Patients Speak, AI Listens: LLM-based Analysis of Online Reviews Uncovers Key Drivers for Urgent Care Satisfaction

2025-03-26

AI Summary

This study identifies key determinants of emergency care service satisfaction to inform community healthcare optimization. Methodologically, it integrates LLM-driven aspect-based sentiment analysis (using GPT and prompt engineering) on Google Maps reviews of urgent care clinics in the U.S. Northeast and Florida with census-block-group-level socioeconomic variables (e.g., poverty rate, uninsurance rate), enabling geospatial association modeling. Results reveal that interpersonal interaction quality and operational efficiency are the strongest, statistically significant predictors of patient satisfaction—whereas conventional clinical quality metrics (e.g., technical competence) show no significant association. Only population density exhibits a weak positive correlation with ratings; all other socioeconomic covariates lack statistical significance. The work introduces a novel three-tier analytical framework—linking review semantics, service dimensions, and community characteristics—establishing a reproducible, real-world-data-driven paradigm for primary-care service evaluation.

Technology Category

• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Search and Optimization: Evaluation and Analysis
• Constraint Satisfaction and Optimization: Satisfiability

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Investigating the public experience of urgent care facilities is essential for promoting community healthcare development. Traditional survey methods often fall short due to limited scope, time, and spatial coverage. Crowdsourcing through online reviews or social media offers a valuable approach to gaining such insights. With recent advancements in large language models (LLMs), extracting nuanced perceptions from reviews has become feasible. This study collects Google Maps reviews across the DMV and Florida areas and conducts prompt engineering with the GPT model to analyze the aspect-based sentiment of urgent care. We first analyze the geospatial patterns of various aspects, including interpersonal factors, operational efficiency, technical quality, finances, and facilities. Next, we determine Census Block Group(CBG)-level characteristics underpinning differences in public perception, including population density, median income, GINI Index, rent-to-income ratio, household below poverty rate, no insurance rate, and unemployment rate. Our results show that interpersonal factors and operational efficiency emerge as the strongest determinants of patient satisfaction in urgent care, while technical quality, finances, and facilities show no significant independent effects when adjusted for in multivariate models. Among socioeconomic and demographic factors, only population density demonstrates a significant but modest association with patient ratings, while the remaining factors exhibit no significant correlations. Overall, this study highlights the potential of crowdsourcing to uncover the key factors that matter to residents and provide valuable insights for stakeholders to improve public satisfaction with urgent care.

Problem

• Analyzes urgent care satisfaction drivers using LLMs and online reviews
• Examines geospatial and socioeconomic factors affecting patient perceptions
• Identifies interpersonal and operational efficiency as key satisfaction determinants

Innovation

• LLM-based sentiment analysis of online reviews
• Geospatial pattern analysis of healthcare aspects
• Census Block Group-level demographic correlation study