Exploring patient perceptions of healthcare service quality through analysis of unstructured feedback

Mechanisms for collecting unstructured feedback (i.e., text comments) from patients of healthcare providers have become commonplace, but analysis techniques to examine such feedback have not been frequently applied in this domain. To fill this gap, we apply a text mining methodology to a large set of textual feedback of physicians by their patients and relate the textual commentary to their numeric ratings. While perceptions of healthcare service quality in the form of numeric ratings are easy to aggregate, freeform textual commentary presents more challenges to extracting useful information. Our methodology explores aggregation of the textual commentary using a topic analysis procedure (i.e., latent Dirichlet allocation) and a sentiment tool (i.e., Diction). We then explore how the extracted topic areas and expressed sentiments relate to the physicians' quantitative ratings of service quality from both patients and other physicians. We analyze 23,537 numeric ratings plus textual feedback provided by patients of 3,712 physicians who have also been recommended by other physicians, and determine process quality satisfaction is an important driver of patient perceived quality, whereas clinical quality better reflects physician perceived quality. Our findings lead us to suggest that to maximize the usefulness of online reviews of physicians, potential patients should parse them for particular quality elements they wish to assess and interpret them within the scope of those quality elements. (C) 2016 Elsevier Ltd. All rights reserved.