Natural language processing of clinical mental health notes may add predictive value to existing suicide risk models

• Published in: Psychological medicine 2021-06, Vol.51 (8), p.1382-1391
• Main Authors: Levis, Maxwell, Leonard Westgate, Christine, Gui, Jiang, Watts, Bradley V., Shiner, Brian
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Cognition; Computerized medical records; Death & dying; Diagnosis; Electronic Health Records; Electronic medical records; Humans; Language; Learning algorithms; Linguistics; Machine Learning; Medical diagnosis; Medical records; Mental Health; Military hospitals; Natural Language Processing; Nearest-neighbor; Original Articles; Patients; Post traumatic stress disorder; Prediction models; Psychotherapy; Sentiment analysis; Suicide; Suicide Prevention; Suicides & suicide attempts; Therapists; Variables; Veterans
• ISSN: 0033-2917; 1469-8978; 1469-8978
• DOI: 10.1017/S0033291720000173

This study evaluated whether natural language processing (NLP) of psychotherapy note text provides additional accuracy over and above currently used suicide prediction models. We used a cohort of Veterans Health Administration (VHA) users diagnosed with post-traumatic stress disorder (PTSD) between 2004-2013. Using a case-control design, cases (those that died by suicide during the year following diagnosis) were matched to controls (those that remained alive). After selecting conditional matches based on having shared mental health providers, we chose controls using a 5:1 nearest-neighbor propensity match based on the VHA's structured Electronic Medical Records (EMR)-based suicide prediction model. For cases, psychotherapist notes were collected from diagnosis until death. For controls, psychotherapist notes were collected from diagnosis until matched case's date of death. After ensuring similar numbers of notes, the final sample included 246 cases and 986 controls. Notes were analyzed using Sentiment Analysis and Cognition Engine, a Python-based NLP package. The output was evaluated using machine-learning algorithms. The area under the curve (AUC) was calculated to determine models' predictive accuracy. NLP derived variables offered small but significant predictive improvement (AUC = 0.58) for patients that had longer treatment duration. A small sample size limited predictive accuracy. Study identifies a novel method for measuring suicide risk over time and potentially categorizing patient subgroups with distinct risk sensitivities. Findings suggest leveraging NLP derived variables from psychotherapy notes offers an additional predictive value over and above the VHA's state-of-the-art structured EMR-based suicide prediction model. Replication with a larger non-PTSD specific sample is required.