1
|
Davis M, Dysart GC, Doupnik SK, Hamm ME, Schwartz KTG, George-Milford B, Ryan ND, Melhem NM, Stepp SD, Brent DA, Young JF. Adolescent, Parent, and Provider Perceptions of a Predictive Algorithm to Identify Adolescent Suicide Risk in Primary Care. Acad Pediatr 2024; 24:645-653. [PMID: 38190885 PMCID: PMC11056301 DOI: 10.1016/j.acap.2023.12.015] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/12/2023] [Revised: 12/27/2023] [Accepted: 12/30/2023] [Indexed: 01/10/2024]
Abstract
OBJECTIVE To understand adolescent, parent, and provider perceptions of a machine learning algorithm for detecting adolescent suicide risk prior to its implementation primary care. METHODS We conducted semi-structured, qualitative interviews with adolescents (n = 9), parents (n = 12), and providers (n = 10; mixture of behavioral health and primary care providers) across two major health systems. Interviews were audio recorded and transcribed with analyses supported by use of NVivo. A codebook was developed combining codes derived inductively from interview transcripts and deductively from implementation science frameworks for content analysis. RESULTS Reactions to the algorithm were mixed. While many participants expressed privacy concerns, they believed the algorithm could be clinically useful for identifying adolescents at risk for suicide and facilitating follow-up. Parents' past experiences with their adolescents' suicidal thoughts and behaviors contributed to their openness to the algorithm. Results also aligned with several key Consolidated Framework for Implementation Research domains. For example, providers mentioned barriers inherent to the primary care setting such as time and resource constraints likely to impact algorithm implementation. Participants also cited a climate of mistrust of science and health care as potential barriers. CONCLUSIONS Findings shed light on factors that warrant consideration to promote successful implementation of suicide predictive algorithms in pediatric primary care. By attending to perspectives of potential end users prior to the development and testing of the algorithm, we can ensure that the risk prediction methods will be well-suited to the providers who would be interacting with them and the families who could benefit.
Collapse
Affiliation(s)
- Molly Davis
- Department of Child and Adolescent Psychiatry and Behavioral Sciences (M Davis, GC Dysart, KTG Schwartz, and JF Young), Children's Hospital of Philadelphia, Philadelphia, Pa; PolicyLab (M Davis, GC Dysart, SK Doupnik, KTG Schwartz, and JF Young), Children's Hospital of Philadelphia, Philadelphia, Pa; Clinical Futures (M Davis and SK Doupnik), Children's Hospital of Philadelphia, Philadelphia, Pa; Department of Psychiatry (M Davis and JF Young), University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa; Penn Implementation Science Center at the Leonard Davis Institute of Health Economics (PISCE@LDI) (M Davis and SK Doupnik), University of Pennsylvania, Philadelphia, Pa.
| | - Gillian C Dysart
- Department of Child and Adolescent Psychiatry and Behavioral Sciences (M Davis, GC Dysart, KTG Schwartz, and JF Young), Children's Hospital of Philadelphia, Philadelphia, Pa; PolicyLab (M Davis, GC Dysart, SK Doupnik, KTG Schwartz, and JF Young), Children's Hospital of Philadelphia, Philadelphia, Pa
| | - Stephanie K Doupnik
- PolicyLab (M Davis, GC Dysart, SK Doupnik, KTG Schwartz, and JF Young), Children's Hospital of Philadelphia, Philadelphia, Pa; Clinical Futures (M Davis and SK Doupnik), Children's Hospital of Philadelphia, Philadelphia, Pa; Penn Implementation Science Center at the Leonard Davis Institute of Health Economics (PISCE@LDI) (M Davis and SK Doupnik), University of Pennsylvania, Philadelphia, Pa; Division of General Pediatrics (SK Doupnik), Children's Hospital of Philadelphia, Philadelphia, Pa; Department of Pediatrics (SK Doupnik), University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa
| | - Megan E Hamm
- Department of Medicine (ME Hamm), University of Pittsburgh, Pittsburgh, Pa
| | - Karen T G Schwartz
- Department of Child and Adolescent Psychiatry and Behavioral Sciences (M Davis, GC Dysart, KTG Schwartz, and JF Young), Children's Hospital of Philadelphia, Philadelphia, Pa; PolicyLab (M Davis, GC Dysart, SK Doupnik, KTG Schwartz, and JF Young), Children's Hospital of Philadelphia, Philadelphia, Pa
| | - Brandie George-Milford
- University of Pittsburgh Medical Center Western Psychiatric Hospital (B George-Milford and DA Brent), Pittsburgh, Pa
| | - Neal D Ryan
- Department of Psychiatry (ND Ryan, NM Melhem, SD Stepp, and DA Brent), University of Pittsburgh School of Medicine, Pittsburgh, Pa; Clinical and Translational Science Institute (ND Ryan), University of Pittsburgh, Pittsburgh, Pa
| | - Nadine M Melhem
- Department of Psychiatry (ND Ryan, NM Melhem, SD Stepp, and DA Brent), University of Pittsburgh School of Medicine, Pittsburgh, Pa
| | - Stephanie D Stepp
- Department of Psychiatry (ND Ryan, NM Melhem, SD Stepp, and DA Brent), University of Pittsburgh School of Medicine, Pittsburgh, Pa
| | - David A Brent
- University of Pittsburgh Medical Center Western Psychiatric Hospital (B George-Milford and DA Brent), Pittsburgh, Pa; Department of Psychiatry (ND Ryan, NM Melhem, SD Stepp, and DA Brent), University of Pittsburgh School of Medicine, Pittsburgh, Pa
| | - Jami F Young
- Department of Child and Adolescent Psychiatry and Behavioral Sciences (M Davis, GC Dysart, KTG Schwartz, and JF Young), Children's Hospital of Philadelphia, Philadelphia, Pa; PolicyLab (M Davis, GC Dysart, SK Doupnik, KTG Schwartz, and JF Young), Children's Hospital of Philadelphia, Philadelphia, Pa; Department of Psychiatry (M Davis and JF Young), University of Pennsylvania Perelman School of Medicine, Philadelphia, Pa
| |
Collapse
|
2
|
Zhou SC, Zhou Z, Tang Q, Yu P, Zou H, Liu Q, Wang XQ, Jiang J, Zhou Y, Liu L, Yang BX, Luo D. Prediction of non-suicidal self-injury in adolescents at the family level using regression methods and machine learning. J Affect Disord 2024; 352:67-75. [PMID: 38360362 DOI: 10.1016/j.jad.2024.02.039] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/07/2022] [Revised: 02/07/2024] [Accepted: 02/12/2024] [Indexed: 02/17/2024]
Abstract
BACKGROUND Adolescent non-suicidal self-injury (NSSI) is a major public health issue. Family factors are significantly associated with NSSI in adolescents, while studies on forecasting NSSI at the family level are still limited. In addition to regression methods, machine learning (ML) techniques have been recommended to improve the accuracy of family-level risk prediction for NSSI. METHODS Using a dataset of 7967 students and their primary caregivers from a cross-sectional study, logistic regression model and random forest model were used to test the forecasting accuracy of NSSI predictions at the family level. Cross-validation was used to assess model prediction performance, including the area under the receiver operator curve (AUC), precision, Brier score, accuracy, sensitivity, specificity, positive predictive value and negative predictive value. RESULTS The top three important family-related predictors within the random forest algorithm included family function (importance:42.66), family conflict (importance:42.18), and parental depression (importance:27.21). The most significant family-related risk predictors and protective predictors identified by the logistic regression model were family history of mental illness (OR:2.25) and help-seeking behaviors of mental distress from parents (OR:0.65), respectively. The AUCs of the two models, logistic regression and random forest, were 0.852 and 0.835, respectively. LIMITATIONS The key limitation is that this cross-sectional survey only enabled the authors to examine predictors that were considered to be proximal rather than distal. CONCLUSIONS These findings highlight the significance of family-related factors in forecasting NSSI in adolescents. Combining both conventional statistical methods and ML methods to improve risk assessment of NSSI at the family level deserves attention.
Collapse
Affiliation(s)
- Si Chen Zhou
- Center for Wise Information Technology of Mental Health Nursing Research, School of Nursing, Wuhan University, Wuhan, China
| | - Zhaohe Zhou
- School of Basic Medical Sciences, Chengdu University, Chengdu, China
| | - Qi Tang
- Center for Wise Information Technology of Mental Health Nursing Research, School of Nursing, Wuhan University, Wuhan, China
| | - Ping Yu
- Wuhan Mental Health Center, Wuhan, China; Wuhan Hospital for Psychotherapy, Wuhan, China
| | - Huijing Zou
- Center for Wise Information Technology of Mental Health Nursing Research, School of Nursing, Wuhan University, Wuhan, China
| | - Qian Liu
- Center for Wise Information Technology of Mental Health Nursing Research, School of Nursing, Wuhan University, Wuhan, China
| | - Xiao Qin Wang
- Center for Wise Information Technology of Mental Health Nursing Research, School of Nursing, Wuhan University, Wuhan, China
| | - Jianmei Jiang
- The Central Hospital of Enshi Tujia Autonomous Prefecture, Enshi, China
| | - Yang Zhou
- Wuhan Mental Health Center, Wuhan, China; Wuhan Hospital for Psychotherapy, Wuhan, China
| | - Lianzhong Liu
- Wuhan Mental Health Center, Wuhan, China; Wuhan Hospital for Psychotherapy, Wuhan, China
| | - Bing Xiang Yang
- Center for Wise Information Technology of Mental Health Nursing Research, School of Nursing, Wuhan University, Wuhan, China; Department of Psychiatry, Renmin Hospital of Wuhan University, Wuhan, China.
| | - Dan Luo
- Center for Wise Information Technology of Mental Health Nursing Research, School of Nursing, Wuhan University, Wuhan, China; Department of Psychiatry, Renmin Hospital of Wuhan University, Wuhan, China.
| |
Collapse
|
3
|
Flores JP, Kahn G, Penfold RB, Stuart EA, Ahmedani BK, Beck A, Boggs JM, Coleman KJ, Daida YG, Lynch FL, Richards JE, Rossom RC, Simon GE, Wilcox HC. Adolescents Who Do Not Endorse Risk via the Patient Health Questionnaire Before Self-Harm or Suicide. JAMA Psychiatry 2024:2818039. [PMID: 38656403 PMCID: PMC11044012 DOI: 10.1001/jamapsychiatry.2024.0603] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/01/2023] [Accepted: 02/16/2024] [Indexed: 04/26/2024]
Abstract
Importance Given that the Patient Health Questionnaire (PHQ) item 9 is commonly used to screen for risk of self-harm and suicide, it is important that clinicians recognize circumstances when at-risk adolescents may go undetected. Objective To understand characteristics of adolescents with a history of depression who do not endorse the PHQ item 9 before a near-term intentional self-harm event or suicide. Design, Setting, and Participants This was a retrospective cohort study design using electronic health record and claims data from January 2009 through September 2017. Settings included primary care and mental health specialty clinics across 7 integrated US health care systems. Included in the study were adolescents aged 13 to 17 years with history of depression who completed the PHQ item 9 within 30 or 90 days before self-harm or suicide. Study data were analyzed September 2022 to April 2023. Exposures Demographic, diagnostic, treatment, and health care utilization characteristics. Main Outcome(s) and Measure(s) Responded "not at all" (score = 0) to PHQ item 9 regarding thoughts of death or self-harm within 30 or 90 days before self-harm or suicide. Results The study included 691 adolescents (mean [SD] age, 15.3 [1.3] years; 541 female [78.3%]) in the 30-day cohort and 1024 adolescents (mean [SD] age, 15.3 [1.3] years; 791 female [77.2%]) in the 90-day cohort. A total of 197 of 691 adolescents (29%) and 330 of 1024 adolescents (32%), respectively, scored 0 before self-harm or suicide on the PHQ item 9 in the 30- and 90-day cohorts. Adolescents seen in primary care (odds ratio [OR], 1.5; 95% CI, 1.0-2.1; P = .03) and older adolescents (OR, 1.2; 95% CI, 1.0-1.3; P = .02) had increased odds of scoring 0 within 90 days of a self-harm event or suicide, and adolescents with a history of inpatient hospitalization and a mental health diagnosis had twice the odds (OR, 2.0; 95% CI, 1.3-3.0; P = .001) of scoring 0 within 30 days. Conversely, adolescents with diagnoses of eating disorders were significantly less likely to score 0 on item 9 (OR, 0.4; 95% CI, 0.2-0.8; P = .007) within 90 days. Conclusions and Relevance Study results suggest that older age, history of an inpatient mental health encounter, or being screened in primary care were associated with at-risk adolescents being less likely to endorse having thoughts of death and self-harm on the PHQ item 9 before a self-harm event or suicide death. As use of the PHQ becomes more widespread in practice, additional research is needed for understanding reasons why many at-risk adolescents do not endorse thoughts of death and self-harm.
Collapse
Affiliation(s)
- Jean P. Flores
- Johns Hopkins Bloomberg School of Public Health, Baltimore, Maryland
| | - Geoffrey Kahn
- Center for Health Policy & Health Services Research, Henry Ford Health, Detroit, Michigan
| | | | | | - Brian K. Ahmedani
- Center for Health Policy & Health Services Research, Henry Ford Health, Detroit, Michigan
| | | | | | - Karen J. Coleman
- Department of Research and Evaluation, Kaiser Permanente Southern California, Pasadena
- Department of Health Systems Science, Kaiser Permanente Bernard J. Tyson School of Medicine, Pasadena, California
| | | | | | | | | | | | - Holly C. Wilcox
- Johns Hopkins Bloomberg School of Public Health, Baltimore, Maryland
| |
Collapse
|
4
|
Dhaubhadel S, Ganguly K, Ribeiro RM, Cohn JD, Hyman JM, Hengartner NW, Kolade B, Singley A, Bhattacharya T, Finley P, Levin D, Thelen H, Cho K, Costa L, Ho YL, Justice AC, Pestian J, Santel D, Zamora-Resendiz R, Crivelli S, Tamang S, Martins S, Trafton J, Oslin DW, Beckham JC, Kimbrel NA, McMahon BH. High dimensional predictions of suicide risk in 4.2 million US Veterans using ensemble transfer learning. Sci Rep 2024; 14:1793. [PMID: 38245528 PMCID: PMC10799879 DOI: 10.1038/s41598-024-51762-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/18/2023] [Accepted: 01/09/2024] [Indexed: 01/22/2024] Open
Abstract
We present an ensemble transfer learning method to predict suicide from Veterans Affairs (VA) electronic medical records (EMR). A diverse set of base models was trained to predict a binary outcome constructed from reported suicide, suicide attempt, and overdose diagnoses with varying choices of study design and prediction methodology. Each model used twenty cross-sectional and 190 longitudinal variables observed in eight time intervals covering 7.5 years prior to the time of prediction. Ensembles of seven base models were created and fine-tuned with ten variables expected to change with study design and outcome definition in order to predict suicide and combined outcome in a prospective cohort. The ensemble models achieved c-statistics of 0.73 on 2-year suicide risk and 0.83 on the combined outcome when predicting on a prospective cohort of [Formula: see text] 4.2 M veterans. The ensembles rely on nonlinear base models trained using a matched retrospective nested case-control (Rcc) study cohort and show good calibration across a diversity of subgroups, including risk strata, age, sex, race, and level of healthcare utilization. In addition, a linear Rcc base model provided a rich set of biological predictors, including indicators of suicide, substance use disorder, mental health diagnoses and treatments, hypoxia and vascular damage, and demographics.
Collapse
Affiliation(s)
| | - Kumkum Ganguly
- Los Alamos National Laboratory, Los Alamos, NM, 87545, USA
| | - Ruy M Ribeiro
- Los Alamos National Laboratory, Los Alamos, NM, 87545, USA
| | - Judith D Cohn
- Los Alamos National Laboratory, Los Alamos, NM, 87545, USA
| | - James M Hyman
- Los Alamos National Laboratory, Los Alamos, NM, 87545, USA
| | | | - Beauty Kolade
- Los Alamos National Laboratory, Los Alamos, NM, 87545, USA
| | - Anna Singley
- Los Alamos National Laboratory, Los Alamos, NM, 87545, USA
| | | | | | - Drew Levin
- Sandia National Laboratory, Albuquerque, NM, 87123, USA
| | - Haedi Thelen
- Sandia National Laboratory, Albuquerque, NM, 87123, USA
| | - Kelly Cho
- Massachusetts Veterans Epidemiology and Research Information Center (MAVERIC), VA Boston Healthcare System, Boston, USA
- Department of Medicine, Brigham and Women's Hospital and Harvard Medical School, Boston, USA
| | - Lauren Costa
- Massachusetts Veterans Epidemiology and Research Information Center (MAVERIC), VA Boston Healthcare System, Boston, USA
| | - Yuk-Lam Ho
- Massachusetts Veterans Epidemiology and Research Information Center (MAVERIC), VA Boston Healthcare System, Boston, USA
| | - Amy C Justice
- VA Connecticut Healthcare System, Yale Schools of Medicine and Public Health, Yale University, West Haven, CT, USA
| | - John Pestian
- Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, USA
| | - Daniel Santel
- Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, USA
| | - Rafael Zamora-Resendiz
- Applied Mathematics and Computational Research Division, Lawrence Berkeley National Laboratory, 1 Cyclotron Rd, Berkeley, CA, 94720, USA
| | - Silvia Crivelli
- Applied Mathematics and Computational Research Division, Lawrence Berkeley National Laboratory, 1 Cyclotron Rd, Berkeley, CA, 94720, USA
| | - Suzanne Tamang
- Program Evaluation and Resource Center, Office of Mental Health and Suicide Prevention, Veterans Affairs Palo Alto Health Care System, Menlo Park, CA, USA
- Department of Medicine, Stanford University, Stanford, California, USA
| | - Susana Martins
- Program Evaluation and Resource Center, Office of Mental Health and Suicide Prevention, Veterans Affairs Palo Alto Health Care System, Menlo Park, CA, USA
| | - Jodie Trafton
- Program Evaluation and Resource Center, Office of Mental Health and Suicide Prevention, Veterans Affairs Palo Alto Health Care System, Menlo Park, CA, USA
| | - David W Oslin
- Cpl Michael J Crescenz VA Medical Center, VISN 4 Mental Illness Research, Education, and Clinical Center; Department of Psychiatry, Perelman School of Medicine, University of Pennsylvania, 3535 Market Street, Philadelphia, PA, 19104, USA
| | - Jean C Beckham
- Durham Veterans Affairs (VA) Health Care System, Durham, NC, USA
- VA Mid-Atlantic Mental Illness Research, Education and Clinical Center, Durham, NC, USA
- Department of Psychiatry and Behavioral Sciences, Duke University School of Medicine, Durham, NC, USA
| | - Nathan A Kimbrel
- Durham Veterans Affairs (VA) Health Care System, Durham, NC, USA
- VA Mid-Atlantic Mental Illness Research, Education and Clinical Center, Durham, NC, USA
- VA Health Services Research and Development Center of Innovation to Accelerate Discovery and Practice Transformation, Durham, NC, USA
- Department of Psychiatry and Behavioral Sciences, Duke University School of Medicine, Durham, NC, USA
| | | |
Collapse
|
5
|
Bentley KH, Madsen EM, Song E, Zhou Y, Castro V, Lee H, Lee YH, Smoller JW. Determining Distinct Suicide Attempts From Recurrent Electronic Health Record Codes: Classification Study. JMIR Form Res 2024; 8:e46364. [PMID: 38190236 PMCID: PMC10804255 DOI: 10.2196/46364] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2023] [Revised: 09/15/2023] [Accepted: 09/27/2023] [Indexed: 01/09/2024] Open
Abstract
BACKGROUND Prior suicide attempts are a relatively strong risk factor for future suicide attempts. There is growing interest in using longitudinal electronic health record (EHR) data to derive statistical risk prediction models for future suicide attempts and other suicidal behavior outcomes. However, model performance may be inflated by a largely unrecognized form of "data leakage" during model training: diagnostic codes for suicide attempt outcomes may refer to prior attempts that are also included in the model as predictors. OBJECTIVE We aimed to develop an automated rule for determining when documented suicide attempt diagnostic codes identify distinct suicide attempt events. METHODS From a large health care system's EHR, we randomly sampled suicide attempt codes for 300 patients with at least one pair of suicide attempt codes documented at least one but no more than 90 days apart. Supervised chart reviewers assigned the clinical settings (ie, emergency department [ED] versus non-ED), methods of suicide attempt, and intercode interval (number of days). The probability (or positive predictive value) that the second suicide attempt code in a given pair of codes referred to a distinct suicide attempt event from its preceding suicide attempt code was calculated by clinical setting, method, and intercode interval. RESULTS Of 1015 code pairs reviewed, 835 (82.3%) were nonindependent (ie, the 2 codes referred to the same suicide attempt event). When the second code in a pair was documented in a clinical setting other than the ED, it represented a distinct suicide attempt 3.3% of the time. The more time elapsed between codes, the more likely the second code in a pair referred to a distinct suicide attempt event from its preceding code. Code pairs in which the second suicide attempt code was assigned in an ED at least 5 days after its preceding suicide attempt code had a positive predictive value of 0.90. CONCLUSIONS EHR-based suicide risk prediction models that include International Classification of Diseases codes for prior suicide attempts as a predictor may be highly susceptible to bias due to data leakage in model training. We derived a simple rule to distinguish codes that reflect new, independent suicide attempts: suicide attempt codes documented in an ED setting at least 5 days after a preceding suicide attempt code can be confidently treated as new events in EHR-based suicide risk prediction models. This rule has the potential to minimize upward bias in model performance when prior suicide attempts are included as predictors in EHR-based suicide risk prediction models.
Collapse
Affiliation(s)
- Kate H Bentley
- Center for Precision Psychiatry, Department of Psychiatry, Massachusetts General Hospital, Boston, MA, United States
- Department of Psychiatry, Harvard Medical School, Boston, MA, United States
| | - Emily M Madsen
- Center for Precision Psychiatry, Department of Psychiatry, Massachusetts General Hospital, Boston, MA, United States
- Psychiatric and Neurodevelopmental Genetics Unit, Center for Genomic Medicine, Massachusetts General Hospital, Boston, MA, United States
| | - Eugene Song
- Center for Precision Psychiatry, Department of Psychiatry, Massachusetts General Hospital, Boston, MA, United States
- Psychiatric and Neurodevelopmental Genetics Unit, Center for Genomic Medicine, Massachusetts General Hospital, Boston, MA, United States
| | - Yu Zhou
- Center for Precision Psychiatry, Department of Psychiatry, Massachusetts General Hospital, Boston, MA, United States
- Psychiatric and Neurodevelopmental Genetics Unit, Center for Genomic Medicine, Massachusetts General Hospital, Boston, MA, United States
| | - Victor Castro
- Mass General Brigham Research Information Science and Computing, Somerville, MA, United States
| | - Hyunjoon Lee
- Center for Precision Psychiatry, Department of Psychiatry, Massachusetts General Hospital, Boston, MA, United States
- Psychiatric and Neurodevelopmental Genetics Unit, Center for Genomic Medicine, Massachusetts General Hospital, Boston, MA, United States
| | - Younga H Lee
- Department of Psychiatry, Harvard Medical School, Boston, MA, United States
- Psychiatric and Neurodevelopmental Genetics Unit, Center for Genomic Medicine, Massachusetts General Hospital, Boston, MA, United States
| | - Jordan W Smoller
- Center for Precision Psychiatry, Department of Psychiatry, Massachusetts General Hospital, Boston, MA, United States
- Department of Psychiatry, Harvard Medical School, Boston, MA, United States
- Psychiatric and Neurodevelopmental Genetics Unit, Center for Genomic Medicine, Massachusetts General Hospital, Boston, MA, United States
| |
Collapse
|
6
|
Abdulazeem H, Whitelaw S, Schauberger G, Klug SJ. A systematic review of clinical health conditions predicted by machine learning diagnostic and prognostic models trained or validated using real-world primary health care data. PLoS One 2023; 18:e0274276. [PMID: 37682909 PMCID: PMC10491005 DOI: 10.1371/journal.pone.0274276] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2022] [Accepted: 08/29/2023] [Indexed: 09/10/2023] Open
Abstract
With the advances in technology and data science, machine learning (ML) is being rapidly adopted by the health care sector. However, there is a lack of literature addressing the health conditions targeted by the ML prediction models within primary health care (PHC) to date. To fill this gap in knowledge, we conducted a systematic review following the PRISMA guidelines to identify health conditions targeted by ML in PHC. We searched the Cochrane Library, Web of Science, PubMed, Elsevier, BioRxiv, Association of Computing Machinery (ACM), and IEEE Xplore databases for studies published from January 1990 to January 2022. We included primary studies addressing ML diagnostic or prognostic predictive models that were supplied completely or partially by real-world PHC data. Studies selection, data extraction, and risk of bias assessment using the prediction model study risk of bias assessment tool were performed by two investigators. Health conditions were categorized according to international classification of diseases (ICD-10). Extracted data were analyzed quantitatively. We identified 106 studies investigating 42 health conditions. These studies included 207 ML prediction models supplied by the PHC data of 24.2 million participants from 19 countries. We found that 92.4% of the studies were retrospective and 77.3% of the studies reported diagnostic predictive ML models. A majority (76.4%) of all the studies were for models' development without conducting external validation. Risk of bias assessment revealed that 90.8% of the studies were of high or unclear risk of bias. The most frequently reported health conditions were diabetes mellitus (19.8%) and Alzheimer's disease (11.3%). Our study provides a summary on the presently available ML prediction models within PHC. We draw the attention of digital health policy makers, ML models developer, and health care professionals for more future interdisciplinary research collaboration in this regard.
Collapse
Affiliation(s)
- Hebatullah Abdulazeem
- Chair of Epidemiology, Department of Sport and Health Sciences, Technical University of Munich (TUM), Munich, Germany
| | - Sera Whitelaw
- Faculty of Medicine and Health Sciences, McGill University, Montreal, Quebec, Canada
| | - Gunther Schauberger
- Chair of Epidemiology, Department of Sport and Health Sciences, Technical University of Munich (TUM), Munich, Germany
| | - Stefanie J. Klug
- Chair of Epidemiology, Department of Sport and Health Sciences, Technical University of Munich (TUM), Munich, Germany
| |
Collapse
|
7
|
Richards JE, Yarborough BJH, Holden E, Shulman L, Stumbo SP, Coley Y, Simon GE. Implementation of Suicide Risk Estimation Analytics to Support Mental Health Care for Quality Improvement. JAMA Netw Open 2022; 5:e2247195. [PMID: 36525278 PMCID: PMC9856428 DOI: 10.1001/jamanetworkopen.2022.47195] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/23/2022] Open
Abstract
This quality improvement study describes use of estimation analytics to augment existing suicide prevention practices during routine mental health specialty encounters at a large US health care system.
Collapse
Affiliation(s)
- Julie E. Richards
- Kaiser Permanente Washington Heath Research Institute, Seattle
- Department of Health Systems & Population Health, University of Washington, Seattle
| | | | - Erika Holden
- Kaiser Permanente Washington Heath Research Institute, Seattle
| | - Lisa Shulman
- Kaiser Permanente Washington Heath Research Institute, Seattle
| | - Scott P. Stumbo
- Kaiser Permanente Northwest Center for Health Research, Portland, Oregon
| | - Yates Coley
- Kaiser Permanente Washington Heath Research Institute, Seattle
- Department of Biostatistics, University of Washington, Seattle
| | - Gregory E. Simon
- Kaiser Permanente Washington Heath Research Institute, Seattle
- Psychiatry and Behavioral Sciences, University of Washington, Seattle
- Kaiser Permanente Washington Department of Mental Health & Wellness, Seattle, Washington
| |
Collapse
|
8
|
Barch DM, Hennefield L, Herzberg MP. What Makes a Useful "Predictor" of Risk for Suicide Attempt? JAMA Psychiatry 2022; 79:948-950. [PMID: 36044232 PMCID: PMC9994208 DOI: 10.1001/jamapsychiatry.2022.2031] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/29/2023]
Affiliation(s)
- Deanna M Barch
- Department of Psychological & Brain Sciences, Washington University in St Louis, St Louis, Missouri.,Department of Psychiatry, Washington University in St Louis, St Louis, Missouri.,Department of Radiology, Washington University in St Louis, St Louis, Missouri
| | - Laura Hennefield
- Department of Psychiatry, Washington University in St Louis, St Louis, Missouri
| | - Max P Herzberg
- Department of Psychiatry, Washington University in St Louis, St Louis, Missouri
| |
Collapse
|