Social isolation is an important social determinant that impacts health outcomes and mortality among patients. The National Academy of Medicine recently recommended to document social isolation in electronic health records(EHR). However, social isolation usually is not recorded as coded data but rather collected from patient self-report or documented in clinical narratives. This study explores natural language processing (NLP) strategy for identifying socially isolated patients from clinical narratives. We used data from the Medical University of South Carolina (MUSC) Research Data Warehouse. Patients 18 years-of-age or older who were diagnosed with prostate cancer between January 1, 2014 and May 31, 2017 were eligible. Of 4,195 eligible prostate cancer patients, we randomly sampled 3,138 patients (75%) as a training dataset. The remaining 1,057 patients (25%) were used as a test dataset to evaluate NLP algorithm performance. A total of 55,516 clinical notes from 3,138 patients were included to develop the lexicon and NLP pipelines for social isolation. Of those, 35 unique patients (1.2%) had social isolation mention(s) in 217 notes. Among 24 terms relevant to social isolation, the most prevalent were “lack of social support,” “lonely,” “social isolation,” “no friends,” and “loneliness”. Among 1,057 patients in the test dataset, 17 patients (1.6%) were identified as having social isolation mention(s) in 40 clinical notes. Domain expert Manual review identified 4 false positive mentions of social isolation and 1 false negatives in 154 notes from randomly selected 52 controls. The NLP pipeline demonstrated 90% precision, 97% recall, and 93% F-measure.
Vivienne Zhu, MD, MS is an assistant professor in the Biomedical Informatics Center (BMIC) at the Medical University of South Carolina (MUSC). Dr. Zhu’s major research area is improving quality of care and health outcomes for patients with chronic conditions using health information technology (HIT). Her expertise incldue computerized clinical decision support (CDSS), electrinic health record (EHR), natural languge processing (NLP) for clincal appliaitons, and predictive analytics. At MUSC, using NLP technology, Dr. Zhu led effort of measuring compliance rate of the Joint Commission standards for critical results reporting and communication and the CMS quality of care reporting. Dr. Zhu is the pricinple investigator and co-investigator for serveral NIH funded studies. She leads an NLP project of identifying and extracting social determinates from clinical notes for prostaet cancer patients. Dr.Zhu has published a nubmer of peer-reviewed scientific papers on medical informatics, patient safety, and health outcomes research