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.

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.

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.

Improving ascertainment of suicidal ideation and suicide attempt with natural language processing.

Methods relying on diagnostic codes to identify suicidal ideation and suicide attempt in Electronic Health Records (EHRs) at scale are suboptimal because suicide-related outcomes are heavily under-coded. We propose to improve the ascertainment of suicidal outcomes using natural language processing (NLP). We developed information retrieval methodologies to search over 200 million notes from the Vanderbilt EHR. Suicide query terms were extracted using word2vec. A weakly supervised approach was designed to label cases of suicidal outcomes. The NLP validation of the top 200 retrieved patients showed high performance for suicidal ideation (area under the receiver operator curve [AUROC]: 98.6, 95% confidence interval [CI] 97.1-99.5) and suicide attempt (AUROC: 97.3, 95% CI 95.2-98.7). Case extraction produced the best performance when combining NLP and diagnostic codes and when accounting for negated suicide expressions in notes. Overall, we demonstrated that scalable and accurate NLP methods can be developed to identify suicidal behavior in EHRs to enhance prevention efforts, predictive models, and precision medicine.

Leveraging electronic health records to inform genetic counseling practice surrounding psychiatric disorders.

Since nearly one-fifth of US adults have a psychiatric disorder, genetic counselors (GCs) will see many patients with these indications. However, GCs' reports of inadequate preparation and low confidence in providing care for patients with psychiatric disorders can limit their ability to meet patient's needs. How frequently psychiatric disorders present in GC sessions is currently unclear. Here, we used deidentified electronic health records (EHR) to estimate the prevalence of 16 psychiatric disorders. In 7,155 GC patients, 34% had a diagnostic code associated with a psychiatric disorder; 23% with anxiety/phobic disorders; 21% with mood disorder/depression; 5% with attention deficit hyperactivity disorder (ADHD); and 1% with psychotic disorders. Compared to 415,709 demographically matched controls, GC patients showed a significantly higher prevalence of psychiatric disorders (GC prevalence: 34%, matched prevalence: 30%, p-value < 0.0001) driven predominantly by anxiety disorder, major depressive disorder, generalized anxiety disorder, and ADHD. Within GC specialties (prenatal: n = 2,674, cancer: n = 1,474, pediatric: n = 465), only pediatric GC patients showed a significant increase in psychiatric disorder prevalence overall (pediatric GC prevalence: 28%, matched prevalence: 13%, p-value < 0.0001). However, significant evidence of increased prevalence existed for generalized anxiety disorder (prenatal GC prevalence 6.4%, matched prevalence: 4.9%, p-value < 0.0001), anxiety disorders (cancer GC prevalence: 26%, matched prevalence: 21%, p-value < 0.0001 and pediatric GC prevalence: 12%, matched prevalence: 5.5%), and ADHD (pediatric GC prevalence: 18%, matched prevalence: 7.9%, p-value < 0.0001). These results highlight the need for additional guidance around care for patients with psychiatric disorders and the value of EHR-based research in genetic counseling.

Phenotypic signatures in clinical data enable systematic identification of patients for genetic testing.

Around 5% of the population is affected by a rare genetic disease, yet most endure years of uncertainty before receiving a genetic test. A common feature of genetic diseases is the presence of multiple rare phenotypes that often span organ systems. Here, we use diagnostic billing information from longitudinal clinical data in the electronic health records (EHRs) of 2,286 patients who received a chromosomal microarray test, and 9,144 matched controls, to build a model to predict who should receive a genetic test. The model achieved high prediction accuracies in a held-out test sample (area under the receiver operating characteristic curve (AUROC), 0.97; area under the precision-recall curve (AUPRC), 0.92), in an independent hospital system (AUROC, 0.95; AUPRC, 0.62), and in an independent set of 172,265 patients in which cases were broadly defined as having an interaction with a genetics provider (AUROC, 0.9; AUPRC, 0.63). Patients carrying a putative pathogenic copy number variant were also accurately identified by the model. Compared with current approaches for genetic test determination, our model could identify more patients for testing while also increasing the proportion of those tested who have a genetic disease. We demonstrate that phenotypic patterns representative of a wide range of genetic diseases can be captured from EHRs to systematize decision-making for genetic testing, with the potential to speed up diagnosis, improve care and reduce costs.