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.

Natural Language Processing, Patient Experience, Care Transitions

A. Coulter, et al., Collecting data on patient experience is not enough: they must be used to improve care, BMJ 348 (2014) g2225.

N. England, The Friends and Family Test, NHS England, 2014.

L. Trigg, Patients' opinions of health care providers for supporting choice and quality improvement, J. Health Serv. Res. Policy 16 (2) (2011) 102-107.

C. Cognetta-Rieke, S. Guney, Analytical insights from patient narratives: the next step for better patient experience, J. Patient Exp. 1 (1) (2014) 20-22.

J. Hewitt-Taylor, C.S. Bond, What e-patients want from the doctor-patient relationship: content analysis of posts on discussion boards, J. Med. Internet Res. 14 (6) (2012) e155, https://doi.org/10.2196/jmir.2068.

C. Fullwood, et al., Patients' experiences of shared decision making in primary care practices in the United kingdom, Med. Decis. Making 33 (1) (2013) 26-36.

C. Rathert, N. Huddleston, Y. Pak, Acute care patients discuss the patient role in patient safety, Health Care Manage. Rev. 36 (2) (2011) 134-144.

A.J. Forster, et al., Adverse events among medical patients after discharge from hospital, CMAJ 170 (3) (2004) 345-349.

A.J. Forster, et al., The incidence and severity of adverse events affecting patients after discharge from the hospital, Ann. Intern. Med. 138 (3) (2003) 161, https://doi.org/10.7326/0003-4819-138-3-200302040-00007.

F. Greaves, et al., Use of sentiment analysis for capturing patient experience from free-text comments posted online, J. Med. Internet Res. 15 (11) (2013) e239, https://doi.org/10.2196/jmir.2721.

F. Greaves, et al., Harnessing the cloud of patient experience: using social media to detect poor quality healthcare, BMJ Qual. Saf. 22 (3) (2013) 251-255.

R. Wagland, et al., Development and testing of a text-mining approach to analyse patients' comments on their experiences of colorectal cancer care, BMJ Qual. Saf. 25 (8) (2016) 604-614.

J.B. Hawkins, et al., Measuring patient-perceived quality of care in US hospitals using Twitter, BMJ Qual. Saf. 25 (6) (2016) 404-413.

K. Doing-Harris, et al., Understanding patient satisfaction with received healthcare services: a natural language processing approach, AMIA Annu. Symp. Proc. 2016 (2016) 524-533.

M. Rastegar-Mojarad, et al., Collecting and analyzing patient experiences of health care from social media, JMIR Res. Protoc. 4 (3) (2015) e78, https://doi.org/10.2196/resprot.3433.

M. Carter, et al., Capturing patient experience: a qualitative study of implementing real-time feedback in primary care, Br. J. Gen. Pract. 66 (652) (2016) e786-e793.

M.J. Horstman, et al., Patient experience with discharge instructions in postdischarge recovery: a qualitative study, BMJ Open 7 (2) (2017) e014842, https://doi.org/10.1136/bmjopen-2016-014842.

B. Hanratty, et al., Transitions at the end of life for older adults - patient, carer and professional perspectives: a mixed-methods study, Southampton (UK), 2014.

E.A. Coleman, Falling through the cracks: challenges and opportunities for improving transitional care for persons with continuous complex care needs, J. Am. Geriatr. Soc. 51 (4) (2003) 549-555.