Development of an early-warning system for high-risk patients for suicide attempt using deep learning and electronic health records
| Autor: | Frank Stearns, Liliana Markovic, Alex N. Sabo, Xuefeng B. Ling, Le Zheng, Shiying Hao, Laura Kanov, Doff B. McElhinney, Minjie Xia, Jiayu Liao, Karl G. Sylvester, Oliver Wang, Modi Liu, Eric Widen, Wei Zhang, Chengyin Ye |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
medicine.medical_specialty
Scientific community Population Poison control Suicide Attempted Suicide prevention Occupational safety and health Article lcsh:RC321-571 03 medical and health sciences Cellular and Molecular Neuroscience 0302 clinical medicine Deep Learning Risk Factors Injury prevention medicine Electronic Health Records Humans Prospective Studies education Psychiatry lcsh:Neurosciences. Biological psychiatry. Neuropsychiatry Biological Psychiatry Depression (differential diagnoses) Retrospective Studies education.field_of_study Framingham Risk Score Suicide attempt business.industry United States 030227 psychiatry Psychiatry and Mental health business Psychiatric disorders 030217 neurology & neurosurgery |
| Zdroj: | Translational Psychiatry Translational Psychiatry, Vol 10, Iss 1, Pp 1-10 (2020) |
| ISSN: | 2158-3188 |
| Popis: | Suicide is the tenth leading cause of death in the United States (US). An early-warning system (EWS) for suicide attempt could prove valuable for identifying those at risk of suicide attempts, and analyzing the contribution of repeated attempts to the risk of eventual death by suicide. In this study we sought to develop an EWS for high-risk suicide attempt patients through the development of a population-based risk stratification surveillance system. Advanced machine-learning algorithms and deep neural networks were utilized to build models with the data from electronic health records (EHRs). A final risk score was calculated for each individual and calibrated to indicate the probability of a suicide attempt in the following 1-year time period. Risk scores were subjected to individual-level analysis in order to aid in the interpretation of the results for health-care providers managing the at-risk cohorts. The 1-year suicide attempt risk model attained an area under the curve (AUC ROC) of 0.792 and 0.769 in the retrospective and prospective cohorts, respectively. The suicide attempt rate in the “very high risk” category was 60 times greater than the population baseline when tested in the prospective cohorts. Mental health disorders including depression, bipolar disorders and anxiety, along with substance abuse, impulse control disorders, clinical utilization indicators, and socioeconomic determinants were recognized as significant features associated with incident suicide attempt. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|