Developing Embedded Taxonomy and Mining Patients’ Interests From Web-Based Physician Reviews: Mixed-Methods Approach

Abstract

BackgroundWeb-based physician reviews are invaluable gold mines that merit further investigation. Although many studies have explored the text information of physician reviews, very few have focused on developing a systematic topic taxonomy embedded in physician reviews. The first step toward mining physician reviews is to determine how the natural structure or dimensions is embedded in reviews. Therefore, it is relevant to develop the topic taxonomy rigorously and systematically.ObjectiveThis study aims to develop a hierarchical topic taxonomy to uncover the latent structure of physician reviews and illustrate its application for mining patients’ interests based on the proposed taxonomy and algorithm.MethodsData comprised 122,716 physician reviews, including reviews of 8501 doctors from a leading physician review website in China (haodf.com), collected between 2007 and 2015. Mixed methods, including a literature review, data-driven-based topic discovery, and human annotation were used to develop the physician review topic taxonomy.ResultsThe identified taxonomy included 3 domains or high-level categories and 9 subtopics or low-level categories. The physician-related domain included the categories of medical ethics, medical competence, communication skills, medical advice, and prescriptions. The patient-related domain included the categories of the patient profile, symptoms, diagnosis, and pathogenesis. The system-related domain included the categories of financing and operation process. The F-measure of the proposed classification algorithm reached 0.816 on average. Symptoms (Cohen d=1.58, Δu=0.216, t=229.75, and P<.001) are more often mentioned by patients with acute diseases, whereas communication skills (Cohen d=−0.29, Δu=−0.038, t=−42.01, and P<.001), financing (Cohen d=−0.68, Δu=−0.098, t=−99.26, and P<.001), and diagnosis and pathogenesis (Cohen d=−0.55, Δu=−0.078, t=−80.09, and P<.001) are more often mentioned by patients with chronic diseases. Patients with mild diseases were more interested in medical ethics (Cohen d=0.25, Δu 0.039, t=8.33, and P<.001), operation process (Cohen d=0.57, Δu 0.060, t=18.75, and P<.001), patient profile (Cohen d=1.19, Δu 0.132, t=39.33, and P<.001), and symptoms (Cohen d=1.91, Δu=0.274, t=62.82, and P<.001). Meanwhile, patients with serious diseases were more interested in medical competence (Cohen d=−0.99, Δu=−0.165, t=−32.58, and P<.001), medical advice and prescription (Cohen d=−0.65, Δu=−0.082, t=−21.45, and P<.001), financing (Cohen d=−0.26, Δu=−0.018, t=−8.45, and P<.001), and diagnosis and pathogenesis (Cohen d=−1.55, Δu=−0.229, t=−50.93, and P<.001).ConclusionsThis mixed-methods approach, integrating literature reviews, data-driven topic discovery, and human annotation, is an effective and rigorous way to develop a physician review topic taxonomy. The proposed algorithm based on Labeled-Latent Dirichlet Allocation can achieve impressive classification results for mining patients’ interests. Furthermore, the mining results reveal marked differences in patients’ inter...

What Do Patients Complain About Online: A Systematic Review and Taxonomy Framework Based on Patient Centeredness

“…Although involvement of family and friends is increasingly viewed as an important component of PCC [1,59-61], patients seldom expressed dissatisfaction with it in our research; apparently far less complained about the low participation of themselves. Compared with technical competence, which constituted a fundamental aspect of health care provision [23], interpersonal attributes of professionals were much more likely to be evaluated by patients; the potential implications of this are twofold: first, consistent with the study by Jia Li et al [26], patients’ needs have different hierarchy, which were firstly stated by Maslow [62], and second, patients have uninformed expectation—“patients are not capable or are reluctant to communicate their expectations” [61], which was validated by Rothenfluh and Schulz [63]. Although there were common concerns across different countries’ patients, variation existed in this study as well.…”

“…Practices observed from the adverse event taxonomy proposed by Harrison et al [24], which facilitated the collection and aggregation of data to compare findings, identify priorities, and develop wide-reaching patient safety solutions, demonstrated the momentousness of a unified, agreed framework with standardized concepts and terms. Despite the large volume of work published in this domain (eg, the studies by Reader et al [25] and Li et al [26]), currently available taxonomies for analyzing online complaints made by patients often lack standardized themes, terminology, and underlying unifying theory, creating difficulties in making sense of data that cannot be used to compare against other services, organizations, or countries. An operational and rigorous framework that classifies complaints made by patients, containing standardized concepts with agreed definitions and preferred terminology and establishing the relationships between concepts based on an explicit and nonoverlapping domain ontology, is required [24].…”

The Impact of a Novel Immersive Virtual Reality Technology Associated with Serious Games in Parkinson’s Disease Patients on Upper Limb Rehabilitation: A Mixed Methods Intervention Study

“…Additionally, the Bing Sentiment Dictionary [47] and the SODictionariesV1.11Spa2 [48] were used to analyze the content of the free text and obtain a description of the acceptance or rejection (polarity) [49] of the OR2-LMC treatment. Content analysis has been used previously in the health sciences to study medical and patient narratives [50,51]. Four phases were used progressively for the analysis of acceptance-rejection (polarity).…”

Online Ratings of Urologists: Comprehensive Analysis

“…Similarly, given the variability in rating scales and domains across the PRW, the inclusion of multiple PRWs and systematic comparison is difficult. Novel methods of automated analysis of text reviews have been recently reported and may allow for a more comprehensive study of text-based patient reviews in the future [30,31].…”