Predicting Alzheimer's Disease onset: A machine learning framework for early diagnosis using biomarker data

Alzheimer’s Disease (AD) is a significant global health issue, and the current diagnostic techniques cannot diagnose the disease at its early stages, hence the difficulty of early therapeutic management. In response to the formulated research problem, this study articulates a new multimodal machine-...

Полное описание

Сохранить в:
Библиографические подробности
Главные авторы: Shehu Mohammed, Neha Malhotra
Формат: Статья
Язык:английский
Опубликовано: Elsevier 2025-01-01
Серии:Computer Methods and Programs in Biomedicine Update
Предметы:
Online-ссылка:http://www.sciencedirect.com/science/article/pii/S2666990025000345
Метки: Добавить метку
Нет меток, Требуется 1-ая метка записи!
_version_ 1839603976772780032
author Shehu Mohammed
Neha Malhotra
author_facet Shehu Mohammed
Neha Malhotra
author_sort Shehu Mohammed
collection DOAJ
description Alzheimer’s Disease (AD) is a significant global health issue, and the current diagnostic techniques cannot diagnose the disease at its early stages, hence the difficulty of early therapeutic management. In response to the formulated research problem, this study articulates a new multimodal machine-learning framework for early AD diagnosis. The main goal is to combine multiple biomarkers: neuroimaging, CSF, genetic, and longitudinal cognitive data and develop a robust model for accurate early AD diagnosis. The importance of this work is in the opportunity to shift diagnostic paradigms by employing deep learning algorithms, including CNNs, LSTM networks, and GNNs to analyze spatial, temporal, and relational patterns across multi-modal data. The methodology involves federated learning and domain adaptation with GANs to integrate data from multiple centers with the patient’s privacy intact. It shows that the proposed multimodal model is superior to single-modality models with an AUC-ROC of 0.94 and reveals that hippocampal volume and plasma p-tau are the most informative biomarkers in the early diagnosis of AD. The study’s implications indicate that combining multimodal data improves diagnostic accuracy and clinical relevance by providing a roadmap to developing personalized medicine and better patient care. Future work will be aimed at increasing the variability of the dataset and the clinical trials to test the model to improve its applicability and performance in actual practice.
format Article
id doaj-art-e8473bcc43cd478ca19dc236d27a24f8
institution Matheson Library
issn 2666-9900
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Computer Methods and Programs in Biomedicine Update
spelling doaj-art-e8473bcc43cd478ca19dc236d27a24f82025-08-02T04:47:54ZengElsevierComputer Methods and Programs in Biomedicine Update2666-99002025-01-018100209Predicting Alzheimer's Disease onset: A machine learning framework for early diagnosis using biomarker dataShehu Mohammed0Neha Malhotra1Corresponding author.; Department of Computer Applications, Lovely Professional University Phagwara, IndiaDepartment of Computer Applications, Lovely Professional University Phagwara, IndiaAlzheimer’s Disease (AD) is a significant global health issue, and the current diagnostic techniques cannot diagnose the disease at its early stages, hence the difficulty of early therapeutic management. In response to the formulated research problem, this study articulates a new multimodal machine-learning framework for early AD diagnosis. The main goal is to combine multiple biomarkers: neuroimaging, CSF, genetic, and longitudinal cognitive data and develop a robust model for accurate early AD diagnosis. The importance of this work is in the opportunity to shift diagnostic paradigms by employing deep learning algorithms, including CNNs, LSTM networks, and GNNs to analyze spatial, temporal, and relational patterns across multi-modal data. The methodology involves federated learning and domain adaptation with GANs to integrate data from multiple centers with the patient’s privacy intact. It shows that the proposed multimodal model is superior to single-modality models with an AUC-ROC of 0.94 and reveals that hippocampal volume and plasma p-tau are the most informative biomarkers in the early diagnosis of AD. The study’s implications indicate that combining multimodal data improves diagnostic accuracy and clinical relevance by providing a roadmap to developing personalized medicine and better patient care. Future work will be aimed at increasing the variability of the dataset and the clinical trials to test the model to improve its applicability and performance in actual practice.http://www.sciencedirect.com/science/article/pii/S2666990025000345Alzheimer's Disease (AD)Early diagnosisMultimodal biomarkersMachine learningDeep learningNeuroimaging
spellingShingle Shehu Mohammed
Neha Malhotra
Predicting Alzheimer's Disease onset: A machine learning framework for early diagnosis using biomarker data
Computer Methods and Programs in Biomedicine Update
Alzheimer's Disease (AD)
Early diagnosis
Multimodal biomarkers
Machine learning
Deep learning
Neuroimaging
title Predicting Alzheimer's Disease onset: A machine learning framework for early diagnosis using biomarker data
title_full Predicting Alzheimer's Disease onset: A machine learning framework for early diagnosis using biomarker data
title_fullStr Predicting Alzheimer's Disease onset: A machine learning framework for early diagnosis using biomarker data
title_full_unstemmed Predicting Alzheimer's Disease onset: A machine learning framework for early diagnosis using biomarker data
title_short Predicting Alzheimer's Disease onset: A machine learning framework for early diagnosis using biomarker data
title_sort predicting alzheimer s disease onset a machine learning framework for early diagnosis using biomarker data
topic Alzheimer's Disease (AD)
Early diagnosis
Multimodal biomarkers
Machine learning
Deep learning
Neuroimaging
url http://www.sciencedirect.com/science/article/pii/S2666990025000345
work_keys_str_mv AT shehumohammed predictingalzheimersdiseaseonsetamachinelearningframeworkforearlydiagnosisusingbiomarkerdata
AT nehamalhotra predictingalzheimersdiseaseonsetamachinelearningframeworkforearlydiagnosisusingbiomarkerdata