Introduction: Evaluation of patient experience among minority groups has been difficult due to lack of representation in traditional health care surveys. This study evaluated the ability of Twitter to monitor patient experiences of racial minority groups in the United States.

Methods: In total, 851,973 patient experience tweets from the United States with geographic location information were collected from an established patient experience dataset from 2013 to 2016. Patient experience tweets discussed any exposure to health care such as care received in a hospital, urgent care, or any other health institution. Tweets about patient experience were compared among racial groups, and trends in sentiment were investigated.

Results: There was a significant correlation between patient experience user counts per state and population estimates from the Census 2016 5-year survey (r²=.99; p<.001). There were significant correlations for Whites, Black, Hispanics/Latinos, Asians/Pacific Islanders and American Indians/Alaska Natives percent distributions in the patient experience dataset with the Census 2016 5-year survey, with correlation coefficients of 0.84, 0.85, 0.98, 0.91 and 0.59, respectively, with all p-values <.001. Compared to Whites, other racial groups had significantly lower patient experience sentiment. Mean sentiment for all racial groups increased from 2013 to 2014, and continued to increase in 2015 and 2016.

Discussion: These findings show the feasibility of using data captured from Twitter to investigate changes in patient experience in the United States between different racial minority groups, highlighting this as a promising approach for capturing experiences beyond traditional surveys administered in hospital settings.