Applying natural language processing and machine learning techniques to patient experience feedback: a systematic review

Abstract

ObjectivesUnstructured free-text patient feedback contains rich information, and analysing these data manually would require a lot of personnel resources which are not available in most healthcare organisations.To undertake a systematic review of the literature on the use of natural language processing (NLP) and machine learning (ML) to process and analyse free-text patient experience data.MethodsDatabases were systematically searched to identify articles published between January 2000 and December 2019 examining NLP to analyse free-text patient feedback. Due to the heterogeneous nature of the studies, a narrative synthesis was deemed most appropriate. Data related to the study purpose, corpus, methodology, performance metrics and indicators of quality were recorded.ResultsNineteen articles were included. The majority (80%) of studies applied language analysis techniques on patient feedback from social media sites (unsolicited) followed by structured surveys (solicited). Supervised learning was frequently used (n=9), followed by unsupervised (n=6) and semisupervised (n=3). Comments extracted from social media were analysed using an unsupervised approach, and free-text comments held within structured surveys were analysed using a supervised approach. Reported performance metrics included the precision, recall and F-measure, with support vector machine and Naïve Bayes being the best performing ML classifiers.ConclusionNLP and ML have emerged as an important tool for processing unstructured free text. Both supervised and unsupervised approaches have their role depending on the data source. With the advancement of data analysis tools, these techniques may be useful to healthcare organisations to generate insight from the volumes of unstructured free-text data.

Assessing Patient-Perceived Hospital Service Quality and Sentiment in Malaysian Public Hospitals Using Machine Learning and Facebook Reviews

“…A comprehensive study of sentiment analysis in a social media platform for health care confirmed the contradictory findings of prevalent views [ 29 ]. Furthermore, additional systematic studies indicate that the polarity of sentiments was affected by the corpus- and thesaurus-based techniques employed in the research [ 28 , 31 ].…”

“…For example, evaluating the relationship between quality dimensions derived from social media reviews and patient satisfaction as measured by prior studies [ 35 , 70 ]. In addition, a comparison of the labeled dataset used in this study to other dictionaries or tools used in prior studies to enhance sentiment and text classification would be beneficial [ 28 , 29 ]. Further, future research may include other social media platforms (e.g., Twitter, Instagram, Tik-Tok, etc.)…”

“…According to the research, conventional patient satisfaction surveys have a variety of disadvantages, and social media has been suggested as a possible alternative for assessing real-time patient satisfaction and mood. Additionally, a systematic review of the use of natural language processing (NLP) and machine learning (ML) to process and analyze patient experience data concluded that manual classification of free text comments remains the ‘gold standard’ method for analysis and is currently the only way to ensure that all pertinent patient comments are coded and analyzed [ 28 ]. Moreover, the study indicates that the patient inputs generated from free-text supplementing structured questionnaires are stable in nature, making them an attractive source of data for supervised learning.…”

“…Nonetheless, social media data are often massive in quantity, posing challenges such as data cleaning, data processing, and the creation of a well-established empirical model of social media content quality [ 28 ]. While this may be accomplished manually via human input, its validity and reliability are widely disputed.…”

Input of Patients for New Diabetes Technology Products

“…NLP often uses machine learning to make sense out of social media comments. 2 One problem with using reviews on social media for making decisions is that sometimes reviews are fake, and reviews on social media websites, while widely accepted by consumers, are not automatically legitimate. 3…”