A Multiagent Summarization and Auto-Evaluation Framework for Medical Text: Development and Evaluation Study
Bibliographic record
Abstract
Background: Although large language models (LLMs) show great promise in processing medical text, they are prone to generating incorrect information, commonly referred to as hallucinations. These inaccuracies present a significant risk for clinical applications where precision is critical. Additionally, relying on human experts to review LLM-generated content to ensure accuracy is costly and time-consuming, which sets a barrier against large-scale deployment of LLMs in health care settings. Objective: The primary objective of this study was to develop an automatic artificial intelligence (AI) system capable of extracting structured information from unstructured medical data and using advanced reasoning techniques to support reliable clinical decision making. A key aspect of this objective is ensuring that the system incorporates self-verification mechanisms, enabling it to assess the accuracy and reliability of its own outputs. By integrating such mechanisms, we aim to enhance the system's robustness, reduce reliance on human intervention, and improve the overall trustworthiness of AI-driven medical summarization and evaluation. Methods: The proposed framework comprises 2 layers: a summarization layer and an evaluation layer. The summarization layer uses Llama2-70B (Meta AI) and Mistral-7B (Mistral AI) models to generate concise summaries from unstructured medical data, focusing on tasks such as consumer health question summarization, biomedical answer summarization, and dialog summarization. The evaluation layer uses GPT-4-turbo (OpenAI) as a judge, leveraging pairwise comparison strategies and different prompt strategies to evaluate summaries across 4 dimensions: coherence, consistency, fluency, and relevance. To validate the framework, we compare the judgments generated by the LLM assistants in the evaluation layer with those provided by medical experts, offering valuable insights into the alignment and reliability of AI-driven evaluations within the medical domain. We also explore a way to handle disagreement among human experts and discuss our methodology in addressing diversity in human perspectives. Results: The study found variability in expert consensus, with average agreement rates of 19.2% among all experts and 54% among groups of 3 experts. GPT-4 (OpenAI) demonstrated alignment with expert judgments, achieving an average agreement rate of 83.06% with at least 1 expert and comparable performance in cross-validation tests. The enhanced guidance in prompt design (prompt-enhanced guidance) improved GPT-4's alignment with expert evaluations compared with a baseline prompt, highlighting the importance of effective prompt engineering in auto-evaluation of summarization tasks. We also evaluated open-source LLMs, including Llama-3.3 (Meta AI) and Mixtral-Large (Mistral AI), and a domain-specific LLM, OpenBioLLM (Aaditya Ura), for comparison as LLM judges. Conclusions: This study highlights the potential of LLMs as reliable tools for unstructured medical data summarization and evaluation to reduce the dependency on human experts and also states the limitations. The proposed framework, multiagent summarization and auto-evaluation, demonstrates scalability and adaptability for clinical applications while addressing key challenges like hallucination and position bias.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".