Measuring Patient-Perceived Quality of Care in U.S. Hospitals Using Twitter

Abstract

BACKGROUND Patients use Twitter to share feedback about their experience receiving health care. Identifying and analyzing the content of posts sent to each hospital may provide a novel real-time measure of quality, supplementing traditional, survey-based approaches. OBJECTIVE To assess the use of Twitter as a supplemental data stream for measuring patient-perceived quality of care in U.S. hospitals and compare patient sentiments about hospitals on Twitter to established quality measures. DESIGN Tweets directed to U.S. hospitals over a 1-year period were classified as having to do with patient experience using a machine learning approach. Additionally, sentiment was calculated for patient experience tweets using natural language processing. KEY RESULTS Roughly half of the hospitals in the U.S. have a presence on Twitter. Of the tweets directed toward these hospitals, ~9% were related to patient experience. Analyses revealed that specific hospital characteristics were associated with lower sentiment. Finally, hospital sentiment was moderately correlated with a commonly used measure of quality. CONCLUSIONS Tweets describing patient experiences in hospitals cover a wide range of patient care aspects and can be identified using automated approaches. These tweets represent a reliable predictor of treatment quality and may be valuable to patients, researchers, policy makers and hospital administrators.