Ethnicity on the Association Between Apolipoprotein E Genotype and Alzheimer Disease. JAMA 1997, 278, 1349–1356. [Google Scholar] [CrossRef]
  6. Berlau, D.J.; Corrada, M.M.; Head, E.; Kawas, C.H. APOE ε2 is associated with intact cognition but increased Alzheimer pathology in the oldest old. Neurology 2009, 72, 829–834. [Google Scholar] [CrossRef]
  7. Artiga, M.J.; Bullido, M.J.; Frank, A.; Sastre, I.; Recuero, M.; Garcia, M.A.; Lendon, C.L.; Han, S.W.; Morris, J.C.; Vazquez, J.; et al. Risk for Alzheimer’s disease correlates with transcriptional activity of the APOE gene. Hum. Mol. Genet. 1998, 7, 1887–1892. [Google Scholar] [CrossRef] [PubMed]
  8. Bekris, L.M.; Millard, S.; Lutz, F.; Li, G.; Galasko, D.R.; Farlow, M.R.; Quinn, J.F.; Kaye, J.A.; Leverenz, J.B.; Tsuang, D.W.; et al. Tau phosphorylation pathway genes and cerebrospinal fluid tau levels in Alzheimer’s disease. Am. J. Med Genet. Part B Neuropsychiatr. Genet. 2012, 159, 874–883. [Google Scholar] [CrossRef] [PubMed]
  9. Laws, S.M.; Hone, E.; Gandy, S.; Martins, R.N. Expanding the association between the APOE gene and the risk of Alzheimer’s disease: Possible roles for APOE promoter polymorphisms and alterations in APOE transcription. J. Neurochem. 2003, 84, 1215–1236. [Google Scholar] [CrossRef] [PubMed]
  10. Roses, A.D. A model for susceptibility polymorphisms for complex diseases: Apolipoprotein E and Alzheimer disease. Neurogenetics 1997, 1, 3–11. [Google Scholar] [CrossRef] [PubMed]
  11. Yuryevna Bokovnya, A.; Rustamovich Begishev, I.; Ilduzovna Khisamova, Z.; Rashidovna Narimanova, N.; Mikhailovna Sherbakova, L. Legal Approaches to Artificial Intelligence Concept and Essence Definition. Rev. San Gregor. 2020, 1, 115–121. [Google Scholar] [CrossRef]
  12. Shapiro, S.C. Artificial intelligence. In Encyclopedia of Artificial Intelligence, 2nd ed.; John Wiley & Sons: New York, NY, USA, 1992; Volume 1. [Google Scholar]
  13. Mitchell, T.M. Machine Learning; Mcgraw-Hill International: New York, NY, USA, 1997. [Google Scholar]
  14. Demner-Fushman, D.; Lin, J. Answering Clinical Questions with Knowledge-Based and Statistical Techniques. Comput. Linguist. 2007, 33, 63–103. [Google Scholar] [CrossRef]
  15. Jones, B.D.; Baumgartner, F.R. The Politics of Attention: How Government Prioritizes Problems; University of Chicago Press: Chichago, IL, USA, 2005. [Google Scholar]
  16. King, G.; Lowe, W. An Automated Information Extraction Tool for International Conflict Data with Performance as Good as Human Coders: A Rare Events Evaluation Design. Int. Organ. 2003, 57, 617–642. [Google Scholar] [CrossRef]
  17. Topol, E.J. High-performance medicine: The convergence of human and artificial intelligence. Nat. Med. 2019, 25, 44–56. [Google Scholar] [CrossRef]
  18. Hashimoto, D.A.; Rosman, G.; Rus, D.; Meireles, O.R.M. Artificial Intelligence in Surgery: Promises and Perils. Ann. Surg. 2018, 268, 70–76. [Google Scholar] [CrossRef] [PubMed]
  19. Bettencourt, C.; Skene, N.; Bandres-Ciga, S.; Anderson, E.; Winchester, L.M.; Foote, I.F.; Schwartzentruber, J.; Botia, J.A.; Nalls, M.; Singleton, A.; et al. Artificial intelligence for dementia genetics and omics. Alzheimer’s Dement. 2023, 19, 5905–5921. [Google Scholar] [CrossRef] [PubMed]
  20. Blei, D.M.; Ng, A.Y.; Jordan, M.I. Latent Dirichlet Allocation. J. Mach. Learn. Res. 2003, 3, 993–1022. [Google Scholar]
  21. Ammirato, S.; Felicetti, A.M.; Rogano, D.; Linzalone, R.; Corvello, V. Digitalising the Systematic Literature Review process: The MySLR platform. Knowl. Manag. Res. Pract. 2022, 21, 777–794. [Google Scholar] [CrossRef]
  22. Denyer, D.; Tranfield, D. Producing a systematic review. In The Sage Handbook of Organizational Research Methods; Sage Publications Ltd.: Thousand Oaks, CA, USA, 2009; pp. 671–689. [Google Scholar]
  23. Chen, Z.; Liu, B. Topic Modeling using Topics from Many Domains, Lifelong Learning and Big Data. Proc. Mach. Learn. Res. 2014, 32, 703–711. Available online: https://proceedings.mlr.press/v32/chenf14.html (accessed on 20 February 2024).
  24. Yi, X.; Allan, J. Evaluating topic models for information retrieval. In Proceedings of the 17th ACM Conference on Information and Knowledge Management, Napa Valley, CA, USA, 26–30 October 2008; Association for Computing Machinery: New York, NY, USA, 2008; pp. 1431–1432. [Google Scholar]
  25. Ballard, C.; Gauthier, S.; Corbett, A.; Brayne, C.; Aarsland, D.; Jones, E. Alzheimer’s disease. Lancet 2011, 377, 1019–1031. [Google Scholar] [CrossRef] [PubMed]
  26. Bertram, L.; Tanzi, R.E. Genome-wide association studies in Alzheimer’s disease. Hum. Mol. Genet. 2009, 18, R137–R145. [Google Scholar] [CrossRef] [PubMed]
  27. Albani, D.; Tettamanti, M.; Batelli, S.; Polito, L.; Dusi, S.; Ateri, E.; Forloni, G.; Lucca, U. Interleukin-1α, interleukin-1β and tumor necrosis factor-α genetic variants and risk of dementia in the very old: Evidence from the “Monzino 80-plus” prospective study. AGE 2012, 34, 519–526. [Google Scholar] [CrossRef]
  28. Andreoli, V.; De Marco, E.V.; Trecroci, F.; Cittadella, R.; Di Palma, G.; Gambardella, A. Potential involvement of GRIN2B encoding the NMDA receptor subunit NR2B in the spectrum of Alzheimer’s disease. J. Neural Transm. 2014, 121, 533–542. [Google Scholar] [CrossRef]
  29. Bagnoli, S.; Cellini, E.; Tedde, A.; Nacmias, B.; Piacentini, S.; Bessi, V.; Bracco, L.; Sorbi, S. Association of IL10 promoter polymorphism in Italian Alzheimer’s disease. Neurosci. Lett. 2007, 418, 262–265. [Google Scholar] [CrossRef] [PubMed]
  30. Bagnoli, S.; Piaceri, I.; Tedde, A.; Bessi, V.; Bracco, L.; Sorbi, S.; Nacmias, B. Tomm40 polymorphisms in Italian Alzheimer’s disease and frontotemporal dementia patients. Neurol. Sci. 2013, 34, 995–998. [Google Scholar] [CrossRef] [PubMed]
  31. Bartoletti-Stella, A.; Tarozzi, M.; Mengozzi, G.; Asirelli, F.; Brancaleoni, L.; Mometto, N.; Stanzani-Maserati, M.; Baiardi, S.; Linarello, S.; Spallazzi, M.; et al. Dementia-related genetic variants in an Italian population of early-onset Alzheimer’s disease. Front. Aging Neurosci. 2022, 14, 969817. [Google Scholar] [CrossRef]
  32. Belloy, M.E.; Eger, S.J.; Le Guen, Y.; Damotte, V.; Ahmad, S.; Ikram, M.A.; Ramirez, A.; Tsolaki, A.C.; Rossi, G.; Jansen, I.E.; et al. Challenges at the APOE locus: A robust quality control approach for accurate APOE genotyping. Alzheimer’s Res. Ther. 2022, 14, 22. [Google Scholar] [CrossRef]
  33. Bizzarro, A.; Seripa, D.; Acciarri, A.; Matera, M.G.; Pilotto, A.; Tiziano, F.D.; Brahe, C.; Masullo, C. The complex interaction between APOE promoter and AD: An Italian case–control study. Eur. J. Hum. Genet. 2009, 17, 938–945. [Google Scholar] [CrossRef]
  34. Bosco, P.; Ferri, R.; Salluzzo, M.G.; Castellano, S.; Signorelli, M.; Nicoletti, F.; Di Nuovo, S.; Drago, F.; Caraci, F. Role of the Transforming-Growth-Factor-β1 Gene in Late-Onset Alzheimer’s Disease: Implications for the Treatment. Curr. Genom. 2013, 14, 147–156. [Google Scholar] [CrossRef]
  35. Broer, L.; Buchman, A.S.; Deelen, J.; Evans, D.S.; Faul, J.D.; Lunetta, K.L.; Sebastiani, P.; Smith, J.A.; Smith, A.V.; Tanaka, T.; et al. GWAS of longevity in CHARGE consortium confirms APOE and FOXO3 candidacy. J. Gerontol. Ser. A Biomed. Sci. Med. Sci. 2015, 70, 110–118. [Google Scholar] [CrossRef]
  36. Bucossi, S.; Polimanti, R.; Mariani, S.; Ventriglia, M.; Bonvicini, C.; Migliore, S.; Manfellotto, D.; Salustri, C.; Vernieri, F.; Rossini, P.M.; et al. Association of K832R and R952K SNPs of Wilson’s disease gene with Alzheimer’s disease. J. Alzheimer’s Dis. 2012, 29, 913–919. [Google Scholar] [CrossRef]
  37. Capurso, C.; Solfrizzi, V.; Colacicco, A.M.; D’Introno, A.; Frisardi, V.; Imbimbo, B.P.; Lorusso, M.; Vendemiale, G.; Denitto, M.; Santamato, A.; et al. Interleukin 6–174 G/C promoter and variable number of tandem repeats (VNTR) gene polymorphisms in sporadic Alzheimer’s disease. Prog. Neuro-Psychopharmacol. Biol. Psychiatry 2010, 34, 177–182. [Google Scholar] [CrossRef]
  38. Capurso, C.; Panza, F.; Seripa, D.; Frisardi, V.; Imbimbo, B.P.; Verdile, G.; Vendemiale, G.; Pilotto, A.; Solfrizzi, V. Polymorphisms in Glutathione S-Transferase Omega-1 Gene and Increased Risk of Sporadic Alzheimer Disease. Rejuvenation Res. 2010, 13, 645–652. [Google Scholar] [CrossRef]
  39. Cellini, E.; Tedde, A.; Bagnoli, S.; Pradella, S.; Piacentini, S.; Sorbi, S.; Nacmias, B. Implication of Sex and SORL1 Variants in Italian Patients with Alzheimer Disease. Arch. Neurol. 2009, 66, 1260–1266. [Google Scholar] [CrossRef] [PubMed]
  40. Ciminelli, B.M.; Menduti, G.; Benussi, L.; Ghidoni, R.; Binetti, G.; Squitti, R.; Rongioletti, M.; Nica, S.; Novelletto, A.; Rossi, L.; et al. Polymorphic Genetic Markers of the GABA Catabolism Pathway in Alzheimer’s Disease. J. Alzheimer’s Dis. 2020, 77, 301–311. [Google Scholar] [CrossRef] [PubMed]
  41. Clarelli, F.; Mascia, E.; Santangelo, R.; Mazzeo, S.; Giacalone, G.; Galimberti, D.; Fusco, F.; Zuffi, M.; Fenoglio, C.; Franceschi, M.; et al. CHRNA7 Gene and Response to Cholinesterase Inhibitors in an Italian Cohort of Alzheimer’s Disease Patients. J. Alzheimer’s Dis. 2016, 52, 1203–1208. [Google Scholar] [CrossRef] [PubMed]
  42. Colacicco, A.M.; Solfrizzi, V.; D’introno, A.; Capurso, C.; Kehoe, P.G.; Seripa, D.; Pilotto, A.; Santamato, A.; Capurso, A.; Panza, F. Alpha-2-macroglobulin gene, oxidized low-density lipoprotein receptor-1 locus, and sporadic Alzheimer’s disease. Neurobiol. Aging 2009, 30, 1518–1520. [Google Scholar] [CrossRef] [PubMed]
  43. Corbo, R.M.; Gambina, G.; Ulizzi, L.; Moretto, G.; Scacchi, R. Genetic Variation of CYP19 (Aromatase) Gene Influences Age at Onset of Alzheimer’s Disease in Women. Dement. Geriatr. Cogn. Disord. 2009, 27, 513–518. [Google Scholar] [CrossRef] [PubMed]
  44. Cruz-Sanabria, F.; Bonilla-Vargas, K.; Estrada, K.; Mancera, O.; Vega, E.; Guerrero, E.; Ortega-Rojas, J.; María, F.M.; Romero, A.; Montañés, P.; et al. Analysis of cognitive performance and polymorphisms of SORL1, PVRL2, CR1, TOMM40, APOE, PICALM, GWAS_14q, CLU, and BIN1 in patients with mild cognitive impairment and cognitively healthy controls. Neurologia 2021, 36, 681–691. [Google Scholar] [CrossRef] [PubMed]
  45. DeMichele-Sweet, M.A.A.; Klei, L.; Creese, B.; Harwood, J.C.; Weamer, E.A.; McClain, L.; Sims, R.; Hernandez, I.; Moreno-Grau, S.; Tárraga, L.; et al. Genome-wide association identifies the first risk loci for psychosis in Alzheimer disease. Mol. Psychiatry 2021, 26, 5797–5811. [Google Scholar] [CrossRef] [PubMed]
  46. Di Maria, E.; Giorgio, E.; Uliana, V.; Bonvicini, C.; Faravelli, F.; Cammarata, S.; Novello, M.C.; Galimberti, D.; Scarpini, E.; Zanetti, O.; et al. Possible Influence of a Non-Synonymous Polymorphism Located in the NGF Precursor on Susceptibility to Late-Onset Alzheimer’s Disease and Mild Cognitive Impairment. J. Alzheimer’s Dis. 2012, 29, 699–705. [Google Scholar] [CrossRef]
  47. Emanuele, E.; Lista, S.; Ghidoni, R.; Binetti, G.; Cereda, C.; Benussi, L.; Maletta, R.; Bruni, A.C.; Politi, P. Chromosome 9p21.3 genotype is associated with vascular dementia and Alzheimer’s disease. Neurobiol. Aging 2011, 32, 1231–1235. [Google Scholar] [CrossRef]
  48. Finckh, U.; van Hadeln, K.; Müller-Thomsen, T.; Alberici, A.; Binetti, G.; Hock, C.; Nitsch, R.M.; Stoppe, G.; Reiss, J.; Gal, A. Association of late-onset Alzheimer disease with a genotype of PLAU, the gene encoding urokinase-type plasminogen activator on chromosome 10q22.2. Neurogenetics 2003, 4, 213–217. [Google Scholar] [CrossRef]
  49. Fortney, K.; Dobriban, E.; Garagnani, P.; Pirazzini, C.; Monti, D.; Mari, D.; Atzmon, G.; Barzilai, N.; Franceschi, C.; Owen, A.B.; et al. Genome-Wide Scan Informed by Age-Related Disease Identifies Loci for Exceptional Human Longevity. PLoS Genet. 2015, 11, e1005728. [Google Scholar] [CrossRef] [PubMed]
  50. Galimberti, D.; Scarpini, E.; Venturelli, E.; Strobel, A.; Herterich, S.; Fenoglio, C.; Guidi, I.; Scalabrini, D.; Cortini, F.; Bresolin, N.; et al. Association of a NOS1 promoter repeat with Alzheimer’s disease. Neurobiol. Aging 2008, 29, 1359–1365. [Google Scholar] [CrossRef]
  51. Guerini, F.R.; Farina, E.; Costa, A.S.; Baglio, F.; Saibene, F.L.; Margaritella, N.; Calabrese, E.; Zanzottera, M.; Bolognesi, E.; Nemni, R.; et al. ApoE and SNAP-25 Polymorphisms Predict the Outcome of Multidimensional Stimulation Therapy Rehabilitation in Alzheimer’s Disease. Neurorehabilit. Neural Repair 2016, 30, 883–893. [Google Scholar] [CrossRef] [PubMed]
  52. Hollingworth, P.; Harold, D.; Sims, R.; Gerrish, A.; Lambert, J.-C.; Carrasquillo, M.M.; Abraham, R.; Hamshere, M.L.; Pahwa, J.S.; Moskvina, V.; et al. Common variants at ABCA7, MS4A6A/MS4A4E, EPHA1, CD33 and CD2AP are associated with Alzheimer’s disease. Nat. Genet. 2011, 43, 429–435. [Google Scholar] [CrossRef] [PubMed]
  53. Jun, G.; Ibrahim-Verbaas, C.A.; Vronskaya, M.; Lambert, J.C.; Chung, J.; Naj, A.C.; Kunkle, B.W.; Wang, L.S.; Bis, J.C.; Bel-lenguez, C.; et al. A novel Alzheimer disease locus located near the gene encoding tau protein. Mol. Psychiatry 2016, 21, 108–117. [Google Scholar] [CrossRef]
  54. Lambert, J.-C.; Heath, S.; Even, G.; Campion, D.; Sleegers, K.; Hiltunen, M.; Combarros, O.; Zelenika, D.; Bullido, M.J.; Tavernier, B.; et al. Genome-wide association study identifies variants at CLU and CR1 associated with Alzheimer’s disease. Nat. Genet. 2009, 41, 1094–1099. [Google Scholar] [CrossRef]
  55. Lambert, J.C.; Ibrahim-Verbaas, C.A.; Harold, D.; Naj, A.C.; Sims, R.; Bellenguez, C.; DeStafano, A.L.; Bis, J.C.; Beecham, G.W.; Grenier-Boley, B.; et al. Meta-Analysis of 74,046 individuals identifies 11 new susceptibility loci for Alzheimer’s disease. Nat. Genet. 2013, 45, 1452–1458. [Google Scholar] [CrossRef]
  56. Lanni, C.; Garbin, G.; Lisa, A.; Biundo, F.; Ranzenigo, A.; Sinforiani, E.; Cuzzoni, G.; Govoni, S.; Ranzani, G.N.; Racchi, M. Influence of COMT Val158Met Polymorphism on Alzheimer’s Disease and Mild Cognitive Impairment in Italian Patients. J. Alzheimer’s Dis. 2012, 32, 919–926. [Google Scholar] [CrossRef]
  57. Laws, S.M.; Perneczky, R.; Wagenpfeil, S.; Müller, U.; Förstl, H.; Martins, R.N.; Kurz, A.; Riemenschneider, M. TNF polymorphisms in Alzheimer disease and functional implications on CSF beta-amyloid levels. Hum. Mutat. 2005, 26, 29–35. [Google Scholar] [CrossRef]
  58. Lescai, F.; Pirazzini, C.; D’Agostino, G.; Santoro, A.; Ghidoni, R.; Benussi, L.; Galimberti, D.; Federica, E.; Marchegiani, F.; Cardelli, M.; et al. Failure to Replicate an Association of rs5984894 SNP in the PCDH11X Gene in a Collection of 1222 Alzheimer’s Disease Affected Patients. J. Alzheimer’s Dis. 2010, 21, 385–388. [Google Scholar] [CrossRef] [PubMed]
  59. Lescai, F.; Chiamenti, A.M.; Codemo, A.; Pirazzini, C.; D’Agostino, G.; Ruaro, C.; Ghidoni, R.; Benussi, L.; Galimberti, D.; Esposito, F.; et al. An APOE Haplotype Associated with Decreased ε4 Expression Increases the Risk of Late Onset Alzheimer’s Disease. J. Alzheimer’s Dis. 2011, 24, 235–245. [Google Scholar] [CrossRef] [PubMed]
  60. Licastro, F.; Chiappelli, M.; Caldarera, C.M.; Porcellini, E.; Carbone, I.; Caruso, C.; Lio, D.; Corder, E.H. Sharing Pathogenetic Mechanisms between Acute Myocardial Infarction and Alzheimer’s Disease as Shown by Partially Overlapping of Gene Variant Profiles. J. Alzheimer’s Dis. 2011, 23, 421–431. [Google Scholar] [CrossRef]
  61. Licastro, F.; Raschi, E.; Carbone, I.; Porcellini, E. Variants in Antiviral Genes are Risk Factors for Cognitive Decline and Dementia. J. Alzheimer’s Dis. 2015, 46, 655–663. [Google Scholar] [CrossRef]
  62. Lio, D.; Licastro, F.; Scola, L.; Chiappelli, M.; Grimaldi, L.M.; Crivello, A.; Colonna-Romano, G.; Candore, G.; Franceschi, C.; Caruso, C. Interleukin-10 promoter polymorphism in sporadic Alzheimer’s disease. Genes Immun. 2003, 4, 234–238. [Google Scholar] [CrossRef]
  63. Lio, D.; Annoni, G.; Licastro, F.; Crivello, A.; Forte, G.I.; Scola, L.; Colonna-Romano, G.; Candore, G.; Arosio, B.; Galimberti, L.; et al. Tumor necrosis factor-α−308A/G polymorphism is associated with age at onset of Alzheimer’s disease. Mech. Ageing Dev. 2006, 127, 567–571. [Google Scholar] [CrossRef]
  64. Lu, R.-C.; Yang, W.; Tan, L.; Sun, F.-R.; Tan, M.-S.; Zhang, W.; Wang, H.-F.; Tan, L. Association of HLA-DRB1 polymorphism with Alzheimer’s disease: A replication and meta-analysis. Oncotarget 2017, 8, 93219–93226. [Google Scholar] [CrossRef] [PubMed]
  65. Lupton, M.K.; Strike, L.; Hansell, N.K.; Wen, W.; Mather, K.A.; Armstrong, N.J.; Thalamuthu, A.; McMahon, K.L.; de Zubicaray, G.I.; Assareh, A.A.; et al. The effect of increased genetic risk for Alzheimer’s disease on hippocampal and amygdala volume. Neurobiol. Aging 2016, 40, 68–77. [Google Scholar] [CrossRef]
  66. Maletta, R.; Smirne, N.; Bernardi, L.; Anfossi, M.; Gallo, M.; Conidi, M.E.; Colao, R.; Puccio, G.; Curcio, S.A.; Laganà, V.; et al. Frequency of Cardiovascular Genetic Risk Factors in a Calabrian Population and Their Effects on Dementia. J. Alzheimer’s Dis. 2018, 61, 1179–1187. [Google Scholar] [CrossRef] [PubMed]
  67. Mariani, S.; Ventriglia, M.; Simonelli, I.; Spalletta, G.; Bucossi, S.; Siotto, M.; Assogna, F.; Melgari, J.M.; Vernieri, F.; Squitti, R. Effects of hemochromatosis and transferrin gene mutations on peripheral iron dyshomeostasis in mild cognitive impairment and Alzheimer’s and Parkinson’s diseases. Front. Aging Neurosci. 2013, 5, 37. [Google Scholar] [CrossRef] [PubMed]
  68. Masri, I.; Salami, A.; El Shamieh, S.; Bissar-Tadmouri, N. rs3851179G>A in PICALM is Protective Against Alzheimer’s Disease in Five Different Countries Surrounding the Mediterranean. Curr. Aging Sci. 2020, 13, 162–168. [Google Scholar] [CrossRef] [PubMed]
  69. Minoretti, P.; Gazzaruso, C.; Di Vito, C.; Emanuele, E.; Bianchi, M.; Coen, E.; Reino, M.; Geroldi, D. Effect of the functional toll-like receptor 4 Asp299Gly polymorphism on susceptibility to late-onset Alzheimer’s disease. Neurosci. Lett. 2006, 391, 147–149. [Google Scholar] [CrossRef]
  70. Montesanto, A.; Crocco, P.; Anfossi, M.; Smirne, N.; Puccio, G.; Colao, R.; Maletta, R.; Passarino, G.; Bruni, A.C.; Rose, G. The Genetic Variability of UCP4 Affects the Individual Susceptibility to Late-Onset Alzheimer’s Disease and Modifies the Disease’s Risk in APOE-ɛ4 Carriers. J. Alzheimer’s Dis. 2016, 51, 1265–1274. [Google Scholar] [CrossRef] [PubMed]
  71. Nacmias, B.; Tedde, A.; Bagnoli, S.; Cellini, E.; Guarnieri, B.M.; Piacentini, S.; Sorbi, S. Implication of GAB2 Gene Polymorphism in Italian Patients with Alzheimer’s Disease. J. Alzheimer’s Dis. 2009, 16, 513–515. [Google Scholar] [CrossRef]
  72. Napolioni, V.; Giannì, P.; Carpi, F.M.; Predazzi, I.M.; Lucarini, N. APOE haplotypes are associated with human longevity in a Central Italy population: Evidence for epistasis with HP 1/2 polymorphism. Clin. Chim. Acta 2011, 412, 1821–1824. [Google Scholar] [CrossRef] [PubMed]
  73. Olgiati, P.; Politis, A.; Albani, D.; Rodilossi, S.; Polito, L.; Zisaki, A.; Piperi, C.; Liappas, I.; Stamouli, E.; Mailis, A.; et al. Effects of SORL1 gene on Alzheimer’s disease. Focus on gender, neuropsychiatric symptoms and pro-inflammatory cytokines. Curr. Alzheimer Res. 2013, 10, 154–164. [Google Scholar] [CrossRef]
  74. Orlacchio, A.; Kawarai, T.; Polidoro, M.; Stefani, A.; Orlacchio, A.; George-Hyslop, P.H.S.; Bernardi, G. Association analysis between Alzheimer’s disease and the Nicastrin gene polymorphisms. Neurosci. Lett. 2002, 333, 115–118. [Google Scholar] [CrossRef]
  75. Pilotto, A.; Franceschi, M.; D’Onofrio, G.; Bizzarro, A.; Mangialasche, F.; Cascavilla, L.; Paris, F.; Matera, M.G.; Pilotto, A.; Daniele, A.; et al. Effect of a CYP2D6 polymorphism on the efficacy of donepezil in patients with Alzheimer disease. Neurology 2009, 73, 761–767. [Google Scholar] [CrossRef]
  76. Pola, R.; Flex, A.; Gaetani, E.; Proia, A.S.; Papaleo, P.; Di Giorgio, A.; Straface, G.; Pecorini, G.; Serricchio, M.; Pola, P. Monocyte chemoattractant protein-1 (MCP-1) gene polymorphism and risk of Alzheimer’s disease in Italians. Exp. Gerontol. 2004, 39, 1249–1252. [Google Scholar] [CrossRef]
  77. Poleggi, A.; Bizzarro, A.; Acciarri, A.; Antuono, P.; Bagnoli, S.; Cellini, E.; Forno, G.D.; Giannattasio, C.; Lauria, A.; Matera, M.G.; et al. Codon 129 polymorphism of prion protein gene in sporadic Alzheimer’s disease. Eur. J. Neurol. 2008, 15, 173–178. [Google Scholar] [CrossRef]
  78. Poli, M.; Gatta, L.B.; Lovati, C.; Mariani, C.; Galimberti, D.; Scarpini, E.; Biunno, I.; Musicco, M.; Dominici, R.; Albertini, A.; et al. Interaction between the APOE ɛ4 allele and the APH-1b c+651T>G SNP in Alzheimer’s disease. Neurobiol. Aging 2008, 29, 1494–1501. [Google Scholar] [CrossRef]
  79. Porrello, E.; Monti, M.C.; Sinforiani, E.; Cairati, M.; Guaita, A.; Montomoli, C.; Govoni, S.; Racchi, M. Estrogen receptor α and APOEɛ4 polymorphisms interact to increase risk for sporadic AD in Italian females. Eur. J. Neurol. 2006, 13, 639–644. [Google Scholar] [CrossRef] [PubMed]
  80. Scacchi, R.; Gambina, G.; Moretto, G.; Corbo, R.M. Association study between P53 and P73 gene polymorphisms and the sporadic late-onset form of Alzheimer’s disease. J. Neural Transm. 2009, 116, 1179–1184. [Google Scholar] [CrossRef]
  81. Scassellati, C.; Zanardini, R.; Squitti, R.; Bocchio-Chiavetto, L.; Bonvicini, C.; Binetti, G.; Zanetti, O.; Cassetta, E.; Gennarelli, M. Promoter haplotypes of interleukin-10 gene and sporadic Alzheimer’s disease. Neurosci. Lett. 2004, 356, 119–122. [Google Scholar] [CrossRef]
  82. Schmidt, R.; Schmidt, H.; Haybaeck, J.; Loitfelder, M.; Weis, S.; Cavalieri, M.; Seiler, S.; Enzinger, C.; Ropele, S.; Erkinjuntti, T.; et al. Heterogeneity in age-related white matter changes. Acta Neuropathol. 2011, 122, 171–185. [Google Scholar] [CrossRef]
  83. Schott, J.M.; Crutch, S.J.; Carrasquillo, M.M.; Uphill, J.; Shakespeare, T.J.; Ryan, N.S.; Yong, K.X.; Lehmann, M.; Boeve, B.F.; Murray, M.E.; et al. Genetic risk factors for the posterior cortical atrophy variant of Alzheimer’s disease. Alzheimer’s Dement. 2016, 12, 862–871. [Google Scholar] [CrossRef]
  84. Scola, L.; Licastro, F.; Chiappelli, M.; Franceschi, C.; Grimaldi, L.M.; Crivello, A.; Colonna-Romano, G.; Candore, G.; Lio, D.; Caruso, C. Allele frequencies of +874T→A single nucleotide polymorphism at the first intron of IFN-γ gene in Alzheimer’s disease patients. Aging Clin. Exp. Res. 2003, 15, 292–295. [Google Scholar] [CrossRef] [PubMed]
  85. Seripa, D.; Matera, M.G.; Franceschi, M.; Bizzarro, A.; Paris, F.; Cascavilla, L.; Rinaldi, M.; Panza, F.; Solfrizzi, V.; Daniele, A.; et al. Association Analysis of GRIN2B, Encoding N-Methyl-D-Aspartate Receptor 2B Subunit, and Alzheimer’s Disease. Dement. Geriatr. Cogn. Disord. 2008, 25, 287–292. [Google Scholar] [CrossRef] [PubMed]
  86. Seripa, D.; Matera, M.G.; Franceschi, M.; Daniele, A.; Bizzarro, A.; Rinaldi, M.; Panza, F.; Fazio, V.M.; Gravina, C.; D’Onofrio, G.; et al. The RELN Locus in Alzheimer’s Disease. J. Alzheimer’s Dis. 2008, 14, 335–344. [Google Scholar] [CrossRef] [PubMed]
  87. Seripa, D.; D’Onofrio, G.; Panza, F.; Cascavilla, L.; Masullo, C.; Pilotto, A. The Genetics of the Human APOE Polymorphism. Rejuvenation Res. 2011, 14, 491–500. [Google Scholar] [CrossRef]
  88. Serpente, M.; Fenoglio, C.; Villa, C.; Cortini, F.; Cantoni, C.; Ridolfi, E.; Clerici, F.; Marcone, A.; Benussi, L.; Ghidoni, R.; et al. Role of OLR1 and Its Regulating hsa-miR369-3p in Alzheimer’s Disease: Genetics and Expression Analysis. J. Alzheimer’s Dis. 2011, 26, 787–793. [Google Scholar] [CrossRef] [PubMed]
  89. Squillario, M.; Abate, G.; Tomasi, F.; Tozzo, V.; Barla, A.; Uberti, D.; Weiner, M.W.; Aisen, P.; Petersen, R.; Clifford, J.R.; et al. A telescope GWAS analysis strategy, based on SNPs-genes-pathways ensamble and on multivariate algorithms, to characterize late onset Alzheimer’s disease. Sci. Rep. 2020, 10, 12063. [Google Scholar] [CrossRef] [PubMed]
  90. Talwar, P.; Kushwaha, S.; Rawat, C.; Kaur, H.; Srivastava, A.; Agarwal, R.; Chandna, P.; Tucci, P.; Saso, L.; Kukreti, R. Validating a Genomic Convergence and Network Analysis Approach Using Association Analysis of Identified Candidate Genes in Alzheimer’s Disease. Front. Genet. 2021, 12, 722221. [Google Scholar] [CrossRef]
  91. Tedde, A.; Bagnoli, S.; Piaceri, I.; Lucenteforte, E.; Bessi, V.; Bracco, L.; Mugelli, A.; Sorbi, S.; Nacmias, B. Different implication of NEDD9 genetic variant in early and late-onset Alzheimer’s disease. Neurosci. Lett. 2010, 477, 121–123. [Google Scholar] [CrossRef]
  92. Tindale, L.C.; Leach, S.; Spinelli, J.J.; Brooks-Wilson, A.R. Lipid and Alzheimer’s disease genes associated with healthy aging and longevity in healthy oldest-old. Oncotarget 2017, 8, 20612–20621. [Google Scholar] [CrossRef]
  93. Tisato, V.; Zuliani, G.; Vigliano, M.; Longo, G.; Franchini, E.; Secchiero, P.; Zauli, G.; Paraboschi, E.M.; Singh, A.V.; Serino, M.L.; et al. Gene-gene interactions among coding genes of iron-homeostasis proteins and APOE-alleles in cognitive impairment diseases. PLoS ONE 2018, 13, e0193867. [Google Scholar] [CrossRef]
  94. Valenza, A.; Bizzarro, A.; Marra, C.; Lauria, A.; Guglielmi, V.; Rossi, C.; Tiziano, F.; Brahe, C.; Masullo, C. The APOE-491 A/T promoter polymorphism effect on cognitive profile of Alzheimer’s patients. Neurosci. Lett. 2010, 472, 199–203. [Google Scholar] [CrossRef]
  95. Venturelli, E.; Galimberti, D.; Lovati, C.; Fenoglio, C.; Scalabrini, D.; Mariani, C.; Forloni, G.; Bresolin, N.; Scarpini, E. The T-786C NOS3 polymorphism in Alzheimer’s disease: Association and influence on gene expression. Neurosci. Lett. 2005, 382, 300–303. [Google Scholar] [CrossRef]
  96. Wang, Z.; Lei, H.; Zheng, M.; Li, Y.; Cui, Y.; Hao, F. Meta-analysis of the Association between Alzheimer Disease and Variants in GAB2, PICALM, and SORL1. Mol. Neurobiol. 2016, 53, 6501–6510. [Google Scholar] [CrossRef] [PubMed]
  97. Bernardi, L.; Frangipane, F.; Smirne, N.; Colao, R.; Puccio, G.; Curcio, S.A.; Mirabelli, M.; Maletta, R.; Anfossi, M.; Gallo, M.; et al. Epidemiology and genetics of frontotemporal dementia: A door-to-door survey in Southern Italy. Neurobiol. Aging 2012, 33, 2948.e1–2948.e10. [Google Scholar] [CrossRef] [PubMed]
  98. Calabretta, A.; Tedeschi, T.; Di Cola, G.; Corradini, R.; Sforza, S.; Marchelli, R. Arginine-based PNA microarrays for APOE genotyping. Mol. Biosyst. 2009, 5, 1323–1330. [Google Scholar] [CrossRef] [PubMed]
  99. Cheng, H.-C.; Sun, Y.; Lai, L.-C.; Chen, S.-Y.; Lee, W.-C.; Chen, J.-H.; Chen, T.-F.; Chen, H.-H.; Wen, L.-L.; Yip, P.-K.; et al. Genetic polymorphisms of nerve growth factor receptor (NGFR) and the risk of Alzheimer’s disease. J. Negat. Results Biomed. 2012, 11, 5. [Google Scholar] [CrossRef] [PubMed]
  100. de Rojas, I.; Moreno-Grau, S.; Tesi, N.; Grenier-Boley, B.; Andrade, V.; Jansen, I.E.; Pedersen, N.L.; Stringa, N.; Zettergren, A.; Hernández, I.; et al. Common variants in Alzheimer’s disease and risk stratification by polygenic risk scores. Nat. Commun. 2021, 12, 3417. [Google Scholar] [CrossRef] [PubMed]
  101. Flex, A.; Gaetani, E.; Proia, A.S.; Pecorini, G.; Straface, G.; Biscetti, F.; Fioroni, G.; Sabusco, A.; Flore, R.; Tondi, P.; et al. Analysis of functional polymorphisms of metalloproteinase genes in persons with vascular dementia and Alzheimer’s disease. J. Gerontol. Ser. A 2006, 61, 1065–1069. [Google Scholar] [CrossRef]
  102. Grünblatt, E.; Reif, A.; Jungwirth, S.; Galimberti, D.; Weber, H.; Scarpini, E.; Sauer, C.; Wichart, I.; Rainer, M.K.; Huber, K.; et al. Genetic variation in the choline O-acetyltransferase gene in depression and Alzheimer’s disease: The VITA and Milano studies. J. Psychiatr. Res. 2011, 45, 1250–1256. [Google Scholar] [CrossRef] [PubMed]
  103. Hansmannel, F.; Lendon, C.; Pasquier, F.; Dumont, J.; Hannequin, D.; Chapuis, J.; Laumet, G.; Ayral, A.-M.; Galimberti, D.; Scarpini, E.; et al. Is the ornithine transcarbamylase gene a genetic determinant of Alzheimer’s disease? Neurosci. Lett. 2009, 449, 76–80. [Google Scholar] [CrossRef]
  104. Hong, S.; Prokopenko, D.; Dobricic, V.; Kilpert, F.; Bos, I.; Vos, S.J.B.; Tijms, B.M.; Andreasson, U.; Blennow, K.; Vandenberghe, R.; et al. Genome-wide association study of Alzheimer’s disease CSF biomarkers in the EMIF-AD Multimodal Biomarker Discovery dataset. Transl. Psychiatry 2020, 10, 403. [Google Scholar] [CrossRef]
  105. Krumbiegel, M.M.; Pasutto, F.; Mardin, C.Y.; Weisschuh, N.; Paoli, D.; Gramer, E.; Weber, B.H.; Kruse, F.E.; Schlötzer-Schrehardt, U.; Reis, A. Apolipoprotein E Genotypes in Pseudoexfoliation Syndrome and Pseudoexfoliation Glaucoma. Eur. J. Gastroenterol. Hepatol. 2010, 19, 561–565. [Google Scholar] [CrossRef]
  106. Lambert, J.-C.; Zelenika, D.; Hiltunen, M.; Chouraki, V.; Combarros, O.; Bullido, M.J.; Tognoni, G.; Fiévet, N.; Boland, A.; Arosio, B.; et al. Evidence of the association of BIN1 and PICALM with the AD risk in contrasting European populations. Neurobiol. Aging 2011, 32, 756.e11–756.e15. [Google Scholar] [CrossRef] [PubMed]
  107. Lambert, J.-C.; Grenier-Boley, B.; Harold, D.; Zelenika, D.; Chouraki, V.; Kamatani, Y.; Sleegers, K.; A Ikram, M.; Hiltunen, M.; Reitz, C.; et al. Genome-wide haplotype association study identifies the FRMD4A gene as a risk locus for Alzheimer’s disease. Mol. Psychiatry 2013, 18, 461–470. [Google Scholar] [CrossRef] [PubMed]
  108. Mazzeo, S.; Bessi, V.; Padiglioni, S.; Bagnoli, S.; Bracco, L.; Sorbi, S.; Nacmias, B. KIBRA T allele influences memory performance and progression of cognitive decline: A 7-year follow-up study in subjective cognitive decline and mild cognitive impairment. Neurol. Sci. 2019, 40, 1559–1566. [Google Scholar] [CrossRef] [PubMed]
  109. Pamio, M.V.; Trevisan, C.; Pigozzo, S.; De Rui, M.; Devita, M.; Girardi, A.; Manzato, E.; Sergi, G.; Coin, A. Are cytochrome P4502D6 and apolipoprotein E genotypes associated with long-term cognitive and functional changes in patients treated with donepezil? Psychogeriatrics 2020, 20, 578–584. [Google Scholar] [CrossRef] [PubMed]
  110. Piccardi, M.; Congiu, D.; Squassina, A.; Manconi, F.; Putzu, P.F.; Mereu, R.M.; Chillotti, C.; Del Zompo, M. Alzheimer’s disease: Case-control association study of polymorphisms in ACHE, CHAT, and BCHE genes in a Sardinian sample. Am. J. Med Genet. Part B Neuropsychiatr. Genet. 2007, 144, 895–899. [Google Scholar] [CrossRef] [PubMed]
  111. Poli, M.; Gatta, L.B.; Dominici, R.; Lovati, C.; Mariani, C.; Albertini, A.; Finazzi, D. Apolipoprotein E haplotyping by denaturing high-performance liquid chromatography. Clin. Chem. Lab. Med. 2005, 43, 512–518. [Google Scholar] [CrossRef]
  112. Polito, L.; Kehoe, P.G.; Davin, A.; Benussi, L.; Ghidoni, R.; Binetti, G.; Quadri, P.; Lucca, U.; Tettamanti, M.; Clerici, F.; et al. The SIRT2 polymorphism rs10410544 and risk of Alzheimer’s disease in two Caucasian case–control cohorts. Alzheimer’s Dement. 2013, 9, 392–399. [Google Scholar] [CrossRef] [PubMed]
  113. Pozzi, F.E.; Conti, E.; Appollonio, I.; Ferrarese, C.; Tremolizzo, L. Predictors of response to acetylcholinesterase inhibitors in dementia: A systematic review. Front. Neurosci. 2022, 16, 998224. [Google Scholar] [CrossRef]
  114. Rademakers, R.; Baker, M.; Gass, J.; Adamson, J.; Huey, E.D.; Momeni, P.; Spina, S.; Coppola, G.; Karydas, A.M.; Stewart, H.; et al. Phenotypic variability associated with progranulin haploinsufficiency in patients with the common 1477C→T (Arg493X) mutation: An international initiative. Lancet Neurol. 2007, 6, 857–868. [Google Scholar] [CrossRef]
  115. de Matos, M.R.; Ferreira, C.; Herukka, S.-K.; Soininen, H.; Janeiro, A.; Santana, I.; Baldeiras, I.; Almeida, M.R.; Lleó, A.; Dols-Icardo, O.; et al. Quantitative Genetics Validates Previous Genetic Variants and Identifies Novel Genetic Players Influencing Alzheimer’s Disease Cerebrospinal Fluid Biomarkers. J. Alzheimer’s Dis. 2018, 66, 639–652. [Google Scholar] [CrossRef]
  116. Serretti, A.; Olgiati, P.; De Ronchi, D. Genetics of Alzheimer’s Disease. A Rapidly Evolving Field. J. Alzheimer’s Dis. 2007, 12, 73–92. [Google Scholar] [CrossRef] [PubMed]
  117. Weiner, M.W.; Veitch, D.P.; Aisen, P.S.; Beckett, L.A.; Cairns, N.J.; Cedarbaum, J.; Green, R.C.; Harvey, D.; Jack, C.R.; Jagust, W.; et al. 2014 Update of the Alzheimer’s Disease Neuroimaging Initiative: A review of papers published since its inception. Alzheimer’s Dement. 2015, 11, e1–e120. [Google Scholar] [CrossRef] [PubMed]
  118. Yu, C.; Yao, Z.; Jiang, Y.; Keller, E.T. Prostate cancer stem cell biology. Minerva Urol. E Nefrol. Ital. J. Urol. Nephrol. 2012, 64, 19–33. [Google Scholar]
  119. van der Maaten LJ, P.; Hinton, G.E. Visualizing high-dimensional data using t-SNE. J. Mach. Learn. Res. 2008, 9, 2579–2605. [Google Scholar]
  120. Haug, C.J.; Drazen, J.M. Artificial Intelligence and Machine Learning in Clinical Medicine, 2023. N. Engl. J. Med. 2023, 388, 1201–1208. [Google Scholar] [CrossRef]
  121. Abrego-Guandique, D.M.; Bonet, M.L.; Caroleo, M.C.; Cannataro, R.; Tucci, P.; Ribot, J.; Cione, E. The Effect of Beta-Carotene on Cognitive Function: A Systematic Review. Brain Sci. 2023, 13, 1468. [Google Scholar] [CrossRef]
  122. Bevacqua, E.; Ammirato, S.; Cione, E.; Curcio, R.; Dolce, V.; Tucci, P. The Potential of MicroRNAs as Non-Invasive Prostate Cancer Biomarkers: A Systematic Literature Review Based on a Machine Learning Approach. Cancers 2022, 14, 5418. [Google Scholar] [CrossRef]
  123. Kim, D.; Im, T. A Systematic Review of Virtual Reality-Based Education Research Using Latent Dirichlet Allocation: Focus on Topic Modeling Technique. Mob. Inf. Syst. 2022, 2022, 1201852. [Google Scholar] [CrossRef]
  124. Mo, Y.; Kontonatsios, G.; Ananiadou, S. Supporting systematic reviews using lda-based document representations. Syst. Rev. 2015, 4, 172. [Google Scholar] [CrossRef]
  125. Bilro, R.; Loureiro, S.; Souto, A. A systematic review of customer behavior in business-to-business markets and agenda for future research. J. Bus. Ind. Mark. 2023, 38, 122–142. [Google Scholar] [CrossRef]
  126. Lenci, A. Distributional semantics in linguistic and cognitive research. Ital. J. Linguist. 2008, 20, 1–31. [Google Scholar]
  127. Gallelli, L.; Cione, E.; Peltrone, F.; Siviglia, S.; Verano, A.; Chirchiglia, D.; Zampogna, S.; Guidetti, V.; Sammartino, L.; Montana, A.; et al. Hsa-miR-34a-5p and hsa-miR-375 as Biomarkers for Monitoring the Effects of Drug Treatment for Migraine Pain in Children and Adolescents: A Pilot Study. J. Clin. Med. 2019, 8, 928. [Google Scholar] [CrossRef] [PubMed]
  128. Perri, M.; Lucente, M.; Cannataro, R.; De Luca, I.F.; Gallelli, L.; Moro, G.; De Sarro, G.; Caroleo, M.C.; Cione, E.; Cafiero, C. Variation in Immune-Related microRNAs Profile in Human Milk Amongst Lactating Women. MicroRNA 2018, 7, 107–114. [Google Scholar] [CrossRef] [PubMed]
Biomedinformatics 04 00033 g001
Figure 1. Pie chart produced by the MySLR platform, which describes the source of the papers, Scopus in fuchsia, Web of Science in blue, and Pubmed in green, before eliminating duplicates.
Figure 1. Pie chart produced by the MySLR platform, which describes the source of the papers, Scopus in fuchsia, Web of Science in blue, and Pubmed in green, before eliminating duplicates.
Biomedinformatics 04 00033 g001
Biomedinformatics 04 00033 g002
Figure 2. Workflow of the machine learning approach via MySLR.
Figure 2. Workflow of the machine learning approach via MySLR.
Biomedinformatics 04 00033 g002
Biomedinformatics 04 00033 g003
Figure 3. Flow diagram showing the algorithm of selection of eligible studies included.
Figure 3. Flow diagram showing the algorithm of selection of eligible studies included.
Biomedinformatics 04 00033 g003
Biomedinformatics 04 00033 g004
Figure 4. Word cloud highlighting the importance of the topic 1 and 2 keywords, adapted from the MySLR platform.
Figure 4. Word cloud highlighting the importance of the topic 1 and 2 keywords, adapted from the MySLR platform.
Biomedinformatics 04 00033 g004
Biomedinformatics 04 00033 g005
Figure 5. The blue column shows the number of documents for each topic by assigning the document to the topic that has the most weight in that document. The red one shows the number of documents for each topic by summing up the actual weight contribution of each topic to respective documents. Produced by MySLR platform.
Figure 5. The blue column shows the number of documents for each topic by assigning the document to the topic that has the most weight in that document. The red one shows the number of documents for each topic by summing up the actual weight contribution of each topic to respective documents. Produced by MySLR platform.
Biomedinformatics 04 00033 g005
Biomedinformatics 04 00033 g006
Figure 6. Papers publication over time. Produced by the MySLR platform.
Figure 6. Papers publication over time. Produced by the MySLR platform.
Biomedinformatics 04 00033 g006
Biomedinformatics 04 00033 g007
Figure 7. Topic papers over time. Produced by the MySLR platform.
Figure 7. Topic papers over time. Produced by the MySLR platform.
Biomedinformatics 04 00033 g007
Biomedinformatics 04 00033 g008
Figure 8. Inter-topic Distance Map related to topic 1. Circle 1 indicates topic 1, circle 2 is topic 2, extracted from the MySLR platform.
Figure 8. Inter-topic Distance Map related to topic 1. Circle 1 indicates topic 1, circle 2 is topic 2, extracted from the MySLR platform.
Biomedinformatics 04 00033 g008
Biomedinformatics 04 00033 g009
Figure 9. Inter-topic Distance Map related to topic 2. Circle 1 indicates topic 1, circle 2 is topic 2, extracted from the MySLR platform.
Figure 9. Inter-topic Distance Map related to topic 2. Circle 1 indicates topic 1, circle 2 is topic 2, extracted from the MySLR platform.
Biomedinformatics 04 00033 g009
Biomedinformatics 04 00033 g010
Figure 10. The t-SNE visualization of each topic. The red dots represent the topic one, the blue dots represent the topic two. Produced by MySLR.
Figure 10. The t-SNE visualization of each topic. The red dots represent the topic one, the blue dots represent the topic two. Produced by MySLR.
Biomedinformatics 04 00033 g010
Table 1. Overview of the characteristics of the papers included by machine learning in topic one.
Table 1. Overview of the characteristics of the papers included by machine learning in topic one.
Name, YearRefGeneMutationsLocalizationOther
Albani et al., 2012[27]------------------------------------------------------------------------------------Not in Alzheimer
Andreoli et al., 2014[28]GRINB2rs7301328 (GRINB2), rs1805482 (GRINB2), rs3026160 (GRINB2), rs1806201 (GRINB2), rs1806191 (GRINB2)ItalyAlzheimer
Bagnoli et al., 2007[29]IL-10rs1800896 (IL-10), rs1800871 (IL-10)ItalyAlzheimer
Bagnoli et al., 2013[30]TOMM40rs157580 (TOMM40), rs2075650 (TOMM40), rs15758 (TOMM40)ItalyAlzheimer
Bartoletti-Stella et al., 2022[31]ELAVL1, EP300, EPHA1, FERMT2, INPP5D, MARK2, MARK4, PICALM PLCG2, PTK2B, RIN3, TOMM40 ZCWPW1, ADAM10, BIN1, CLU, CR1c.112A > G (ADAM10), c.556dupC (ADAM10), c.696C > A (BIN1), c.865G > A (BIN1), c.1462-3C > T (BIN1), c.509C > T (CLU), c.4956G > A (CR1), c.4356T > C (CR1), c.765C > T (ELAVL1), c.2194C > T (EP300), c.928A > G (EPHA1), c.1077G > C (FERMT2), c.1538C > T (FERMT2), c.470G > A (INPP5D), c.2085C > T (INPP5D), c.1611C > T (MARK2), c.1553C > T (MARK4), c.1231G > C (PICALM), c.3379C > A (PLGC2), c.408G > A (PLCG2), c.2591C > T (PTK2B), c.2377T > C (RIN3),c.384C > G (TOMM40), c.1834C > T (ZCWPW1), c.314A > G (ZCWPW1), c.283-5T > G (ZCWPW1)ItalyAlzheimer
Belloy et al., 2022[32]ApoErs439401 (ApoE)Not in ItalyAlzheimer
Bizzarro et al., 2009[33]ApoErs449647 (ApoE), rs405509 (ApoE), rs769446 (ApoE), rs429358 (ApoE)
rs7412 (ApoE)		ItalyAlzheimer
Bosco et al., 2013[34]---------------------------------------------------------------------------------Review
Broer et al., 2015[35]---------------------------------------------------------------------------------------Not Alzheimer
Bucossi et al., 2012[36]ATP7Brs1061472 (ATP7B), rs732774 (ATP7B)ItalyAlzheimer
Capurso et al., 2010[37]IL-6–174 G/C (IL-6)ItalyAlzheimer
Capurso et al., 2010[38]GSTO1, APOErs7412 (ApoE), rs429358 (ApoE), rs4925 (GSTO1), rs1804834 (GSTO1)ItalyAlzheimer
Cellini et al., 2009[39]SORL1rs661057 (SORL1), rs11218304 (SORL1), rs560573 (SORL1), rs12364988 (SORL1), rs668387 (SORL1), rs689021 (SORL1), rs641120 (SORL1), rs556349 (SORL1), rs2070045 (SORL1), rs1699102 (SORL1), rs3824968 (SORL1), rs2282649 (SORL1), rs1010159 (SORL1)ItalyAlzheimer
Ciminelli et al., 2020[40]AKR7A2,
ALDH5A1, ABAT		rs4646832 (ALDH5A1), rs4646828 (ALDH5A1), rs2760118 (ALDH5A1), rs3765310 (ALDH5A1), rs1043657 (AKR7A2), rs1731017 (ABAT)ItalyAlzheimer
Clarelli et al., 2016[41]CHRNA7rs6494223 (CHRNA7),
rs8024987 (CHRNA7)		ItalyAlzheimer
Colacicco et al.,2009[42]A2M, ORL1rs669 (A2M), +1073 (ORL1) +1071 (ORL1)ItalyAlzheimer
Corbo et al.,2009[43]CYP19rs12907866 (CYP19), rs17601241 (CYP19), rs4646 (CYP19)ItalyAlzheimer
Cruz-Sanabria et al., 2021[44]-------------------------------------------------------------------------------------Not Alzheimer
DeMichele-Sweet et al., 2021[45]ENPP6, SUMF1rs9994623 (ENPP6), rs201109606 (SUMF1)Not in ItalyAlzheimer
Di Maria et al., 2012[46]NGFrs6330 (NGF), rs11466110 (NGF), rs11466111 (NGF), rs6325 (NGF), rs35941329 (NGF)ItalyAlzheimer
Emanuele et al., 2011[47]CDKN2B-AS1rs1333049 (CDKN2B-AS1)ItalyAlzheimer
Finckh et al., 2003[48]PLAU−141 C/T (PLAU)ItalyAlzheimer
Fortney et al., 2015[49]----------------------------------------------------------------------------------Not alzheimer
Galimberti et al., 2008[50]NOS 1Ex1f-VNTR (NOS1)ItalyAlzheimer
Guerini et al., 2016[51]SNAP-25rs363050 (SNAP-25), rs363039 (SNAP-25), rs363043 (SNAP-25)ItalyAlzheimer
Hollingworth et al., 2011[52]CUX2, CDK1, CNTN5, C16orf88, IQCK, MS4A6A, CR1, MS4A6A, BIN1, ABCA7rs3764650 (ABCA7), rs744373 (BIN1), rs670139 (MS4A4E), rs3818361 (CR1), rs610932 (MS4A6A), rs7191155 (IQCK), rs4782279 (IQCK), rs1858973 (IQCK), rs739565 (C16orf88), rs10501927 (CNTN5), Rs10761558 (CDK1), rs3809278 (CUX2)ItalyAlzheimer
Jun et al., 2016[53]ARL17Brs2732703 (ARL17B)NRAlzheimer
Lambert et al., 2009[54]CLU, CR1rs11136000 (CLU), rs2279590 (CLU), rs9331888 (CLU), rs6656401 (CR1), rs3818361 (CR1)ItalyAlzheimer
Lambert et al., 2013[55]BIN1, HLA-DRB5/HLA-DRB1, ZCWPW1, PTK2B, CELF1, MS4A6Ars6733839 (BIN1), rs9271192 (HLA-DRB5/HLA-DRB1), rs1476679 (ZCWPW1), rs28834970 (PTK2B), rs9331896 (CLU), rs10838725 (CELF1), rs983392 (MS4A6A)ItalyAlzheimer
Lanni et al., 2012[56]COMTrs4680 (COMT)ItalyAlzheimer
Laws et al., 2005[57]TNFrs1799724 (TNF), rs1800629 (TNF)Not in ItalyAlzheimer
Lescai et al., 2010[58]PCDH11Xrs5984894 (PCDH11X)ItalyAlzheimer
Lescai et al., 2011[59]ApoErs449647 (ApoE), rs769446 (ApoE), rs405509 (ApoE), rs429358 (ApoE), rs7412 (ApoE)ItalyAlzheimer
Licastro et al., 2011[60]IL10, TNF, IL6, IFNG [SERPINA3, HMGCR–1082G/A(IL10), –308 G/A(TNF),
−174 G/C (IL6), +874 T/A (IFNG), –51 G/T (SERPINA 3), –911 C/A(HMGCR)		ItalyAlzheimer
Licastro et al., 2015[61]IL-28 b, Med23rs12979860 (IL-28 B),
rs3756784 (MED 23)		ItalyAlzheimer
Lio et al., 2003[62]IL-10−1082 G/A (IL-10), −819 C/T (IL-10), −592 C/A (IL-10)ItalyAlzheimer
Lio et al., 2006[63]TNF-α−308 G/A (TNF-α)ItalyAlzheimer
Lu et al., 2017[64]HLA-DRB1rs9271192 (HLA-DRB1)Not in ItalyAlzheimer
Lupton et al., 2016[65]TREM2rs9394721 (TREM2)Not in ItalyAlzheimer
Maletta et al., 2018[66]MTHFR, ACE, AGT, CYP7A1, PAI-1, FII G20210A, FV HR2 H1299R, FV Leiden, GPIIIa, CETPrs1801133 (MTHFR), rs1801131 (MTHFR), rs1799752 (ACE), rs699 (AGT), 844ins68 (CBS),rs3808607 (CYP7A1), rs1799889 (PAI-1), rs1799963 (FII G20210A), rs1800595 (FV HR2 H1299R), rs6025 (FV Leiden), rs5918 (GPIIIa), rs5882 (CETP)ItalyAlzheimer
Mariani et al., 2013[67]HFE, TF, C282Yrs1800562 (C282Y), rs1799945 (HFE), rs1049296 (TF)ItalyAlzheimer
Masri et al., 2020[68]PICALMrs3851179G > A (PICALM)Not in ItalyAlzheimer
Minoretti et al., 2006[69]TLR4Asp299Gly (TLR4)ItalyAlzheimer
Montesanto et al., 2016[70]UCP2, UCP3, UCP4, UCP5rs2306820 (UCP3), rs655717 (UCP2), rs660339 (UCP2), rs659366 (UCP2), rs635441 (UCP2), rs1685354 (UCP3), rs2734827 (UCP3), rs1800849 (UCP3), rs10498769 (UCP4), rs12192544 (UCP4), rs3757241 (UCP4), rs9472817 (UCP4), rs17314910 (UCP5), rs6637742 (UCP5), rs3007756 (UCP5), rs5930414 (UCP5)ItalyAlzheimer
Nacmias et al., 2009[71]GAB2rs2373115 (GAB2)ItalyAlzheimer
Napolioni et al., 2011[72]--------------------------------------------------------------------------------------Not Alzheimer
Olgiati et al., 2013[73]SORL1rs668387 (SORL1), rs68902 (SORL1), rs641120 (SORL1)NRAlzheimer
Orlacchio et al., 2002[74]NCSTN237 G/A (NCSTN) 747 C/T (NCSTN)ItalyAlzheimer
Pilotto et al., 2009[75]CYP2D6rs1080985 (CYP2D6)ItalyAlzheimer
Pola et al., 2004[76]MCP-1−2518 A/G (MCP-1)ItalyAlzheimer
Poleggi et al., 2008[77]PRNPMet129- Val (PRNP)ItalyAlzheimer
Poli et al., 2008[78]APH-1bC + 651T > G (APH-1b)ItalyAlzheimer
Porrello et al., 2006[79]Er-αPvuII (−397 T/C), XbaI (−351 A/G) (Er-α)ItalyAlzheimer
Scacchi et al., 2009[80]P53, P73rs1042522 (P53), rs2273953 (P73),
rs1801173 (P73), rs3765728 (P73), rs1801174 (P73)		ItalyAlzheimer
Scasellati et al., 2004[81]IL-10−1082 G/A (IL-10), −819 T/C (IL-10), −592 C/A (IL-10)ItalyAlzheimer
Schmidt et al., 2011[82]--------------------------------------------------------------------------------------Not in Alzheimer
Schott et al., 2016[83]CR1, BIN1, INPP5D, SCARB2, SNCA, MEF2C, CD2AP, EPHA1, NME8, ZCWPW, CLU, PTK2B, CELF1, MS4A4E, PICALM, SORL1, FERMT2, SLC4A4, RIN3, ABCA7, APOE, CD33, EXOC3L2,
BLOC1S3, MARK4, CASS4		rs3818361 (CR1), rs744373 (BIN1), rs35349669 (INPP5D), rs6825004 (SCARB2), rs7687945 (SNCA), rs190982 (MEF2C), rs10948363 (CD2AP), rs11767557 (EPHA1), rs2718058 (NME8), rs1476679 (ZCWPW), rs11136000 (CLU), rs28834970 (PTK2B), rs10838725 (CELF1), rs10838725 (MS4A4E), rs10838725 (PICALM), rs670139 (SORL1), rs983392 (FERMT2), rs3851179 (SLC4A4), rs11218343 (RIN3), rs17125944 (ABCA7), rs10498633 (APOE), rs3764650 (CD33), rs2075650 (EXOCL3L2), rs3865444 (BLOC1S3),rs597668 (MARK4), rs7274581 (CAS4)Not only in ItalyAlzheimer
Scola et al., 2003[84]IFN-γ+874T→A (IFN-γ)ItalyAlzheimer
Seripa et al., 2008[85]GRIN2Brs1019385 (GRIN2B), rs1806201 (GRIN2B), rs890 (GRIN2B)ItalyAlzheimer
Seripa et al., 2008[86]RELN, LIMK2rs607755 (RELN), rs2229864 (LIMK2)ItalyAlzheimer
Seripa et al., 2011[87]---------------------------------------------------------------------------------------Review
Serpente et al., 2011[88]ORL1rs1050283 (ORL1)ItalyAlzheimer
Squillario et al., 2020[89]TOMM40, GRM7rs2075650 (TOMM40), rs8106922 (TOMM40), rs9311976
(GRM7), rs266410 (GRM7)		NRAlzheimer
Talwar et al., 2021[90]ApoE, EGFR, ACTBrs405509 (ApoE), rs7259620 (ApoE), rs769449 (ApoE), rs725617 (ApoE),
rs7256173 (ApoE), rs6970262 (EGFR), rs852423 (ACTB)		Not in ItalyAlzheimer
Tedde et al., 2010[91]NEDD9rs760678 (NEDD9)ItalyAlzheimer
Tindale et al., 2017[92]---------------------------------------------------------------------------------------Not Alzheimer
Tisato et al., 2018[93]TF, HFE, FPN1, HAMPHFE C282Y, HFE H63D, FPN1 −8CG, HAMP −582AG, TF P570SItalyAlzheimer
Valenza et al., 2010[94]ApoE−491 A/T (ApoE)ItalyAlzheimer
Venturelli et al., 2005[95]eNOST-786C (eNOS)ItalyAlzheimer
Wang et al., 2016[96]GAB2, PICALM, SORL1rs1010159 (SORL1), rs12285364 (SORL1), rs1699102 (SORL1), rs2070045 (SORL1), rs2282649 (SORL1), rs3824968 (SORL1), rs4935774 (SORL1), rs556349 (SORL1), rs641120 (SORL1), rs661057 (SORL1), rs668387 (SORL1), rs689021 (SORL1), rs3851179 (PICALM), rs541458 (PICALM), rs2373115 (GAB2)Not in ItalyAlzheimer
NR: not reported.
Table 2. Overview of the characteristics of the papers included by machine learning in topic two.
Table 2. Overview of the characteristics of the papers included by machine learning in topic two.
Name, YearRefGeneMutationsLocalizationOther
Bernardi et al., 2012[97]-----------------------------------------------------------------------------------------Not Alzheimer
Calabretta et al., 2009[98]-----------------------------------------------------------------------------------------Not Alzheimer
Cheng et al., 2012[99]NGFRrs734194 (NGFR), rs2072445 (NGFR), rs2072446 (NGFR), rs741072 (NGFR), rs741073 (NGFR)Not in ItalyAlzheimer
De Rojas et al., 2021[100]PRKD3/NDUFAF7, SHARPIN, PLCG2, CHRNE, APPrs876461 (PRKD3/NDUFAF7), rs34674752 (SHARPIN), rs34173062 (SHARPIN), rs3935877 (PLCG2),
rs72835061 (CHRNE),
rs2154481 (APP)		NRAlzheimer
Flex et al., 2006[101]MMP-1, MMP-3, MMP-92G2G (MMP-1),
1G2G (MMP-1),
5A5A (MMP-3),
TT (MMP-9)		ItalyAlzheimer
Grunbatt et al., 2011[102]CHATrs10776585 (CHAT), rs2289305 (CHAT), rs3750752 (CHAT), rs12356649 (CHAT), rs11591558 (CHAT), rs8178984 (CHAT), rs1153783 (CHAT), rs1880676 (CHAT), rs12359885 (CHAT), rs8178990 (CHAT), rs10082479 (CHAT), rs17775758 (CHAT), rs7903612 (CHAT), rs7091005 (CHAT), rs2889759 (CHAT), rs4838391 (CHAT), rs11101186 (CHAT), rs10857520 (CHAT)ItalyAlzheimer
Hansmannel et al., 2010[103]OTCrs5963409 (OTC),
rs5963411 (OTC)		ItalyAlzheimer
Hong et al., 2020[104]ApoE, LINC01570, TOMM40, LOC124903153, NECTIN 2, LOC107985236, LINC01030, LINC00624, APOC1, ADAMTS3, ADGRB3, FZD4-DT, LOC107984589, SLC2A3, NMNAT2rs429358 (ApoE), rs10400961 (LINC01570), rs34095326 (TOMM40), rs1004954 (LOC124903153),
rs34794167 (LOC124903153),
rs6857 (NECTIN2), rs12857276 (LOC124903153),
rs7254133 (GRCh38?),
rs2209929 (LOC124903153),
rs3814341 (LOC107985236),
rs2023625 (LINC01030), rs35386129 (LOC124903153),
rs2321744 (LOC124903153), rs985017 (LOC124903153), rs769449 (ApoE),
rs985018 (LOC124903153), rs36015381 (LOC124903153), rs34528363 (LOC124903153), rs12972970 (NECTIN2), rs12972156 (NECTIN2), rs68058618 (GRCh38?), rs12429500 (LOC124903153),
rs6672481 (LINC00624),
rs2353964 (LINC00624), rs10900366 (LINC00624), rs12721051 (APOC1), rs12408395 (LINC00624),
rs9592217 (LOC124903153),
rs9598510 (LOC124903153),
rs10900364 (LINC00624), rs11240038 (LINC00624),rs9598511 (LOC124903153), rs6657402 (LINC00624), rs2353972 (LINC00624), rs36055662 (ADAMTS3), rs117950083 (ADGRB3)
rs35709873 (LOC124903153), rs56131196 (APOC1),
rs4420638 (APOC1),
rs55696402 (LOC124903153),
rs11605035 (FZD4-DT),
rs11606999 (FZD4-DT), rs11607037 (FZD4-DT),rs10898566 (FZD4-DT), rs10898565 (FZD4-DT),rs12999830 (GRCh38), rs11240037 (GRCh38),
rs11240043 (LINC00624), rs2075650 (TOMM40),
rs34404554 (TOMM40), rs4600098 (LINC00624),
rs6684440 (LINC00624), rs4381253 (LINC00624),
rs6683579 (LINC00624), rs6657222 (LINC00624),
rs2883315 (LINC00624), rs4339909 (LINC00624),
rs6696385 (LINC00624), rs11581799 (LINC00624), rs11556505 (TOMM40), rs4375326 (LINC00624),
rs11576468 (LINC00624), rs11589438 (LINC00624), rs12742771 (LINC00624), rs11240050 (LINC00624),
rs78581038 (LOC107984589), rs12812878 (SLC2A3),
rs6695692 (LINC00624),
rs6688033 (LINC00624),
rs11234901 (FZD4-DT),
rs6688244 (LINC00624), rs6678706 (LINC00624), rs11605694 (FZD4-DT),rs58619449 (FZD4-DT),
rs58370115 (FZD4-DT), rs7127641 (FZD4-DT),
rs61809265 (NMNAT2), rs35519936 (LOC124903153), rs34342646 (NECTIN2),rs10414043 (APOC1), rs72639166 (FZD4-DT),rs7256200 (APOC1)		Not in ItalyAlzheimer
Krumbiegel et al., 2010[105]-----------------------------------------------------------------------------------------Not Alzheimer
Lambert et al., 2011[106]BIN1, EXO3CL2, PICALMrs744373 (BIN1), rs597668 (EXO3CL2), rs541458 (PICALM)ItalyAlzheimer
Lambert et al., 2013[107]FRMD4Ars7081208 (FRMD4A), rs2446581 (FRMD4A), rs17314229 (FRMD4A)ItalyAlzheimer
Mazzeo et al., 2019[108]-----------------------------------------------------------------------------------------Not Alzheimer
Pamio et al., 2020[109]CYP2D6rs1080985 (CYP2D6)ItalyAlzheimer
Piccardi et al., 2007[110]CHAT, AChErs2177369 (CHAT), rs12705094 (AChE), rs3087504 (AChE), rs3757869 (AChE)ItalyAlzheimer
Poli et al., 2005[111]ApoErs11542041 (ApoE), rs11542035 (ApoE), rs769455 (ApoE)ItalyNot Alzheimer
Polito et al., 2013[112]SIRT2, SIRT3rs10410544 (SIRT2), rs4980329(SIRT3),
rs536715 (SIRT3),
rs2015 (SIRT2),
rs3825075 (SIRT3), rs11880757 (SIRT2), rs11879010 (SIRT2), rs11667030 (SIRT2)		ItalyAlzheimer
Pozzi et al., 2022[113]-----------------------------------------------------------------------------------------SR
Rademakers et al., 2007[114]GRN, MAPTArg493X (GRN), rs1052553 (MAPT), rs7412 (ApoE), rs429358 (ApoE), rs4792937(GRN), rs2879096 (GRN),
c.–7–320G→C (GRN),
rs34424835 (GRN), rs9897528 (GRN), rs25646 (GRN), c.835 + 7A→G (GRN), rs5848 (GRN), rs34424835 (GRN)		Not in ItalyAlzheimer
Ramos De Matos et al., 2018[115]APOE, LOC100129500, PVRL2, SNAR-I, TOMM40, INPP5, CD2AP, GLIS3, PVRL2, CASS4rs35349669(INPP5), rs1316356 (SNAR-1),
rs9877502 (SNAR-1),
rs9349407 (CD2AP),
rs514716 (GLIS3),
rs12972156 (PVRL2), rs34342646 (PVRL2), rs71352238 (TOMM40),rs157580 (TOMM40),
rs2075650 (TOMM40),
rs34404554 (TOMM40),
rs11556505 (TOMM40),
rs769449 (APOE),
rs429358 (APOE),
rs439401 (LOC100129500),
rs7274581 (CASS4)		Italy *Alzheimer
Serretti et al., 2007[116]-----------------------------------------------------------------------------------------Review
Weiner et al., 2015[117]-----------------------------------------------------------------------------------------Review
Yu et al., 2012[118]-----------------------------------------------------------------------------------------Not Alzheimer
SR: Systematic Review. * European Studies involving Italy.
Table 3. Main characteristics of the studies fit our query.
Table 3. Main characteristics of the studies fit our query.
Name, YearRef.GeneMutationsLocalization
Bizzarro et al., 2009[33]ApoErs449647, rs405509, rs769446Italy
Capurso et al., 2010[38]ApoErs7412, rs429358Italy
Lescai et al., 2011[59]ApoErs449647, rs769446, rs405509, rs429358, rs7412Italy
Valenza et al., 2010[94]ApoE−491 AT vs −491 AAItaly
Ramos de matos et al., 2018[115]ApoErs769449, rs429358Italy *
* European Studies involving Italy.
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Saraceno, G.F.; Abrego-Guandique, D.M.; Cannataro, R.; Caroleo, M.C.; Cione, E. Machine Learning Approach to Identify Case-Control Studies on ApoE Gene Mutations Linked to Alzheimer’s Disease in Italy. BioMedInformatics 2024, 4, 600-622. https://doi.org/10.3390/biomedinformatics4010033

AMA Style

Saraceno GF, Abrego-Guandique DM, Cannataro R, Caroleo MC, Cione E. Machine Learning Approach to Identify Case-Control Studies on ApoE Gene Mutations Linked to Alzheimer’s Disease in Italy. BioMedInformatics. 2024; 4(1):600-622. https://doi.org/10.3390/biomedinformatics4010033

Chicago/Turabian Style

Saraceno, Giorgia Francesca, Diana Marisol Abrego-Guandique, Roberto Cannataro, Maria Cristina Caroleo, and Erika Cione. 2024. "Machine Learning Approach to Identify Case-Control Studies on ApoE Gene Mutations Linked to Alzheimer’s Disease in Italy" BioMedInformatics 4, no. 1: 600-622. https://doi.org/10.3390/biomedinformatics4010033

Article Metrics

Back to TopTop