Hyunjoon Lee
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
Research Interests
Hyunjoon Lee has a total of 107 co-authors. Here are the top co-authors by number of shared publications:
- Jordan Wassertheil Smoller
Harvard Medical School
11 shared publications - Victor M. Castro
Massachusetts General Hospital
6 shared publications - Karmel W. Choi
Department of Psychiatry, Massachusetts General Hospital, Harvard University
5 shared publications - Lea Karatheodoris Davis
Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, USA
5 shared publications - Emily Madsen
Department of Psychiatry, Massachusetts General Hospital
4 shared publications Jordan W. Smoller
Massachusetts General Hospital
4 shared publications
Latest Publications
- Open Access
- 2 March 2026
- Published by American Medical Association (AMA) in JAMA Network Open
- Vol. 9 (3) , e260589
Clinical Note–Extracted Psychosocial Factors for Predicting Suicide Attempt Among ED Patients With Suicidal Ideation
Importance: The Joint Commission recommends universal suicide screening in emergency departments (EDs), which emphasizes the need to identify at-risk individuals. Existing suicide risk prediction models rely primarily on clinical data and demonstrate limited performance. The potential of incorporating psychosocial information to enhance predictive performance remains understudied. Objective: To evaluate whether augmenting clinical data–based risk scores with psychosocial factors improves the prediction of suicide attempt (SA). Design, Setting, and Participants: This retrospective prognostic study based on electronic health record data included 4661 ED patients discharged after presentation for suicidal ideation (SI) from middle Tennessee hospitals between June 1, 2018, and February 27, 2024. Main Outcomes and Measures: The primary outcome was SA within 90 days of ED admission and time-to-event in days. Clinical data–based Vanderbilt Suicide Attempt and Ideation Likelihood (VSAIL) score and 6 psychosocial factors (homelessness, financial insecurity, chronic stress, social isolation, loneliness, and adverse childhood experiences) derived from clinical notes were integrated using a Cox proportional hazards regression model. Performance metrics included area under the receiver operating curve (AUROC), area under the precision-recall curve (AUPRC), positive predictive value (PPV), negative predictive value, sensitivity, and specificity. Performance was evaluated for models trained on (1) VSAIL, (2) psychosocial factors, and (3) VSAIL plus psychosocial factors. Results: This study included 3382 Vanderbilt University Hospital (VUH) (mean [SD] age, 26.1 [15.6] years; 1751 males [51.8%]) and 1279 Regional Health Systems (RHS) (mean [SD] age, 34.5 [18.0] years; 715 males [55.9%]) ED visits for SI. Within 90 days, SAs were reported in 160 (4.7%) VUH and 34 (2.7%) RHS ED visits for SI. Compared with VSAIL alone, VSAIL plus psychosocial factors was associated with significantly increased median AUROC (VUH: 0.645 [IQR, 0.645-0.645] vs 0.734 [IQR, 0.719-0.747]; P < .001; RHS: 0.547 [IQR, 0.547-0.547] vs 0.680 [IQR, 0.672-0.687]; P < .001), AUPRC (VUH: 0.083 [IQR, 0.083-0.083] vs 0.122 [IQR, 0.111-0.137]; P < .001; RHS: 0.029 [IQR, 0.029-0.029] vs 0.054 [IQR, 0.052-0.058]; P < .001), and PPV (VUH: 0.093 [IQR, 0.082-0.094] vs 0.143 [IQR, 0.123-0.161]; P < .001; RHS: 0.042 [IQR, 0.040-0.043] vs 0.112 [IQR, 0.096-0.129]; P < .001) while maintaining specificities above 0.90. Chronic stress emerged as the strongest predictor of SA (β = 0.643 [95% CI, 0.427-0.859]; P < .001). Conclusions and Relevance: In this prognostic study of patients discharged from the ED after presentation for SI, augmenting a clinical data–based suicide risk prediction model with clinical note–extracted psychosocial factors was associated with significantly higher predictive performance. These findings suggest that psychosocial factors can enhance risk stratification and support targeted interventions, such as therapies addressing chronic stress.
- 2 March 2026
- Published by American Medical Association (AMA) in JAMA Network Open
- Vol. 9 (3) , e260589
Open AccessClinical Note–Extracted Psychosocial Factors for Predicting Suicide Attempt Among ED Patients With Suicidal Ideation
Importance: The Joint Commission recommends universal suicide screening in emergency departments (EDs), which emphasizes the need to identify at-risk individuals. Existing suicide risk prediction models rely primarily on clinical data and demonstrate limited performance. The potential of incorporating psychosocial information to enhance predictive performance remains understudied. Objective: To evaluate whether augmenting clinical data–based risk scores with psychosocial factors improves the prediction of suicide attempt (SA). Design, Setting, and Participants: This retrospective prognostic study based on electronic health record data included 4661 ED patients discharged after presentation for suicidal ideation (SI) from middle Tennessee hospitals between June 1, 2018, and February 27, 2024. Main Outcomes and Measures: The primary outcome was SA within 90 days of ED admission and time-to-event in days. Clinical data–based Vanderbilt Suicide Attempt and Ideation Likelihood (VSAIL) score and 6 psychosocial factors (homelessness, financial insecurity, chronic stress, social isolation, loneliness, and adverse childhood experiences) derived from clinical notes were integrated using a Cox proportional hazards regression model. Performance metrics included area under the receiver operating curve (AUROC), area under the precision-recall curve (AUPRC), positive predictive value (PPV), negative predictive value, sensitivity, and specificity. Performance was evaluated for models trained on (1) VSAIL, (2) psychosocial factors, and (3) VSAIL plus psychosocial factors. Results: This study included 3382 Vanderbilt University Hospital (VUH) (mean [SD] age, 26.1 [15.6] years; 1751 males [51.8%]) and 1279 Regional Health Systems (RHS) (mean [SD] age, 34.5 [18.0] years; 715 males [55.9%]) ED visits for SI. Within 90 days, SAs were reported in 160 (4.7%) VUH and 34 (2.7%) RHS ED visits for SI. Compared with VSAIL alone, VSAIL plus psychosocial factors was associated with significantly increased median AUROC (VUH: 0.645 [IQR, 0.645-0.645] vs 0.734 [IQR, 0.719-0.747]; P < .001; RHS: 0.547 [IQR, 0.547-0.547] vs 0.680 [IQR, 0.672-0.687]; P < .001), AUPRC (VUH: 0.083 [IQR, 0.083-0.083] vs 0.122 [IQR, 0.111-0.137]; P < .001; RHS: 0.029 [IQR, 0.029-0.029] vs 0.054 [IQR, 0.052-0.058]; P < .001), and PPV (VUH: 0.093 [IQR, 0.082-0.094] vs 0.143 [IQR, 0.123-0.161]; P < .001; RHS: 0.042 [IQR, 0.040-0.043] vs 0.112 [IQR, 0.096-0.129]; P < .001) while maintaining specificities above 0.90. Chronic stress emerged as the strongest predictor of SA (β = 0.643 [95% CI, 0.427-0.859]; P < .001). Conclusions and Relevance: In this prognostic study of patients discharged from the ED after presentation for SI, augmenting a clinical data–based suicide risk prediction model with clinical note–extracted psychosocial factors was associated with significantly higher predictive performance. These findings suggest that psychosocial factors can enhance risk stratification and support targeted interventions, such as therapies addressing chronic stress.
- Open Access
- 4 June 2024
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 19 (6) , e0303079
Patterns and correlates of mental healthcare utilization during the COVID-19 pandemic among individuals with pre-existing mental disorder
How did mental healthcare utilization change during the COVID-19 pandemic period among individuals with pre-existing mental disorder? Understanding utilization patterns of these at-risk individuals and identifying those most likely to exhibit increased utilization could improve patient stratification and efficient delivery of mental health services. This study leveraged large-scale electronic health record (EHR) data to describe mental healthcare utilization patterns among individuals with pre-existing mental disorder before and during the COVID-19 pandemic and identify correlates of high mental healthcare utilization. Using EHR data from a large healthcare system in Massachusetts, we identified three “pre-existing mental disorder” groups (PMD) based on having a documented mental disorder diagnosis within the 6 months prior to the March 2020 lockdown, related to: (1) stress-related disorders (e.g., depression, anxiety) (N = 115,849), (2) serious mental illness (e.g., schizophrenia, bipolar disorders) (N = 11,530), or (3) compulsive behavior disorders (e.g., eating disorder, OCD) (N = 5,893). We also identified a “historical comparison” group (HC) for each PMD (N = 113,604, 11,758, and 5,387, respectively) from the previous year (2019). We assessed the monthly number of mental healthcare visits from March 13 to December 31 for PMDs in 2020 and HCs in 2019. Phenome-wide association analyses (PheWAS) were used to identify clinical correlates of high mental healthcare utilization. We found the overall number of mental healthcare visits per patient during the pandemic period in 2020 was 10–12% higher than in 2019. The majority of increased visits was driven by a subset of high mental healthcare utilizers (top decile). PheWAS results indicated that correlates of high utilization (prior mental disorders, chronic pain, insomnia, viral hepatitis C, etc.) were largely similar before and during the pandemic, though several conditions (e.g., back pain) were associated with high utilization only during the pandemic. Limitations included that we were not able to examine other risk factors previously shown to influence mental health during the pandemic (e.g., social support, discrimination) due to lack of social determinants of health information in EHR data. Mental healthcare utilization among patients with pre-existing mental disorder increased overall during the pandemic, likely due to expanded access to telemedicine. Given that clinical correlates of high mental healthcare utilization in a major hospital system were largely similar before and during the COVID-19 pandemic, resource stratification based on known risk factor profiles may aid hospitals in responding to heightened mental healthcare needs during a pandemic.
- 4 June 2024
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 19 (6) , e0303079
Open AccessPatterns and correlates of mental healthcare utilization during the COVID-19 pandemic among individuals with pre-existing mental disorder
How did mental healthcare utilization change during the COVID-19 pandemic period among individuals with pre-existing mental disorder? Understanding utilization patterns of these at-risk individuals and identifying those most likely to exhibit increased utilization could improve patient stratification and efficient delivery of mental health services. This study leveraged large-scale electronic health record (EHR) data to describe mental healthcare utilization patterns among individuals with pre-existing mental disorder before and during the COVID-19 pandemic and identify correlates of high mental healthcare utilization. Using EHR data from a large healthcare system in Massachusetts, we identified three “pre-existing mental disorder” groups (PMD) based on having a documented mental disorder diagnosis within the 6 months prior to the March 2020 lockdown, related to: (1) stress-related disorders (e.g., depression, anxiety) (N = 115,849), (2) serious mental illness (e.g., schizophrenia, bipolar disorders) (N = 11,530), or (3) compulsive behavior disorders (e.g., eating disorder, OCD) (N = 5,893). We also identified a “historical comparison” group (HC) for each PMD (N = 113,604, 11,758, and 5,387, respectively) from the previous year (2019). We assessed the monthly number of mental healthcare visits from March 13 to December 31 for PMDs in 2020 and HCs in 2019. Phenome-wide association analyses (PheWAS) were used to identify clinical correlates of high mental healthcare utilization. We found the overall number of mental healthcare visits per patient during the pandemic period in 2020 was 10–12% higher than in 2019. The majority of increased visits was driven by a subset of high mental healthcare utilizers (top decile). PheWAS results indicated that correlates of high utilization (prior mental disorders, chronic pain, insomnia, viral hepatitis C, etc.) were largely similar before and during the pandemic, though several conditions (e.g., back pain) were associated with high utilization only during the pandemic. Limitations included that we were not able to examine other risk factors previously shown to influence mental health during the pandemic (e.g., social support, discrimination) due to lack of social determinants of health information in EHR data. Mental healthcare utilization among patients with pre-existing mental disorder increased overall during the pandemic, likely due to expanded access to telemedicine. Given that clinical correlates of high mental healthcare utilization in a major hospital system were largely similar before and during the COVID-19 pandemic, resource stratification based on known risk factor profiles may aid hospitals in responding to heightened mental healthcare needs during a pandemic.
- Open Access
- 25 January 2024
- Published by Springer Nature in Translational Psychiatry
- Vol. 14 (1) , 1-7
Development and multi-site external validation of a generalizable risk prediction model for bipolar disorder
Bipolar disorder is a leading contributor to disability, premature mortality, and suicide. Early identification of risk for bipolar disorder using generalizable predictive models trained on diverse cohorts around the United States could improve targeted assessment of high risk individuals, reduce misdiagnosis, and improve the allocation of limited mental health resources. This observational case-control study intended to develop and validate generalizable predictive models of bipolar disorder as part of the multisite, multinational PsycheMERGE Network across diverse and large biobanks with linked electronic health records (EHRs) from three academic medical centers: in the Northeast (Massachusetts General Brigham), the Mid-Atlantic (Geisinger) and the Mid-South (Vanderbilt University Medical Center). Predictive models were developed and valid with multiple algorithms at each study site: random forests, gradient boosting machines, penalized regression, including stacked ensemble learning algorithms combining them. Predictors were limited to widely available EHR-based features agnostic to a common data model including demographics, diagnostic codes, and medications. The main study outcome was bipolar disorder diagnosis as defined by the International Cohort Collection for Bipolar Disorder, 2015. In total, the study included records for 3,529,569 patients including 12,533 cases (0.3%) of bipolar disorder. After internal and external validation, algorithms demonstrated optimal performance in their respective development sites. The stacked ensemble achieved the best combination of overall discrimination (AUC = 0.82–0.87) and calibration performance with positive predictive values above 5% in the highest risk quantiles at all three study sites. In conclusion, generalizable predictive models of risk for bipolar disorder can be feasibly developed across diverse sites to enable precision medicine. Comparison of a range of machine learning methods indicated that an ensemble approach provides the best performance overall but required local retraining. These models will be disseminated via the PsycheMERGE Network website.
- 25 January 2024
- Published by Springer Nature in Translational Psychiatry
- Vol. 14 (1) , 1-7
Open AccessDevelopment and multi-site external validation of a generalizable risk prediction model for bipolar disorder
Bipolar disorder is a leading contributor to disability, premature mortality, and suicide. Early identification of risk for bipolar disorder using generalizable predictive models trained on diverse cohorts around the United States could improve targeted assessment of high risk individuals, reduce misdiagnosis, and improve the allocation of limited mental health resources. This observational case-control study intended to develop and validate generalizable predictive models of bipolar disorder as part of the multisite, multinational PsycheMERGE Network across diverse and large biobanks with linked electronic health records (EHRs) from three academic medical centers: in the Northeast (Massachusetts General Brigham), the Mid-Atlantic (Geisinger) and the Mid-South (Vanderbilt University Medical Center). Predictive models were developed and valid with multiple algorithms at each study site: random forests, gradient boosting machines, penalized regression, including stacked ensemble learning algorithms combining them. Predictors were limited to widely available EHR-based features agnostic to a common data model including demographics, diagnostic codes, and medications. The main study outcome was bipolar disorder diagnosis as defined by the International Cohort Collection for Bipolar Disorder, 2015. In total, the study included records for 3,529,569 patients including 12,533 cases (0.3%) of bipolar disorder. After internal and external validation, algorithms demonstrated optimal performance in their respective development sites. The stacked ensemble achieved the best combination of overall discrimination (AUC = 0.82–0.87) and calibration performance with positive predictive values above 5% in the highest risk quantiles at all three study sites. In conclusion, generalizable predictive models of risk for bipolar disorder can be feasibly developed across diverse sites to enable precision medicine. Comparison of a range of machine learning methods indicated that an ensemble approach provides the best performance overall but required local retraining. These models will be disseminated via the PsycheMERGE Network website.
- Open Access
- 8 January 2024
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 8 (1) , e46364
Determining Distinct Suicide Attempts From Recurrent Electronic Health Record Codes: Classification Study
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.
- 8 January 2024
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 8 (1) , e46364
Open AccessDetermining Distinct Suicide Attempts From Recurrent Electronic Health Record Codes: Classification Study
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.
- Open Access
Evaluating the impact of modeling choices on the performance of integrated genetic and clinical models
The value of genetic information for improving the performance of clinical risk prediction models has yielded variable conclusions. Many methodological decisions have the potential to contribute to differential results across studies. Here, we performed multiple modeling experiments integrating clinical and demographic data from electronic health records (EHR) and genetic data to understand which decision points may affect performance. Clinical data in the form of structured diagnostic codes, medications, procedural codes, and demographics were extracted from two large independent health systems and polygenic risk scores (PRS) were generated across all patients with genetic data in the corresponding biobanks. Crohn’s disease was used as the model phenotype based on its substantial genetic component, established EHR-based definition, and sufficient prevalence for model training and testing. We investigated the impact of PRS integration method, as well as choices regarding training sample, model complexity, and performance metrics. Overall, our results show that including PRS resulted in higher performance by some metrics but the gain in performance was only robust when combined with demographic data alone. Improvements were inconsistent or negligible after including additional clinical information. The impact of genetic information on performance also varied by PRS integration method, with a small improvement in some cases from combining PRS with the output of a clinical model (late-fusion) compared to its inclusion an additional feature (early-fusion). The effects of other modeling decisions varied between institutions though performance increased with more compute-intensive models such as random forest. This work highlights the importance of considering methodological decision points in interpreting the impact on prediction performance when including PRS information in clinical models.
Open AccessEvaluating the impact of modeling choices on the performance of integrated genetic and clinical models
The value of genetic information for improving the performance of clinical risk prediction models has yielded variable conclusions. Many methodological decisions have the potential to contribute to differential results across studies. Here, we performed multiple modeling experiments integrating clinical and demographic data from electronic health records (EHR) and genetic data to understand which decision points may affect performance. Clinical data in the form of structured diagnostic codes, medications, procedural codes, and demographics were extracted from two large independent health systems and polygenic risk scores (PRS) were generated across all patients with genetic data in the corresponding biobanks. Crohn’s disease was used as the model phenotype based on its substantial genetic component, established EHR-based definition, and sufficient prevalence for model training and testing. We investigated the impact of PRS integration method, as well as choices regarding training sample, model complexity, and performance metrics. Overall, our results show that including PRS resulted in higher performance by some metrics but the gain in performance was only robust when combined with demographic data alone. Improvements were inconsistent or negligible after including additional clinical information. The impact of genetic information on performance also varied by PRS integration method, with a small improvement in some cases from combining PRS with the output of a clinical model (late-fusion) compared to its inclusion an additional feature (early-fusion). The effects of other modeling decisions varied between institutions though performance increased with more compute-intensive models such as random forest. This work highlights the importance of considering methodological decision points in interpreting the impact on prediction performance when including PRS information in clinical models.
- Open Access
Identifying modifiable comorbidities of schizophrenia by integrating electronic health records and polygenic risk
Patients with schizophrenia have substantial comorbidity contributing to reduced life expectancy of 10-20 years. Identifying which comorbidities might be modifiable could improve rates of premature mortality in this population. We hypothesize that conditions that frequently co-occur but lack shared genetic risk with schizophrenia are more likely to be products of treatment, behavior, or environmental factors and therefore potentially modifiable. To test this hypothesis, we calculated phenome-wide comorbidity from electronic health records (EHR) in 250,000 patients in each of two independent health care institutions (Vanderbilt University Medical Center and Mass General Brigham) and association with schizophrenia polygenic risk scores (PRS) across the same phenotypes (phecodes) in linked biobanks. Comorbidity with schizophrenia was significantly correlated across institutions (r = 0.85) and consistent with prior literature. After multiple test correction, there were 77 significant phecodes comorbid with schizophrenia. Overall, comorbidity and PRS association were highly correlated (r = 0.55, p = 1.29×10 −118 ), however, 36 of the EHR identified comorbidities had significantly equivalent schizophrenia PRS distributions between cases and controls. Fifteen of these lacked any PRS association and were enriched for phenotypes known to be side effects of antipsychotic medications (e.g., “movement disorders”, “convulsions”, “tachycardia”) or other schizophrenia related factors such as from smoking (“bronchitis”) or reduced hygiene (e.g., “diseases of the nail”) highlighting the validity of this approach. Other phenotypes implicated by this approach where the contribution from shared common genetic risk with schizophrenia was minimal included tobacco use disorder, diabetes, and dementia. This work demonstrates the consistency and robustness of EHR-based schizophrenia comorbidities across independent institutions and with the existing literature. It identifies comorbidities with an absence of shared genetic risk indicating other causes that might be more modifiable and where further study of causal pathways could improve outcomes for patients.
Open AccessIdentifying modifiable comorbidities of schizophrenia by integrating electronic health records and polygenic risk
Patients with schizophrenia have substantial comorbidity contributing to reduced life expectancy of 10-20 years. Identifying which comorbidities might be modifiable could improve rates of premature mortality in this population. We hypothesize that conditions that frequently co-occur but lack shared genetic risk with schizophrenia are more likely to be products of treatment, behavior, or environmental factors and therefore potentially modifiable. To test this hypothesis, we calculated phenome-wide comorbidity from electronic health records (EHR) in 250,000 patients in each of two independent health care institutions (Vanderbilt University Medical Center and Mass General Brigham) and association with schizophrenia polygenic risk scores (PRS) across the same phenotypes (phecodes) in linked biobanks. Comorbidity with schizophrenia was significantly correlated across institutions (r = 0.85) and consistent with prior literature. After multiple test correction, there were 77 significant phecodes comorbid with schizophrenia. Overall, comorbidity and PRS association were highly correlated (r = 0.55, p = 1.29×10 −118 ), however, 36 of the EHR identified comorbidities had significantly equivalent schizophrenia PRS distributions between cases and controls. Fifteen of these lacked any PRS association and were enriched for phenotypes known to be side effects of antipsychotic medications (e.g., “movement disorders”, “convulsions”, “tachycardia”) or other schizophrenia related factors such as from smoking (“bronchitis”) or reduced hygiene (e.g., “diseases of the nail”) highlighting the validity of this approach. Other phenotypes implicated by this approach where the contribution from shared common genetic risk with schizophrenia was minimal included tobacco use disorder, diabetes, and dementia. This work demonstrates the consistency and robustness of EHR-based schizophrenia comorbidities across independent institutions and with the existing literature. It identifies comorbidities with an absence of shared genetic risk indicating other causes that might be more modifiable and where further study of causal pathways could improve outcomes for patients.
- Open Access
- 10 April 2023
- Published by Elsevier in Biological Psychiatry
- Vol. 93 (9) , S288
479. Performance Differences in Electronic Health Record Algorithm for Bipolar Disorder by Race and Ethnicity: An Assessment From the Psychemerge Diversity Initiative
- 10 April 2023
- Published by Elsevier in Biological Psychiatry
- Vol. 93 (9) , S288
Open Access479. Performance Differences in Electronic Health Record Algorithm for Bipolar Disorder by Race and Ethnicity: An Assessment From the Psychemerge Diversity Initiative
- Open Access
- 21 March 2023
- Published by Elsevier in Psychiatry Research
- Vol. 323, 115175
An efficient landmark model for prediction of suicide attempts in multiple clinical settings
- 21 March 2023
- Published by Elsevier in Psychiatry Research
- Vol. 323, 115175
Open AccessAn efficient landmark model for prediction of suicide attempts in multiple clinical settings
- Open Access
- 8 February 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Determining Distinct Suicide Attempts From Recurrent Electronic Health Record Codes: Classification Study (Preprint)
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.
- 8 February 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessDetermining Distinct Suicide Attempts From Recurrent Electronic Health Record Codes: Classification Study (Preprint)
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.