Machine learning for suicidology: A practical review of exploratory and hypothesis-driven approaches

被引:23
作者
Cox, Christopher R. [1 ]
Moscardini, Emma H. [1 ]
Cohen, Alex S. [1 ,2 ]
Tucker, Raymond P. [1 ]
机构
[1] Louisiana State Univ, Dept Psychol, Baton Rouge, LA 70803 USA
[2] Louisiana State Univ, Ctr Computat & Technol, Baton Rouge, LA 70803 USA
关键词
Machine learning; Suicide; Suicidal thoughts and behaviors; Prediction; Structured sparsity; LOGISTIC-REGRESSION; RIDGE REGRESSION; RISK-FACTORS; PREDICTION; CLASSIFICATION; DEPRESSION; SELECTION; PATTERNS; IDEATION;
D O I
10.1016/j.cpr.2020.101940
中图分类号
B849 [应用心理学];
学科分类号
040203 ;
摘要
Machine learning is being used to discover models to predict the progression from suicidal ideation to action in clinical populations. While quantifiable improvements in prediction accuracy have been achieved over theory -driven efforts, models discovered through machine learning continue to fall short of clinical relevance. Thus, the value of machine learning for reaching this objective is hotly contested. We agree that machine learning, treated as a "black box" approach antithetical to theory-building, will not discover clinically relevant models of suicide. However, such models may be developed through deliberate synthesis of dataand theory-driven approaches. By providing an accessible overview of essential concepts and common methods, we highlight how generalizable models and scientific insight may be obtained by incorporating prior knowledge and expectations to machine learning research, drawing examples from suicidology. We then discuss challenges investigators will face when using machine learning to discover models of low prevalence outcomes, such as suicide.
引用
收藏
页数:11
相关论文
共 71 条
[1]  
Amini P, 2016, IRAN J PUBLIC HEALTH, V45, P1179
[2]  
[Anonymous], 2006, Journal of the Royal Statistical Society, Series B
[3]   Validation of an Electronic Health Record-Based Suicide Risk Prediction Modeling Approach Across Multiple Health Care Systems [J].
Barak-Corren, Yuval ;
Castro, Victor M. ;
Nock, Matthew K. ;
Mandl, Kenneth D. ;
Madsen, Emily M. ;
Seiger, Ashley ;
Adams, William G. ;
Applegate, R. Joseph ;
Bernstam, Elmer, V ;
Klann, Jeffrey G. ;
McCarthy, Ellen P. ;
Murphy, Shawn N. ;
Natter, Marc ;
Ostasiewski, Brian ;
Patibandla, Nandan ;
Rosenthal, Gary E. ;
Silva, George S. ;
Wei, Kun ;
Weber, Griffin M. ;
Weiler, Sarah R. ;
Reis, Ben Y. ;
Smoller, Jordan W. .
JAMA NETWORK OPEN, 2020, 3 (03)
[4]   Big Data and Machine Learning in Health Care [J].
Beam, Andrew L. ;
Kohane, Isaac S. .
JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 2018, 319 (13) :1317-1318
[5]   Prediction Models for Suicide Attempts and Deaths: A Systematic Review and Simulation [J].
Belsher, Bradley E. ;
Smolenski, Derek J. ;
Pruitt, Larry D. ;
Bush, Nigel E. ;
Beech, Erin H. ;
Workman, Don E. ;
Morgan, Rebecca L. ;
Evatt, Daniel P. ;
Tucker, Jennifer ;
Skopp, Nancy A. .
JAMA PSYCHIATRY, 2019, 76 (06) :642-651
[6]   The Two Cultures of Computational Psychiatry [J].
Bennett, Daniel ;
Silverstein, Steven M. ;
Niv, Yael .
JAMA PSYCHIATRY, 2019, 76 (06) :563-564
[7]   Improving risk prediction accuracy for new soldiers in the US Army by adding self-report survey data to administrative data [J].
Bernecker, Samantha L. ;
Rosellini, Anthony J. ;
Nock, Matthew K. ;
Chiu, Wai Tat ;
Gutierrez, Peter M. ;
Hwang, Irving ;
Joiner, Thomas E. ;
Naifeh, James A. ;
Sampson, Nancy A. ;
Zaslavsky, Alan M. ;
Stein, Murray B. ;
Ursano, Robert J. ;
Kessler, Ronald C. .
BMC PSYCHIATRY, 2018, 18
[8]   Influence of Resampling on Accuracy of Imbalanced Classification [J].
Burnaev, E. ;
Erofeev, P. ;
Papanov, A. .
EIGHTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2015), 2015, 9875
[9]  
Burnap Pete, 2017, Online Soc Netw Media, V2, P32, DOI 10.1016/j.osnem.2017.08.001
[10]   Clinical correlates of inpatient suicide [J].
Busch, KA ;
Fawcett, J ;
Jacobs, DG .
JOURNAL OF CLINICAL PSYCHIATRY, 2003, 64 (01) :14-19