Novel Use of Natural Language Processing (NLP) to Predict Suicidal Ideation and Psychiatric Symptoms in a Text-Based Mental Health Intervention in Madrid

• Published in: Computational and mathematical methods in medicine Vol. 2016; no. 2016; pp. 1 - 8
• Main Authors: Hou, Sherry, Mullin, Brian, Chen, Pei, Progovac, Ana M., Cook, Benjamin L., Baca-García, Enrique
• Format: Journal Article
• Language: English
• Published: Cairo, Egypt Hindawi Publishing Corporation 01.01.2016
• Subjects: Adult; Algorithms; Diagnosis, Computer-Assisted; Female; Follow-Up Studies; Hospitalization; Hospitals, Psychiatric; Humans; Machine Learning; Male; Mental Disorders - physiopathology; Mental Health Services; Middle Aged; Natural Language Processing; Patient Discharge; Predictive Value of Tests; Psychometrics; Reminder Systems; Reproducibility of Results; Self-Injurious Behavior; Sensitivity and Specificity; Spain; Suicide, Attempted - prevention & control; Surveys and Questionnaires; Telemedicine - methods; Text Messaging; Young Adult
• ISSN: 1748-670X; 1748-6718
• DOI: 10.1155/2016/8708434

Natural language processing (NLP) and machine learning were used to predict suicidal ideation and heightened psychiatric symptoms among adults recently discharged from psychiatric inpatient or emergency room settings in Madrid, Spain. Participants responded to structured mental and physical health instruments at multiple follow-up points. Outcome variables of interest were suicidal ideation and psychiatric symptoms (GHQ-12). Predictor variables included structured items (e.g., relating to sleep and well-being) and responses to one unstructured question, “how do you feel today?” We compared NLP-based models using the unstructured question with logistic regression prediction models using structured data. The PPV, sensitivity, and specificity for NLP-based models of suicidal ideation were 0.61, 0.56, and 0.57, respectively, compared to 0.73, 0.76, and 0.62 of structured data-based models. The PPV, sensitivity, and specificity for NLP-based models of heightened psychiatric symptoms (GHQ-12 ≥ 4) were 0.56, 0.59, and 0.60, respectively, compared to 0.79, 0.79, and 0.85 in structured models. NLP-based models were able to generate relatively high predictive values based solely on responses to a simple general mood question. These models have promise for rapidly identifying persons at risk of suicide or psychological distress and could provide a low-cost screening alternative in settings where lengthy structured item surveys are not feasible.