Predictive modeling: the role of opioid use in suicide risk

Grant Details

Funder: NIDA

Grant Number: R01DA047724

Grant Period: 8/15/2018 – 6/30/2022

Narrative: Suicide deaths and opioid-related overdose deaths have both been increasing in recent years. These two public health crises have substantial overlap: our preliminary work suggests that between 22% and 37% of opioid-related overdoses are suicides or suicide attempts. Healthcare settings are ideal places to intervene to prevent suicides, however clinicians need better tools to recognize the patients at greatest risk. We developed models that predict risk of suicide attempt or death with 83% to 86% accuracy. However, these models do not include important opioid-related variables. In a parallel body of work, we developed algorithms based on coded electronic health record (EHR) data to identify opioid-related overdoses and classify them as unintentional or intentional suicides. The proposed project integrates these two existing lines of research. Our suicide risk prediction dataset includes seven large healthcare systems and approximately 20 million visits by 3 million patients; it is currently being expanded to include additional outcomes and visits through 2016, and additional predictors, however inclusion of opioid-related variables was not part of the funded supplement. In the proposed study, we will determine whether including variables related to illicit and prescribed opioid use, opioid use disorder, discontinuation or significant dose reductions of prescription opioids, or prior non-fatal opioid-related overdoses improves predictions of suicide attempts or death within 90 days following an outpatient healthcare visit. We will also develop models that specifically predict opioid- related suicide attempts and deaths in the sample as a whole and among people prescribed opioid medications, and determine if the predictors of opioid-related suicide attempts or deaths are consistent for men and women. The goal of the proposed work is to maximize the performance of our models in order to create the best available tools for clinicians to help reduce future suicides. We have an established collaboration with the largest national EHR vendor and are working to develop an EHR-based, point-of-care clinical tool to predict suicide attempts and deaths based on our research findings. This work will therefore have a direct impact on clinical practice by providing clinicians with an efficient, evidence-based tool to evaluate suicide risk. The work will also provide critical data on understudied opioid-related predictors and moderators of suicide.

Lead Site: KPNW (PI Bobbi Jo Yarborough)

Participating Sites: HFHS, HPI, KPCO, KPHI, KPSC, KPWA

Current Status

Summary of Findings


Care of Mental, Physical and Substance Use Syndromes (COMPASS)

Project Name:
Care of Mental, Physical and Substance Use Syndromes (COMPASS)
Principal Investigator:
Sanne Magnan, MD PhD; Evaluation Director: Leif Solberg, MD
Principal Investigator Contact Information:
Principal Investigator institution:
Institute for Clinical Systems Improvement; HealthPartners Institute
Centers for Medicare & Medicaid Services (CMS) / Center for Medicare & Medicaid Innovation (CMMI)
Funding Period:
07/2012 – 06/2015
Health care increasingly needs to develop ways to manage individuals with multiple coexisting chronic conditions. COMPASS is a partnership among 9 organizations and 18 care delivery systems nationally to implement the Collaborative Care model for patients in primary care suffering from depression as well as diabetes and/or cardiovascular disease that are not under control. The initiative reached approximately 4,000 patients in seven states, and improved depression in 40% and achieved control in 23% with diabetes and 58% with hypertension while improving patient satisfaction with care and physician satisfaction with the resources needed to manage such patients.
Grant Number:
Participating Sites:               
AIMS (Advancing Integrated Mental Health Solutions) Center at the University of Washington
Community Health Plan of Washington (CHPW)
HealthPartners Institute
Kaiser Permanente Colorado (KPCO)
Kaiser Permanente Southern California (KPSC)
Michigan Center for Clinical Systems Improvement (Mi-CCSI)
Mount Auburn Cambridge Independent Practice Association (MACIPA)
Pittsburgh Regional Health Initiative (PRHI)
Institute for Clinical Systems Improvement (ICSI)
Sanne Magnan, MD, PhD
Claire Neeley, MD
Leif Solberg, MD
Arne Beck, PhD
Karen Coleman, PhD
Jurgen Unutzer, MD
Rebecca Rossom, MD, MS
Lauren Crain, PhD
Michael Maciosek, PhD
Robin Whitebird, PhD, MSW, LISW
Major Goals:
The major goals are to increase the proportion of these complex uncontrolled patients who are now under control by 20% for patients with diabetes or hypertension, and to improve depression in 40%, while reducing healthcare costs
Description of study sample:
This was a demonstration project aimed at adults with active depression plus either diabetes or cardiovascular disease that were not under control. We initially targeted patients with Medicare or Medicaid, but later added other patient groups because of the unexpected difficulty of identifying and recruiting such patients.
Current Status:
The project was completed in 6/15, but most participating medical groups have continued it with a variety of modifications to fit their settings and needs
Study Registration:
Coleman KJ, Hemmila T, Valenti MD, Smith 4, Quarrell R, Ruona LK, Brandenfels E, Hann B, Hinnenkamp T, Parra MD, Monkman J, Vos S, Rossom RC. Understanding the experience of care managers and relationship with patient outcomes: the COMPASS initiative. Gen Hosp Psychiatry. 2016 Aug 18. pii: S0163-8343(16)30164-5. doi: 10.1016/j.genhosppsych.2016.03.003. [Epub ahead of print]Coleman KJ, Magnan S, Neely C, Solberg L, Beck A, Trevis J, Heim C, Williams M, Katzelnick D, Unützer J, Pollock B, Hafer E, Ferguson R, Williams S. The COMPASS initiative: description of a nationwide collaborative approach to the care of patients with depression and diabetes and/or cardiovascular disease. Gen Hosp Psychiatry. 2016 Aug 18. pii: S0163-8343(16)30166-9. doi: 10.1016/j.genhosppsych.2016.05.007. [Epub ahead of print]Rossom RC, Solberg LI, Magnan S, Crain AL, Beck A, Coleman KJ, Katzelnick D, Williams MD, Neely C, Ohnsorg K, Whitebird R, Brandenfels E, Pollock B, Ferguson R, Williams S, Unützer J. Impact of a national collaborative care initiative for patients with depression and diabetes or cardiovascular disease. Gen Hosp Psychiatry. 2016 Aug 18. pii: S0163-8343(16)30165-7. doi: 10.1016/j.genhosppsych.2016.05.006. [Epub ahead of print]Solberg LI, Ferguson R, Ohnsorg KA, Crain AL, Williams MD, Ziegenfuss JY, et al. The challenges of collecting and using patient care data from diverse care systems: lessons from COMPASS. Am J Med Qual 2017;32(5):494-499.Whitebird RR, Solberg LI, Crain AL, Rossom RC, Beck A, Neely C, Dreskin M, Coleman KJ. Clinician burnout and satisfaction with resources in caring for complex patients. Gen Hosp Psychiatry. 2017;44(1):91-95. Jul 16. pii: S0163-8343(16)30167-0. doi: 10.1016/j.genhosppsych.2016.03.004. [Epub ahead of print]Solberg LI, Ohnsorg KA, Parker ED, Ferguson R, Magnan S, Whitebird RR, Neely C, Brandenfels E, Williams MD, Dreskin M, Hinnenkamp T, Ziegenfuss JY. Preventable hospital and emergency department events: lessons from a large innovation project. The Permanente Journal 2018 (In press).
Lessons Learned:
It is possible to have multiple diverse health care organizations collaborate on a common improvement project and to use a common data system to aggregate data for reporting and analysis, although there are many challenges to doing so. Other lessons are available in the above publications. Additional publication in development describes the relation between care manager contacts and systematic case review to depression improvement.
What’s next?
Most participating organizations are continuing to use individually adapted versions of the COMPASS model for care but there will be no follow-on group project.