Objective: The purpose of this article was to determine whether longitudinal historical data, commonly available in electronic health record (EHR) systems, can be used to predict patients’ future risk of suicidal behavior.
Method: Bayesian models were developed using a retrospective cohort approach. EHR data from a large health care database spanning 15 years (1998–2012) of inpatient and outpatient visits were used to predict future documented suicidal behavior (i.e., suicide attempt or death). Patients with three or more visits (N=1,728,549) were included. ICD-9-based case definition for suicidal behavior was derived by expert clinician consensus review of 2,700 narrative EHR notes (from 520 patients), supplemented by state death certificates. Model performance was evaluated retrospectively using an independent testing set.
This activity is only available to AJP CME subscribers.
Don't have a subscription to AJP CME? Subscribe Now!
- AJP Subscriber – 12 Month CME Subscription: $150.00
- Non AJP Subscriber – 12 Month CME Subscription: $300.00
If you have questions about AJP CME subscriptions, please contact email@example.com.
The participant will describe how risk screening techniques can be deployed to study electronic health records for potential risk of suicidal behavior.
This program is designed for all psychiatrists in clinical practice, residents in Graduate Medical Education programs, medical students interested in psychiatry, and other physicians who wish to advance their current knowledge of clinical medicine.
Duration: 1 hour
Begin Date: February 1, 2017
End Date: January 31, 2019
In order to earn CME credit, subscribers should read through the material presented in the article. After reading the article, complete the quiz and submit your evaluation and study hours (up to 1 AMA PRA Category 1 Credit™). A score of 60% or higher is required to receive credit.
The American Psychiatric Association (APA) is accredited by the Accreditation Council for Continuing Medical Education (ACCME) to provide continuing medical education for physicians.
The APA designates this journal-based CME activity for a maximum of 1 AMA PRA Category 1 Credit™. Physicians should only claim credit commensurate with the extent of their participation in the activity.
Title: Predicting Suicidal Behavior From Longitudinal Electronic Health Records
Authors: Yuval Barak-Corren, M.S., Victor M. Castro, M.S., Solomon Javitt, M.D., Alison G. Hoffnagle, M.S., Yael Dai, B.A., Roy H. Perlis, M.D., M.Sc., Matthew K. Nock, Ph.D., Jordan W. Smoller, M.D., Sc.D., Ben Y. Reis, Ph.D.
Affiliations: From the Predictive Medicine Group, Boston Children’s Hospital Informatics Program, Boston (Y.B.-C., S.J., B.Y.R.); the Technion, Israeli Institute of Technology, Haifa, Israel (Y.B.-C.); the Partners Research Information Systems and Computing, Boston (V.M.C.); the Department of Psychiatry, Massachusetts General Hospital, Boston (A.G.H., Y.D., R.H.P., M.K.N., J.W.S.); the Psychiatric and Neurodevelopmental Genetics Unit, Center for Human Genetic Research, Massachusetts General Hospital, Boston (A.G.H., Y.D., R.H.P., J.W.S.); the Department of Psychology, Harvard University, Boston (M.K.N.); and Harvard Medical School, Boston (R.H.P., J.W.S., B.Y.R.).
Disclosures: Dr. Perlis has served on scientific advisory boards for or as a consultant to Genomind, Perfect Health, Proteus Biomedical, PsyBrain, and RID Ventures; and he has also received support from Healthrageous, Massachusetts General Hospital, and Pfizer. All other authors report no financial relationships with commercial interests.
Discussion of unapproved or investigational use of products*: Yes.
*APA policy requires disclosure by CME authors of unapproved or investigational use of products discussed in CME programs. Off-label use of medications by individual physicians is permitted and common. Decisions about off-label use can be guided by scientific literature and clinical experience.
Robert Freedman, M.D. (Editor-in-Chief, AJP); Susan K. Schultz, M.D. (Deputy Editor, AJP); Michael D. Roy (Editorial Director, AJP); Michael A. Pogachar (Online Content Manager, Journals).
Dr. Schultz has received research support from the Alzheimer’s Disease Cooperative Study for projects conducted in partnership with Toyama Chemical Company and in partnership with Eli Lilly and Company. Dr. Freedman, Mr. Roy, and Mr. Pogachar report no financial relationships with commercial interests.
Optimal System Configuration:
- Flash Player: Adobe Flash Player 10.1+
- Browser: Firefox 3+, Internet Explorer 8.0+, Safari 4.0+, or Google Chrome 7.0+
- Operating System: Windows XP+ or Mac OS X 10.4+
- Internet Connection: 1 Mbps or higher
- Screen Resolution: 1024 x 768 pixels.
- Windows PC:500-MHz Pentium II; Windows XP or higher; 128 MB RAM; Video Card at least 64MB of video memory; Sound Card at least 16-bit; Macromedia Flash Player 10 or higher, audio playback with speakers for programs with video content; Firefox 1.1+, Internet Explorer 7.0+, Safari 1.0+, Google Chrome, or Opera
- Macintosh: Mac OS X 10.3 or higher with latest updates installed; 1.83MHz Intel Core Duo or faster; RAM: 128MB or more; Video Card: at least 64MB of video memory; Sound Card: at least 16-bit
For assistance: Contact firstname.lastname@example.org for questions about this course | Contact email@example.com for technical assistance