Pilot Testing Suicide Risk Prediction Algorithms in Primary Care

NCT07068685 | Enrolling By Invitation

• 2 other identifiers: 2019330R34MH132829
• Study Type: interventional
• Target: 500,000
• Locations: 1 country
• Sites: 1

Brief Summary

The goal of this pilot study is to learn whether the use of suicide risk prediction algorithms in primary care can help identify people who may benefit from extra mental health monitoring. Specifically, this study aims to measure how use of the suicide risk prediction algorithm to prompt extra mental health monitoring among adult primary care patients impacts proportions of patients identified at risk of suicide and engaged in safety planning. Secondarily, we plan to measure proportions of patients identified at risk of suicide via mental health monitoring (irrespective of engagement in safety planning).

Conditions

Suicide Prevention; Suicide Risk | Patient

Outcome Measures

Primary Outcomes (1)

• Suicide Risk Safety Plan Documentation

  Indicator for whether a patient was identified at risk of suicide (using the PHQ-9 and C-SSRS) and had a safety planning intervention documented in the EMR on the day of, or in the following 14 days of a primary care encounter, using a standardized template based on the brief suicide risk safety plan intervention developed by Drs. Stanley \& Brown to mitigate risk

  Rates for primary care encounters will be compared before and after implementation, during the 13 month study period 3/05/2025-4/05/2026 (implementation launch 10/6/2025)

Secondary Outcomes (4)

• Suicidal ideation symptom assessment

  Rates of assessment for primary care encounters will be compared before and after implementation, during the 13 month study period 3/05/2025-4/05/2026 (implementation launch 10/6/2025)

• Prior month intent/planning for suicide attempt

  Rates for primary care encounters will be compared before and after implementation, during the 13 month study period 3/05/2025-4/05/2026 (implementation launch 10/6/2025)

• Suicide risk assessment

  Rates for primary care encounters will be compared before and after implementation, during the 13 month study period 3/05/2025-4/05/2026 (implementation launch 10/6/2025)

• Frequent suicidal ideation reported (in prior 2-weeks)

  Rates for primary care encounters will be compared before and after implementation, during the 13 month study period 3/05/2025-4/05/2026 (implementation launch 10/6/2025)

Study Arms (2)

Suicide risk monitoring

EXPERIMENTAL

Quality improvement intervention: 6 months following implementation of the suicide risk prediction algorithm in primary care to prompt extra mental health monitoring.

Other: Suicide risk prediction algorithm

Usual Care

NO INTERVENTION

Interventions

Suicide risk prediction algorithm OTHER

Use of a suicide risk prediction algorithm, developed by the Mental Health Research Network (MHRN), will be used to prompt additional mental health monitoring. Mental health monitoring will include asking patients about suicidal thoughts (via the ninth question of the Patient Health Questionnaire-9, PHQ-9), followed by suicide risk assessment (via use of a brief self-administered version of the Columbia Suicide Risk Severity Rating Scale, C-SSRS), followed by Safety Planning with a designated member of the primary care team.

Also known as: suicide care clinical decision support

Suicide risk monitoring

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

Sponsors & Collaborators

• Kaiser Permanente: lead
• National Institute of Mental Health (NIMH): collaborator
• University of Washington: collaborator

Study Sites (1)

Kaiser Permanente Washington Health Research Institute

Seattle, Washington, 98101, United States

Location

MeSH Terms

Conditions

Suicide Prevention

Condition Hierarchy (Ancestors)

Suicide; Self-Injurious Behavior; Behavioral Symptoms; Behavior

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: NON RANDOMIZED
• Masking: NONE
• Purpose: HEALTH SERVICES RESEARCH
• Intervention Model: CROSSOVER
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Model Details: Retrospective pre-post design

Study Record Dates

• First Submitted: July 2, 2025
• First Posted: July 16, 2025
• Study Start: March 5, 2025
• Primary Completion: April 30, 2026
• Study Completion (Estimated): April 1, 2027
• Last Updated: March 20, 2026

Record last verified: 2026-03

Data Sharing

• IPD Sharing: Will not share

Locations

US (1)