Enhancing Visual Inspection Capability of Multi-Modal Large Language Models on Medical Time Series with Supportive Conformalized and Interpretable Small Specialized Models

• URL: http://arxiv.org/abs/2501.16215v1
• Date: Mon, 27 Jan 2025 17:07:20 GMT
• Title: Enhancing Visual Inspection Capability of Multi-Modal Large Language Models on Medical Time Series with Supportive Conformalized and Interpretable Small Specialized Models
• Authors: Huayu Li, Xiwen Chen, Ci Zhang, Stuart F. Quan, William D. S. Killgore, Shu-Fen Wung, Chen X. Chen, Geng Yuan, Jin Lu, Ao Li,
• Abstract summary: Large language models (LLMs) exhibit remarkable capabilities in visual inspection of medical time-series data. Small specialized models (SSMs) excel in targeted tasks but lack the contextual reasoning required for complex clinical decision-making. We propose ConMIL, a decision-support SSM that integrates seamlessly with LLMs.
• Score: 10.465626812447018
• License:
• Abstract: Large language models (LLMs) exhibit remarkable capabilities in visual inspection of medical time-series data, achieving proficiency comparable to human clinicians. However, their broad scope limits domain-specific precision, and proprietary weights hinder fine-tuning for specialized datasets. In contrast, small specialized models (SSMs) excel in targeted tasks but lack the contextual reasoning required for complex clinical decision-making. To address these challenges, we propose ConMIL (Conformalized Multiple Instance Learning), a decision-support SSM that integrates seamlessly with LLMs. By using Multiple Instance Learning (MIL) to identify clinically significant signal segments and conformal prediction for calibrated set-valued outputs, ConMIL enhances LLMs' interpretative capabilities for medical time-series analysis. Experimental results demonstrate that ConMIL significantly improves the performance of state-of-the-art LLMs, such as ChatGPT4.0 and Qwen2-VL-7B. Specifically, \ConMIL{}-supported Qwen2-VL-7B achieves 94.92% and 96.82% precision for confident samples in arrhythmia detection and sleep staging, compared to standalone LLM accuracy of 46.13% and 13.16%. These findings highlight the potential of ConMIL to bridge task-specific precision and broader contextual reasoning, enabling more reliable and interpretable AI-driven clinical decision support.

Related papers

• Limitations of Large Language Models in Clinical Problem-Solving Arising from Inflexible Reasoning [3.3482359447109866]
  Large Language Models (LLMs) have attained human-level accuracy on medical question-answer (QA) benchmarks. Their limitations in navigating open-ended clinical scenarios have recently been shown. We present the medical abstraction and reasoning corpus (M-ARC) We find that LLMs, including current state-of-the-art o1 and Gemini models, perform poorly compared to physicians on M-ARC.
  arXiv  Detail & Related papers  (2025-02-05T18:14:27Z)
• Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval [61.70489848327436]
  KARE is a novel framework that integrates knowledge graph (KG) community-level retrieval with large language models (LLMs) reasoning. Extensive experiments demonstrate that KARE outperforms leading models by up to 10.8-15.0% on MIMIC-III and 12.6-12.7% on MIMIC-IV for mortality and readmission predictions.
  arXiv  Detail & Related papers  (2024-10-06T18:46:28Z)
• CoMMIT: Coordinated Instruction Tuning for Multimodal Large Language Models [68.64605538559312]
  In this paper, we analyze the MLLM instruction tuning from both theoretical and empirical perspectives. Inspired by our findings, we propose a measurement to quantitatively evaluate the learning balance. In addition, we introduce an auxiliary loss regularization method to promote updating of the generation distribution of MLLMs.
  arXiv  Detail & Related papers  (2024-07-29T23:18:55Z)
• XAI4LLM. Let Machine Learning Models and LLMs Collaborate for Enhanced In-Context Learning in Healthcare [16.79952669254101]
  We develop a novel method for zero-shot/few-shot in-context learning (ICL) using a multi-layered structured prompt. We also explore the efficacy of two communication styles between the user and Large Language Models (LLMs) Our study systematically evaluates the diagnostic accuracy and risk factors, including gender bias and false negative rates.
  arXiv  Detail & Related papers  (2024-05-10T06:52:44Z)
• AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator [69.51568871044454]
  We introduce textbfAI Hospital, a framework simulating dynamic medical interactions between emphDoctor as player and NPCs. This setup allows for realistic assessments of LLMs in clinical scenarios. We develop the Multi-View Medical Evaluation benchmark, utilizing high-quality Chinese medical records and NPCs.
  arXiv  Detail & Related papers  (2024-02-15T06:46:48Z)
• Combining Insights From Multiple Large Language Models Improves Diagnostic Accuracy [0.0]
  Large language models (LLMs) are proposed as viable diagnostic support tools or even spoken of as replacements for "curbside consults" We assessed and compared the accuracy of differential diagnoses obtained by asking individual commercial LLMs against the accuracy of differential diagnoses synthesized by aggregating responses from combinations of the same LLMs.
  arXiv  Detail & Related papers  (2024-02-13T21:24:21Z)
• XAI for In-hospital Mortality Prediction via Multimodal ICU Data [57.73357047856416]
  We propose an efficient, explainable AI solution for predicting in-hospital mortality via multimodal ICU data. We employ multimodal learning in our framework, which can receive heterogeneous inputs from clinical data and make decisions. Our framework can be easily transferred to other clinical tasks, which facilitates the discovery of crucial factors in healthcare research.
  arXiv  Detail & Related papers  (2023-12-29T14:28:04Z)
• Surpassing GPT-4 Medical Coding with a Two-Stage Approach [1.7014913888753238]
  GPT-4 LLM predicts an excessive number of ICD codes for medical coding tasks, leading to high recall but low precision. We introduce LLM-codex, a two-stage approach to predict ICD codes that first generates evidence proposals and then employs an LSTM-based verification stage. Our model is the only approach that simultaneously achieves state-of-the-art results in medical coding accuracy, accuracy on rare codes, and sentence-level evidence identification.
  arXiv  Detail & Related papers  (2023-11-22T23:35:13Z)
• Redefining Digital Health Interfaces with Large Language Models [69.02059202720073]
  Large Language Models (LLMs) have emerged as general-purpose models with the ability to process complex information. We show how LLMs can provide a novel interface between clinicians and digital technologies. We develop a new prognostic tool using automated machine learning.
  arXiv  Detail & Related papers  (2023-10-05T14:18:40Z)
• Mixed-Integer Projections for Automated Data Correction of EMRs Improve Predictions of Sepsis among Hospitalized Patients [7.639610349097473]
  We introduce an innovative projections-based method that seamlessly integrates clinical expertise as domain constraints. We measure the distance of corrected data from the constraints defining a healthy range of patient data, resulting in a unique predictive metric we term as "trust-scores" We show an AUROC of 0.865 and a precision of 0.922, that surpasses conventional ML models without such projections.
  arXiv  Detail & Related papers  (2023-08-21T15:14:49Z)
• Self-Verification Improves Few-Shot Clinical Information Extraction [73.6905567014859]
  Large language models (LLMs) have shown the potential to accelerate clinical curation via few-shot in-context learning. They still struggle with issues regarding accuracy and interpretability, especially in mission-critical domains such as health. Here, we explore a general mitigation framework using self-verification, which leverages the LLM to provide provenance for its own extraction and check its own outputs.
  arXiv  Detail & Related papers  (2023-05-30T22:05:11Z)

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.