A systematic literature review on the significance of deep learning and machine learning in predicting Alzheimer's disease

• Published in: Artificial intelligence in medicine Vol. 154; p. 102928
• Main Authors: Kaur, Arshdeep, Mittal, Meenakshi, Bhatti, Jasvinder Singh, Thareja, Suresh, Singh, Satwinder
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.08.2024
• Subjects: Algorithms; Alzheimer Disease - diagnosis; Alzheimer Disease - diagnostic imaging; Alzheimer's disease; Biomarkers; Classification; Deep Learning; Humans; Machine Learning; Magnetic Resonance Imaging; Magnetic Resonance Imaging - methods; Mild Cognitive Impairment; Neuroimaging - methods; Positron Emission Tomography; Positron-Emission Tomography - methods; Prediction; Magnetic Resonance Imaging; Prediction; Classification; Positron Emission Tomography; Mild Cognitive Impairment; Alzheimer's disease; Machine Learning; Deep Learning
• ISSN: 0933-3657; 1873-2860; 1873-2860
• DOI: 10.1016/j.artmed.2024.102928

Alzheimer's disease (AD) is the most prevalent cause of dementia, characterized by a steady decline in mental, behavioral, and social abilities and impairs a person's capacity for independent functioning. It is a fatal neurodegenerative disease primarily affecting older adults. The purpose of this literature review is to investigate various AD detection techniques, datasets, input modalities, algorithms, libraries, and performance evaluation metrics used to determine which model or strategy may provide superior performance. The initial search yielded 807 papers, but only 100 research articles were chosen after applying the inclusion-exclusion criteria. This SLR analyzed research items published between January 2019 and December 2022. The ACM, Elsevier, IEEE Xplore Digital Library, PubMed, Springer and Taylor & Francis were systematically searched. The current study considers articles that used Magnetic Resonance Imaging (MRI), Positron Emission Tomography (PET), APOe4 genotype, Diffusion Tensor Imaging (DTI) and Cerebrospinal Fluid (CSF) biomarkers. The study was performed following Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) guidelines. According to the literature survey, most studies (n = 76) used the DL strategy. The datasets used by studies were primarily derived from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The majority of studies (n = 73) used single-modality neuroimaging data, while the remaining used multi-modal input data. In a multi-modality approach, the combination of MRI and PET scans is commonly preferred. Also, Regarding the algorithm used, Convolution Neural Network (CNN) showed the highest accuracy, 100 %, in classifying AD vs. CN subjects whereas the SVM was the most common ML algorithm, with a maximum accuracy of 99.82 %. •The review of 100 studies were selected for Classification of AD, CN and MCI with ML and DL Algo.•Studies on Machine Learning, Deep Learning for Neuroimaging (MRI, PET), Apoe4 genetic, and CSF biomarkers for disease detection are compared.•MRI and PET are the most widely used biomarkers. The ADNI database is the most prominent dataset for detecting AD•Study results showed that CNN achieved 100% accuracy for ADD. Other evaluation parameters discussed include Precision, Sensitivity, Specificity, F1 score, and AUC.•This review is valuable for researchers working on AI and medical applications with ML/DL-based AD detection.