A Feasibility Study Using a Machine Learning Suicide Risk Prediction Model Based on Open-Ended Interview Language in Adolescent Therapy Sessions

Joshua Cohen, Jennifer Wright-Berryman, Lesley Rohlfs, Donald Wright, Marci Campbell, Debbie Gingrich, Daniel Santel and John Pestian
Additional contact information
Joshua Cohen: Clarigent Health, 5412 Courseview Drive, Suite 210, Mason, OH 45040, USA
Jennifer Wright-Berryman: Department of Social Work, College of Allied Health Sciences, University of Cincinnati, Cincinnati, OH 45221, USA
Lesley Rohlfs: Clarigent Health, 5412 Courseview Drive, Suite 210, Mason, OH 45040, USA
Donald Wright: Clarigent Health, 5412 Courseview Drive, Suite 210, Mason, OH 45040, USA
Marci Campbell: Clarigent Health, 5412 Courseview Drive, Suite 210, Mason, OH 45040, USA
Debbie Gingrich: The Children’s Home, 5050 Madison Road, Cincinnati, OH 45227, USA
Daniel Santel: Department of Pediatrics, Division of Biomedical Informatics, Cincinnati Children’s Hospital Medical Center, Cincinnati, OH 45229, USA
John Pestian: Department of Pediatrics, Division of Biomedical Informatics, Cincinnati Children’s Hospital Medical Center, Cincinnati, OH 45229, USA

IJERPH, 2020, vol. 17, issue 21, 1-17

Abstract: Background: As adolescent suicide rates continue to rise, innovation in risk identification is warranted. Machine learning can identify suicidal individuals based on their language samples. This feasibility pilot was conducted to explore this technology’s use in adolescent therapy sessions and assess machine learning model performance. Method: Natural language processing machine learning models to identify level of suicide risk using a smartphone app were tested in outpatient therapy sessions. Data collection included language samples, depression and suicidality standardized scale scores, and therapist impression of the client’s mental state. Previously developed models were used to predict suicidal risk. Results: 267 interviews were collected from 60 students in eight schools by ten therapists, with 29 students indicating suicide or self-harm risk. During external validation, models were trained on suicidal speech samples collected from two separate studies. We found that support vector machines (AUC: 0.75; 95% CI: 0.69–0.81) and logistic regression (AUC: 0.76; 95% CI: 0.70–0.82) lead to good discriminative ability, with an extreme gradient boosting model performing the best (AUC: 0.78; 95% CI: 0.72–0.84). Conclusion: Voice collection technology and associated procedures can be integrated into mental health therapists’ workflow. Collected language samples could be classified with good discrimination using machine learning methods.

Keywords: machine learning; natural language processing; suicidal risk; risk assessment; mental health; therapy; suicidal ideation (search for similar items in EconPapers)
JEL-codes: I I1 I3 Q Q5 (search for similar items in EconPapers)
Date: 2020
References: View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/1660-4601/17/21/8187/pdf (application/pdf)
https://www.mdpi.com/1660-4601/17/21/8187/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jijerp:v:17:y:2020:i:21:p:8187-:d:440622

Access Statistics for this article

IJERPH is currently edited by Ms. Jenna Liu

More articles in IJERPH from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().