Improving Suicide Risk Prediction with Social Determinants Data

Grant Details

Funder: NIMH

Grant Number: R56MH125794-01A1

Grant Period: 1/1/2022 – 12/31/2022

Brief Narrative: Suicide accounted for 47,511 deaths in the United States in 2019 and the suicide rate has increased by 39% since 1999. Suicide prevention is an NIMH research priority. Recent research in estimating machine learning algorithms to predict suicide risk has been tremendously successful. The models have been implemented as part of routine prevention programs in health systems such as Kaiser Permanente Washington, HealthPartners, and the Veterans Health Administration. Despite these successes, existing models have important shortcomings. A significant proportion of suicides followed healthcare visits where the predicted risk was low (and where an intervention might have taken place otherwise). The models do not currently include any information about social determinants of suicide (e.g., living alone, financial stress) or negative life events (NLE), such as divorce, bankruptcy, and criminal arrest. Adding social determinants data and NLE data to models may improve predictive accuracy. The specific aims of this study are: (1) expand and enhance the risk prediction dataset with over 1500 date-stamped variables describing social determinants of suicide risk and NLE; (2) construct and evaluate suicide risk prediction models using social determinants and NLE data alone; (3) construct and evaluate suicide risk prediction models using social determinants, NLE and healthcare data together and estimate interaction terms between social determinants, NLE, and healthcare predictors. An example would be “depression diagnosis” interacted with “divorce filing in last 30 days”. This will be the first large scale study to incorporate individual-level, date-stamped measures of social determinants and NLE into machine learning suicide risk prediction models. Upon successful completion of this study we expect to know how much incorporating these new data contributes to the accuracy of suicide risk prediction models. This will be an important next step towards implementing better suicide prevention programs and reducing overall suicide rates.

Lead Site: KPWA (PI Rob Penfold)

Participating Sites: N/A

Current Status

We fielded the discrete choice experiment in mid-October 2022. Planned recruitment is 720.

Summary of Findings

Publications

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

Publications

Implementing Predictive Models for Identifying Suicide Risk in Adolescents

Grant Details

Funder: NIMH (MHRN III Feasibility Pilot Program)

Grant Number: U19MH121738

Project Period: 7/1/2022 – 6/30/2023

Narrative:

Background: Adolescent suicide is an urgent public health crisis. Suicide is currently the second leading cause of death among adolescents ages 10-24. Despite decades of research, suicide attempt rates continue to rise across the U.S., particularly among adolescents. Furthermore, new data suggests that adolescents were disparately impacted by the COVID-19 pandemic, with some states reporting increased rates of suicide among youth, galvanizing the urgency for increased prevention. People who die by suicide often see healthcare providers, and specifically primary care providers prior to death, including adolescents. Therefore, identifying suicide risk in healthcare settings among adolescents is an important prevention opportunity.

Mental Health Research Network (MHRN) researchers (led by Greg Simon) have developed suicide risk prediction algorithms that have potential to vastly improve identification of individuals at high risk of suicide, including adolescents. While promising, there is very little evidence to guide routine use of this powerful suicide risk identification method during healthcare encounters with adolescents. A recently completed MHRN project (led by Bobbi Jo Yarborough) explored barriers and facilitators of the use of suicide risk algorithms among adult patients, clinicians, and administrators across three MHRN systems. These stakeholders were generally supportive of implementation, but some patient participants expressed concerns about suicide risk information resulting in coercive treatment, and clinician participants expressed desire for opportunities supporting their role in implementation decision-making.

No studies (to our knowledge) have explored perspectives of adolescents, their parents/guardians or adolescent providers about how suicide risk prediction models should be implemented. Therefore, we plan to build from prior MHRN work and qualitatively elicit adolescent care providers’ perceived barriers and facilitators to implementation of these models in care delivery and their ideologies regarding risk thresholds and risk-concordant care. Simultaneously, we plan to build a qualitative understanding adolescents and family perceptions, ideas, and preferences regarding the use of suicide risk prediction models in their care.

Research questions: (1) What perspectives do primary care providers have on suicide risk prediction algorithms and what suggestions or considerations do they have for clinical practice? (2) How do primary care providers envision risk concordant care delivery to look like in clinical practice? (3) What are adolescent and parent/caregiver perceptions and preferences on the use of suicide risk predications models as a tool for enhanced clinical care? (4) What ideas or suggestions do adolescents and parents/caregivers have for comfortable and effective implementation of risk prediction algorithms in primary care?

Methods: Provider interview guides will be developed based on interview findings by the prior qualitative MHRN study (described above) which used the Consolidated Framework for Implementation Research (CFIR), with additional questions aimed at understanding risk thresholds and associated concordant care. Caregiver and adolescent interviews will explore their thoughts, ideas, and preferences regarding EHR-based suicide risk prediction models as part of patient standard of care. We will aim to interview 10-15 adolescent care providers and 10-15 caregiver-adolescent dyads across the two sites. Care providers will be purposively selected in consultation with KPWA leaders involved in an initiative to improve adolescent access to timely mental health care. The suicide risk prediction algorithm will be used to purposively sample adolescents at high risk of suicide and their parent/guardian caregivers. Identified dyads will be recruited via mailed and telephone invitation materials (developed from a prior project recruiting adolescents & caregivers). Interviews will be audio-recorded, transcribed and double-coded to support thematic content analysis.

Planned products: A synthesis of stakeholder needs/perspectives to support suicide risk prediction model implementation in routine care delivery for adolescents. This key deliverable will be used to support: 1) current predictive analytic implementation efforts across MHRN sites 2) an external grant submission to NIMH focused on application of Human-Centered Design methods to design, build, and test clinical decision support for identifying and engaging adolescents at high-risk of suicide in evidence-based healthcare, 2) a peer-reviewed manuscript submission led by Taylor Ryan, MS (PhD student in Health Systems & Population Health at the University of Washington) & Julie Richards, MPH, PhD (MHRN researcher and faculty advisor at UW).

Lead Site: KPWA (PI Julie Richards)

Participating Sites: N/A

Current Status:

Summary of Findings:

Publications:

Syncing Screening and Services for Suicide Prevention across Health and Justice Systems

Grant Details

Title: Project 1: Syncing Screening and Services for Suicide Prevention across Health and Justice Systems

Funder: NIMH

Parent project number: 1P50MH127512

Sub-project ID: 8576

Project period: 08/22/2022 – 07/31/2027

Brief Narrative: This is a 5-year Signature Project within the NIMH-funded P50 Suicide Prevention Center, titled The National Center for Health and Justice Integration for Suicide Prevention. As suicide rates in the United States continue to rise, with nearly 50,000 suicide deaths and over 1 million suicide attempts annually per most recent data, increased attention has been paid to how to best integrate and coordinate suicide risk identification and prevention across multiple sectors, where some of our most vulnerable community members “fall through the cracks” in the continuum of care. Perhaps nowhere is this need for coordination and integration more pronounced than at the intersection of the US jail system, with over 10 million admissions per year, and the community healthcare system; an intercept known to impact individuals at disproportionately high risk for suicide. Given that roughly 10% of all suicides in the US with known circumstances occur following a recent criminal legal stressor (often arrest and jail detention), reducing suicide risk in the year after jail detention could have a noticeable impact on national suicide rates. There is thus a vital need to develop suicide risk care pathways between jails and healthcare systems to offer immediate access to care. Yet this process has been stymied by major fissures in the integration of data and clinical information between jails and health systems, preventing effective coordination of care between these community sectors. To address these needs, the proposed Signature Project is a Hybrid Type I effectiveness-implementation trial that harmonizes local jail booking and release data with healthcare records at two large healthcare systems in Minnesota and Michigan, to identify health system patients who are released from jail, and to pair the data linkage with randomization into usual care or a multi-level health system suicide prevention care pathway (consisting of care coordination, Safety Planning, Caring Contacts, and a telehealth delivered Coping Long- Term with Active Suicide Program). In so doing, this project leverages the study team’s experience in health system data linkage in the NIMH-funded Mental Health Research Network, from which the participating healthcare systems were chosen, as well as in suicide prevention around the period of jail detention and release (i.e., in the SPIRIT Trial), and in telephone-based suicide prevention intervention (i.e., in ED-SAFE). The proposed project will randomize 1050 individuals into the 5S intervention at both sites (comparing to more than 60,000 people in a usual care no contact comparison arm). Findings on suicide attempt and death outcomes, healthcare utilization mechanisms, cost- effectiveness, and implementation factors will provide data for a future fully scaled implementation trial and widespread adoption in community settings. Notably, the proposed Signature Project will be the first trial of a comprehensive health system intervention to prevent suicide in response to patients’ justice involvement.

  • Lead MHRN site: HFHS (PI: Brian Ahmedani)
  • Participating site: HPI (co-I: Rebecca Rossom)

Evaluating Effectiveness and Implementation of a Risk Model for Suicide Prevention Across Health Systems

Grant Details

Title: Evaluating Effectiveness and Implementation of a Risk Model for Suicide Prevention Across Health Systems

Funder: NIMH

Grant number: 1R01MH130548

Project period: 08/23/2022 – 05/31/2026

Brief Narrative: Suicide is a major public health concern in the United States; nearly 50,000 individuals die by suicide annually and almost 1.5 million attempt suicide. To date, identification of individuals at risk for suicide has relied on suicide risk screening practices, including using a variety of self- report instruments. However, sensitivity of these measures are only moderate; more precise tools for identifying patients at risk for suicide are needed. Suicide risk models, developed by our team, incorporate health records data and historical self-report screening questionnaire responses to improve accuracy of risk prediction. Our models have outperformed traditional clinical screening and similar risk models for adults receiving care in outpatient mental health specialty settings. However, while accurate, they have not been evaluated in real world care; whether the models actually increase identification or result in patients receiving more suicide prevention services, fewer crisis services, or making fewer suicide attempts is unknown. There is substantial clinical interest in implementing suicide risk models but little scientific evidence about the effectiveness of these models in real world settings compared to standard screening practices alone. Additionally, there is almost no guidance for their implementation in healthcare. The proposed project leverages the NIMH-funded Mental Health Research Network (MHRN), a collaboration of large health systems with established clinical data infrastructure to support multi-site studies. MHRN members Henry Ford Health System, Kaiser Permanente Northwest, and HealthPartners will participate in this project and collectively serve >170,000 behavioral health patients per year. The patient populations are diverse, including thousands of individuals with Medicaid and Medicare. Each of these systems has implemented a suicide prevention care model in their behavioral health departments, including robust suicide risk screening and assessment processes. However, none of these systems has implemented a suicide risk model. The proposed project includes a pragmatic trial approach with randomization of behavioral health clinics across the three participating health systems. It is innovative because it seeks to implement an MHRN suicide risk model (intervention) into each system’s existing suicide prevention care model (usual care) to increase the reach and effectiveness of the suicide prevention care models. Sites will receive implementation planning support based on stakeholder feedback from preliminary studies and deliverables include an implementation planning tool kit to facilitate spread. This high-impact study has important clinical implications as health systems consider whether it makes sense to enhance their existing suicide prevention care models with a suicide risk model. It is timely because many health systems are advancing toward suicide risk model implementation without evidence to support this innovation.

  • Lead site:
    • KPNW (PI Bobbi Jo Yarborough)
  • Participating sites:
    • HFHS (co-I Brian Ahmedani)
    • HPI (co-I Rebecca Rossom)

Population-based outreach to prevent suicide attempts: Too big a step?

Our randomized trial of outreach programs to prevent suicide attempts tested a long step beyond what we knew from previous research.  We hoped that low-intensity adaptations of proven effective interventions – delivered primarily online – could scale up to prevent suicide attempts at the population level.  And we were wrong.  Not only did neither of the programs we tested prevent self-harm or suicide attempts, one of them may have increased risk.

Looking back, we can say that we tried too long a step beyond interventions proven to work.  We can try to unpack that long step into a few smaller pieces.  First, our trial included the broad population of people at increased risk (where most suicide attempts occur) rather than the much smaller population of people at highest risk (where previous interventions had been tested).  Second, we emphasized outreach to people who were not seeking additional help rather than limiting to volunteers who agreed in advance to accept the extra services we were offering.  Third, we tested low-intensity interventions, delivered primarily by online messaging rather than more personal and intensive interventions delivered by telephone or face-to-face.

We could have started by separately testing each of those smaller steps rather than trying to cross the creek all at once.  But any smaller trial testing one of those small steps would have taken two or three years.  Testing one smaller step after another would have taken even longer.  Given rising suicide mortality rates throughout the 2010s, we chose not to wait several years before trying a large step.  We believed the programs we tested were close enough to the solid ground of proven interventions, and we certainly hoped they would expand the reach of effective prevention.

Regardless of the time required, it may not have been helpful to divide that big step into smaller pieces.  We could have limited the trial to people at highest risk, but then we would not have studied low-intensity online interventions.  We could have limited the trial to people who agreed in advance to accept extra services, but then we would not have studied outreach interventions.

After we published our findings, we did hear questions and suggestions about each piece of the big step we tried:  Why not focus on those at highest risk?  Why not test more intense or robust interventions?  Why include people who were not interested in the treatments you were offering?  But if we’d done all of those things, we would have just replicated research that was already done – and ended up right back where we started.  Back in 2015, we already knew that traditional clinical interventions, like Dialectical Behavior Therapy, could decrease risk in treatment-seeking people with recent self-harm or hospitalization.  Replicating that evidence would not inform population-based prevention programs for the broader population of people at increased risk.     

We are certainly not giving up on the idea of population-based programs to prevent suicidal behavior.  So we’re thinking about ways to try smaller steps.  Rather than small steps, we may need to look for a completely new place to get across the creek.  Our suggestion box is open.

Greg Simon

Reduce Racial/Ethnic Disparities in Suicide Risk Prediction (RED)

Grant Details

Title: Innovative methods to reduce racial and ethnic disparities in suicide risk prediction

Funder: NIMH

Grant number: 1R01MH125821

Grant period: 1/1/2022 – 12/31/2025

Brief Narrative: Suicide risk prediction models are being used by health care systems to guide delivery of suicide prevention interventions, but these prediction models may not accurately identify high-risk patients in racial and ethnic subgroups that are less prevalent or have lower rates of suicide attempt and death. This project will reduce racial and ethnic disparities in suicide risk models by developing methods for prediction model estimation that optimize performance within subgroups, rather than across the whole population, and adjust for misclassification of suicide outcomes. We will also design sample size calculations that evaluate the ability of a prediction study to accurately identify high-risk individuals within racial and ethnic subgroups.

  • Lead site:
    • KPWA (PI Yates Coley)
  • Participating sites:
    • University of Washington (Co-I Noah Simon)
    • KPSC (Co-I Karen Coleman)

Awarded budget (total cost): $1,622,626

Human Subjects: Reviewed by KPWA IRB, IRBNet# 1870253

Current status

Statistical methods research is underway. IRB and data use approvals are in place for all planned analyses. Current activities are focused on methods for accounting for outcome misclassification; evaluating variable importance in suicide prediction models; and designing estimation methods to optimize performance in racial/ethnic subgroups.

Summary of findings

Publications

Pragmatic Trial of Stepped Care for Adolescent Suicide Prevention (Youth SPOT)

Grant Details

Funder: Patient-Centered Outcomes Research Institute (PCORI)

Contract Number: PLACER-2020C3-20902

Project Period: 12/01/2021 – 11/30/2027

Brief narrative:

Adolescent suicide is the second leading cause of death in teenagers. Preventing suicide in teens would keep them safe, allow them to get the mental health help that they need, and also protect families, friends, and communities from grief and loss. There are several programs that have been shown to work for preventing suicide, including an approach called dialectical behavior therapy (DBT). However, the studies done so far are so small that it is still unknown whether DBT works for all groups of teens—teens at medium risk versus those at very high risk, boys versus girls, younger versus older teens—or whether different approaches may work better for some groups. This is important information, because it would help teens and their families to make the best choices from several suicide prevention program options. Hospitals, clinics, doctors, and therapists also need information about what suicide prevention services work best and should be made more available. The goal of this study is to answer these questions.

The first aim, which will be completed in the first 18 months of the project, will be to plan the main study comparing two approaches to suicide prevention in collaboration with young people who have lived with suicidal behavior, their parents, doctors, and therapists. The second aim will be to compare how well these two approaches work to prevent suicide attempts in a group of 9,800 teens. The third aim is to see whether the two approaches lead to differences in the mental health care each teen receives—like being hospitalized, taking medications, seeing therapists, and so on—and to see which program works best for different groups, such as young men versus young women, or Hispanic teens and those who are not Hispanic, as well as what works best for teens who are at medium, medium-high, and high risk for suicide.

The first suicide prevention approach is called “stepped care,” and offers three levels of services to teens, depending on their level of risk. Medium-risk teens will be offered monthly phone check-ins; medium-high risk teens will also be offered a chance to work with a therapist to create and use safety plans that spell out how teens can keep themselves safe and what they will do if they feel suicidal. Teens at the highest level of risk will also be offered DBT group therapy for six months. The second suicide prevention approach is called Zero Suicide (ZS) care. This program is used by many healthcare clinics, hospitals, and therapy centers across the United States. It encourages therapists and doctors to ask about suicide frequently, and to make sure that teens who are at risk of suicide are connected to the best health care available, which might be regular therapy, medications, or a combination of the two.

To determine who to include in this study, the team will use a computer program to predict the chance that a teen will make a suicide attempt in the next six months. This program uses data collected by the healthcare system and is about 85 percent accurate. Teens who are at medium or high risk of suicide based on the computer program will be assigned by chance, like the flip of a coin, to one of two suicide prevention approaches. The team will use healthcare and government databases to see what happens for teens over 12 months so the team can compare rates of suicide attempts, self-harm, and healthcare use.

The goal is to help teens to be treated in a way that allows them the most personal freedom. The results from this study will help health insurers and clinics decide what kinds of suicide prevention care to offer and to cover. They will also help doctors and therapists decide what approaches to recommend to patients, and help individual teens and their families decide what kind of care to receive. The team will share its results with researchers, healthcare organizations, and national groups that advocate for youth suicide prevention to make sure that they will have the information they need to make choices about the best suicide prevention options for all types of teens.

  • Lead Sites:
    • KPNW (Clinical Coordinating Center, co-PI Greg Clarke)
    • KPGA (Data Coordinating Center, co-PI Courtney McCracken)
  • Participating Sites:
    • KPWA (site PI Rob Penfold)
    • HealthPartners (site PI Rebecca Rossom)
    • Georgia State University (site PI Ashli Owen-Smith)
    • UCLA (site PI Joan Asarnow)
    • California State Lutheran University (Site PI Jamie Bedics)

Awarded Budget (total cost): $21,324,820

Funding Announcement

Personnel Contact List

Human Subjects: YES

Current status

Pilot testing of outreach and intervention delivery will begin in October 2022.

Summary of findings

Publications

MHRN III Pilot Project 1: Stakeholder Views on Implementation of Suicide Risk Prediction Models

Grant Details

Funder: NIMH

Grant Number: U19MH121738

Grant Period: 09/24/2019 – 6/30/2021

Narrative: Age-adjusted suicide rates have been increasing in the U.S. over the past two decades. In 2017, more than 47,000 Americans died of suicide. Health care visits represent opportunities for suicide prevention because most individuals make an outpatient health care visit within a year of their suicide death and almost half have a visit within a month of their death. However, suicide risk is not always easily recognizable to clinicians—traditional clinical prediction is hardly better than chance. Predictive modeling that identifies patterns in “big data” from administrative and electronic health records has proven superior to clinical suicide risk prediction and routinely used suicide screening instruments. While predictive modeling holds promise for suicide prevention, how models should be implemented in routine clinical practice and the contextual factors that influence their use are understudied. The potential benefits of any risk prediction model, including those designed to identify suicide risks, are dependent on making sure that the models are deployed in a manner that does not harm patients, supports clinical care management, and is sustainable for health care delivery systems. We propose a pre-implementation pilot study in three settings, using one-on-one, in-depth interviews to explore health system administrators’, clinicians’, and patients’ expectations, experiences with, concerns, and suggestions for the early use of suicide risk prediction models. In the first setting, health system administrators are still considering what might be the best implementation approach. Interviews will help us understand how various stakeholder expectations match what is actually occurring in the two other settings where small pilot studies will be in process. One of these settings is planning outreach to high-risk patients independent of health care visits while the other is planning delivery of risk scores at the point of care. By studying different implementation strategies, we can compare relative advantages and disadvantages. We are particularly interested in effects on clinical workflows, clinician-patient relationships, and patient experiences. While there is an emerging literature supporting the promise of predictive models in health care, implementation factors and patient impacts have been largely ignored. Yet decisions regarding design and modeling methods and implementation processes should be driven by stakeholder requirements. Results of this pilot study will have important clinical implications and will not only inform large-scale implementation of suicide risk prediction models in health systems across the country but will also inform development of future risk prediction models and associated care processes tailored to stakeholders needs more generally (not limited to suicide risk). The long-term goals of this pilot project are to inform ongoing health system-level efforts to reduce suicide prevalence and prevent suicides by optimizing the use of suicide risk prediction tools.

  • Lead Site:
    • Overall PI: KPNW (Bobbi Jo Yarborough)
  • Participating Sites/Subcontractors:
    • HPI (site project lead Rebecca Rossom)
    • KPWA (site project lead Julie Richards; site PI Greg Simon)
  • Funder Contacts
    • Science Officer: Susan Azrin
    • Program Official: Michael Freed
    • Grants Management Official: Julie Bergerud

Documents

Funding Announcement

Notice of Award

Personnel Contact List

Current Status

We have completed and analyzed interviews with 10 health care administrators, 30 clinicians in behavioral health departments, and 62 patients across three health systems.

Summary of Findings

Administrators and clinicians

  • Use of a suicide risk prediction model and two differing implementation approaches were acceptable.
  • Clinicians desired opportunities for input on implementation decision-making.
  • They wanted to know how this manner of risk identification enhanced existing suicide prevention efforts.
  • They wanted additional training on how the models determined risk and why some patients appeared at risk while others do not.
  • Clinicians were concerned about lack of suicide prevention resources for newly identified patients.
  • They wanted clear procedures for situations when they could not reach patients or when patients remained at-risk over a sustained period.
  • They would like consolidated suicide risk information in a dedicated module in the EHR to increase efficiency.

Patients

  • Patients were generally supportive of suicide risk prediction models derived from EHR data.
  • Concerns included: 1) apprehension about inducing anxiety and suicidal thoughts, or 2) triggering coercive treatment, particularly among those who reported prior negative experiences seeking mental health care.
  • Participants engaged in mental health care or case management expected to be asked about suicide risk and largely appreciated suicide risk conversations
  • Patients preferred conversations to come from clinicians comfortable discussing suicidality.

Publications

Yarborough BJH, Stumbo SP. Patient perspectives on acceptability of, and implementation preferences for, use of electronic health records and machine learning to identify suicide risk. Gen Hosp Psychiatry. 2021 May-Jun;70:31-37. doi: 10.1016/j.genhosppsych.2021.02.008.

Yarborough BJH, Stumbo SP, Schneider JL, Richards JE, Hooker SA, Rossom RC . Patient expectations of and experiences with a suicide risk identification algorithm in clinical practice. BMC Psychiatry. 2022 Jul 23;22(1):494. doi: 10.1186/s12888-022-04129-1 .

MHRN III Infrastructure: Methods Core

Grant Details

Funder: NIMH

Grant Number: U19MH121738

Grant Period: 09/23/2019 – 06/30/2020

Narrative: The Methods Core will include an Informatics Unit, led by Drs. Gregory Simon and Christine Stewart, and a Scientific Analysis Unit, led by Drs. Susan Shortreed and Patrick Heagerty. The Informatics Unit will continue highly successful work over the past 8 years, supporting routine data quality assessment and descriptive analyses of diagnosis and treatment patterns across all participating health systems. New work will include development of tools and resources to assess and minimize privacy risks when sharing sensitive health data for research and development of specific new data areas (perinatal mental health and prenatal exposures, expanded list of patient-reported outcomes, and assessments of social determinants of health). The Informatics Unit will provide consultation to all MHRN core and affiliated projects and share all resources with other researchers and health systems via MHRN’s public repository of specifications, code lists, and analytic code. The Scientific Analysis Unit will support to all MHRN core and affiliated projects via project-specific consultation and development of a learning community of analysts and biostatisticians across MHRN research centers. This Unit will also focus on development and dissemination of analytic methods in two areas directly relevant to MHRN research. Work on evaluating adaptive treatment strategies will build on Dr. Shortreed’s recently funded methods grant to evaluate and disseminate methods for using health system data to tailor treatments for individuals with more chronic or severe mental health conditions, focusing on assessing treatment effects when treatments are adjusted or switched according to previous treatment failures or adverse effects. Work on stakeholder-driven predictive analytics will build on MHRN’s development of accurate suicide risk prediction models, focusing on matching specific study designs and model development methods with stakeholder priorities and implementation constraints.

Lead Site: KPWA (PI Greg Simon)

Participating Sites: University of Washington (Site PI Patrick Heagerty) 

  • Funder Contacts
    • Science Officer: Susan Azrin
    • Program Official: Michael Freed
    • Grants Management Official: Jackie Chia

Documents & Reports

Submitted Proposal

Specific Aims

Research Plan

Notice of Award

Personnel Contact List

Publications