2025
doi: 10.12720/jait.16.6.854-868
Beyond Classical Approaches: Fine-Tuning Clinical BERT Model on Structured Data for Alzheimer’s Disease Diagnosis
Hager Saleh1,2,3,*
,
Michael McCann4 ,
John G. Breslin1,5 ,
Shaker El-Sappagh6,7
- 1Insight Research Ireland Centre for Data Analytics, University of Galway, Galway H91 TK33, Ireland
- 2Atlantic Technological University, Letterkenny, Ireland
- 3Faculty of Computers and Artificial Intelligence, Hurghada University, Hurghada, Egypt
- 4Department of Computing, Atlantic Technological University, Letterkenny, Ireland
- 5School of Engineering, University of Galway, Galway H91 TK33, Ireland
- 6Faculty of Computer Science and Engineering, Galala University, Suez, Egypt
- 7Faculty of Computers and Artificial Intelligence, Benha University, Banha, Egypt
- Manuscript receivedFebruary 11, 2025
- revisedMarch 11, 2025
- acceptedMarch 27, 2025
- publishedJune 19, 2025
Abstract
Alzheimer’s Disease (AD) is a neurodegenerative disorder requiring early diagnosis for effective intervention. This study presents a comprehensive evaluation of classical machine learning models, fine-tuned BERT-based models, and Large Language Models (LLMs) for AD diagnosis using structured data. The comparative analysis demonstrates that fine-tuned BERT-based models, particularly BioBERT and ClinicalBERT, achieve superior performance, with BioBERT attaining an accuracy of 94.48%, precision of 94.64%, recall of 94.48%, and an F1-score of 94.52% based only on structured numerical data. These models outperform classical approaches such as random forest and AdaBoost, which achieved accura-cies of 91.87% and 91.41%, respectively. In contrast, LLMs, including GPT-4 and LLama 3.2, exhibited suboptimal results, with GPT reaching a maximum accuracy of 53.988% in the zero-shot setting, highlighting their limitations in handling structured clinical data without extensive fine-tuning. The study highlights the importance of domain-specific fine-tuning, as general-purpose LLMs struggle with structured data due to their reliance on prompt engineering. While traditional ML models provide a solid baseline, fine-tuned BERT models offer enhanced diagnostic capabilities by capturing intricate data relationships.
Keywords
- Alzheimer’s disease diagnosis
- Large Language Model (LLM)
- language model
- in-context learning
How to Cite
Hager Saleh, Michael McCann, John G. Breslin, and Shaker El-Sappagh, "Beyond Classical Approaches: Fine-Tuning Clinical BERT Model on Structured Data for Alzheimer’s Disease Diagnosis," Journal of Advances in Information Technology, vol. 16, no. 6, pp. 854-868, 2025. https://doi.org/10.12720/jait.16.6.854-868
Copyright & License
Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
