AI-Based Diagnosis of Alzheimer’s Disease Using Brain MRI: Can Artificial Intelligence Improve Early Detection and Diagnostic Accuracy?

Background/Objectives: Alzheimer’s disease (AD) is a neurological disorder that adversely affects cognition, memory, and overall quality of life. Identifying AD in its initial phase is especially challenging when patients display cognitive impairments. Conventional methods rely on physicians to manually examine patients and analyze images, which is time-consuming and prone to errors. This review examines the use of artificial intelligence (AI) techniques for diagnosing AD using CT scans and MRI brain imaging. Methods: Research papers published from 2018 to 2026 were sourced from Google Scholar, IEEE Xplore, and Semantic Scholar. The techniques that were investigated in this study include Convolutional Neural Networks, 3D Convolutional Neural Networks, transfer learning, Vision Transformers, ensemble models, and multimodal approaches. Five research questions were posed to analyse the practicality of using AI-driven techniques in clinical settings, their novelty, scalability, robustness, and accuracy. Results: This study found that AI models can autonomously extract information from brain images and yield highly accurate results, with numerous researches demonstrating over 90% accuracy. Deep learning applied to MRI imaging is effective, while CT-based techniques can detect brain alterations when MRI is inaccessible. Different data types, including imaging, age, medical history, and vocal characteristics, can provide valuable insights into AD. However, issues remain, such as dataset discrepancies, variations among scanners and individuals, and insufficient testing of complex models on diverse populations. Conclusions: Future efforts should focus on accurate and transparent AI, integration of multiple data types, rapid and secure models, and testing on large datasets from multiple hospitals. AI should be developed to assist physicians in accurately diagnosing AD rather than replacing them.

Authors

Publication Details

Journal
Preprints.org
Published
2026-11-16
DOI
https://doi.org/10.20944/preprints202611.1533.v1
Primary Topic
Dementia and Cognitive Impairment Research
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

AI-Based Diagnosis of Alzheimer’s Disease Using Brain MRI: Can Artificial Intelligence Improve Early Detection and Diagnostic Accuracy?

Arvind Mukundan, Riya Karmakar, Sarthak Jadhav, Sachin Jadhav et al.
2 links
Preprints.org
Dementia and Cognitive Impairment Research
preprint

AI-Based Diagnosis of Alzheimer’s Disease Using Brain MRI: Can Artificial Intelligence Improve Early Detection and Diagnostic Accuracy?

Arvind Mukundan, Riya Karmakar, Sarthak Jadhav, Sachin Jadhav, Shubham Kote, Aditya Malunjkar, Sudhanshu Sarwade, Shardul Gorde
preprint en

Abstract

Background/Objectives: Alzheimer’s disease (AD) is a neurological disorder that adversely affects cognition, memory, and overall quality of life. Identifying AD in its initial phase is especially challenging when patients display cognitive impairments. Conventional methods rely on physicians to manually examine patients and analyze images, which is time-consuming and prone to errors. This review examines the use of artificial intelligence (AI) techniques for diagnosing AD using CT scans and MRI brain imaging. Methods: Research papers published from 2018 to 2026 were sourced from Google Scholar, IEEE Xplore, and Semantic Scholar. The techniques that were investigated in this study include Convolutional Neural Networks, 3D Convolutional Neural Networks, transfer learning, Vision Transformers, ensemble models, and multimodal approaches. Five research questions were posed to analyse the practicality of using AI-driven techniques in clinical settings, their novelty, scalability, robustness, and accuracy. Results: This study found that AI models can autonomously extract information from brain images and yield highly accurate results, with numerous researches demonstrating over 90% accuracy. Deep learning applied to MRI imaging is effective, while CT-based techniques can detect brain alterations when MRI is inaccessible. Different data types, including imaging, age, medical history, and vocal characteristics, can provide valuable insights into AD. However, issues remain, such as dataset discrepancies, variations among scanners and individuals, and insufficient testing of complex models on diverse populations. Conclusions: Future efforts should focus on accurate and transparent AI, integration of multiple data types, rapid and secure models, and testing on large datasets from multiple hospitals. AI should be developed to assist physicians in accurately diagnosing AD rather than replacing them.

Preprints.org
Good health and well-being
Dementia and Cognitive Impairment Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon