What's the difference between patients' evaluation in different periods of COVID-19 pandemic and different types of hospitals? A Research on Hospital Comments Based on ChatGPT Technology and "Dianping" Website (Preprint)

Abstract

In the era of the Internet, individuals have increasingly accustomed themselves to gathering necessary information and expressing their opinions on public online platforms. The healthcare sector is no exception, as these evaluations to a certain extent influence people's healthcare decisions. In China, the widespread outbreak of COVID-19 has had an impact on the strained doctor-patient relationships and patients' healthcare-seeking behaviors. This, in turn, raises the question of how patient evaluations of hospitals have undergone transformations as a result.

To investigate the variances in patient evaluations received by hospitals during different periods and across different types of healthcare facilities amidst the COVID-19 pandemic. Utilizing ChatGPT technology, negative comments pertaining to hospitals were analyzed, and potential actionable measures were identified to enhance patient satisfaction. This study aims to provide insights for hospital administrators when dealing with unforeseen public health crises.

A Java-based program was developed to gather patient evaluations from Dianping, a popular consumer review website. Evaluations were collected from the top 50 comprehensive hospitals nationwide, as well as nominated specialized hospitals in pediatric care, tumor, and obstetrics and gynecology. Statistical analysis of the rating scores was conducted using SPSS. Furthermore, ChatGPT was utilized to categorize the content of the evaluations.

A total of 30,317 valid evaluation records were collected, including 7,696 negative evaluations. Analysis of these data revealed a significant impact of the pandemic on hospital evaluation scores. Overall, there was a significant increase in average evaluation scores during the outbreak (P＜.001). Furthermore, there were notable differences in the composition of negative comments among different types of hospitals (P＜.001). Children’s hospitals received sensitive feedback regarding waiting times and treatment effectiveness, while patients at maternity hospitals showed a greater concern for the attitude of healthcare providers. Patients at tumor hospitals expressed a desire for timely examinations and treatments, especially during the pandemic period.

The COVID-19 pandemic has a significant impact on patient evaluation scores. There are variations in the scores and content of evaluations among different types of specialized hospitals. Utilizing ChatGPT to analyze patient evaluation content represents an innovative approach for statistically assessing factors contributing to patient dissatisfaction. The findings of this study could provide valuable insights for hospital administrators to foster more harmonious physician-patient relationships and enhance hospital performance during public health emergencies.