Harvesting the wisdom of the crowd: using online ratings to explore care experiences in regions

The Credibility of Physician Rating Websites: A Systematic Literature Review

OBJECTIVES

Increasingly, the credibility of online reviews is drawing critical attention due to the lack of control mechanisms, the constant debate about fake reviews and, last but not least, current developments in the field of artificial intelligence. For this reason, the aim of this study was to examine the extent to which assessments recorded on physician rating websites (PRWs) are credible, based on a comparison to other evaluation criteria.

METHODS

Referring to the PRISMA guidelines, a comprehensive literature search was conducted across different scientific databases. Data were synthesized by comparing individual statistical outcomes, objectives and conclusions.

RESULTS

The chosen search strategy led to a database of 36,755 studies of which 28 were ultimately included in the systematic review. The literature review yielded mixed results regarding the credibility of PRWs. While seven publications supported the credibility of PRWs, six publications found no correlation between PRWs and alternative datasets. 15 studies reported mixed results.

CONCLUSIONS

This study has shown that ratings on PRWs seem to be credible when relying primarily on patients' perception. However, these portals seem inadequate to represent alternative comparative values such as the medical quality of physicians. For health policy makers our results show that decisions based on patients' perceptions may be well supported by data from PRWs. For all other decisions, however, PRWs do not seem to contain sufficiently useful data.

A data-driven population health management approach: The Extramural LUMC Academic Network data infrastructure

Improving population health and reducing inequalities through better integrated health and social care services is high up on the agenda of policymakers internationally. In recent years, regional cross-domain partnerships have emerged in several countries, which aim to achieve better population health, quality of care and a reduction in the per capita costs. These cross-domain partnerships aim to have a strong data foundation and are committed to continuous learning in which data plays an essential role. This paper describes our approach towards the development of the regional integrative population-based data infrastructure Extramural LUMC (Leiden University Medical Center) Academic Network (ELAN), in which we linked routinely collected medical, social and public health data at the patient level from the greater The Hague and Leiden area. Furthermore, we discuss the methodological issues of routine care data and the lessons learned about privacy, legislation and reciprocities. The initiative presented in this paper is relevant for international researchers and policy-makers because a unique data infrastructure has been set up that contains data across different domains, providing insights into societal issues and scientific questions that are important for data driven population health management approaches.

Measuring Regional Quality of Health Care Using Unsolicited Online Data: Text Analysis Study

Background

Regional population management (PM) health initiatives require insight into experienced quality of care at the regional level. Unsolicited online provider ratings have shown potential for this use. This study explored the addition of comments accompanying unsolicited online ratings to regional analyses.

Objective

The goal was to create additional insight for each PM initiative as well as overall comparisons between these initiatives by attempting to determine the reasoning and rationale behind a rating.

Methods

The Dutch Zorgkaart database provided the unsolicited ratings from 2008 to 2017 for the analyses. All ratings included both quantitative ratings as well as qualitative text comments. Nine PM regions were used to aggregate ratings geographically. Sentiment analyses were performed by categorizing ratings into negative, neutral, and positive ratings. Per category, as well as per PM initiative, word frequencies (ie, unigrams and bigrams) were explored. Machine learning—naïve Bayes and random forest models—was applied to identify the most important predictors for rating overall sentiment and for identifying PM initiatives.

Results

A total of 449,263 unsolicited ratings were available in the Zorgkaart database: 303,930 positive ratings, 97,739 neutral ratings, and 47,592 negative ratings. Bigrams illustrated that feeling like not being “taken seriously” was the dominant bigram in negative ratings, while bigrams in positive ratings were mostly related to listening, explaining, and perceived knowledge. Comparing bigrams between PM initiatives showed a lot of overlap but several differences were identified. Machine learning was able to predict sentiments of comments but was unable to distinguish between specific PM initiatives.

Conclusions

Adding information from text comments that accompany online ratings to regional evaluations provides insight for PM initiatives into the underlying reasons for ratings. Text comments provide useful overarching information for health care policy makers but due to a lot of overlap, they add little region-specific information. Specific outliers for some PM initiatives are insightful.

What Do Patients Say About Doctors Online? A Systematic Review of Studies on Patient Online Reviews

Background

The number of patient online reviews (PORs) has grown significantly, and PORs have played an increasingly important role in patients’ choice of health care providers.

Objective

The objective of our study was to systematically review studies on PORs, summarize the major findings and study characteristics, identify literature gaps, and make recommendations for future research.

Methods

A major database search was completed in January 2019. Studies were included if they (1) focused on PORs of physicians and hospitals, (2) reported qualitative or quantitative results from analysis of PORs, and (3) peer-reviewed empirical studies. Study characteristics and major findings were synthesized using predesigned tables.

Results

A total of 63 studies (69 articles) that met the above criteria were included in the review. Most studies (n=48) were conducted in the United States, including Puerto Rico, and the remaining were from Europe, Australia, and China. Earlier studies (published before 2010) used content analysis with small sample sizes; more recent studies retrieved and analyzed larger datasets using machine learning technologies. The number of PORs ranged from fewer than 200 to over 700,000. About 90% of the studies were focused on clinicians, typically specialists such as surgeons; 27% covered health care organizations, typically hospitals; and some studied both. A majority of PORs were positive and patients’ comments on their providers were favorable. Although most studies were descriptive, some compared PORs with traditional surveys of patient experience and found a high degree of correlation and some compared PORs with clinical outcomes but found a low level of correlation.

Conclusions

PORs contain valuable information that can generate insights into quality of care and patient-provider relationship, but it has not been systematically used for studies of health care quality. With the advancement of machine learning and data analysis tools, we anticipate more research on PORs based on testable hypotheses and rigorous analytic methods.

Trial Registration

International Prospective Register of Systematic Reviews (PROSPERO) CRD42018085057; https://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=85057 (Archived by WebCite at http://www.webcitation.org/76ddvTZ1C)