PheMIME: an interactive web app and knowledge base for phenome-wide, multi-institutional multimorbidity analysis.

OBJECTIVES: To address the need for interactive visualization tools and databases in characterizing multimorbidity patterns across different populations, we developed the Phenome-wide Multi-Institutional Multimorbidity Explorer (PheMIME). This tool leverages three large-scale EHR systems to facilitate efficient analysis and visualization of disease multimorbidity, aiming to reveal both robust and novel disease associations that are consistent across different systems and to provide insight for enhancing personalized healthcare strategies. MATERIALS AND METHODS: PheMIME integrates summary statistics from phenome-wide analyses of disease multimorbidities, utilizing data from Vanderbilt University Medical Center, Mass General Brigham, and the UK Biobank. It offers interactive and multifaceted visualizations for exploring multimorbidity. Incorporating an enhanced version of associationSubgraphs, PheMIME also enables dynamic analysis and inference of disease clusters, promoting the discovery of complex multimorbidity patterns. A case study on schizophrenia demonstrates its capability for generating interactive visualizations of multimorbidity networks within and across multiple systems. Additionally, PheMIME supports diverse multimorbidity-based discoveries, detailed further in online case studies. RESULTS: The PheMIME is accessible at https://prod.tbilab.org/PheMIME/. A comprehensive tutorial and multiple case studies for demonstration are available at https://prod.tbilab.org/PheMIME_supplementary_materials/. The source code can be downloaded from https://github.com/tbilab/PheMIME. DISCUSSION: PheMIME represents a significant advancement in medical informatics, offering an efficient solution for accessing, analyzing, and interpreting the complex and noisy real-world patient data in electronic health records. CONCLUSION: PheMIME provides an extensive multimorbidity knowledge base that consolidates data from three EHR systems, and it is a novel interactive tool designed to analyze and visualize multimorbidities across multiple EHR datasets. It stands out as the first of its kind to offer extensive multimorbidity knowledge integration with substantial support for efficient online analysis and interactive visualization.

Defining Suicidal Thought and Behavior Phenotypes for Genetic Studies.

Background: Standardized definitions of suicidality phenotypes, including suicidal ideation (SI), attempt (SA), and death (SD) are a critical step towards improving understanding and comparison of results in suicide research. The complexity of suicidality contributes to heterogeneity in phenotype definitions, impeding evaluation of clinical and genetic risk factors across studies and efforts to combine samples within consortia. Here, we present expert and data-supported recommendations for defining suicidality and control phenotypes to facilitate merging current/legacy samples with definition variability and aid future sample creation. Methods: A subgroup of clinician researchers and experts from the Suicide Workgroup of the Psychiatric Genomics Consortium (PGC) reviewed existing PGC definitions for SI, SA, SD, and control groups and generated preliminary consensus guidelines for instrument-derived and international classification of disease (ICD) data. ICD lists were validated in two independent datasets (N = 9,151 and 12,394). Results: Recommendations are provided for evaluated instruments for SA and SI, emphasizing selection of lifetime measures phenotype-specific wording. Recommendations are also provided for defining SI and SD from ICD data. As the SA ICD definition is complex, SA code list recommendations were validated against instrument results with sensitivity (range = 15.4% to 80.6%), specificity (range = 67.6% to 97.4%), and positive predictive values (range = 0.59-0.93) reported. Conclusions: Best-practice guidelines are presented for the use of existing information to define SI/SA/SD in consortia research. These proposed definitions are expected to facilitate more homogeneous data aggregation for genetic and multisite studies. Future research should involve refinement, improved generalizability, and validation in diverse populations.

Comorbidity Profiles of Posttraumatic Stress Disorder Across the Medical Phenome.

Background: Previous epidemiological research has linked posttraumatic stress disorder (PTSD) with specific physical health problems, but the comprehensive landscape of medical conditions associated with PTSD remains uncharacterized. Electronic health records provide an opportunity to overcome clinical knowledge gaps and uncover associations with biological relevance that potentially vary by sex. Methods: PTSD was defined among biobank participants (N = 145,959) in 3 major healthcare systems using 2 ICD code-based definitions: broad (≥1 PTSD or acute stress codes vs. 0; n cases = 16,706) and narrow (≥2 PTSD codes vs. 0; n cases = 3325). Using a phenome-wide association study design, we tested associations between each PTSD definition and all prevalent disease umbrella categories, i.e., phecodes. We also conducted sex-stratified phenome-wide association study analyses including a sex × diagnosis interaction term in each logistic regression. Results: A substantial number of phecodes were significantly associated with PTSDNarrow (61%) and PTSDBroad (83%). While the strongest associations were shared between the 2 definitions, PTSDBroad captured 334 additional phecodes not significantly associated with PTSDNarrow and exhibited a wider range of significantly associated phecodes across various categories, including respiratory, genitourinary, and circulatory conditions. Sex differences were observed in that PTSDBroad was more strongly associated with osteoporosis, respiratory failure, hemorrhage, and pulmonary heart disease among male patients and with urinary tract infection, acute pharyngitis, respiratory infections, and overweight among female patients. Conclusions: This study provides valuable insights into a diverse range of comorbidities associated with PTSD, including both known and novel associations, while highlighting the influence of sex differences and the impact of defining PTSD using electronic health records.

Posttraumatic stress disorder (PTSD) is a debilitating psychiatric disorder that some people develop following a traumatic event. In addition to mental symptoms, PTSD can impact human health in ways other ways; for example, there are many known conditions that co-occur with PTSD, such as cardiovascular conditions. In this study, we set out to understand the breadth and degree to which PTSD co-occurs with medical outcomes in a sample of over 146,000 patients across 3 large medical systems. We found that both narrowly and broadly defined PTSD diagnosis co-occurred with hundreds of medical conditions, and the strongest associations were with other psychiatric disorders, respiratory conditions (asthma, GERD), sleep-related conditions, and pain. These results provide insights into future genetic studies of PTSD in large-scale biobanks and deepen our understanding of the complex needs of patients with PTSD.

Heterogeneity in suicide risk: Evidence from personalized dynamic models.

Most theories of suicide propose within-person changes in psychological states cause suicidal thoughts/behaviors; however, most studies use between-person analyses. Thus, there are little empirical data exploring current theories in the way they are hypothesized to occur. We used a form of statistical modeling called group iterative multiple model estimation (GIMME) to explore one theory of suicide: The Interpersonal Theory of Suicide (IPTS). GIMME estimates personalized statistical models for each individual and associations shared across individuals. Data were from a real-time monitoring study of individuals with a history of suicidal thoughts/behavior (adult sample: participants = 111, observations = 25,242; adolescent sample: participants = 145, observations = 26,182). Across both samples, none of theorized IPTS effects (i.e., contemporaneous effect from hopeless to suicidal thinking) were shared at the group level. There was significant heterogeneity in the personalized models, suggesting there are different pathways through which different people come to experience suicidal thoughts/behaviors. These findings highlight the complexity of suicide risk and the need for more personalized approaches to assessment and prediction.

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.

Validation of an ICD-Code-Based Case Definition for Psychotic Illness Across Three Health Systems.

BACKGROUND AND HYPOTHESIS: Psychosis-associated diagnostic codes are increasingly being utilized as case definitions for electronic health record (EHR)-based algorithms to predict and detect psychosis. However, data on the validity of psychosis-related diagnostic codes is limited. We evaluated the positive predictive value (PPV) of International Classification of Diseases (ICD) codes for psychosis. STUDY DESIGN: Using EHRs at 3 health systems, ICD codes comprising primary psychotic disorders and mood disorders with psychosis were grouped into 5 higher-order groups. 1133 records were sampled for chart review using the full EHR. PPVs (the probability of chart-confirmed psychosis given ICD psychosis codes) were calculated across multiple treatment settings. STUDY RESULTS: PPVs across all diagnostic groups and hospital systems exceeded 70%: Mass General Brigham 0.72 [95% CI 0.68-0.77], Boston Children's Hospital 0.80 [0.75-0.84], and Boston Medical Center 0.83 [0.79-0.86]. Schizoaffective disorder PPVs were consistently the highest across sites (0.80-0.92) and major depressive disorder with psychosis were the most variable (0.57-0.79). To determine if the first documented code captured first-episode psychosis (FEP), we excluded cases with prior chart evidence of a diagnosis of or treatment for a psychotic illness, yielding substantially lower PPVs (0.08-0.62). CONCLUSIONS: We found that the first documented psychosis diagnostic code accurately captured true episodes of psychosis but was a poor index of FEP. These data have important implications for the case definitions used in the development of risk prediction models designed to predict or detect undiagnosed psychosis.

Managing differential performance of polygenic risk scores across groups: Real-world experience of the eMERGE Network.

The differential performance of polygenic risk scores (PRSs) by group is one of the major ethical barriers to their clinical use. It is also one of the main practical challenges for any implementation effort. The social repercussions of how people are grouped in PRS research must be considered in communications with research participants, including return of results. Here, we outline the decisions faced and choices made by a large multi-site clinical implementation study returning PRSs to diverse participants in handling this issue of differential performance. Our approach to managing the complexities associated with the differential performance of PRSs serves as a case study that can help future implementers of PRSs to plot an anticipatory course in response to this issue.

Multi-ancestry meta-analysis of tobacco use disorder identifies 461 potential risk genes and reveals associations with multiple health outcomes.

Tobacco use disorder (TUD) is the most prevalent substance use disorder in the world. Genetic factors influence smoking behaviours and although strides have been made using genome-wide association studies to identify risk variants, most variants identified have been for nicotine consumption, rather than TUD. Here we leveraged four US biobanks to perform a multi-ancestral meta-analysis of TUD (derived via electronic health records) in 653,790 individuals (495,005 European, 114,420 African American and 44,365 Latin American) and data from UK Biobank (ncombined = 898,680). We identified 88 independent risk loci; integration with functional genomic tools uncovered 461 potential risk genes, primarily expressed in the brain. TUD was genetically correlated with smoking and psychiatric traits from traditionally ascertained cohorts, externalizing behaviours in children and hundreds of medical outcomes, including HIV infection, heart disease and pain. This work furthers our biological understanding of TUD and establishes electronic health records as a source of phenotypic information for studying the genetics of TUD.

Interoperability of phenome-wide multimorbidity patterns: a comparative study of two large-scale EHR systems.

Background: Electronic health records (EHR) are increasingly used for studying multimorbidities. However, concerns about accuracy, completeness, and EHRs being primarily designed for billing and administrative purposes raise questions about the consistency and reproducibility of EHR-based multimorbidity research. Methods: Utilizing phecodes to represent the disease phenome, we analyzed pairwise comorbidity strengths using a dual logistic regression approach and constructed multimorbidity as an undirected weighted graph. We assessed the consistency of the multimorbidity networks within and between two major EHR systems at local (nodes and edges), meso (neighboring patterns), and global (network statistics) scales. We present case studies to identify disease clusters and uncover clinically interpretable disease relationships. We provide an interactive web tool and a knowledge base combining data from multiple sources for online multimorbidity analysis. Findings: Analyzing data from 500,000 patients across Vanderbilt University Medical Center and Mass General Brigham health systems, we observed a strong correlation in disease frequencies (Kendall's τ = 0.643) and comorbidity strengths (Pearson ρ = 0.79). Consistent network statistics across EHRs suggest similar structures of multimorbidity networks at various scales. Comorbidity strengths and similarities of multimorbidity connection patterns align with the disease genetic correlations. Graph-theoretic analyses revealed a consistent core-periphery structure, implying efficient network clustering through threshold graph construction. Using hydronephrosis as a case study, we demonstrated the network's ability to uncover clinically relevant disease relationships and provide novel insights. Interpretation: Our findings demonstrate the robustness of large-scale EHR data for studying phenome-wide multimorbidities. The alignment of multimorbidity patterns with genetic data suggests the potential utility for uncovering shared biology of diseases. The consistent core-periphery structure offers analytical insights to discover complex disease interactions. This work also sets the stage for advanced disease modeling, with implications for precision medicine. Funding: VUMC Biostatistics Development Award, the National Institutes of Health, and the VA CSRD.

Integrating Electronic Health Records and Polygenic Risk to Identify Genetically Unrelated Comorbidities of Schizophrenia That May Be Modifiable.

Background: Patients with schizophrenia have substantial comorbidity that contributes to reduced life expectancy of 10 to 20 years. Identifying modifiable comorbidities could improve rates of premature mortality. 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 are enriched for potentially modifiable associations. Methods: Phenome-wide comorbidity was calculated from electronic health records of 250,000 patients across 2 independent health care institutions (Vanderbilt University Medical Center and Mass General Brigham); associations with schizophrenia polygenic risk scores were calculated across the same phenotypes in linked biobanks. Results: Schizophrenia comorbidity was significantly correlated across institutions (r = 0.85), and the 77 identified comorbidities were consistent with prior literature. Overall, comorbidity and polygenic risk score associations were significantly correlated (r = 0.55, p = 1.29 × 10-118). However, directly testing for the absence of genetic effects identified 36 comorbidities that had significantly equivalent schizophrenia polygenic risk score distributions between cases and controls. This set included phenotypes known to be consequences of antipsychotic medications (e.g., movement disorders) or of the disease such as reduced hygiene (e.g., diseases of the nail), thereby validating the approach. It also highlighted phenotypes with less clear causal relationships and minimal genetic effects such as tobacco use disorder and diabetes. Conclusions: This work demonstrates the consistency and robustness of electronic health record-based schizophrenia comorbidities across independent institutions and with the existing literature. It identifies known and novel comorbidities with an absence of shared genetic risk, indicating other causes that may be modifiable and where further study of causal pathways could improve outcomes for patients.

Patients with schizophrenia have many co-occurring diseases that contribute substantially to premature mortality of 10 to 20 years. Conditions that are comorbid but lack shared genetic risk with schizophrenia are likely to have causes that are more modifiable. Here, we calculated comorbidity from electronic health records from 2 independent health care institutions and associations with schizophrenia polygenic risk scores across the same phenotypes in linked biobanks. We identified known and novel diseases comorbid with schizophrenia, thereby validating our approach.

Polygenic Risk for Type 2 Diabetes in African Americans.

African Americans (AAs) have been underrepresented in polygenic risk score (PRS) studies. Here, we integrated genome-wide data from multiple observational studies on type 2 diabetes (T2D), encompassing a total of 101,987 AAs, to train and optimize an AA-focused T2D PRS (PRSAA), using a Bayesian polygenic modeling method. We further tested the score in three independent studies with a total of 7,275 AAs and compared the PRSAA with other published scores. Results show that a 1-SD increase in the PRSAA was associated with 40-60% increase in the odds of T2D (odds ratio [OR] 1.60, 95% CI 1.37-1.88; OR 1.40, 95% CI 1.16-1.70; and OR 1.45, 95% CI 1.30-1.62) across three testing cohorts. These models captured 1.0-2.6% of the variance (R2) in T2D on the liability scale. The positive predictive values for three calculated score thresholds (the top 2%, 5%, and 10%) ranged from 14 to 35%. The PRSAA, in general, performed similarly to existing T2D PRS. The need remains for larger data sets to continue to evaluate the utility of within-ancestry scores in the AA population.

Validation of an ICD-code-based case definition for psychotic illness across three health systems.

Background and Hypothesis: Early detection of psychosis is critical for improving outcomes. Algorithms to predict or detect psychosis using electronic health record (EHR) data depend on the validity of the case definitions used, typically based on diagnostic codes. Data on the validity of psychosis-related diagnostic codes is limited. We evaluated the positive predictive value (PPV) of International Classification of Diseases (ICD) codes for psychosis. Study Design: Using EHRs at three health systems, ICD codes comprising primary psychotic disorders and mood disorders with psychosis were grouped into five higher-order groups. 1,133 records were sampled for chart review using the full EHR. PPVs (the probability of chart-confirmed psychosis given ICD psychosis codes) were calculated across multiple treatment settings. Study Results: PPVs across all diagnostic groups and hospital systems exceeded 70%: Massachusetts General Brigham 0.72 [95% CI 0.68-0.77], Boston Children's Hospital 0.80 [0.75-0.84], and Boston Medical Center 0.83 [0.79-0.86]. Schizoaffective disorder PPVs were consistently the highest across sites (0.80-0.92) and major depressive disorder with psychosis were the most variable (0.57-0.79). To determine if the first documented code captured first-episode psychosis (FEP), we excluded cases with prior chart evidence of a diagnosis of or treatment for a psychotic illness, yielding substantially lower PPVs (0.08-0.62). Conclusions: We found that the first documented psychosis diagnostic code accurately captured true episodes of psychosis but was a poor index of FEP. These data have important implications for the development of risk prediction models designed to predict or detect undiagnosed psychosis.

Optimizing precision medicine for second-step depression treatment: a machine learning approach.

BACKGROUND: Less than a third of patients with depression achieve successful remission with standard first-step antidepressant monotherapy. The process for determining appropriate second-step care is often based on clinical intuition and involves a protracted course of trial and error, resulting in substantial patient burden and unnecessary delay in the provision of optimal treatment. To address this problem, we adopt an ensemble machine learning approach to improve prediction accuracy of remission in response to second-step treatments. METHOD: Data were derived from the Level 2 stage of the STAR*D dataset, which included 1439 patients who were randomized into one of seven different second-step treatment strategies after failing to achieve remission during first-step antidepressant treatment. Ensemble machine learning models, comprising several individual algorithms, were evaluated using nested cross-validation on 155 predictor variables including clinical and demographic measures. RESULTS: The ensemble machine learning algorithms exhibited differential classification performance in predicting remission status across the seven second-step treatments. For the full set of predictors, AUC values ranged from 0.51 to 0.82 depending on the second-step treatment type. Predicting remission was most successful for cognitive therapy (AUC = 0.82) and least successful for other medication and combined treatment options (AUCs = 0.51-0.66). CONCLUSION: Ensemble machine learning has potential to predict second-step treatment. In this study, predictive performance varied by type of treatment, with greater accuracy in predicting remission in response to behavioral treatments than to pharmacotherapy interventions. Future directions include considering more informative predictor modalities to enhance prediction of second-step treatment response.

Continuous-Time and Dynamic Suicide Attempt Risk Prediction with Neural Ordinary Differential Equations.

Suicide is one of the leading causes of death in the US, and the number of attributable deaths continues to increase. Risk of suicide-related behaviors (SRBs) is dynamic, and SRBs can occur across a continuum of time and locations. However, current SRB risk assessment methods, whether conducted by clinicians or through machine learning models, treat SRB risk as static and are confined to specific times and locations, such as following a hospital visit. Such a paradigm is unrealistic as SRB risk fluctuates and creates time gaps in the availability of risk scores. Here, we develop two closely related model classes, Event-GRU-ODE and Event-GRU-Discretized, that can predict the dynamic risk of events as a continuous trajectory based on Neural ODEs, an advanced AI model class for time series prediction. As such, these models can estimate changes in risk across the continuum of future time points, even without new observations, and can update these estimations as new data becomes available. We train and validate these models for SRB prediction using a large electronic health records database. Both models demonstrated high discrimination performance for SRB prediction (e.g., AUROC > 0.92 in the full, general cohort), serving as an initial step toward developing novel and comprehensive suicide prevention strategies based on dynamic changes in risk.

Polygenic risk for suicide attempt is associated with lifetime suicide attempt in US soldiers independent of parental risk.

BACKGROUND: Suicide is a leading cause of death worldwide. Whereas some studies have suggested that a direct measure of common genetic liability for suicide attempts (SA), captured by a polygenic risk score for SA (SA-PRS), explains risk independent of parental history, further confirmation would be useful. Even more unsettled is the extent to which SA-PRS is associated with lifetime non-suicidal self-injury (NSSI). METHODS: We used summary statistics from the largest available GWAS study of SA to generate SA-PRS for two non-overlapping cohorts of soldiers of European ancestry. These were tested in multivariable models that included parental major depressive disorder (MDD) and parental SA. RESULTS: In the first cohort, 417 (6.3 %) of 6573 soldiers reported lifetime SA and 1195 (18.2 %) reported lifetime NSSI. In a multivariable model that included parental history of MDD and parental history of SA, SA-PRS remained significantly associated with lifetime SA [aOR = 1.26, 95%CI:1.13-1.39, p < 0.001] per standardized unit SA-PRS]. In the second cohort, 204 (4.2 %) of 4900 soldiers reported lifetime SA, and 299 (6.1 %) reported lifetime NSSI. In a multivariable model that included parental history of MDD and parental history of SA, SA-PRS remained significantly associated with lifetime SA [aOR = 1.20, 95%CI:1.04-1.38, p = 0.014]. A combined analysis of both cohorts yielded similar results. In neither cohort or in the combined analysis was SA-PRS significantly associated with NSSI. CONCLUSIONS: PRS for SA conveys information about likelihood of lifetime SA (but not NSSI, demonstrating specificity), independent of self-reported parental history of MDD and parental history of SA. LIMITATIONS: At present, the magnitude of effects is small and would not be immediately useful for clinical decision-making or risk-stratified prevention initiatives, but this may be expected to improve with further iterations. Also critical will be the extension of these findings to more diverse populations.

Identifying genetic differences between bipolar disorder and major depression through multiple GWAS.

Background: Accurate diagnosis of bipolar disorder (BD) is difficult in clinical practice, with an average delay between symptom onset and diagnosis of about 7 years. A key reason is that the first manic episode is often preceded by a depressive one, making it difficult to distinguish BD from unipolar major depressive disorder (MDD). Aims: Here, we use genome-wide association analyses (GWAS) to identify differential genetic factors and to develop predictors based on polygenic risk scores that may aid early differential diagnosis. Methods: Based on individual genotypes from case-control cohorts of BD and MDD shared through the Psychiatric Genomics Consortium, we compile case-case-control cohorts, applying a careful merging and quality control procedure. In a resulting cohort of 51,149 individuals (15,532 BD cases, 12,920 MDD cases and 22,697 controls), we perform a variety of GWAS and polygenic risk scores (PRS) analyses. Results: While our GWAS is not well-powered to identify genome-wide significant loci, we find significant SNP-heritability and demonstrate the ability of the resulting PRS to distinguish BD from MDD, including BD cases with depressive onset. We replicate our PRS findings, but not signals of individual loci in an independent Danish cohort (iPSYCH 2015 case-cohort study, N=25,966). We observe strong genetic correlation between our case-case GWAS and that of case-control BD. Conclusions: We find that MDD and BD, including BD with a depressive onset, are genetically distinct. Further, our findings support the hypothesis that Controls - MDD - BD primarily lie on a continuum of genetic risk. Future studies with larger and richer samples will likely yield a better understanding of these findings and enable the development of better genetic predictors distinguishing BD and, importantly, BD with depressive onset from MDD.

Distinguishing different psychiatric disorders using DDx-PRS.

Despite great progress on methods for case-control polygenic prediction (e.g. schizophrenia vs. control), there remains an unmet need for a method that genetically distinguishes clinically related disorders (e.g. schizophrenia (SCZ) vs. bipolar disorder (BIP) vs. depression (MDD) vs. control); such a method could have important clinical value, especially at disorder onset when differential diagnosis can be challenging. Here, we introduce a method, Differential Diagnosis-Polygenic Risk Score (DDx-PRS), that jointly estimates posterior probabilities of each possible diagnostic category (e.g. SCZ=50%, BIP=25%, MDD=15%, control=10%) by modeling variance/covariance structure across disorders, leveraging case-control polygenic risk scores (PRS) for each disorder (computed using existing methods) and prior clinical probabilities for each diagnostic category. DDx-PRS uses only summary-level training data and does not use tuning data, facilitating implementation in clinical settings. In simulations, DDx-PRS was well-calibrated (whereas a simpler approach that analyzes each disorder marginally was poorly calibrated), and effective in distinguishing each diagnostic category vs. the rest. We then applied DDx-PRS to Psychiatric Genomics Consortium SCZ/BIP/MDD/control data, including summary-level training data from 3 case-control GWAS ( N =41,917-173,140 cases; total N =1,048,683) and held-out test data from different cohorts with equal numbers of each diagnostic category (total N =11,460). DDx-PRS was well-calibrated and well-powered relative to these training sample sizes, attaining AUCs of 0.66 for SCZ vs. rest, 0.64 for BIP vs. rest, 0.59 for MDD vs. rest, and 0.68 for control vs. rest. DDx-PRS produced comparable results to methods that leverage tuning data, confirming that DDx-PRS is an effective method. True diagnosis probabilities in top deciles of predicted diagnosis probabilities were considerably larger than prior baseline probabilities, particularly in projections to larger training sample sizes, implying considerable potential for clinical utility under certain circumstances. In conclusion, DDx-PRS is an effective method for distinguishing clinically related disorders.

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.

Substance Use, Suicidal Thoughts, and Psychiatric Comorbidities Among High School Students.

This cross-sectional study evaluates the dose-dependent association between alcohol, cannabis, and nicotine use and psychiatric symptoms among participants in the Substance Use and Risk Factor Survey and the Youth Risk Behavior Survey.

mixWAS: An efficient distributed algorithm for mixed-outcomes genome-wide association studies.

Genome-wide association studies (GWAS) have been instrumental in identifying genetic associations for various diseases and traits. However, uncovering genetic underpinnings among traits beyond univariate phenotype associations remains a challenge. Multi-phenotype associations (MPA), or genetic pleiotropy, offer important insights into shared genes and pathways among traits, enhancing our understanding of genetic architectures of complex diseases. GWAS of biobank-linked electronic health record (EHR) data are increasingly being utilized to identify MPA among various traits and diseases. However, methodologies that can efficiently take advantage of distributed EHR to detect MPA are still lacking. Here, we introduce mixWAS, a novel algorithm that efficiently and losslessly integrates multiple EHRs via summary statistics, allowing the detection of MPA among mixed phenotypes while accounting for heterogeneities across EHRs. Simulations demonstrate that mixWAS outperforms the widely used MPA detection method, Phenome-wide association study (PheWAS), across diverse scenarios. Applying mixWAS to data from seven EHRs in the US, we identified 4,534 MPA among blood lipids, BMI, and circulatory diseases. Validation in an independent EHR data from UK confirmed 97.7% of the associations. mixWAS fundamentally improves the detection of MPA and is available as a free, open-source software.