Chain-of-Thought Reasoning with Large Language Models for Clinical Alzheimer's Disease Assessment and Diagnosis

• URL: http://arxiv.org/abs/2602.13979v1
• Date: Sun, 15 Feb 2026 03:56:24 GMT
• Title: Chain-of-Thought Reasoning with Large Language Models for Clinical Alzheimer's Disease Assessment and Diagnosis
• Authors: Tongze Zhang, Jun-En Ding, Melik Ozolcer, Fang-Ming Hung, Albert Chih-Chieh Yang, Feng Liu, Yi-Rou Ji, Sang Won Bae,
• Abstract summary: Alzheimer's disease (AD) has become a prevalent neurodegenerative disease worldwide.<n>Large language models (LLMs) have been increasingly applied to the medical field using electronic health records.<n>We propose leveraging LLMs to perform Chain-of-Thought (CoT) reasoning on patients' clinical EHRs.
• Score: 5.934813916147763
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Alzheimer's disease (AD) has become a prevalent neurodegenerative disease worldwide. Traditional diagnosis still relies heavily on medical imaging and clinical assessment by physicians, which is often time-consuming and resource-intensive in terms of both human expertise and healthcare resources. In recent years, large language models (LLMs) have been increasingly applied to the medical field using electronic health records (EHRs), yet their application in Alzheimer's disease assessment remains limited, particularly given that AD involves complex multifactorial etiologies that are difficult to observe directly through imaging modalities. In this work, we propose leveraging LLMs to perform Chain-of-Thought (CoT) reasoning on patients' clinical EHRs. Unlike direct fine-tuning of LLMs on EHR data for AD classification, our approach utilizes LLM-generated CoT reasoning paths to provide the model with explicit diagnostic rationale for AD assessment, followed by structured CoT-based predictions. This pipeline not only enhances the model's ability to diagnose intrinsically complex factors but also improves the interpretability of the prediction process across different stages of AD progression. Experimental results demonstrate that the proposed CoT-based diagnostic framework significantly enhances stability and diagnostic performance across multiple CDR grading tasks, achieving up to a 15% improvement in F1 score compared to the zero-shot baseline method.

Related papers

• ClinDEF: A Dynamic Evaluation Framework for Large Language Models in Clinical Reasoning [58.01333341218153]
  We propose ClinDEF, a dynamic framework for assessing clinical reasoning in LLMs through simulated diagnostic dialogues.<n>Our method generates patient cases and facilitates multi-turn interactions between an LLM-based doctor and an automated patient agent.<n>Experiments show that ClinDEF effectively exposes critical clinical reasoning gaps in state-of-the-art LLMs.
  arXiv  Detail & Related papers  (2025-12-29T12:58:58Z)
• Integrating Genomics into Multimodal EHR Foundation Models [56.31910745104141]
  This paper introduces an innovative EHR foundation model that integrates Polygenic Risk Scores (PRS) as a foundational data modality.<n>The framework aims to learn complex relationships between clinical data and genetic predispositions.<n>This approach is pivotal for unlocking new insights into disease prediction, proactive health management, risk stratification, and personalized treatment strategies.
  arXiv  Detail & Related papers  (2025-10-24T15:56:40Z)
• Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models [51.91760712805404]
  We introduce VivaBench, a benchmark for evaluating sequential clinical reasoning in large language models (LLMs)<n>Our dataset consists of 1762 physician-curated clinical vignettes structured as interactive scenarios that simulate a (oral) examination in medical training.<n>Our analysis identified several failure modes that mirror common cognitive errors in clinical practice.
  arXiv  Detail & Related papers  (2025-10-11T16:24:35Z)
• A Disease-Centric Vision-Language Foundation Model for Precision Oncology in Kidney Cancer [54.58205672910646]
  RenalCLIP is a visual-language foundation model for characterization, diagnosis and prognosis of renal mass.<n>It achieved better performance and superior generalizability across 10 core tasks spanning the full clinical workflow of kidney cancer.
  arXiv  Detail & Related papers  (2025-08-22T17:48:19Z)
• End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning [52.12425911708585]
  Deep-DxSearch is an agentic RAG system trained end-to-end with reinforcement learning (RL)<n>In Deep-DxSearch, we first construct a large-scale medical retrieval corpus comprising patient records and reliable medical knowledge sources.<n> Experiments demonstrate that our end-to-end RL training framework consistently outperforms prompt-engineering and training-free RAG approaches.
  arXiv  Detail & Related papers  (2025-08-21T17:42:47Z)
• A Novel Multimodal Framework for Early Detection of Alzheimers Disease Using Deep Learning [0.0]
  Alzheimers Disease (AD) is a progressive neurodegenerative disorder that poses significant challenges in its early diagnosis.<n>Traditional diagnostic methods fall short of capturing the multifaceted nature of the disease.<n>We propose a novel framework for the early detection of AD that integrates data from three primary sources: MRI imaging, cognitive assessments, and biomarkers.
  arXiv  Detail & Related papers  (2025-08-05T03:46:59Z)
• Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications [59.721265428780946]
  Large Language Models (LLMs) in medicine have enabled impressive capabilities, yet a critical gap remains in their ability to perform systematic, transparent, and verifiable reasoning.<n>This paper provides the first systematic review of this emerging field.<n>We propose a taxonomy of reasoning enhancement techniques, categorized into training-time strategies and test-time mechanisms.
  arXiv  Detail & Related papers  (2025-08-01T14:41:31Z)
• Cross-modal Causal Intervention for Alzheimer's Disease Prediction [13.584994367762398]
  We propose a visual-language causality-inspired framework named Cross-modal Causal Intervention with Mediator for Alzheimer's Disease Diagnosis (MediAD)<n>Our framework implicitly mitigates the effect of both observable and unobservable confounders through a unified causal intervention method.
  arXiv  Detail & Related papers  (2025-07-18T14:21:24Z)
• Right Prediction, Wrong Reasoning: Uncovering LLM Misalignment in RA Disease Diagnosis [16.057157876625794]
  Large language models (LLMs) offer a promising pre-screening tool, improving early disease detection and providing enhanced healthcare access for underprivileged communities.<n>With impressive accuracy in prediction across a range of diseases, LLMs have the potential to revolutionize clinical pre-screening and decision-making for various medical conditions.
  arXiv  Detail & Related papers  (2025-04-09T05:04:01Z)
• Improving Interactive Diagnostic Ability of a Large Language Model Agent Through Clinical Experience Learning [17.647875658030006]
  This study investigates the underlying mechanisms behind the performance degradation phenomenon.<n>We developed a plug-and-play method enhanced (PPME) LLM agent, leveraging over 3.5 million electronic medical records from Chinese and American healthcare facilities.<n>Our approach integrates specialized models for initial disease diagnosis and inquiry into the history of the present illness, trained through supervised and reinforcement learning techniques.
  arXiv  Detail & Related papers  (2025-02-24T06:24:20Z)
• MINDSETS: Multi-omics Integration with Neuroimaging for Dementia Subtyping and Effective Temporal Study [0.7751705157998379]
  Alzheimer's disease (AD) and vascular dementia (VaD) are the two most prevalent dementia types. This paper presents an innovative multi-omics approach to accurately differentiate AD from VaD, achieving a diagnostic accuracy of 89.25%.
  arXiv  Detail & Related papers  (2024-11-06T10:13:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.