Predicting Undesired Treatment Outcomes With Machine Learning in Mental Health Care: Multisite Study

被引:4
作者
Van Mens, Kasper [1 ,2 ]
Lokkerbol, Joran [3 ]
Wijnen, Ben [4 ]
Janssen, Richard [5 ,6 ]
de Lange, Robert [7 ]
Tiemens, Bea [1 ,8 ,9 ]
机构
[1] Radboud Univ Nijmegen, Behav Sci Inst, Houtlaan 4, NL-6525 XZ Nijmegen, Gelderland, Netherlands
[2] Altrecht Mental Healthcare, Data Sci, Utrecht, Netherlands
[3] Trimbos Inst, Ctr Econ Evaluat Machine Learning, Netherlands Inst Mental Hlth & Addic, Utrecht, Netherlands
[4] Maastricht Univ Med Ctr, Dept Clin Epidemiol & Med Technol Assessment, Maastricht, Netherlands
[5] Erasmus Univ, Erasmus Sch Hlth Policy & Management, Hlth Care Governance, Rotterdam, Netherlands
[6] Tilburg Univ, Sci Ctr Care & Welf Tranzo, Tilburg, Netherlands
[7] Alan Turing Inst, Amere, Netherlands
[8] Indigo Serv Org, Utrecht, Netherlands
[9] Pro Persona Res, Renkum, Netherlands
关键词
treatment outcomes; mental health; machine learning; treatment; model; Netherlands; data; risk; risk signaling; technology; clinical practice; model performance; STEPPED CARE; DATA SCIENCE; DEPRESSION; VARIABLES; MODELS;
D O I
10.2196/44322
中图分类号
R-058 [];
学科分类号
摘要
Background: Predicting which treatment will work for which patient in mental health care remains a challenge.Objective: The aim of this multisite study was 2-fold: (1) to predict patients' response to treatment in Dutch basic mental health care using commonly available data from routine care and (2) to compare the performance of these machine learning models across three different mental health care organizations in the Netherlands by using clinically interpretable models.Methods: Using anonymized data sets from three different mental health care organizations in the Netherlands (n=6452), we applied a least absolute shrinkage and selection operator regression 3 times to predict the treatment outcome. The algorithms were internally validated with cross-validation within each site and externally validated on the data from the other sites.Results: The performance of the algorithms, measured by the area under the curve of the internal validations as well as the corresponding external validations, ranged from 0.77 to 0.80.Conclusions: Machine learning models provide a robust and generalizable approach in automated risk signaling technology to identify cases at risk of poor treatment outcomes. The results of this study hold substantial implications for clinical practice by demonstrating that the performance of a model derived from one site is similar when applied to another site (ie, good external validation).
引用
收藏
页数:10
相关论文
共 35 条
[1]   Machine Learning for Precision Psychiatry: Opportunities and Challenges [J].
Bzdok, Danilo ;
Meyer-Lindenberg, Andreas .
BIOLOGICAL PSYCHIATRY-COGNITIVE NEUROSCIENCE AND NEUROIMAGING, 2018, 3 (03) :223-230
[2]   Cross-trial prediction of treatment outcome in depression: a machine learning approach [J].
Chekroud, Adam Mourad ;
Zotti, Ryan Joseph ;
Shehzad, Zarrar ;
Gueorguieva, Ralitza ;
Johnson, Marcia K. ;
Trivedi, Madhukar H. ;
Cannon, Tyrone D. ;
Krystal, John Harrison ;
Corlett, Philip Robert .
LANCET PSYCHIATRY, 2016, 3 (03) :243-250
[3]  
Cohen J., 1988, Statistical Power Analysis for the Behavioral Sciences, V2nd, DOI 10.4324/9780203771587
[4]   The outcome questionnaire (OQ-45) in a Dutch population: A cross-cultural validation [J].
de Jong, Kim ;
Nugter, M. Annet ;
Polak, Marike G. ;
Wagenborg, Johannes E. A. ;
Spinhoven, Philip ;
Heiser, Willem J. .
CLINICAL PSYCHOLOGY & PSYCHOTHERAPY, 2007, 14 (04) :288-301
[5]   Feedback-informed treatment versus usual psychological treatment for depression and anxiety: a multisite, open-label, cluster randomised controlled trial [J].
Delgadillo, Jaime ;
de Jong, Kim ;
Lucock, Mike ;
Lutz, Wolfgang ;
Rubel, Julian ;
Gilbody, Simon ;
Ali, Shehzad ;
Aguirre, Elisa ;
Appleton, Mark ;
Nevin, Jacqueline ;
O'Hayon, Harry ;
Patel, Ushma ;
Sainty, Andrew ;
Spencer, Peter ;
McMillan, Dean .
LANCET PSYCHIATRY, 2018, 5 (07) :564-572
[6]   The new field of 'precision psychiatry' [J].
Fernandes, Brisa S. ;
Williams, Leanne M. ;
Steiner, Johann ;
Leboyer, Marion ;
Carvalho, Andre F. ;
Berk, Michael .
BMC MEDICINE, 2017, 15
[7]  
Freitas A.A., 2014, ACM SIGKDD Explorations Newslett., V15, P1, DOI [10.1145/2594473.2594475, DOI 10.1145/2594473.2594475]
[8]   Regularization Paths for Generalized Linear Models via Coordinate Descent [J].
Friedman, Jerome ;
Hastie, Trevor ;
Tibshirani, Rob .
JOURNAL OF STATISTICAL SOFTWARE, 2010, 33 (01) :1-22
[9]   What big data can do for treatment in psychiatry [J].
Gillan, Claire M. ;
Whelan, Robert .
CURRENT OPINION IN BEHAVIORAL SCIENCES, 2017, 18 :34-42
[10]   Artificial Intelligence for Mental Health and Mental Illnesses: an Overview [J].
Graham, Sarah ;
Depp, Colin ;
Lee, Ellen E. ;
Nebeker, Camille ;
Tu, Xin ;
Kim, Ho-Cheol ;
Jeste, Dilip V. .
CURRENT PSYCHIATRY REPORTS, 2019, 21 (11)