医学
分类
代理(统计)
家庭医学
门诊部
人工智能
内科学
计算机科学
机器学习
作者
Lauren M. Shapiro,Kevin A. Thomas,Sara L. Eppler,Raj Behal,Jeffery Yao,Robin N. Kamal
出处
期刊:Hand
[SAGE Publishing]
日期:2021-01-21
卷期号:17 (6): 1201-1206
被引量:2
标识
DOI:10.1177/1558944720988078
摘要
Background: Actionable feedback from patients after a clinic visit can help inform ways to better deliver patient-centered care. A 2-word assessment may serve as a proxy for lengthy post-visit questionnaires. We tested the use of a 2-word assessment in an outpatient hand clinic. Methods: New patients were asked to provide a 2-word assessment of the following: (1) their physician; (2) their overall experience; and (3) recommendations for improvement and their likelihood to recommend (LTR) after their clinic visit. Sentiment analysis was used to categorize results into positive, neutral, or negative sentiment. Recommendations for improvement were classified into physician issue, system issue, or neither. We evaluated the relationship between LTR status, sentiment, actionable improvement opportunities, and classification (physician issue, system issue, or neither). Recommendations for improvement were classified into themes based on prior literature. Results: Sixty-seven (97.1%) patients noted positive sentiment toward their physician; 67 (97.1%) noted positive sentiment toward their overall experience. About 31% of improvement recommendations were system-based, 5.9% were physician-based, and 62.7% were neither. Patients not LTR were more likely to leave actionable opportunities for improvement than those LTR ( P = .01). Recommendations for improvement were classified into predetermined themes relating to: (1) physician interaction; (2) check-in process; (3) facilities; (4) unnecessary visit; and (5) appointment delays. Conclusion: Patients not likely to recommend provided actionable opportunities for improvement using a simple 2-word assessment. Implementation of a 2-word assessment in a hand clinic can be used to obtain actionable, real-time patient feedback that can inform operational change and improve the patient experience.
科研通智能强力驱动
Strongly Powered by AbleSci AI