Background: Patient experience is a cornerstone of quality healthcare, yet continuity of care, particularly during transitions, remains a significant challenge. Traditional feedback mechanisms often lack the depth to capture nuanced patient perspectives on these critical junctures. Natural Language Processing (NLP) offers a scalable solution to analyze vast quantities of unstructured free-text feedback, providing rich insights into patient journeys.
Objective: This study aimed to leverage NLP and machine learning to analyze free-text patient feedback from diverse healthcare settings to identify key themes, sentiments, and specific pain points related to patient experience continuity during care transitions.
Methods: Over 69,000 free-text patient responses collected from various NHS settings (outpatient, inpatient, A&E, and maternity) were analyzed using NLP techniques, including sentiment analysis and trigram analysis. A Support Vector Machine (SVM) model was employed for theme classification, with its performance compared against five other machine learning models.
Results: The SVM model demonstrated superior classification accuracy, achieving 74.5% for outpatient feedback, 72.2% for inpatient, 71.5% for A&E, and 62.7% for maternity feedback. Sentiment analysis revealed that negative feedback predominantly centered on critical transition points, specifically discharge processes, information continuity, and follow-up care. Frequent negative trigrams identified across settings included “seeing different doctor,” “improve discharge process,” and “information aftercare lacking,” underscoring systemic issues in care handovers and communication.
Conclusion: This study demonstrates the viability and efficacy of using NLP and machine learning to process large-scale patient feedback, efficiently uncovering specific areas of dissatisfaction related to care transitions. The insights gained provide actionable intelligence for healthcare providers to design targeted quality improvement interventions, fostering enhanced communication, discharge planning, and inter-departmental coordination to improve patient experience continuity and advance patient-centered care.