Hesameddin Mostaghimi , Daniel A. Cohen , Hamid. R. Okhravi , Bahar Niknejad , Michel A. Audette
{"title":"The multifactorial nature of Alzheimer’s disease: A review of diverse determinants and the essential role of multimodal machine learning","authors":"Hesameddin Mostaghimi , Daniel A. Cohen , Hamid. R. Okhravi , Bahar Niknejad , Michel A. Audette","doi":"10.1016/j.aggp.2025.100207","DOIUrl":null,"url":null,"abstract":"<div><div>Alzheimer’s disease (AD), the most prevalent form of dementia, arises from a complex interplay of determinants, including neurological and cognitive impairments, molecular and genetic markers, systemic comorbidities, and lifestyle-related factors. While traditional research has often focused on individual or narrow sets of determinants, recent advancements highlight the necessity of examining these diverse contributors in unison. In addition, the rapid growth of heterogeneous multimodal data in healthcare necessitates sophisticated analytical frameworks. In this review, we first summarize the evidence on the broad spectrum of AD risk factors and mechanisms, and then discuss the necessity and potential of multimodal machine learning (ML) techniques in integrating complex datasets, which could ultimately lead to personalized therapeutic strategies for this disease. This narrative review qualitatively synthesizes 250 peer-reviewed studies published between 2010 and 2024.</div></div>","PeriodicalId":100119,"journal":{"name":"Archives of Gerontology and Geriatrics Plus","volume":"2 4","pages":"Article 100207"},"PeriodicalIF":0.0000,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Archives of Gerontology and Geriatrics Plus","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2950307825000888","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Alzheimer’s disease (AD), the most prevalent form of dementia, arises from a complex interplay of determinants, including neurological and cognitive impairments, molecular and genetic markers, systemic comorbidities, and lifestyle-related factors. While traditional research has often focused on individual or narrow sets of determinants, recent advancements highlight the necessity of examining these diverse contributors in unison. In addition, the rapid growth of heterogeneous multimodal data in healthcare necessitates sophisticated analytical frameworks. In this review, we first summarize the evidence on the broad spectrum of AD risk factors and mechanisms, and then discuss the necessity and potential of multimodal machine learning (ML) techniques in integrating complex datasets, which could ultimately lead to personalized therapeutic strategies for this disease. This narrative review qualitatively synthesizes 250 peer-reviewed studies published between 2010 and 2024.