Search

Supplemental Digital Content is available in the text., Background: Atrial fibrillation (AF) is associated with substantial morbidity, especially when it goes undetected. If new-onset AF could be predicted, targeted screening could be used to find it early. We hypothesized that a deep neural network could predict new-onset AF from the resting 12-lead ECG and that this prediction may help identify those at risk of AF-related stroke. Methods: We used 1.6 M resting 12-lead digital ECG traces from 430 000 patients collected from 1984 to 2019. Deep neural networks were trained to predict new-onset AF (within 1 year) in patients without a history of AF. Performance was evaluated using areas under the receiver operating characteristic curve and precision-recall curve. We performed an incidence-free survival analysis for a period of 30 years following the ECG stratified by model predictions. To simulate real-world deployment, we trained a separate model using all ECGs before 2010 and evaluated model performance on a test set of ECGs from 2010 through 2014 that were linked to our stroke registry. We identified the patients at risk for AF-related stroke among those predicted to be high risk for AF by the model at different prediction thresholds. Results: The area under the receiver operating characteristic curve and area under the precision-recall curve were 0.85 and 0.22, respectively, for predicting new-onset AF within 1 year of an ECG. The hazard ratio for the predicted high- versus low-risk groups over a 30-year span was 7.2 (95% CI, 6.9–7.6). In a simulated deployment scenario, the model predicted new-onset AF at 1 year with a sensitivity of 69% and specificity of 81%. The number needed to screen to find 1 new case of AF was 9. This model predicted patients at high risk for new-onset AF in 62% of all patients who experienced an AF-related stroke within 3 years of the index ECG. Conclusions: Deep learning can predict new-onset AF from the 12-lead ECG in patients with no previous history of AF. This prediction may help identify patients at risk for AF-related strokes.

Background: Atrial fibrillation (AF) risk estimation using clinical factors with or without genetic information may identify AF screening candidates more accurately than the guideline-based age threshold of ≥65 years. Methods: We analyzed 4 samples across the United States and Europe (derivation: UK Biobank; validation: FINRISK, Geisinger MyCode Initiative, and Framingham Heart Study). We estimated AF risk using the CHARGE-AF (Cohorts for Heart and Aging Research in Genomic Epidemiology AF) score and a combination of CHARGE-AF and a 1168-variant polygenic score (Predict-AF). We compared the utility of age, CHARGE-AF, and Predict-AF for predicting 5-year AF by quantifying discrimination and calibration. Results: Among 543 093 individuals, 8940 developed AF within 5 years. In the validation sets, CHARGE-AF (C index range, 0.720–0.824) and Predict-AF (0.749–0.831) had largely comparable discrimination, both favorable to continuous age (0.675–0.801). Calibration was similar using CHARGE-AF (slope range, 0.67–0.87) and Predict-AF (0.65–0.83). Net reclassification improvement using Predict-AF versus CHARGE-AF was modest (net reclassification improvement range, 0.024–0.057) but more favorable among individuals aged Conclusions: AF risk estimation using clinical factors may prioritize individuals for AF screening more precisely than the age threshold endorsed in current guidelines. The additional value of genetic predisposition is modest but greatest among younger individuals.

Background: Atrial fibrillation (AF) is associated with stroke, especially when AF goes undetected. Deep neural networks (DNN) can predict incident AF from a 12-lead resting ECG. We hypothesize that use of a DNN to predict new onset AF from an ECG may identify patients at risk of sustaining a potentially preventable AF-related stroke. Methods: We trained a DNN model to predict new-onset AF using 382,604 ECGs prior to 2010. We then evaluated the model performance on a test set of ECGs from 2010 through 2014 linked to patients in an institutional stroke registry. There were 181,969 patients in the test set with at least one ECG and no prior history of AF. Of those patients 3,497 (1.9%) had a stroke following an ECG that did not show AF. Within the set of patients with stroke, 375 had the stroke within 3 years of the ECG and were diagnosed with new AF between -3 and 365 days of the stroke. We considered these potentially preventable AF-related strokes. We report the sensitivity and positive predictive value (PPV) of the model for appropriately risk stratifying these 375 patients who sustained a potentially preventable AF-related stroke. Results: We used F β scores to identify different risk prediction thresholds (operating points) for the model. Operating points chosen by F 0.5 , F 1 , and F 2 scores identified 4, 12, and 21% of the population as high risk for the development of AF within 1 year (Figure 1). Screening 1, 4, 12, and 21% of the overall population resulted in PPV of 28, 21, 15, and 12%, respectively, for identification of new onset AF in one year. Using those same thresholds yielded sensitivities of 4, 17, 45, and 62% for identifying potentially preventable AF-related strokes. The different risk prediction thresholds resulted in a low (120-162) number needed to screen to detect one potentially preventable AF-related stroke at 3 years. Conclusions: Use of a deep learning model to predict new onset AF may identify patients at high risk of sustaining a potentially preventable AF-related stroke.

BackgroundAtrial fibrillation (AF) is associated with substantial morbidity, especially when it goes undetected. If new onset AF could be predicted, targeted population screening could be used to find it early. We hypothesized that a deep neural network could predict new onset AF from the resting 12-lead electrocardiogram (ECG) and that this prediction may help prevent AF-related stroke.MethodsWe used 1.6M resting 12-lead ECG voltage-time traces from 430k patients collected from 1984-2019 in this study. Deep neural networks were trained to predict new onset AF (within 1 year) in patients without a history of AF. Performance was evaluated using areas under the receiver operating characteristic curve (AUROC) and precision-recall curve (AUPRC). We performed an incidence-free survival analysis for a period of 30 years following the ECG stratified by model predictions. To simulate real-world deployment, we trained a separate model using all ECGs prior to 2010 and evaluated model performance on a test set of ECGs from 2010 through 2014 that were linked to our stroke registry. We used standard metrics to explore different prediction thresholds for the model and also calculated how many AF-related strokes might be potentially prevented.ResultsThe AUROC and AUPRC were 0.83 and 0.21, respectively, for predicting new onset AF within 1 year of an ECG. Adding age and sex improved the AUROC to 0.85 and the AUPRC to 0.23. The hazard ratio for the predicted high- vs. low-risk groups over a 30-year span was 7.2 [95% confidence interval: 6.9 – 7.6]. In a simulated deployment scenario, using the F2 score to select the risk prediction threshold, the model predicted new onset AF at 1 year with a sensitivity of 69%, specificity of 81%, and positive predictive value (PPV) of 12%. This model correctly predicted new onset AF in 62% of all patients that experienced an AF-related stroke within 3 years of the ECG.ConclusionsDeep learning can predict new onset AF from the 12-lead ECG in patients with no prior history of AF. This prediction may prove useful in preventing AF-related strokes.

Aims We investigated the relationship between clinically assessed left ventricular ejection fraction (LVEF) and survival in a large, heterogeneous clinical cohort. Methods and results Physician-reported LVEF on 403 977 echocardiograms from 203 135 patients were linked to all-cause mortality using electronic health records (1998–2018) from US regional healthcare system. Cox proportional hazards regression was used for analyses while adjusting for many patient characteristics including age, sex, and relevant comorbidities. A dataset including 45 531 echocardiograms and 35 976 patients from New Zealand was used to provide independent validation of analyses. During follow-up of the US cohort, 46 258 (23%) patients who had undergone 108 578 (27%) echocardiograms died. Overall, adjusted hazard ratios (HR) for mortality showed a u-shaped relationship for LVEF with a nadir of risk at an LVEF of 60–65%, a HR of 1.71 [95% confidence interval (CI) 1.64–1.77] when ≥70% and a HR of 1.73 (95% CI 1.66–1.80) at LVEF of 35–40%. Similar relationships with a nadir at 60–65% were observed in the validation dataset as well as for each age group and both sexes. The results were similar after further adjustments for conditions associated with an elevated LVEF, including mitral regurgitation, increased wall thickness, and anaemia and when restricted to patients reported to have heart failure at the time of the echocardiogram. Conclusion Deviation of LVEF from 60% to 65% is associated with poorer survival regardless of age, sex, or other relevant comorbidities such as heart failure. These results may herald the recognition of a new phenotype characterized by supra-normal LVEF.

Type 2 diabetes mellitus (T2DM) is a major health and economic burden because of the seriousness of the disease and its complications. Improvements in short- and long-term glycemic control is the goal of diabetes treatment. To investigate the longitudinal management of T2DM at Geisinger, we interrogated the electronic health record (EHR) information and identified a T2DM cohort including 125,477 patients using the Electronic Medical Records and Genomics Network (eMERGE) T2DM phenotyping algorithm. We investigated the annual anti-diabetic medication usage and the overall glycemic control using hemoglobin A1c (HbA1c). Metformin remains the most frequently medication despite the availability of the new classes of anti-diabetic medications. Median value of HbA1c decreased to 7% in 2002 and since remained stable, indicating a good glycemic management in Geisinger population. Using metformin as a pilot study, we identified three groups of patients with distinct HbA1c trajectories after metformin treatment. The variabilities in metformin response is mainly explained by the baseline HbA1c. The pharmacogenomic analysis of metformin identified a missense variant rs75740279 (Leu/Val) for STAU2 associated with the metformin response. This strategy can be applied to study other anti-diabeticmedications. Such research will facilitate the translational healthcare for better T2DM management.

Population genomic screening has been demonstrated to detect at-risk individuals who would not be clinically identified otherwise. However, there are concerns about the increased utilization of unnecessary services and the associated increase in costs. The objectives of this study are twofold: (1) determine whether there is a difference in healthcare utilization and costs following disclosure of a pathogenic/likely pathogenic (P/LP) BRCA1/2 variant via a genomic screening program, and (2) measure the post-disclosure uptake of National Comprehensive Cancer Network (NCCN) guideline-recommended risk management. We retrospectively reviewed electronic health record (EHR) and billing data from a female population of BRCA1/2 P/LP variant carriers without a personal history of breast or ovarian cancer enrolled in Geisinger&rsquo, s MyCode genomic screening program with at least a one-year post-disclosure observation period. We identified 59 women for the study cohort out of 50,726 MyCode participants. We found no statistically significant differences in inpatient and outpatient utilization and average total costs between one-year pre- and one-year post-disclosure periods ($18,821 vs. $19,359, p = 0.76). During the first year post-disclosure, 49.2% of women had a genetic counseling visit, 45.8% had a mammography and 32.2% had an MRI. The uptake of mastectomy and oophorectomy was 3.5% and 11.8%, respectively, and 5% of patients received chemoprevention.

BackgroundPolycystic ovary syndrome (PCOS) is the most common endocrine disorder affecting women of reproductive age. Previous studies have identified genetic variants associated with PCOS identified by different diagnostic criteria. The Rotterdam Criteria is the broadest and able to identify the most PCOS cases.ObjectivesTo identify novel associated genetic variants, we extracted PCOS cases and controls from the electronic health records (EHR) based on the Rotterdam Criteria and performed a genome-wide association study (GWAS).Study DesignWe developed a PCOS phenotyping algorithm based on the Rotterdam criteria and applied it to three EHR-linked biobanks to identify cases and controls for genetic study. In discovery phase, we performed individual GWAS using the Geisinger’s MyCode and the eMERGE cohorts, which were then meta-analyzed. We attempted validation of the significantly association loci (P−6) in the BioVU cohort. All association analyses used logistic regression, assuming an additive genetic model, and adjusted for principal components to control for population stratification. An inverse-variance fixed effect model was adopted for meta-analyses. Additionally, we examined the top variants to evaluate their associations with each criterion in the phenotyping algorithm. We used STRING to identify protein-protein interaction network.ResultsWe identified 2,995 PCOS cases and 53,599 controls in total (2,742cases and 51,438 controls from the discovery phase; 253 cases and 2,161 controls in the validation phase). GWAS identified one novel genome-wide significant variant rs17186366 (OR=1.37 [1.23,1.54], P=2.8×10−8) located nearSOD2. Additionally, two loci with suggestive association were also identified: rs113168128 (OR=1.72 [1.42,2.10], P=5.2 x10−8), an intronic variant ofERBB4that is independent from the previously published variants, and rs144248326 (OR=2.13 [1.52,2.86], P=8.45×10−7), a novel intronic variant inWWTR1. In the further association tests of the top 3 SNPs with each criterion in the PCOS algorithm, we found that rs17186366 was associated with polycystic and hyperandrogenism, while rs11316812 and rs144248326 were mainly associated with oligomenorrhea or infertility. Besides ERBB4, we also validated the association withDENND1A1.ConclusionThrough a discovery-validation GWAS on PCOS cases and controls identified from EHR using an algorithm based on Rotterdam criteria, we identified and validated a novel association with variants withinERBB4. We also identified novel associations nearbySOD2andWWTR1. These results suggest the eGFR and Hippo pathways in the disease etiology. With previously identified PCOS-associated lociYAP1, theERBB4-YAP1-WWTR1network implicates the epidermal growth factor receptor and the Hippo pathway in the multifactorial etiology of PCOS.

Deletion of glutathione S-transferase µ1 (GSTM1) is common in populations and has been asserted to associate with chronic kidney disease progression in some research studies. The association needs to be validated. We estimated GSTM1 copy number using whole exome sequencing data in the DiscovEHR cohort. Kidney failure was defined as requiring dialysis or receiving kidney transplant using data from the electronic health record and linkage to the United States Renal Data System, or the most recent eGFR < 15 ml/min/1.73m2. In a cohort of 46,983 unrelated participants, 28.8% of blacks and 52.1% of whites had 0 copies of GSTM1. Over a mean of 9.2 years follow-up, 645 kidney failure events were observed in 46,187 white participants, and 28 in 796 black participants. No significant association was observed between GSTM1 copy number and kidney failure in Cox regression adjusting for age, sex, BMI, smoking status, genetic principal components, or co-morbid conditions (hypertension, diabetes, heart failure, coronary artery disease, and stroke), whether using a genotypic, dominant, or recessive model. In sensitivity analyses, GSTM1 copy number was not associated with kidney failure in participants that were 45 years or older at baseline, had baseline eGFR < 60 ml/min per 1.73 m2, or with baseline year between 1996-2002. In conclusion, we found no association between GSTM1 copy number and kidney failure in a large cohort study.Translational StatementDeletion of GSTM1 has been shown to be associated with higher risk of kidney failure. However, inconsistent results have been reported. We used electronic health record and whole exome sequencing data of a large cohort from a single healthcare system to evaluate the association between GSTM1 copy number and risk of kidney failure. We found no significant association between GSTM1 copy number and risk of kidney failure overall, or in multiple sensitivity and subgroup analyses.

The electrocardiogram (ECG) is a widely used medical test, consisting of voltage versus time traces collected from surface recordings over the heart1. Here we hypothesized that a deep neural network (DNN) can predict an important future clinical event, 1-year all-cause mortality, from ECG voltage–time traces. By using ECGs collected over a 34-year period in a large regional health system, we trained a DNN with 1,169,662 12-lead resting ECGs obtained from 253,397 patients, in which 99,371 events occurred. The model achieved an area under the curve (AUC) of 0.88 on a held-out test set of 168,914 patients, in which 14,207 events occurred. Even within the large subset of patients (n = 45,285) with ECGs interpreted as ‘normal’ by a physician, the performance of the model in predicting 1-year mortality remained high (AUC = 0.85). A blinded survey of cardiologists demonstrated that many of the discriminating features of these normal ECGs were not apparent to expert reviewers. Finally, a Cox proportional-hazard model revealed a hazard ratio of 9.5 (P

Background Empirical data on conditions that increase risk of coronavirus disease 2019 (COVID-19) progression are needed to identify high risk individuals. We performed a comprehensive quantitative assessment of pre-existing clinical phenotypes associated with COVID-19-related hospitalization. Methods Phenome-wide association study (PheWAS) of SARS-CoV-2-positive patients from an integrated health system (Geisinger) with system-level outpatient/inpatient COVID-19 testing capacity and retrospective electronic health record (EHR) data to assess pre-COVID-19 pandemic clinical phenotypes associated with hospital admission (hospitalization). Results Of 12,971 individuals tested for SARS-CoV-2 with sufficient pre-COVID-19 pandemic EHR data at Geisinger, 1604 were SARS-CoV-2 positive and 354 required hospitalization. We identified 21 clinical phenotypes in 5 disease categories meeting phenome-wide significance (P-4), including: six kidney phenotypes, e.g. end stage renal disease or stage 5 CKD (OR = 11.07, p = 1.96x10-8), six cardiovascular phenotypes, e.g. congestive heart failure (OR = 3.8, p = 3.24x10-5), five respiratory phenotypes, e.g. chronic airway obstruction (OR = 2.54, p = 3.71x10-5), and three metabolic phenotypes, e.g. type 2 diabetes (OR = 1.80, p = 7.51x10-5). Additional analyses defining CKD based on estimated glomerular filtration rate, confirmed high risk of hospitalization associated with pre-existing stage 4 CKD (OR 2.90, 95% CI: 1.47, 5.74), stage 5 CKD/dialysis (OR 8.83, 95% CI: 2.76, 28.27), and kidney transplant (OR 14.98, 95% CI: 2.77, 80.8) but not stage 3 CKD (OR 1.03, 95% CI: 0.71, 1.48). Conclusions This study provides quantitative estimates of the contribution of pre-existing clinical phenotypes to COVID-19 hospitalization and highlights kidney disorders as the strongest factors associated with hospitalization in an integrated US healthcare system.

Importance The activity of lipoprotein lipase (LPL) is the rate-determining step in clearing triglyceride-rich lipoproteins from the circulation. Mutations that damage the LPL gene ( LPL ) lead to lifelong deficiency in enzymatic activity and can provide insight into the relationship of LPL to human disease. Objective To determine whether rare and/or common variants in LPL are associated with early-onset coronary artery disease (CAD). Design, Setting, and Participants In a cross-sectional study, LPL was sequenced in 10 CAD case-control cohorts of the multinational Myocardial Infarction Genetics Consortium and a nested CAD case-control cohort of the Geisinger Health System DiscovEHR cohort between 2010 and 2015. Common variants were genotyped in up to 305 699 individuals of the Global Lipids Genetics Consortium and up to 120 600 individuals of the CARDIoGRAM Exome Consortium between 2012 and 2014. Study-specific estimates were pooled via meta-analysis. Exposures Rare damaging mutations in LPL included loss-of-function variants and missense variants annotated as pathogenic in a human genetics database or predicted to be damaging by computer prediction algorithms trained to identify mutations that impair protein function. Common variants in the LPL gene region included those independently associated with circulating triglyceride levels. Main Outcomes and Measures Circulating lipid levels and CAD. Results Among 46 891 individuals with LPL gene sequencing data available, the mean (SD) age was 50 (12.6) years and 51% were female. A total of 188 participants (0.40%; 95% CI, 0.35%-0.46%) carried a damaging mutation in LPL , including 105 of 32 646 control participants (0.32%) and 83 of 14 245 participants with early-onset CAD (0.58%). Compared with 46 703 noncarriers, the 188 heterozygous carriers of an LPL damaging mutation displayed higher plasma triglyceride levels (19.6 mg/dL; 95% CI, 4.6-34.6 mg/dL) and higher odds of CAD (odds ratio = 1.84; 95% CI, 1.35-2.51; P LPL variants resulted in an odds ratio for CAD of 1.51 (95% CI, 1.39-1.64; P = 1.1 × 10 −22 ) per 1-SD increase in triglycerides. Conclusions and Relevance The presence of rare damaging mutations in LPL was significantly associated with higher triglyceride levels and presence of coronary artery disease. However, further research is needed to assess whether there are causal mechanisms by which heterozygous lipoprotein lipase deficiency could lead to coronary artery disease.

PurposeArrhythmogenic right ventricular cardiomyopathy (ARVC) is an inherited heart disease. Clinical follow-up of incidental findings in ARVC-associated genes is recommended. We aimed to determine the prevalence of disease thus ascertained.MethodsIndividuals (n = 30,716) underwent exome sequencing. Variants in PKP2, DSG2, DSC2, DSP, JUP, TMEM43, or TGFβ3 that were database-listed as pathogenic or likely pathogenic were identified and evidence-reviewed. For subjects with putative loss-of-function (pLOF) variants or variants of uncertain significance (VUS), electronic health records (EHR) were reviewed for ARVC diagnosis, diagnostic criteria, and International Classification of Diseases (ICD-9) codes.ResultsEighteen subjects had pLOF variants; none of these had an EHR diagnosis of ARVC. Of 14 patients with an electrocardiogram, one had a minor diagnostic criterion; the rest were normal. A total of 184 subjects had VUS, none of whom had an ARVC diagnosis. The proportion of subjects with VUS with major (4%) or minor (13%) electrocardiogram diagnostic criteria did not differ from that of variant-negative controls. ICD-9 codes showed no difference in defibrillator use, electrophysiologic abnormalities or nonischemic cardiomyopathies in patients with pLOF or VUSs compared with controls.ConclusionpLOF variants in an unselected cohort were not associated with ARVC phenotypes based on EHR review. The negative predictive value of EHR review remains uncertain.

Unleashing the power of precision medicine Precision medicine promises the ability to identify risks and treat patients on the basis of pathogenic genetic variation. Two studies combined exome sequencing results for over 50,000 people with their electronic health records. Dewey et al. found that ∼3.5% of individuals in their cohort had clinically actionable genetic variants. Many of these variants affected blood lipid levels that could influence cardiovascular health. Abul-Husn et al. extended these findings to investigate the genetics and treatment of familial hypercholesterolemia, a risk factor for cardiovascular disease, within their patient pool. Genetic screening helped identify at-risk patients who could benefit from increased treatment. Science , this issue p. 10.1126/science.aaf6814 , p. 10.1126/science.aaf7000

Key Points Question Can population-level genomic screening identify those at risk for disease? Findings In this cross-sectional study of an unselected population cohort of 50 726 adults who underwent exome sequencing, pathogenic and likely pathogenic BRCA1 and BRCA2 variants were found in a higher proportion of patients than was previously reported. Meaning Current methods to identify BRCA1/2 variant carriers may not be sufficient as a screening tool; population genomic screening for hereditary breast and ovarian cancer may better identify patients at high risk and provide an intervention opportunity to reduce mortality and morbidity., Importance Detection of disease-associated variants in the BRCA1 and BRCA2 (BRCA1/2) genes allows for cancer prevention and early diagnosis in high-risk individuals. Objectives To identify pathogenic and likely pathogenic (P/LP) BRCA1/2 variants in an unselected research cohort, and to characterize the features associated with P/LP variants. Design, Setting, and Participants This is a cross-sectional study of adult volunteers (n = 50 726) who underwent exome sequencing at a single health care system (Geisinger Health System, Danville, Pennsylvania) from January 1, 2014, to March 1, 2016. Participants are part of the DiscovEHR cohort and were identified through the Geisinger MyCode Community Health Initiative. They consented to a research protocol that included sequencing and return of actionable test results. Clinical data from electronic health records and clinical visits were correlated with variants. Comparisons were made between those with (cases) and those without (controls) P/LP variants in BRCA1/2. Main Outcomes Prevalence of P/LP BRCA1/2 variants in cohort, proportion of variant carriers not previously ascertained through clinical testing, and personal and family history of relevant cancers among BRCA1/2 variant carriers and noncarriers. Results Of the 50 726 health system patients who underwent exome sequencing, 50 459 (99.5%) had no expected pathogenic BRCA1/2 variants and 267 (0.5%) were BRCA1/2 carriers. Of the 267 cases (148 [55.4%] were women and 119 [44.6%] were men with a mean [range] age of 58.9 [23-90] years), 183 (68.5%) received clinically confirmed results in their electronic health record. Among the 267 participants with P/LP BRCA1/2 variants, 219 (82.0%) had no prior clinical testing, 95 (35.6%) had BRCA1 variants, and 172 (64.4%) had BRCA2 variants. Syndromic cancer diagnoses were present in 11 (47.8%) of the 23 deceased BRCA1/2 carriers and in 56 (20.9%) of all 267 BRCA1/2 carriers. Among women, 31 (20.9%) of 148 variant carriers had a personal history of breast cancer, compared with 1554 (5.2%) of 29 880 noncarriers (odds ratio [OR], 5.95; 95% CI, 3.88-9.13; P, This cross-sectional study investigates the ascertainment of pathogenic and likely pathogenic BRCA1/2 variants among US adults enrolled in the MyCode Community Health Initiative.