JMIR Publications

ABSTRACT

Background:

Accurately measure the healthcare needs of patients with different diseases remains a challenge for global healthcare management. The need for new methods to be able to assess the healthcare resources required by patients with different diseases is crucial in order to avoid wasting healthcare resources.

Objective:

This study aimed to assessing dissatisfaction from the perspective of patients with different diseases that can help to optimize the allocation of healthcare resources and better achieve several of the Sustainable Development Goals (SDGs), including SDG 3 (good health and well-being) and SDG 10 (reduced inequality).

Methods:

We used ChatGPT to perform sentiment analysis of patient reviews based on the Aspect-based Sentiment Analysis (ABSA) prompts in the following three aspects: patient experience, physician skills and efficiency, infrastructure and administration. Additionally, we used the International Classification of Diseases-11th revision (ICD-11) API to classify the sentiment analysis results into different disease categories.

Results:

The results show that our method has a weighted total precision, F1 score, and recall of 0.907, 0.793, and 0.748. The accuracy of the three sampling methods was 90.1%, 88.5%, and 89.4%. Using our approach, we can identify that the dissatisfaction is highest for sex-related diseases and lowest for circulatory diseases and that the needs for better infrastructure and administration is much higher for blood-related diseases than for other diseases in China.

Conclusions:

The results prove that our method can accomplish this task excellently, while our proposed approach can provide insights on applying latest Large Language Model (LLM) technologies for improving healthcare and demonstrate their potential applications for optimizing resources.