JMIR Publications

ABSTRACT

Background:

Kidney stones, a prevalent urinary disease, pose significant health risks. Factors like insufficient water intake or a high-protein diet increase an individual’s susceptibility to the disease. Social media platforms can be a valuable avenue for users to share their experiences in managing these risk factors. Analyzing such patient-reported information can provide crucial insights into risk factors, potentially leading to improved quality of life for other patients.

Objective:

This study aims to develop an intelligent model (KSrisk-GPT) based on a large language model (LLM) to identify potential kidney stone risk factors from user experiences shared online. Additionally, this work aims to investigate the potential applications of LLMs in public health.

Methods:

This study collected data under the topic of kidney stones on Zhihu in the past five years and obtained 11,819 user comments. Experts organized the most common risk factors for kidney stones into 6 types. Then, we use the Least-to-Most (LtM) prompting in the Chain-of-Thought (CoT) prompting to enable GPT-4.0 to think like an expert, and ask the GPT to identify risk factors from the comments. Metrics including accuracy, precision, recall and F-score were used to evaluate the performance of such a model.

Results:

Our proposed method outperforms other models in identifying comments containing risk factors with 95.9% of accuracy and F-score, with the precision of 95.6% and the recall of 96.2%. Out of the 863 comments identified with risk factors, our analysis showed the most mentioned risk factors for kidney stones in Zhihu user discussions mainly include dietary habits (high protein, high calcium intake), insufficient water intake, genetic factors and lifestyle. In addition, new potential risk factors were discovered with GPT, such as excessive use of supplements like vitamin C and calcium, laxatives and hyperparathyroidism.

Conclusions:

Comments from social media users offer a novel perspective and as a new data source for disease prevention and understanding patient journeys. Our method not only shed light on using LLMs to efficiently summarizes risk factors from extensive social media data, but also LLMs’ potential of reducing risk factors of health conditions and disease prevention.