The Power of Combining Data and Knowledge: GPT-4o is an Effective Interpreter of Machine Learning Models in Predicting Lymph Node Metastasis of Lung Cancer

TL;DR

This study introduces a novel ensemble approach combining GPT-4o's medical knowledge with machine learning models to improve the accuracy of predicting lymph node metastasis in lung cancer patients.

Contribution

The paper presents a new method that integrates large language models with machine learning to enhance clinical prediction accuracy, demonstrating improved performance in LNM prediction.

Findings

Achieved an AUC of 0.778 and AP of 0.426, outperforming baseline models.

GPT-4o effectively leverages medical knowledge and model probabilities for better predictions.

The ensemble method significantly improves clinical risk prediction performance.

Abstract

Lymph node metastasis (LNM) is a crucial factor in determining the initial treatment for patients with lung cancer, yet accurate preoperative diagnosis of LNM remains challenging. Recently, large language models (LLMs) have garnered significant attention due to their remarkable text generation capabilities. Leveraging the extensive medical knowledge learned from vast corpora, LLMs can estimate probabilities for clinical problems, though their performance has historically been inferior to data-driven machine learning models. In this paper, we propose a novel ensemble method that combines the medical knowledge acquired by LLMs with the latent patterns identified by machine learning models to enhance LNM prediction performance. Initially, we developed machine learning models using patient data. We then designed a prompt template to integrate the patient data with the predicted probability from the machine learning model. Subsequently, we instructed GPT-4o, the most advanced LLM developed by OpenAI, to estimate the likelihood of LNM based on patient data and then adjust the estimate using the machine learning output. Finally, we collected three outputs from the GPT-4o using the same prompt and ensembled these results as the final prediction. Using the proposed method, our models achieved an AUC value of 0.778 and an AP value of 0.426 for LNM prediction, significantly improving predictive performance compared to baseline machine learning models. The experimental results indicate that GPT-4o can effectively leverage its medical knowledge and the probabilities predicted by machine learning models to achieve more accurate LNM predictions. These findings demonstrate that LLMs can perform well in clinical risk prediction tasks, offering a new paradigm for integrating medical knowledge and patient data in clinical predictions.