Lauren M. Weinstock
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Lauren M. Weinstock has a total of 307 co-authors. Here are the top co-authors by number of shared publications:
Ivan W. Miller
Department of Psychiatry and Human Behavior, The Warren Alpert Medical School, Brown University, Providence, Rhode Island
22 shared publications- Shirley Yen
Harvard Medical School Beth Israel Deaconess Medical Center Boston Massachusetts USA
13 shared publications - Heather Hower
University of California San Diego (UCSD) La Jolla California USA
10 shared publications - Brandon A. Gaudiano
Brown University
9 shared publications Michael Strober
David Geffen School of Medicine, University of California at Los Angeles, Los Angeles, California
9 shared publicationsMary Kay Gill
UPMC Western Psychiatric Hospital, University of Pittsburgh, Pittsburgh, Pennsylvania
8 shared publications
Latest Publications
- Open Access
- 21 June 2026
- Published by Center for Open Science in PsyArXiv
Development of a Consensus Statement to Guide AI Chatbot Responses to Suicide Risk Disclosure
Importance: Adults and youth are increasingly confiding in generative artificial intelligence (AI) chatbots for help with suicidal thoughts, but there is no guidance on best practices for chatbot responses to suicide risk disclosure. Additionally, there are no taxonomies of potential harms, benefits, or contextual factors that may impact these responses. Objective: To develop a consensus statement to guide AI chatbot responses to suicide risk disclosure and taxonomize potential harms, benefits, and contexts. Design: An online modified Delphi study, informed by a systematic literature review, included two surveys and an intervening meeting (February-May 2026). Individuals with financial conflicts of interest (COIs) offered input but were not included in consensus determinations. Setting: Surveys were anonymous and the meeting was virtual.Participants: Contributors included experts in suicide prevention, digital technologies, AI chatbots, and bioethics, including researchers and clinicians (n=27 of 28 originally contacted; n=20 without COIs) and people with lived experience (n=3 of 14 indicating potential interest; no COIs). A third of all contributors endorsed relevant lived experience. Exposure: Participation in consensus processes. Main Outcomes and Measures: Surveys listed potential chatbot responses, which were rated for appropriateness on a 4-point Likert scale across five suicide risk levels defined by the Columbia Suicide Severity Rating Scale. Harms, benefits, and contexts were similarly rated. A-priori consensus cut-offs were set at 70% agreement that a response was moderately or very appropriate. Results: Provision of validation/support, psychoeducation, and coping strategies are appropriate at low risk. Intervention delivery is appropriate at intermediate risk while encouragement to reach out to close others and to human providers is appropriate across risk levels. Facilitating connections to close others is appropriate across all but the highest risk while facilitating connections to crisis resources is appropriate at higher risk. Chatbots reaching out directly to emergency contacts or crisis resources is appropriate at high risk or never appropriate, with more support among youth than adults. Taxonomies of potential harms, benefits, and contexts were generated. Conclusions and Relevance: This statement provides guidance for the development of chatbots and relevant policies pending research on the impact of responses on clinical outcomes and stakeholder perspectives.
- 21 June 2026
- Published by Center for Open Science in PsyArXiv
Open AccessDevelopment of a Consensus Statement to Guide AI Chatbot Responses to Suicide Risk Disclosure
Importance: Adults and youth are increasingly confiding in generative artificial intelligence (AI) chatbots for help with suicidal thoughts, but there is no guidance on best practices for chatbot responses to suicide risk disclosure. Additionally, there are no taxonomies of potential harms, benefits, or contextual factors that may impact these responses. Objective: To develop a consensus statement to guide AI chatbot responses to suicide risk disclosure and taxonomize potential harms, benefits, and contexts. Design: An online modified Delphi study, informed by a systematic literature review, included two surveys and an intervening meeting (February-May 2026). Individuals with financial conflicts of interest (COIs) offered input but were not included in consensus determinations. Setting: Surveys were anonymous and the meeting was virtual.Participants: Contributors included experts in suicide prevention, digital technologies, AI chatbots, and bioethics, including researchers and clinicians (n=27 of 28 originally contacted; n=20 without COIs) and people with lived experience (n=3 of 14 indicating potential interest; no COIs). A third of all contributors endorsed relevant lived experience. Exposure: Participation in consensus processes. Main Outcomes and Measures: Surveys listed potential chatbot responses, which were rated for appropriateness on a 4-point Likert scale across five suicide risk levels defined by the Columbia Suicide Severity Rating Scale. Harms, benefits, and contexts were similarly rated. A-priori consensus cut-offs were set at 70% agreement that a response was moderately or very appropriate. Results: Provision of validation/support, psychoeducation, and coping strategies are appropriate at low risk. Intervention delivery is appropriate at intermediate risk while encouragement to reach out to close others and to human providers is appropriate across risk levels. Facilitating connections to close others is appropriate across all but the highest risk while facilitating connections to crisis resources is appropriate at higher risk. Chatbots reaching out directly to emergency contacts or crisis resources is appropriate at high risk or never appropriate, with more support among youth than adults. Taxonomies of potential harms, benefits, and contexts were generated. Conclusions and Relevance: This statement provides guidance for the development of chatbots and relevant policies pending research on the impact of responses on clinical outcomes and stakeholder perspectives.
- Open Access
- 6 May 2026
- Published by Elsevier in Journal of Affective Disorders
- Vol. 409, 121922
Feasibility and acceptability of Interpersonal Social Rhythm Therapy (IPSRT) for perinatal bipolar disorder
- 6 May 2026
- Published by Elsevier in Journal of Affective Disorders
- Vol. 409, 121922
Open AccessFeasibility and acceptability of Interpersonal Social Rhythm Therapy (IPSRT) for perinatal bipolar disorder
- Open Access
- 25 March 2026
- Published by Elsevier in Journal of Psychiatric Research
- Vol. 198, 175-181
Who's getting care? Acute treatment utilization following an emergency department visit among adults with major psychiatric disorders and suicidal thoughts and behaviors
- 25 March 2026
- Published by Elsevier in Journal of Psychiatric Research
- Vol. 198, 175-181
Open AccessWho's getting care? Acute treatment utilization following an emergency department visit among adults with major psychiatric disorders and suicidal thoughts and behaviors
- Open Access
- 7 March 2026
- Published by Wiley in Bipolar Disorders
- Vol. 28 (2) , e70099
Psychological Therapies and the Bipolar Disorder ‘Iceberg’: Going Deeper Than Current Mood and Relapse Prevention Planning
- 7 March 2026
- Published by Wiley in Bipolar Disorders
- Vol. 28 (2) , e70099
Open AccessPsychological Therapies and the Bipolar Disorder ‘Iceberg’: Going Deeper Than Current Mood and Relapse Prevention Planning
- Open Access
- 10 January 2026
- Published by Springer Nature in Pilot and Feasibility Studies
- Vol. 12 (1)
Implementing a peer navigation program for individuals with serious mental illness in the criminal legal system: insights and lessons learned
Peer-provided services play a crucial role in healthcare delivery across health care issues. This study describes the process of implementing a peer naviga
- 10 January 2026
- Published by Springer Nature in Pilot and Feasibility Studies
- Vol. 12 (1)
Open AccessImplementing a peer navigation program for individuals with serious mental illness in the criminal legal system: insights and lessons learned
Peer-provided services play a crucial role in healthcare delivery across health care issues. This study describes the process of implementing a peer naviga
- Open Access
- 3 November 2025
- Published by American Medical Association (AMA) in JAMA Network Open
- Vol. 8 (11) , e2543156
Safety Planning vs Standard Care for Suicide Prevention After Pretrial Jail Detention
Importance: In the US, 1 in 5 adult suicide decedents has spent at least 1 night in jail in the year prior to death. Objective: To evaluate the effectiveness of the Safety Planning Intervention (SPI) with telephone follow-up as an adjunct to enhanced standard care (ESC) compared with ESC alone for reducing suicide events in the 12 months following release from pretrial jail detention. Design, Setting, and Participants: This randomized clinical trial included individuals with past 30-day suicide risk (suicide ideation with intent and/or suicide attempt) in pretrial jail detention who were recruited from 2 jails from May 11, 2016, to November 13, 2018, with a 12-month follow-up after release. Data analysis was completed from April 2023 to May 2025. Interventions: All participants received ESC. The SPI included a safety planning session in jail followed by 4 to 8 telephone calls 6 months after jail release. Main Outcomes and Measures: The primary outcome was the number of suicide events (a composite of suicide attempts and behaviors, suicide-related hospitalizations, and suicide deaths). Secondary outcomes included the number of suicide attempts, weeks and severity of active suicidal ideation, time to first suicide event, psychiatric symptoms, functioning, and hypothesized mediators. Suicidal ideation and behaviors were assessed using the Columbia-Suicide Severity Rating Scale, the Longitudinal Interval Follow-Up Evaluation, and record reviews from area hospitals. Deaths were identified through hospital, state, and national death records. Hospitalizations were measured with the Treatment History Interview and hospital records. Results: Of 800 participants randomized in jail, 655 (mean [SD] age, 33.0 [10.4] years; 473 males [72%]) were released to the community and included in analyses. Of those, 593 (91%) completed at least 1 follow-up interview. Medical records were available for all 655 participants (100%). Per person-year of follow-up over 12 months, those in the SPI group compared with those in the ESC group had 42% fewer suicide events (mean [SE], 1.82 [0.18] vs 3.11 [0.32]; mean [SE] difference, −1.30 [0.37]; P < .001), 55% fewer suicide attempts (mean [SE], 1.06 [0.14] vs 2.35 [0.33]; mean [SE] difference, −1.33 [0.38]; P < .001). Differences in weeks of suicidal ideation were not statistically significant (mean [SE], 10.39 [0.78] vs 12.86 [1.02]; mean [SE] difference, −2.47 [1.28]; P = .06). There were no other observed differences in outcomes. Conclusions and Relevance: In this randomized clinical trial of the SPI compared with ESC, those in the SPI group experienced reduced suicide risk by 42% in the year after jail release. These results suggest that SPI is effective for reducing suicide risk during this high-risk period. Trial Registration: ClinicalTrials.gov Identifier: NCT02759172
- 3 November 2025
- Published by American Medical Association (AMA) in JAMA Network Open
- Vol. 8 (11) , e2543156
Open AccessSafety Planning vs Standard Care for Suicide Prevention After Pretrial Jail Detention
Importance: In the US, 1 in 5 adult suicide decedents has spent at least 1 night in jail in the year prior to death. Objective: To evaluate the effectiveness of the Safety Planning Intervention (SPI) with telephone follow-up as an adjunct to enhanced standard care (ESC) compared with ESC alone for reducing suicide events in the 12 months following release from pretrial jail detention. Design, Setting, and Participants: This randomized clinical trial included individuals with past 30-day suicide risk (suicide ideation with intent and/or suicide attempt) in pretrial jail detention who were recruited from 2 jails from May 11, 2016, to November 13, 2018, with a 12-month follow-up after release. Data analysis was completed from April 2023 to May 2025. Interventions: All participants received ESC. The SPI included a safety planning session in jail followed by 4 to 8 telephone calls 6 months after jail release. Main Outcomes and Measures: The primary outcome was the number of suicide events (a composite of suicide attempts and behaviors, suicide-related hospitalizations, and suicide deaths). Secondary outcomes included the number of suicide attempts, weeks and severity of active suicidal ideation, time to first suicide event, psychiatric symptoms, functioning, and hypothesized mediators. Suicidal ideation and behaviors were assessed using the Columbia-Suicide Severity Rating Scale, the Longitudinal Interval Follow-Up Evaluation, and record reviews from area hospitals. Deaths were identified through hospital, state, and national death records. Hospitalizations were measured with the Treatment History Interview and hospital records. Results: Of 800 participants randomized in jail, 655 (mean [SD] age, 33.0 [10.4] years; 473 males [72%]) were released to the community and included in analyses. Of those, 593 (91%) completed at least 1 follow-up interview. Medical records were available for all 655 participants (100%). Per person-year of follow-up over 12 months, those in the SPI group compared with those in the ESC group had 42% fewer suicide events (mean [SE], 1.82 [0.18] vs 3.11 [0.32]; mean [SE] difference, −1.30 [0.37]; P < .001), 55% fewer suicide attempts (mean [SE], 1.06 [0.14] vs 2.35 [0.33]; mean [SE] difference, −1.33 [0.38]; P < .001). Differences in weeks of suicidal ideation were not statistically significant (mean [SE], 10.39 [0.78] vs 12.86 [1.02]; mean [SE] difference, −2.47 [1.28]; P = .06). There were no other observed differences in outcomes. Conclusions and Relevance: In this randomized clinical trial of the SPI compared with ESC, those in the SPI group experienced reduced suicide risk by 42% in the year after jail release. These results suggest that SPI is effective for reducing suicide risk during this high-risk period. Trial Registration: ClinicalTrials.gov Identifier: NCT02759172
- Open Access
- 25 June 2025
- Published by JMIR Publications Inc. in JMIR Research Protocols
- Vol. 14 (1) , e68517
Suicide Risk Screening in Jails: Protocol for a Pilot Study Leveraging the Mental Health Research Network Algorithm and Health Care Data
Background: Suicide in local jails occurs at a higher rate than in the general population, requiring improvements to risk screening methods. Current suicide risk screening practices in jails are insufficient: They are commonly not conducted using validated screening instruments, not collected by clinically trained professionals, and unlikely to capture honest responses due to the chaotic nature of booking areas. Therefore, new technologies could improve such practices. Several studies have indicated that machine learning (ML) models considerably improve accuracy and have positive predictive value in detecting suicide risk compared with practice as usual (PAU). This study will use administrative data and ML modeling to improve suicide risk detection at jail booking. Objective: This study is primarily focused on gathering preliminary information about the feasibility and practicality of using administrative data and ML modeling for suicide risk detection but also incorporates elements of hypothesis testing pertaining to clinical outcomes. Methods: The study uniquely contributes to our understanding of suicide risk by further validating an existing ML model developed and previously validated by the Mental Health Research Network using Medicaid outpatient health care claims data. This validation uses complete claims data on a sample of approximately 6000 individuals booked into 2 diverse jails in a midwestern state. This model validation uses 313 unique demographic and clinical characteristics from 5 years of historical health care data. It detects suicide risk in jails and postrelease by using merged jail, Medicaid, and vital records data. The study will use jail administrative data for September 1, 2021, through February 28, 2022; Medicaid records data for September 1, 2016, through March 31, 2023; and vital records data for March 1, 2022, through March 31, 2023. Results: First, the algorithm will be validated on the data gathered for the jail sample using the C-statistic and area under the receiver operating characteristic curve. Second, the resulting model will be compared with the jails’ suicide identification PAU to assess risk and detection of identified suicide attempts and deaths from intake through 120 days and 13 months after jail release. The funding timeline for this project is August 1, 2022, through July 31, 2025. The algorithm’s predictions and actual event incidence will be linked and validated in the spring of 2025, with results ready for publication in the fall of 2025. Conclusions: The study will also investigate implementation factors, such as feasibility, acceptability, and appropriateness, to optimize jail uptake. Interview data on the implementation factors will be gathered in the summer of 2025, with expected dissemination in 2026. We hypothesize that a combination of intake screening PAU and the ML model will be the optimal approach, in that the combination will be more accurate and can have practical application in this context. International Registered Report Identifier (IRRID): DERR1-10.2196/68517
- 25 June 2025
- Published by JMIR Publications Inc. in JMIR Research Protocols
- Vol. 14 (1) , e68517
Open AccessSuicide Risk Screening in Jails: Protocol for a Pilot Study Leveraging the Mental Health Research Network Algorithm and Health Care Data
Background: Suicide in local jails occurs at a higher rate than in the general population, requiring improvements to risk screening methods. Current suicide risk screening practices in jails are insufficient: They are commonly not conducted using validated screening instruments, not collected by clinically trained professionals, and unlikely to capture honest responses due to the chaotic nature of booking areas. Therefore, new technologies could improve such practices. Several studies have indicated that machine learning (ML) models considerably improve accuracy and have positive predictive value in detecting suicide risk compared with practice as usual (PAU). This study will use administrative data and ML modeling to improve suicide risk detection at jail booking. Objective: This study is primarily focused on gathering preliminary information about the feasibility and practicality of using administrative data and ML modeling for suicide risk detection but also incorporates elements of hypothesis testing pertaining to clinical outcomes. Methods: The study uniquely contributes to our understanding of suicide risk by further validating an existing ML model developed and previously validated by the Mental Health Research Network using Medicaid outpatient health care claims data. This validation uses complete claims data on a sample of approximately 6000 individuals booked into 2 diverse jails in a midwestern state. This model validation uses 313 unique demographic and clinical characteristics from 5 years of historical health care data. It detects suicide risk in jails and postrelease by using merged jail, Medicaid, and vital records data. The study will use jail administrative data for September 1, 2021, through February 28, 2022; Medicaid records data for September 1, 2016, through March 31, 2023; and vital records data for March 1, 2022, through March 31, 2023. Results: First, the algorithm will be validated on the data gathered for the jail sample using the C-statistic and area under the receiver operating characteristic curve. Second, the resulting model will be compared with the jails’ suicide identification PAU to assess risk and detection of identified suicide attempts and deaths from intake through 120 days and 13 months after jail release. The funding timeline for this project is August 1, 2022, through July 31, 2025. The algorithm’s predictions and actual event incidence will be linked and validated in the spring of 2025, with results ready for publication in the fall of 2025. Conclusions: The study will also investigate implementation factors, such as feasibility, acceptability, and appropriateness, to optimize jail uptake. Interview data on the implementation factors will be gathered in the summer of 2025, with expected dissemination in 2026. We hypothesize that a combination of intake screening PAU and the ML model will be the optimal approach, in that the combination will be more accurate and can have practical application in this context. International Registered Report Identifier (IRRID): DERR1-10.2196/68517
- Open Access
- 25 May 2025
- Published by SAGE Publications in The Canadian Journal of Psychiatry
- Vol. 70 (8) , 639-648
Criminal Justice System Contacts among Suicide Decedents in Toronto, 1998-2020: An Observational Study: Démêlés avec le système de justice pénale parmi les personnes décédées par suicide à Toronto, entre 1998 et 2020 : Une étude d’observation
Objective: This exploratory correlational study explored the demographic, clinical, and offence-type characteristics of people with documented past-year contact with the criminal justice system (CJS) in Toronto, Canada who died by suicide. We aimed to compare demographic and clinical factors among individuals with CJS contact who died by suicide to those without recorded CJS contact who died by suicide. Methods: Coroners’ final death reports from all recorded suicide deaths in Toronto between 1 January 1998 and 31 December 2020 were retrieved by research staff and coded at the Office of the Chief Coroner (OCC) of Ontario. A series of bivariate analyses and binary logistic regression analyses were performed to compare demographic and clinically relevant characteristics between these groups. Descriptive statistics relating to demographic, clinical, and offence-type characteristics were reported. Results: A total of 5,288 people died by suicide, of whom 251 (4.7% of all suicides) had recorded CJS contact prior to death. Assault, physical assault, impaired driving, serious/death threats, and sexual assault were the most common criminal charges among those in the CJS contact group. When compared with the no recorded CJS contact group, the CJS contact group was slightly younger ( M = 40.0, SD = ±13.4 vs. M = 47.5, SD = ±18.1, p < 0 .001 ), had a higher proportion of males (85.6% vs. 69.9%, p < 0 .001 ), more commonly experienced interpersonal (36.3% vs. 14.5%, p < 0 .001 ) and/or relationship break-up/breakdown stressors (16.7% vs. 7.5%, p < 0 .001 ), and substance misuse or substance use disorders (37.5% vs. 18%, p < 0 .001 ). Conclusions: Our findings highlight that younger men with interpersonal stressors and/or substance misuse characterize suicide decedents with recorded CJS contact in Toronto, Canada. Suicide prevention efforts and strategies should consider the profile differences among those navigating the CJS. Plain Language Summary Title: Criminal Justice System Contacts among Suicide Decedents in Toronto
- 25 May 2025
- Published by SAGE Publications in The Canadian Journal of Psychiatry
- Vol. 70 (8) , 639-648
Open AccessCriminal Justice System Contacts among Suicide Decedents in Toronto, 1998-2020: An Observational Study: Démêlés avec le système de justice pénale parmi les personnes décédées par suicide à Toronto, entre 1998 et 2020 : Une étude d’observation
Objective: This exploratory correlational study explored the demographic, clinical, and offence-type characteristics of people with documented past-year contact with the criminal justice system (CJS) in Toronto, Canada who died by suicide. We aimed to compare demographic and clinical factors among individuals with CJS contact who died by suicide to those without recorded CJS contact who died by suicide. Methods: Coroners’ final death reports from all recorded suicide deaths in Toronto between 1 January 1998 and 31 December 2020 were retrieved by research staff and coded at the Office of the Chief Coroner (OCC) of Ontario. A series of bivariate analyses and binary logistic regression analyses were performed to compare demographic and clinically relevant characteristics between these groups. Descriptive statistics relating to demographic, clinical, and offence-type characteristics were reported. Results: A total of 5,288 people died by suicide, of whom 251 (4.7% of all suicides) had recorded CJS contact prior to death. Assault, physical assault, impaired driving, serious/death threats, and sexual assault were the most common criminal charges among those in the CJS contact group. When compared with the no recorded CJS contact group, the CJS contact group was slightly younger ( M = 40.0, SD = ±13.4 vs. M = 47.5, SD = ±18.1, p < 0 .001 ), had a higher proportion of males (85.6% vs. 69.9%, p < 0 .001 ), more commonly experienced interpersonal (36.3% vs. 14.5%, p < 0 .001 ) and/or relationship break-up/breakdown stressors (16.7% vs. 7.5%, p < 0 .001 ), and substance misuse or substance use disorders (37.5% vs. 18%, p < 0 .001 ). Conclusions: Our findings highlight that younger men with interpersonal stressors and/or substance misuse characterize suicide decedents with recorded CJS contact in Toronto, Canada. Suicide prevention efforts and strategies should consider the profile differences among those navigating the CJS. Plain Language Summary Title: Criminal Justice System Contacts among Suicide Decedents in Toronto
- Open Access
- 7 November 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Suicide Risk Screening in Jails: Protocol for a Pilot Study Leveraging the Mental Health Research Network Algorithm and Health Care Data (Preprint)
BACKGROUND Suicide in local jails occurs at a higher rate than in the general population, requiring improvements to risk screening methods. Current suicide risk screening practices in jails are insufficient: They are commonly not conducted using validated screening instruments, not collected by clinically trained professionals, and unlikely to capture honest responses due to the chaotic nature of booking areas. Therefore, new technologies could improve such practices. Several studies have indicated that machine learning (ML) models considerably improve accuracy and have positive predictive value in detecting suicide risk compared with practice as usual (PAU). This study will use administrative data and ML modeling to improve suicide risk detection at jail booking. OBJECTIVE This study is primarily focused on gathering preliminary information about the feasibility and practicality of using administrative data and ML modeling for suicide risk detection but also incorporates elements of hypothesis testing pertaining to clinical outcomes. METHODS The study uniquely contributes to our understanding of suicide risk by further validating an existing ML model developed and previously validated by the Mental Health Research Network using Medicaid outpatient health care claims data. This validation uses complete claims data on a sample of approximately 6000 individuals booked into 2 diverse jails in a midwestern state. This model validation uses 313 unique demographic and clinical characteristics from 5 years of historical health care data. It detects suicide risk in jails and postrelease by using merged jail, Medicaid, and vital records data. The study will use jail administrative data for September 1, 2021, through February 28, 2022; Medicaid records data for September 1, 2016, through March 31, 2023; and vital records data for March 1, 2022, through March 31, 2023. RESULTS First, the algorithm will be validated on the data gathered for the jail sample using the C-statistic and area under the receiver operating characteristic curve. Second, the resulting model will be compared with the jails’ suicide identification PAU to assess risk and detection of identified suicide attempts and deaths from intake through 120 days and 13 months after jail release. The funding timeline for this project is August 1, 2022, through July 31, 2025. The algorithm’s predictions and actual event incidence will be linked and validated in the spring of 2025, with results ready for publication in the fall of 2025. CONCLUSIONS The study will also investigate implementation factors, such as feasibility, acceptability, and appropriateness, to optimize jail uptake. Interview data on the implementation factors will be gathered in the summer of 2025, with expected dissemination in 2026. We hypothesize that a combination of intake screening PAU and the ML model will be the optimal approach, in that the combination will be more accurate and can have practical application in this context. INTERNATIONAL REGISTERED REPORT DERR1-10.2196/68517
- 7 November 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessSuicide Risk Screening in Jails: Protocol for a Pilot Study Leveraging the Mental Health Research Network Algorithm and Health Care Data (Preprint)
BACKGROUND Suicide in local jails occurs at a higher rate than in the general population, requiring improvements to risk screening methods. Current suicide risk screening practices in jails are insufficient: They are commonly not conducted using validated screening instruments, not collected by clinically trained professionals, and unlikely to capture honest responses due to the chaotic nature of booking areas. Therefore, new technologies could improve such practices. Several studies have indicated that machine learning (ML) models considerably improve accuracy and have positive predictive value in detecting suicide risk compared with practice as usual (PAU). This study will use administrative data and ML modeling to improve suicide risk detection at jail booking. OBJECTIVE This study is primarily focused on gathering preliminary information about the feasibility and practicality of using administrative data and ML modeling for suicide risk detection but also incorporates elements of hypothesis testing pertaining to clinical outcomes. METHODS The study uniquely contributes to our understanding of suicide risk by further validating an existing ML model developed and previously validated by the Mental Health Research Network using Medicaid outpatient health care claims data. This validation uses complete claims data on a sample of approximately 6000 individuals booked into 2 diverse jails in a midwestern state. This model validation uses 313 unique demographic and clinical characteristics from 5 years of historical health care data. It detects suicide risk in jails and postrelease by using merged jail, Medicaid, and vital records data. The study will use jail administrative data for September 1, 2021, through February 28, 2022; Medicaid records data for September 1, 2016, through March 31, 2023; and vital records data for March 1, 2022, through March 31, 2023. RESULTS First, the algorithm will be validated on the data gathered for the jail sample using the C-statistic and area under the receiver operating characteristic curve. Second, the resulting model will be compared with the jails’ suicide identification PAU to assess risk and detection of identified suicide attempts and deaths from intake through 120 days and 13 months after jail release. The funding timeline for this project is August 1, 2022, through July 31, 2025. The algorithm’s predictions and actual event incidence will be linked and validated in the spring of 2025, with results ready for publication in the fall of 2025. CONCLUSIONS The study will also investigate implementation factors, such as feasibility, acceptability, and appropriateness, to optimize jail uptake. Interview data on the implementation factors will be gathered in the summer of 2025, with expected dissemination in 2026. We hypothesize that a combination of intake screening PAU and the ML model will be the optimal approach, in that the combination will be more accurate and can have practical application in this context. INTERNATIONAL REGISTERED REPORT DERR1-10.2196/68517
- 17 April 2024
- Published by Wiley in Bipolar Disorders
- Vol. 26 (6) , 523-528
Psychological therapies for people with bipolar disorder: Where are we now, and what is next? ISBD Psychological Interventions Taskforce—Position paper
- 17 April 2024
- Published by Wiley in Bipolar Disorders
- Vol. 26 (6) , 523-528
Psychological therapies for people with bipolar disorder: Where are we now, and what is next? ISBD Psychological Interventions Taskforce—Position paper