PDF herunterladen
Appl Clin Inform 2021; 12(04): 778-787
DOI: 10.1055/s-0041-1733908
Research Article

Evaluation of Electronic Health Record-Based Suicide Risk Prediction Models on Contemporary Data

Rod L. Walker
1   Kaiser Permanente Washington Health Research Institute, Seattle, Washington, United States
,
Susan M. Shortreed
1   Kaiser Permanente Washington Health Research Institute, Seattle, Washington, United States
,
Rebecca A. Ziebell
1   Kaiser Permanente Washington Health Research Institute, Seattle, Washington, United States
,
Eric Johnson
1   Kaiser Permanente Washington Health Research Institute, Seattle, Washington, United States
,
Jennifer M. Boggs
2   Kaiser Permanente Colorado, Institute for Health Research, Aurora, Colorado, United States
,
Frances L. Lynch
3   Kaiser Permanente Northwest, Center for Health Research, Portland, Oregon, United States
,
Yihe G. Daida
4   Kaiser Permanente Hawaii, Center for Integrated Health Care Research, Honolulu, Hawaii, United States
,
Brian K. Ahmedani
5   Henry Ford Health System, Center for Health Policy & Health Services Research, Detroit, Michigan, United States
,
Rebecca Rossom
6   Department of Research, HealthPartners Institute, Minneapolis, Minnesota, United States
,
Karen J. Coleman
7   Department of Research and Evaluation, Kaiser Permanente Southern California, Pasadena, California, United States
,
Gregory E. Simon
1   Kaiser Permanente Washington Health Research Institute, Seattle, Washington, United States
› Institutsangaben Funding This work was supported by cooperative agreements U19 MH092201 and U19 MH121738 with the National Institute of Mental Health.
› Weitere Informationen
   Lizenzen und Reprints

Abstract

Background Suicide risk prediction models have been developed by using information from patients' electronic health records (EHR), but the time elapsed between model development and health system implementation is often substantial. Temporal changes in health systems and EHR coding practices necessitate the evaluation of such models in more contemporary data.

Objectives A set of published suicide risk prediction models developed by using EHR data from 2009 to 2015 across seven health systems reported c-statistics of 0.85 for suicide attempt and 0.83 to 0.86 for suicide death. Our objective was to evaluate these models' performance with contemporary data (2014–2017) from these systems.

Methods We evaluated performance using mental health visits (6,832,439 to mental health specialty providers and 3,987,078 to general medical providers) from 2014 to 2017 made by 1,799,765 patients aged 13+ across the health systems. No visits in our evaluation were used in the previous model development. Outcomes were suicide attempt (health system records) and suicide death (state death certificates) within 90 days following a visit. We assessed calibration and computed c-statistics with 95% confidence intervals (CI) and cut-point specific estimates of sensitivity, specificity, and positive/negative predictive value.

Results Models were well calibrated; 46% of suicide attempts and 35% of suicide deaths in the mental health specialty sample were preceded by a visit (within 90 days) with a risk score in the top 5%. In the general medical sample, 53% of attempts and 35% of deaths were preceded by such a visit. Among these two samples, respectively, c-statistics were 0.862 (95% CI: 0.860–0.864) and 0.864 (95% CI: 0.860–0.869) for suicide attempt, and 0.806 (95% CI: 0.790–0.822) and 0.804 (95% CI: 0.782–0.829) for suicide death.

Conclusion Performance of the risk prediction models in this contemporary sample was similar to historical estimates for suicide attempt but modestly lower for suicide death. These published models can inform clinical practice and patient care today.

Keywords

suicide - mental health - electronic health records - statistics - health care systems

Protection of Human and Subjects Protections

This research study was performed in compliance with the responsible institutional review boards for each health system that approved use of de-identified records data for the study.


Supplementary Material



Publikationsverlauf

Eingereicht: 16. Februar 2021

Angenommen: 01. Juli 2021

Artikel online veröffentlicht:
18. August 2021

© 2021. Thieme. All rights reserved.

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany

 

  • References

  • 1 Simon GE, Coleman KJ, Rossom RC. et al. Risk of suicide attempt and suicide death following completion of the Patient Health Questionnaire depression module in community practice. J Clin Psychiatry 2016; 77 (02) 221-227
    CrossrefPubMedGoogle Scholar
  • 2 Barak-Corren Y, Castro VM, Javitt S. et al. Predicting suicidal behavior from longitudinal electronic health records. Am J Psychiatry 2017; 174 (02) 154-162
    CrossrefPubMedGoogle Scholar
  • 3 Choi SB, Lee W, Yoon JH, Won JU, Kim DW. Ten-year prediction of suicide death using Cox regression and machine learning in a nationwide retrospective cohort study in South Korea. J Affect Disord 2018; 231: 8-14
    CrossrefPubMedGoogle Scholar
  • 4 Kessler RC, Hwang I, Hoffmire CA. et al. Developing a practical suicide risk prediction model for targeting high-risk patients in the Veterans health Administration. Int J Methods Psychiatr Res 2017; 26 (03) e1575
    CrossrefPubMedGoogle Scholar
  • 5 Simon GE, Johnson E, Lawrence JM. et al. Predicting suicide attempts and suicide deaths following outpatient visits using electronic health records. Am J Psychiatry 2018; 175 (10) 951-960
    CrossrefPubMedGoogle Scholar
  • 6 Walsh CG, Ribeiro JD, Franklin JC. Predicting risk of suicide attempts over time through machine learning. Clin Psychol Sci 2017; 5 (03) 457-469
    CrossrefPubMedGoogle Scholar
  • 7 Agniel D, Kohane IS, Weber GM. Biases in electronic health record data due to processes within the healthcare system: retrospective observational study. BMJ 2018; 361: k1479
    CrossrefPubMedGoogle Scholar
  • 8 Andreu-Perez J, Poon CC, Merrifield RD, Wong ST, Yang GZ. Big data for health. IEEE J Biomed Health Inform 2015; 19 (04) 1193-1208
    CrossrefPubMedGoogle Scholar
  • 9 Pérez-Benito FJ, Sáez C, Conejero JA, Tortajada S, Valdivieso B, García-Gómez JM. Temporal variability analysis reveals biases in electronic health records due to hospital process reengineering interventions over seven years. PLoS One 2019; 14 (08) e0220369
    CrossrefPubMedGoogle Scholar
  • 10 Rockenschaub P, Nguyen V, Aldridge RW, Acosta D, García-Gómez JM, Sáez C. Data-driven discovery of changes in clinical code usage over time: a case-study on changes in cardiovascular disease recording in two English electronic health records databases (2001-2015). BMJ Open 2020; 10 (02) e034396
    CrossrefPubMedGoogle Scholar
  • 11 Rossom RC, Simon GE, Beck A. et al. Facilitating action for suicide prevention by learning health care systems. Psychiatr Serv 2016; 67 (08) 830-832
    CrossrefPubMedGoogle Scholar
  • 12 Ross TR, Ng D, Brown JS. et al. The HMO research network virtual data warehouse: a public data model to support collaboration. EGEMS (Wash DC) 2014; 2 (01) 1049
    PubMedGoogle Scholar
  • 13 Charlson M, Szatrowski TP, Peterson J, Gold J. Validation of a combined comorbidity index. J Clin Epidemiol 1994; 47 (11) 1245-1251
    CrossrefPubMedGoogle Scholar
  • 14 Tibshirani R. Regression shrinkage and selection via the lasso. J R Stat Soc Series B Stat Methodol 1996; 58 (01) 267-288
    PubMedGoogle Scholar
  • 15 Zeger SL, Liang KY. Longitudinal data analysis for discrete and continuous outcomes. Biometrics 1986; 42 (01) 121-130
    CrossrefPubMedGoogle Scholar
  • 16 R Core Team. R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria: 2019
    Google Scholar
  • 17 Sing T, Sander O, Beerenwinkel N, Lengauer T. ROCR: visualizing classifier performance in R. Bioinformatics 2005; 21 (20) 3940-3941
    CrossrefPubMedGoogle Scholar
  • 18 Lenert MC, Matheny ME, Walsh CG. Prognostic models will be victims of their own success, unless…. J Am Med Inform Assoc 2019; 26 (12) 1645-1650
    CrossrefPubMedGoogle Scholar
  • 19 Toll DB, Janssen KJ, Vergouwe Y, Moons KG. Validation, updating and impact of clinical prediction rules: a review. J Clin Epidemiol 2008; 61 (11) 1085-1094
    CrossrefPubMedGoogle Scholar
  • 20 Davis SE, Lasko TA, Chen G, Siew ED, Matheny ME. Calibration drift in regression and machine learning models for acute kidney injury. J Am Med Inform Assoc 2017; 24 (06) 1052-1061
    CrossrefPubMedGoogle Scholar
  • 21 Simon GE, Shortreed SM, Johnson E. et al. What health records data are required for accurate prediction of suicidal behavior?. J Am Med Inform Assoc 2019; 26 (12) 1458-1465
    CrossrefPubMedGoogle Scholar
  • 22 Ghassemi M, Naumann T, Schulam P, Beam AL, Chen IY, Ranganath R. A review of challenges and opportunities in machine learning for health. AMIA Jt Summits Transl Sci Proc 2020; 2020: 191-200
    PubMedGoogle Scholar
  • 23 Su C, Xu Z, Pathak J, Wang F. Deep learning in mental health outcome research: a scoping review. Transl Psychiatry 2020; 10 (01) 116
    CrossrefPubMedGoogle Scholar
  • 24 Goldstein BA, Navar AM, Pencina MJ, Ioannidis JP. Opportunities and challenges in developing risk prediction models with electronic health records data: a systematic review. J Am Med Inform Assoc 2017; 24 (01) 198-208
    CrossrefPubMedGoogle Scholar
  • 25 Van Calster B, Wynants L, Timmerman D, Steyerberg EW, Collins GS. Predictive analytics in health care: how can we know it works?. J Am Med Inform Assoc 2019; 26 (12) 1651-1654
    CrossrefPubMedGoogle Scholar