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.

Prospective, multi-site study of healthcare utilization after actionable monogenic findings from clinical sequencing.

As large-scale genomic screening becomes increasingly prevalent, understanding the influence of actionable results on healthcare utilization is key to estimating the potential long-term clinical impact. The eMERGE network sequenced individuals for actionable genes in multiple genetic conditions and returned results to individuals, providers, and the electronic health record. Differences in recommended health services (laboratory, imaging, and procedural testing) delivered within 12 months of return were compared among individuals with pathogenic or likely pathogenic (P/LP) findings to matched individuals with negative findings before and after return of results. Of 16,218 adults, 477 unselected individuals were found to have a monogenic risk for arrhythmia (n = 95), breast cancer (n = 96), cardiomyopathy (n = 95), colorectal cancer (n = 105), or familial hypercholesterolemia (n = 86). Individuals with P/LP results more frequently received services after return (43.8%) compared to before return (25.6%) of results and compared to individuals with negative findings (24.9%; p < 0.0001). The annual cost of qualifying healthcare services increased from an average of $162 before return to $343 after return of results among the P/LP group (p < 0.0001); differences in the negative group were non-significant. The mean difference-in-differences was $149 (p < 0.0001), which describes the increased cost within the P/LP group corrected for cost changes in the negative group. When stratified by individual conditions, significant cost differences were observed for arrhythmia, breast cancer, and cardiomyopathy. In conclusion, less than half of individuals received billed health services after monogenic return, which modestly increased healthcare costs for payors in the year following return.

Characterizing genetic profiles for high triglyceride levels in U.S. patients of African ancestry.

Hypertriglyceridemia (HTG) is a common cardiovascular risk factor characterized by elevated triglyceride (TG) levels. Researchers have assessed the genetic factors that influence HTG in studies focused predominantly on individuals of European ancestry. However, relatively little is known about the contribution of genetic variation of HTG in people of African ancestry (AA), potentially constraining research and treatment opportunities. Our objective was to characterize genetic profiles among individuals of AA with mild-to-moderate HTG and severe HTG versus those with normal TGs by leveraging whole-genome sequencing data and longitudinal electronic health records available in the All of Us program. We compared the enrichment of functional variants within five canonical TG metabolism genes, an AA-specific polygenic risk score for TGs, and frequencies of 145 known potentially causal TG variants between HTG patients and normal TG among a cohort of AA patients (N = 15,373). Those with mild-to-moderate HTG (N = 342) and severe HTG (N ≤ 20) were more likely to carry APOA5 p.S19W (odds ratio = 1.94, 95% confidence interval = [1.48-2.54], P = 1.63 × 10-6 and OR = 3.65, 95% confidence interval: [1.22-10.93], P = 0.02, respectively) than those with normal TG. They were also more likely to have an elevated (top 10%) polygenic risk score, elevated carriage of potentially causal variant alleles, and carry any genetic risk factor. Alternative definitions of HTG yielded comparable results. In conclusion, individuals of AA with HTG were enriched for genetic risk factors compared to individuals with normal TGs.

High-throughput framework for genetic analyses of adverse drug reactions using electronic health records.

Understanding the contribution of genetic variation to drug response can improve the delivery of precision medicine. However, genome-wide association studies (GWAS) for drug response are uncommon and are often hindered by small sample sizes. We present a high-throughput framework to efficiently identify eligible patients for genetic studies of adverse drug reactions (ADRs) using "drug allergy" labels from electronic health records (EHRs). As a proof-of-concept, we conducted GWAS for ADRs to 14 common drug/drug groups with 81,739 individuals from Vanderbilt University Medical Center's BioVU DNA Biobank. We identified 7 genetic loci associated with ADRs at P < 5 × 10-8, including known genetic associations such as CYP2D6 and OPRM1 for CYP2D6-metabolized opioid ADR. Additional expression quantitative trait loci and phenome-wide association analyses added evidence to the observed associations. Our high-throughput framework is both scalable and portable, enabling impactful pharmacogenomic research to improve precision medicine.

Correction: A missense variant in Mitochondrial Amidoxime Reducing Component 1 gene and protection against liver disease.

[This corrects the article DOI: 10.1371/journal.pgen.1008629.].

Genome-Wide Association Study of CKD Progression.

SIGNIFICANCE STATEMENT: Rapid progression of CKD is associated with poor clinical outcomes. Most previous studies looking for genetic factors associated with low eGFR have used cross-sectional data. The authors conducted a meta-analysis of genome-wide association studies of eGFR decline among 116,870 participants with CKD, focusing on longitudinal data. They identified three loci (two of them novel) associated with longitudinal eGFR decline. In addition to the known UMOD/PDILT locus, variants within BICC1 were associated with significant differences in longitudinal eGFR slope. Variants within HEATR4 also were associated with differences in eGFR decline, but only among Black/African American individuals without diabetes. These findings help characterize molecular mechanisms of eGFR decline in CKD and may inform new therapeutic approaches for progressive kidney disease. BACKGROUND: Rapid progression of CKD is associated with poor clinical outcomes. Despite extensive study of the genetics of cross-sectional eGFR, only a few loci associated with eGFR decline over time have been identified. METHODS: We performed a meta-analysis of genome-wide association studies of eGFR decline among 116,870 participants with CKD-defined by two outpatient eGFR measurements of <60 ml/min per 1.73 m 2 , obtained 90-365 days apart-from the Million Veteran Program and Vanderbilt University Medical Center's DNA biobank. The primary outcome was the annualized relative slope in outpatient eGFR. Analyses were stratified by ethnicity and diabetes status and meta-analyzed thereafter. RESULTS: In cross-ancestry meta-analysis, the strongest association was rs77924615, near UMOD / PDILT ; each copy of the G allele was associated with a 0.30%/yr faster eGFR decline ( P = 4.9×10 -27 ). We also observed an association within BICC1 (rs11592748), where every additional minor allele was associated with a 0.13%/yr slower eGFR decline ( P = 5.6×10 -9 ). Among participants without diabetes, the strongest association was the UMOD/PDILT variant rs36060036, associated with a 0.27%/yr faster eGFR decline per copy of the C allele ( P = 1.9×10 -17 ). Among Black participants, a significantly faster eGFR decline was associated with variant rs16996674 near APOL1 (R 2 =0.29 with the G1 high-risk genotype); among Black participants with diabetes, lead variant rs11624911 near HEATR4 also was associated with a significantly faster eGFR decline. We also nominally replicated loci with known associations with eGFR decline, near PRKAG2, FGF5, and C15ORF54. CONCLUSIONS: Three loci were significantly associated with longitudinal eGFR change at genome-wide significance. These findings help characterize molecular mechanisms of eGFR decline and may contribute to the development of new therapeutic approaches for progressive CKD.

Natural language processing to identify lupus nephritis phenotype in electronic health records.

BACKGROUND: Systemic lupus erythematosus (SLE) is a rare autoimmune disorder characterized by an unpredictable course of flares and remission with diverse manifestations. Lupus nephritis, one of the major disease manifestations of SLE for organ damage and mortality, is a key component of lupus classification criteria. Accurately identifying lupus nephritis in electronic health records (EHRs) would therefore benefit large cohort observational studies and clinical trials where characterization of the patient population is critical for recruitment, study design, and analysis. Lupus nephritis can be recognized through procedure codes and structured data, such as laboratory tests. However, other critical information documenting lupus nephritis, such as histologic reports from kidney biopsies and prior medical history narratives, require sophisticated text processing to mine information from pathology reports and clinical notes. In this study, we developed algorithms to identify lupus nephritis with and without natural language processing (NLP) using EHR data from the Northwestern Medicine Enterprise Data Warehouse (NMEDW). METHODS: We developed five algorithms: a rule-based algorithm using only structured data (baseline algorithm) and four algorithms using different NLP models. The first NLP model applied simple regular expression for keywords search combined with structured data. The other three NLP models were based on regularized logistic regression and used different sets of features including positive mention of concept unique identifiers (CUIs), number of appearances of CUIs, and a mixture of three components (i.e. a curated list of CUIs, regular expression concepts, structured data) respectively. The baseline algorithm and the best performing NLP algorithm were externally validated on a dataset from Vanderbilt University Medical Center (VUMC). RESULTS: Our best performing NLP model incorporated features from both structured data, regular expression concepts, and mapped concept unique identifiers (CUIs) and showed improved F measure in both the NMEDW (0.41 vs 0.79) and VUMC (0.52 vs 0.93) datasets compared to the baseline lupus nephritis algorithm. CONCLUSION: Our NLP MetaMap mixed model improved the F-measure greatly compared to the structured data only algorithm in both internal and external validation datasets. The NLP algorithms can serve as powerful tools to accurately identify lupus nephritis phenotype in EHR for clinical research and better targeted therapies.

Efficient Catalytic Degradation of Methyl Orange by Various ZnO-Doped Lignin-Based Carbons.

Herein, a series of ZnO-doped lignin-based carbons (LC/ZnO) were successfully prepared from different types of lignin and used for methyl orange (MO) photocatalytic degradation. The apparent morphology, internal structure, and photoelectric properties of prepared LC/ZnO composites and their effects on subsequent MO photocatalytic degradation were investigated by various characterization techniques. The results showed that the LC/ZnO composites that were prepared in this work mainly consisted of highly dispersed ZnO nanoparticles and lignin-based carbon nano-sheets, which were beneficial for subsequent photogenerated electrons and holes formation, dispersion, and migration. The MO could be significantly degraded with various ZnO-doped lignin-based carbons, especially over the LCSL/ZnO, and the maximum degradation rate was 96.9% within 30 min under the simulated 300w sunlight exposure. The experiments of free radical elimination showed that the photocatalytic degradation of MO over LC/ZnO were a result of the co-action of multiple free radicals, and h+ might play the predominant roles in MO degradation. In addition, the pH of the solution had little effect on MO degradation, and the MO could be effectively degraded even in an alkaline solution of pH = 12.0. The cycling experiments showed that the prepared LC/ZnO had a good stability for MO photodegradation, especially for LCSL/ZnO, even after 5 times recycling, and the degradation rate of MO only dropped from 97.0% to 93.0%. The research not only provided a fundamental theory for the efficient photocatalytic degradation of MO by LC/ZnO composites, but also offered a new insight into lignin valorization.

Arrhythmia Variant Associations and Reclassifications in the eMERGE-III Sequencing Study.

BACKGROUND: Sequencing Mendelian arrhythmia genes in individuals without an indication for arrhythmia genetic testing can identify carriers of pathogenic or likely pathogenic (P/LP) variants. However, the extent to which these variants are associated with clinically meaningful phenotypes before or after return of variant results is unclear. In addition, the majority of discovered variants are currently classified as variants of uncertain significance, limiting clinical actionability. METHODS: The eMERGE-III study (Electronic Medical Records and Genomics Phase III) is a multicenter prospective cohort that included 21 846 participants without previous indication for cardiac genetic testing. Participants were sequenced for 109 Mendelian disease genes, including 10 linked to arrhythmia syndromes. Variant carriers were assessed with electronic health record-derived phenotypes and follow-up clinical examination. Selected variants of uncertain significance (n=50) were characterized in vitro with automated electrophysiology experiments in HEK293 cells. RESULTS: As previously reported, 3.0% of participants had P/LP variants in the 109 genes. Herein, we report 120 participants (0.6%) with P/LP arrhythmia variants. Compared with noncarriers, arrhythmia P/LP carriers had a significantly higher burden of arrhythmia phenotypes in their electronic health records. Fifty-four participants had variant results returned. Nineteen of these 54 participants had inherited arrhythmia syndrome diagnoses (primarily long-QT syndrome), and 12 of these 19 diagnoses were made only after variant results were returned (0.05%). After in vitro functional evaluation of 50 variants of uncertain significance, we reclassified 11 variants: 3 to likely benign and 8 to P/LP. CONCLUSIONS: Genome sequencing in a large population without indication for arrhythmia genetic testing identified phenotype-positive carriers of variants in congenital arrhythmia syndrome disease genes. As the genomes of large numbers of people are sequenced, the disease risk from rare variants in arrhythmia genes can be assessed by integrating genomic screening, electronic health record phenotypes, and in vitro functional studies. REGISTRATION: URL: https://www. CLINICALTRIALS: gov; Unique identifier; NCT03394859.

Predictive Utility of Polygenic Risk Scores for Coronary Heart Disease in Three Major Racial and Ethnic Groups.

Because polygenic risk scores (PRSs) for coronary heart disease (CHD) are derived from mainly European ancestry (EA) cohorts, their validity in African ancestry (AA) and Hispanic ethnicity (HE) individuals is unclear. We investigated associations of "restricted" and genome-wide PRSs with CHD in three major racial and ethnic groups in the U.S. The eMERGE cohort (mean age 48 ± 14 years, 58% female) included 45,645 EA, 7,597 AA, and 2,493 HE individuals. We assessed two restricted PRSs (PRSTikkanen and PRSTada; 28 and 50 variants, respectively) and two genome-wide PRSs (PRSmetaGRS and PRSLDPred; 1.7 M and 6.6 M variants, respectively) derived from EA cohorts. Over a median follow-up of 11.1 years, 2,652 incident CHD events occurred. Hazard and odds ratios for the association of PRSs with CHD were similar in EA and HE cohorts but lower in AA cohorts. Genome-wide PRSs were more strongly associated with CHD than restricted PRSs were. PRSmetaGRS, the best performing PRS, was associated with CHD in all three cohorts; hazard ratios (95% CI) per 1 SD increase were 1.53 (1.46-1.60), 1.53 (1.23-1.90), and 1.27 (1.13-1.43) for incident CHD in EA, HE, and AA individuals, respectively. The hazard ratios were comparable in the EA and HE cohorts (pinteraction = 0.77) but were significantly attenuated in AA individuals (pinteraction= 2.9 × 10-3). These results highlight the potential clinical utility of PRSs for CHD as well as the need to assemble diverse cohorts to generate ancestry- and ethnicity PRSs.

Genome-wide Study Identifies Association between HLA-B∗55:01 and Self-Reported Penicillin Allergy.

Hypersensitivity reactions to drugs are often unpredictable and can be life threatening, underscoring a need for understanding their underlying mechanisms and risk factors. The extent to which germline genetic variation influences the risk of commonly reported drug allergies such as penicillin allergy remains largely unknown. We extracted data from the electronic health records of more than 600,000 participants from the UK, Estonian, and Vanderbilt University Medical Center's BioVU biobanks to study the role of genetic variation in the occurrence of self-reported penicillin hypersensitivity reactions. We used imputed SNP to HLA typing data from these cohorts to further fine map the human leukocyte antigen (HLA) association and replicated our results in 23andMe's research cohort involving a total of 1.12 million individuals. Genome-wide meta-analysis of penicillin allergy revealed two loci, including one located in the HLA region on chromosome 6. This signal was further fine-mapped to the HLA-B∗55:01 allele (OR 1.41 95% CI 1.33-1.49, p value 2.04 × 10-31) and confirmed by independent replication in 23andMe's research cohort (OR 1.30 95% CI 1.25-1.34, p value 1.00 × 10-47). The lead SNP was also associated with lower lymphocyte counts and in silico follow-up suggests a potential effect on T-lymphocytes at HLA-B∗55:01. We also observed a significant hit in PTPN22 and the GWAS results correlated with the genetics of rheumatoid arthritis and psoriasis. We present robust evidence for the role of an allele of the major histocompatibility complex (MHC) I gene HLA-B in the occurrence of penicillin allergy.

Education and electronic medical records and genomics network, challenges, and lessons learned from a large-scale clinical trial using polygenic risk scores.

Polygenic risk scores (PRS) have potential to improve health care by identifying individuals that have elevated risk for common complex conditions. Use of PRS in clinical practice, however, requires careful assessment of the needs and capabilities of patients, providers, and health care systems. The electronic Medical Records and Genomics (eMERGE) network is conducting a collaborative study which will return PRS to 25,000 pediatric and adult participants. All participants will receive a risk report, potentially classifying them as high risk (∼2-10% per condition) for 1 or more of 10 conditions based on PRS. The study population is enriched by participants from racial and ethnic minority populations, underserved populations, and populations who experience poorer medical outcomes. All 10 eMERGE clinical sites conducted focus groups, interviews, and/or surveys to understand educational needs among key stakeholders-participants, providers, and/or study staff. Together, these studies highlighted the need for tools that address the perceived benefit/value of PRS, types of education/support needed, accessibility, and PRS-related knowledge and understanding. Based on findings from these preliminary studies, the network harmonized training initiatives and formal/informal educational resources. This paper summarizes eMERGE's collective approach to assessing educational needs and developing educational approaches for primary stakeholders. It discusses challenges encountered and solutions provided.

Evaluating and mitigating bias in machine learning models for cardiovascular disease prediction.

OBJECTIVE: The study aims to investigate whether machine learning-based predictive models for cardiovascular disease (CVD) risk assessment show equivalent performance across demographic groups (such as race and gender) and if bias mitigation methods can reduce any bias present in the models. This is important as systematic bias may be introduced when collecting and preprocessing health data, which could affect the performance of the models on certain demographic sub-cohorts. The study is to investigate this using electronic health records data and various machine learning models. METHODS: The study used large de-identified Electronic Health Records data from Vanderbilt University Medical Center. Machine learning (ML) algorithms including logistic regression, random forest, gradient-boosting trees, and long short-term memory were applied to build multiple predictive models. Model bias and fairness were evaluated using equal opportunity difference (EOD, 0 indicates fairness) and disparate impact (DI, 1 indicates fairness). In our study, we also evaluated the fairness of a non-ML baseline model, the American Heart Association (AHA) Pooled Cohort Risk Equations (PCEs). Moreover, we compared the performance of three different de-biasing methods: removing protected attributes (e.g., race and gender), resampling the imbalanced training dataset by sample size, and resampling by the proportion of people with CVD outcomes. RESULTS: The study cohort included 109,490 individuals (mean [SD] age 47.4 [14.7] years; 64.5% female; 86.3% White; 13.7% Black). The experimental results suggested that most ML models had smaller EOD and DI than PCEs. For ML models, the mean EOD ranged from -0.001 to 0.018 and the mean DI ranged from 1.037 to 1.094 across race groups. There was a larger EOD and DI across gender groups, with EOD ranging from 0.131 to 0.136 and DI ranging from 1.535 to 1.587. For debiasing methods, removing protected attributes didn't significantly reduced the bias for most ML models. Resampling by sample size also didn't consistently decrease bias. Resampling by case proportion reduced the EOD and DI for gender groups but slightly reduced accuracy in many cases. CONCLUSIONS: Among the VUMC cohort, both PCEs and ML models were biased against women, suggesting the need to investigate and correct gender disparities in CVD risk prediction. Resampling by proportion reduced the bias for gender groups but not for race groups.

Representing and utilizing clinical textual data for real world studies: An OHDSI approach.

Clinical documentation in electronic health records contains crucial narratives and details about patients and their care. Natural language processing (NLP) can unlock the information conveyed in clinical notes and reports, and thus plays a critical role in real-world studies. The NLP Working Group at the Observational Health Data Sciences and Informatics (OHDSI) consortium was established to develop methods and tools to promote the use of textual data and NLP in real-world observational studies. In this paper, we describe a framework for representing and utilizing textual data in real-world evidence generation, including representations of information from clinical text in the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM), the workflow and tools that were developed to extract, transform and load (ETL) data from clinical notes into tables in OMOP CDM, as well as current applications and specific use cases of the proposed OHDSI NLP solution at large consortia and individual institutions with English textual data. Challenges faced and lessons learned during the process are also discussed to provide valuable insights for researchers who are planning to implement NLP solutions in real-world studies.

Race, Genotype, and Azathioprine Discontinuation : A Cohort Study.

BACKGROUND: Thiopurines are an important class of immunosuppressants despite their risk for hematopoietic toxicity and narrow therapeutic indices. Benign neutropenia related to an ACKR1 variant (rs2814778-CC) is common among persons of African ancestries. OBJECTIVE: To test whether rs2814778-CC was associated with azathioprine discontinuation attributed to hematopoietic toxicity and lower thiopurine dosing. DESIGN: Retrospective cohort study. SETTING: Two tertiary care centers. PATIENTS: Thiopurine users with White or Black race. MEASUREMENTS: Azathioprine discontinuation attributed to hematopoietic toxicity. Secondary outcomes included weight-adjusted final dose, leukocyte count, and change in leukocyte count. RESULTS: The rate of azathioprine discontinuation attributed to hematopoietic toxicity was 3.92 per 100 person-years among patients with the CC genotype (n = 101) and 1.34 per 100 person-years among those with the TT or TC genotype (n = 1365) (hazard ratio [HR] from competing-risk model, 2.92 [95% CI, 1.57 to 5.41]). The risk remained significant after adjustment for race (HR, 2.61 [CI, 1.01 to 6.71]). The risk associated with race alone (HR, 2.13 [CI, 1.21 to 3.75]) was abrogated by adjustment for genotype (HR, 1.13 [CI, 0.48 to 2.69]). Lower last leukocyte count and lower dosing were significant among patients with the CC genotype. Lower dosing was validated in an external cohort of 94 children of African ancestries prescribed the thiopurine 6-mercaptopurine (6-MP) for acute lymphoblastic leukemia. The CC genotype was independently associated with lower 6-MP dose intensity relative to the target daily dose of 75 mg/m2 (median, 0.83 [IQR, 0.70 to 0.94] for the CC genotype vs. 0.94 [IQR, 0.72 to 1.13] for the TT or TC genotype; P = 0.013). LIMITATIONS: Unmeasured confounding; data limited to tertiary centers. CONCLUSION: Patients with the CC genotype had higher risk for azathioprine discontinuation attributed to hematopoietic toxicity and lower thiopurine doses. Genotype was associated with those risks, even after adjustment for race. PRIMARY FUNDING SOURCE: National Institutes of Health.

A missense variant in Mitochondrial Amidoxime Reducing Component 1 gene and protection against liver disease.

Analyzing 12,361 all-cause cirrhosis cases and 790,095 controls from eight cohorts, we identify a common missense variant in the Mitochondrial Amidoxime Reducing Component 1 gene (MARC1 p.A165T) that associates with protection from all-cause cirrhosis (OR 0.91, p = 2.3*10-11). This same variant also associates with lower levels of hepatic fat on computed tomographic imaging and lower odds of physician-diagnosed fatty liver as well as lower blood levels of alanine transaminase (-0.025 SD, 3.7*10-43), alkaline phosphatase (-0.025 SD, 1.2*10-37), total cholesterol (-0.030 SD, p = 1.9*10-36) and LDL cholesterol (-0.027 SD, p = 5.1*10-30) levels. We identified a series of additional MARC1 alleles (low-frequency missense p.M187K and rare protein-truncating p.R200Ter) that also associated with lower cholesterol levels, liver enzyme levels and reduced risk of cirrhosis (0 cirrhosis cases for 238 R200Ter carriers versus 17,046 cases of cirrhosis among 759,027 non-carriers, p = 0.04) suggesting that deficiency of the MARC1 enzyme may lower blood cholesterol levels and protect against cirrhosis.

Minority-centric meta-analyses of blood lipid levels identify novel loci in the Population Architecture using Genomics and Epidemiology (PAGE) study.

Lipid levels are important markers for the development of cardio-metabolic diseases. Although hundreds of associated loci have been identified through genetic association studies, the contribution of genetic factors to variation in lipids is not fully understood, particularly in U.S. minority groups. We performed genome-wide association analyses for four lipid traits in over 45,000 ancestrally diverse participants from the Population Architecture using Genomics and Epidemiology (PAGE) Study, followed by a meta-analysis with several European ancestry studies. We identified nine novel lipid loci, five of which showed evidence of replication in independent studies. Furthermore, we discovered one novel gene in a PrediXcan analysis, minority-specific independent signals at eight previously reported loci, and potential functional variants at two known loci through fine-mapping. Systematic examination of known lipid loci revealed smaller effect estimates in African American and Hispanic ancestry populations than those in Europeans, and better performance of polygenic risk scores based on minority-specific effect estimates. Our findings provide new insight into the genetic architecture of lipid traits and highlight the importance of conducting genetic studies in diverse populations in the era of precision medicine.

Machine Learning to Predict Interstage Mortality Following Single Ventricle Palliation: A NPC-QIC Database Analysis.

There is high risk of mortality between stage I and stage II palliation of single ventricle heart disease. This study aimed to leverage advanced machine learning algorithms to optimize risk-prediction models and identify features most predictive of interstage mortality. This study utilized retrospective data from the National Pediatric Cardiology Quality Improvement Collaborative and included all patients who underwent stage I palliation and survived to hospital discharge (2008-2019). Multiple machine learning models were evaluated, including logistic regression, random forest, gradient boosting trees, extreme gradient boost trees, and light gradient boosting machines. A total of 3267 patients were included with 208 (6.4%) interstage deaths. Machine learning models were trained on 180 clinical features. Digoxin use at discharge was the most influential factor resulting in a lower risk of interstage mortality (p < 0.0001). Stage I surgery with Blalock-Taussig-Thomas shunt portended higher risk than Sano conduit (7.8% vs 4.4%, p = 0.0002). Non-modifiable risk factors identified with increased risk of interstage mortality included female sex, lower gestational age, and lower birth weight. Post-operative risk factors included the requirement of unplanned catheterization and more severe atrioventricular valve insufficiency at discharge. Light gradient boosting machines demonstrated the best performance with an area under the receiver operative characteristic curve of 0.642. Advanced machine learning algorithms highlight a number of modifiable and non-modifiable risk factors for interstage mortality following stage I palliation. However, model performance remains modest, suggesting the presence of unmeasured confounders that contribute to interstage risk.

Psychiatric manifestations of rare variation in medically actionable genes: a PheWAS approach.

BACKGROUND: As genomic sequencing moves closer to clinical implementation, there has been an increasing acceptance of returning incidental findings to research participants and patients for mutations in highly penetrant, medically actionable genes. A curated list of genes has been recommended by the American College of Medical Genetics and Genomics (ACMG) for return of incidental findings. However, the pleiotropic effects of these genes are not fully known. Such effects could complicate genetic counseling when returning incidental findings. In particular, there has been no systematic evaluation of psychiatric manifestations associated with rare variation in these genes. RESULTS: Here, we leveraged a targeted sequence panel and real-world electronic health records from the eMERGE network to assess the burden of rare variation in the ACMG-56 genes and two psychiatric-associated genes (CACNA1C  and TCF4) across common mental health conditions in 15,181 individuals of European descent. As a positive control, we showed that this approach replicated the established association between rare mutations in LDLR and hypercholesterolemia with no visible inflation from population stratification. However, we did not identify any genes significantly enriched with rare deleterious variants that confer risk for common psychiatric disorders after correction for multiple testing. Suggestive associations were observed between depression and rare coding variation in PTEN (P = 1.5 × 10-4), LDLR (P = 3.6 × 10-4), and CACNA1S (P = 5.8 × 10-4). We also observed nominal associations between rare variants in KCNQ1 and substance use disorders (P = 2.4 × 10-4), and APOB and tobacco use disorder (P = 1.1 × 10-3). CONCLUSIONS: Our results do not support an association between psychiatric disorders and incidental findings in medically actionable gene mutations, but power was limited with the available sample sizes. Given the phenotypic and genetic complexity of psychiatric phenotypes, future work will require a much larger sequencing dataset to determine whether incidental findings in these genes have implications for risk of psychopathology.

Genome-wide association analyses of common infections in a large practice-based biobank.

INTRODUCTION: Infectious diseases are common causes of morbidity and mortality worldwide. Susceptibility to infection is highly heritable; however, little has been done to identify the genetic determinants underlying common infectious diseases. One GWAS was performed using 23andMe information about self-reported infections; we set out to confirm previous loci and identify new ones using medically diagnosed infections. METHODS: We used the electronic health record (EHR)-based biobank at Vanderbilt and diagnosis codes to identify cases of 12 infectious diseases in white patients: urinary tract infection, pneumonia, chronic sinus infections, otitis media, candidiasis, streptococcal pharyngitis, herpes zoster, herpes labialis, hepatitis B, infectious mononucleosis, tuberculosis (TB) or a positive TB test, and hepatitis C. We selected controls from patients with no diagnosis code for the candidate disease and matched by year of birth, sex, and calendar year at first and last EHR visits. We conducted GWAS using SAIGE and transcriptome-wide analysis (TWAS) using S-PrediXcan. We also conducted phenome-wide association study to understand associations between identified genetic variants and clinical phenotypes. RESULTS: We replicated three 23andMe loci (p ≤ 0.05): herpes zoster and rs7047299-A (p = 2.6 × 10-3) and rs2808290-C (p = 9.6 × 10-3;); otitis media and rs114947103-C (p = 0.04). We also identified 2 novel regions (p ≤ 5 × 10-8): rs113235453-G for otitis media (p = 3.04 × 10-8), and rs10422015-T for candidiasis (p = 3.11 × 10-8). In TWAS, four gene-disease associations were significant: SLC30A9 for otitis media (p = 8.06 × 10-7); LRP3 and WDR88 for candidiasis (p = 3.91 × 10-7 and p = 1.95 × 10-6); and AAMDC for hepatitis B (p = 1.51 × 10-6). CONCLUSION: We conducted GWAS and TWAS for 12 infectious diseases and identified novel genetic contributors to the susceptibility of infectious diseases.