Productivity Innovation in the Context of Digital Transformation – A Study of ChatGPT in Outpatient Satisfaction Follow-up

Abstract

The aim of this study was to explore the construction of hospital outpatient satisfaction scale and evaluation model, and to optimize outpatient satisfaction performance assessment indices. A satisfaction survey was conducted on 3988 outpatients in July-August 2024 using the ChatGPT artificial intelligence recall system with a structured human-computer interaction mechanism. On the basis of single-factor analysis, a binary unconditional logistic regression model was constructed to further screen the influencing factors and analyze the priority improvement areas through the importance matrix. The scale used in the survey was pre-validated by reliability and validity tests, and all statistical analyses were uniformly performed using SPSS 21.0 software. Satisfaction scores were high, with high scores for information technology convenience experience, consultation environment experience, and overall feeling experience, and low scores for service experience. Satisfaction influencing factors were gender, age, and department of consultation. Priority needs to be given to improving history inquiry and communication services, examination report interpretation services, and treatment plan and medication discussion services; and secondary improvements in privacy services, and respectful or comforting services. The outpatient satisfaction scale designed in this study has practical value, and the application of ChatGPT-based intelligent information follow-up system reduces the cost of follow-up, improves the efficiency of follow-up, and enhances the overall service level.