Can Large Language Models Logically Predict Myocardial Infarction? Evaluation based on UK Biobank Cohort

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhi, Yuxing, Guo, Yuan, Yuan, Kai, Wang, Hesong, Xu, Heng, Yao, Haina, Yang, Albert C, Huang, Guangrui, Duan, Yuping
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914954696720384
author Zhi, Yuxing
Guo, Yuan
Yuan, Kai
Wang, Hesong
Xu, Heng
Yao, Haina
Yang, Albert C
Huang, Guangrui
Duan, Yuping
author_facet Zhi, Yuxing
Guo, Yuan
Yuan, Kai
Wang, Hesong
Xu, Heng
Yao, Haina
Yang, Albert C
Huang, Guangrui
Duan, Yuping
contents Background: Large language models (LLMs) have seen extraordinary advances with applications in clinical decision support. However, high-quality evidence is urgently needed on the potential and limitation of LLMs in providing accurate clinical decisions based on real-world medical data. Objective: To evaluate quantitatively whether universal state-of-the-art LLMs (ChatGPT and GPT-4) can predict the incidence risk of myocardial infarction (MI) with logical inference, and to further make comparison between various models to assess the performance of LLMs comprehensively. Methods: In this retrospective cohort study, 482,310 participants recruited from 2006 to 2010 were initially included in UK Biobank database and later on resampled into a final cohort of 690 participants. For each participant, tabular data of the risk factors of MI were transformed into standardized textual descriptions for ChatGPT recognition. Responses were generated by asking ChatGPT to select a score ranging from 0 to 10 representing the risk. Chain of Thought (CoT) questioning was used to evaluate whether LLMs make prediction logically. The predictive performance of ChatGPT was compared with published medical indices, traditional machine learning models and other large language models. Conclusions: Current LLMs are not ready to be applied in clinical medicine fields. Future medical LLMs are suggested to be expert in medical domain knowledge to understand both natural languages and quantified medical data, and further make logical inferences.
format Preprint
id arxiv_https___arxiv_org_abs_2409_14478
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Can Large Language Models Logically Predict Myocardial Infarction? Evaluation based on UK Biobank Cohort
Zhi, Yuxing
Guo, Yuan
Yuan, Kai
Wang, Hesong
Xu, Heng
Yao, Haina
Yang, Albert C
Huang, Guangrui
Duan, Yuping
Artificial Intelligence
Background: Large language models (LLMs) have seen extraordinary advances with applications in clinical decision support. However, high-quality evidence is urgently needed on the potential and limitation of LLMs in providing accurate clinical decisions based on real-world medical data. Objective: To evaluate quantitatively whether universal state-of-the-art LLMs (ChatGPT and GPT-4) can predict the incidence risk of myocardial infarction (MI) with logical inference, and to further make comparison between various models to assess the performance of LLMs comprehensively. Methods: In this retrospective cohort study, 482,310 participants recruited from 2006 to 2010 were initially included in UK Biobank database and later on resampled into a final cohort of 690 participants. For each participant, tabular data of the risk factors of MI were transformed into standardized textual descriptions for ChatGPT recognition. Responses were generated by asking ChatGPT to select a score ranging from 0 to 10 representing the risk. Chain of Thought (CoT) questioning was used to evaluate whether LLMs make prediction logically. The predictive performance of ChatGPT was compared with published medical indices, traditional machine learning models and other large language models. Conclusions: Current LLMs are not ready to be applied in clinical medicine fields. Future medical LLMs are suggested to be expert in medical domain knowledge to understand both natural languages and quantified medical data, and further make logical inferences.
title Can Large Language Models Logically Predict Myocardial Infarction? Evaluation based on UK Biobank Cohort
topic Artificial Intelligence
url https://arxiv.org/abs/2409.14478