Biomedical engineering and computational biology · 2026
A Scoping Review of Machine Learning-Based Prediction of Alzheimer's Disease Using Blood Biomarkers.
СтатьяОбзорНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Bhatti Muhammad Hamza Rafique, Aly Amir, Khan Asiya, Awan Shakil
Аннотация
BACKGROUND: Alzheimer's disease (AD) is a progressive neurodegenerative disorder of late life that causes cognitive and functional decline and substantial mortality. Machine learning (ML) is increasingly used to discover patterns in clinical and biomarker data that support earlier and more accurate AD detection.
OBJECTIVES: This scoping review addresses three core research questions. First, we investigate recent trends in using machine-learning techniques to detect Alzheimer's disease using blood biomarkers. Second, we identify the blood biomarkers involved in Alzheimer's detection and evaluate how machine learning has been applied to improve the diagnostic capabilities of these biomarkers. Third, we highlight significant challenges associated with using machine learning for blood biomarker data in Alzheimer's detection and examine proposed advancements or solutions to handle these problems.
METHODS: In June 2025, we searched six academic databases to identify relevant papers on blood biomarkers and ML methods for Alzheimer's Disease. Search queries were developed based on our predefined research questions. Papers were then screened using defined inclusion and exclusion criteria, where titles, abstracts, and full texts of articles were systematically reviewed.
RESULTS: Following the screening approach, we selected 36 papers that fulfilled our inclusion and exclusion criteria. Through careful examination, we classified blood biomarkers into four types: transcriptomics, proteomics, multi-omic biomarkers, and general elemental blood biomarkers. Across these studies, proteomic blood biomarkers consistently emerged as significant indicators for Alzheimer's disease, including Alpha-2-Macroglobulin (A2M), Apolipoprotein E (ApoE), Eotaxin-3 (EOT3), plasma phosphorylated tau (p-tau 181), and neurofilament light chain (NfL). Furthermore, we explored challenges such as small sample sizes, lack of standardization, heterogeneity, and data imbalance.
CONCLUSIONS: This review provides insights into how combining blood biomarkers with ML can enhance AD prediction. The review summarizes key challenges and identifies critical gaps for future research.
OBJECTIVES: This scoping review addresses three core research questions. First, we investigate recent trends in using machine-learning techniques to detect Alzheimer's disease using blood biomarkers. Second, we identify the blood biomarkers involved in Alzheimer's detection and evaluate how machine learning has been applied to improve the diagnostic capabilities of these biomarkers. Third, we highlight significant challenges associated with using machine learning for blood biomarker data in Alzheimer's detection and examine proposed advancements or solutions to handle these problems.
METHODS: In June 2025, we searched six academic databases to identify relevant papers on blood biomarkers and ML methods for Alzheimer's Disease. Search queries were developed based on our predefined research questions. Papers were then screened using defined inclusion and exclusion criteria, where titles, abstracts, and full texts of articles were systematically reviewed.
RESULTS: Following the screening approach, we selected 36 papers that fulfilled our inclusion and exclusion criteria. Through careful examination, we classified blood biomarkers into four types: transcriptomics, proteomics, multi-omic biomarkers, and general elemental blood biomarkers. Across these studies, proteomic blood biomarkers consistently emerged as significant indicators for Alzheimer's disease, including Alpha-2-Macroglobulin (A2M), Apolipoprotein E (ApoE), Eotaxin-3 (EOT3), plasma phosphorylated tau (p-tau 181), and neurofilament light chain (NfL). Furthermore, we explored challenges such as small sample sizes, lack of standardization, heterogeneity, and data imbalance.
CONCLUSIONS: This review provides insights into how combining blood biomarkers with ML can enhance AD prediction. The review summarizes key challenges and identifies critical gaps for future research.