Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Prediction of Suicide-Related Events by Analyzing Electronic Medical Records from PTSD Patients with Bipolar Disorder

Fan, Peihao and Guo, Xiaojiang and Qi, Xiguang and Matharu, Mallika and Patel, Ravi and Sakolsky, Dara and Kirisci, Levent and Silverstein, Jonathan C. and Wang, Lirong (2020) Prediction of Suicide-Related Events by Analyzing Electronic Medical Records from PTSD Patients with Bipolar Disorder. Brain Sciences, 10 (11). p. 784. ISSN 2076-3425

Published Version

Download (2MB) | Preview


Around 800,000 people worldwide die from suicide every year and it’s the 10th leading cause of death in the US. It is of great value to build a mathematic model that can accurately predict suicide especially in high-risk populations. Several different ML-based models were trained and evaluated using features obtained from electronic medical records (EMRs). The contribution of each feature was calculated to determine how it impacted the model predictions. The best-performing model was selected for analysis and decomposition. Random forest showed the best performance with true positive rates (TPR) and positive predictive values (PPV) of greater than 80%. The use of Aripiprazole, Levomilnacipran, Sertraline, Tramadol, Fentanyl, or Fluoxetine, a diagnosis of autistic disorder, schizophrenic disorder, or substance use disorder at the time of a diagnosis of both PTSD and bipolar disorder, were strong indicators for no SREs within one year. The use of Trazodone and Citalopram at baseline predicted the onset of SREs within one year. Additional features with potential protective or hazardous effects for SREs were identified by the model. We constructed an ML-based model that was successful in identifying patients in a subpopulation at high-risk for SREs within a year of diagnosis of both PTSD and bipolar disorder. The model also provides feature decompositions to guide mechanism studies. The validation of this model with additional EMR datasets will be of great value in resource allocation and clinical decision making.


Social Networking:
Share |


Item Type: Article
Status: Published
CreatorsEmailPitt UsernameORCID
Fan, Peihaopef14@pitt.edupef14
Guo, Xiaojiangxig53@pitt.eduxig53
Qi, Xiguangxiq24@pitt.eduxiq24
Matharu, Mallikamam802@pitt.edumam802
Patel, Ravirmp40@pitt.edurmp40
Kirisci, Leventlevent@pitt.edulevent
Silverstein, Jonathan
Wang, Lirongliw30@pitt.eduliw30
Date: 27 October 2020
Date Type: Publication
Journal or Publication Title: Brain Sciences
Volume: 10
Number: 11
Publisher: MDPI AG
Page Range: p. 784
DOI or Unique Handle: 10.3390/brainsci10110784
Schools and Programs: School of Pharmacy > Pharmaceutical Sciences
Refereed: Yes
Uncontrolled Keywords: PTSD, bipolar disorder, machine learning, random forest, suicide-related events, model decomposition
ISSN: 2076-3425
Official URL:
Funders: National Institutes of Health
Article Type: Research Article
Date Deposited: 04 Jun 2021 19:40
Last Modified: 04 Jun 2021 19:40


Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item