Muesli Intake May Protect Against Coronary Artery Disease: Mendelian Randomization on 13 Dietary Traits.

BACKGROUND: Diet is a key modifiable risk factor of coronary artery disease (CAD). However, the causal effects of specific dietary traits on CAD risk remain unclear. With the expansion of dietary data in population biobanks, Mendelian randomization (MR) could help enable the efficient estimation of causality in diet-disease associations. OBJECTIVES: The primary goal was to test causality for 13 common dietary traits on CAD risk using a systematic 2-sample MR framework. A secondary goal was to identify plasma metabolites mediating diet-CAD associations suspected to be causal. METHODS: Cross-sectional genetic and dietary data on up to 420,531 UK Biobank and 184,305 CARDIoGRAMplusC4D individuals of European ancestry were used in 2-sample MR. The primary analysis used fixed effect inverse-variance weighted regression, while sensitivity analyses used weighted median estimation, MR-Egger regression, and MR-Pleiotropy Residual Sum and Outlier. RESULTS: Genetic variants serving as proxies for muesli intake were negatively associated with CAD risk (OR: 0.74; 95% CI: 0.65-0.84; P = 5.385 × 10-4). Sensitivity analyses using weighted median estimation supported this with a significant association in the same direction. Additionally, we identified higher plasma acetate levels as a potential mediator (OR: 0.03; 95% CI: 0.01-0.12; P = 1.15 × 10-4). CONCLUSIONS: Muesli, a mixture of oats, seeds, nuts, dried fruit, and milk, may causally reduce CAD risk. Circulating levels of acetate, a gut microbiota-derived short-chain fatty acid, could be mediating its cardioprotective effects. These findings highlight the role of gut flora in cardiovascular health and help prioritize randomized trials on dietary interventions for CAD.

Genome-first evaluation with exome sequence and clinical data uncovers underdiagnosed genetic disorders in a large healthcare system.

Population-based genomic screening may help diagnose individuals with disease-risk variants. Here, we perform a genome-first evaluation for nine disorders in 29,039 participants with linked exome sequences and electronic health records (EHRs). We identify 614 individuals with 303 pathogenic/likely pathogenic or predicted loss-of-function (P/LP/LoF) variants, yielding 644 observations; 487 observations (76%) lack a corresponding clinical diagnosis in the EHR. Upon further investigation, 75 clinically undiagnosed observations (15%) have evidence of symptomatic untreated disease, including familial hypercholesterolemia (3 of 6 [50%] undiagnosed observations with disease evidence) and breast cancer (23 of 106 [22%]). These genetic findings enable targeted phenotyping that reveals new diagnoses in previously undiagnosed individuals. Disease yield is greater with variants in penetrant genes for which disease is observed in carriers in an independent cohort. The prevalence of P/LP/LoF variants exceeds that of clinical diagnoses, and some clinically undiagnosed carriers are discovered to have disease. These results highlight the potential of population-based genomic screening.

Time-to-Event Genome-Wide Association Study for Incident Cardiovascular Disease in People With Type 2 Diabetes.

OBJECTIVE: To identify genetic risk factors for incident cardiovascular disease (CVD) among people with type 2 diabetes (T2D). RESEARCH DESIGN AND METHODS: We conducted a multiancestry time-to-event genome-wide association study for incident CVD among people with T2D. We also tested 204 known coronary artery disease (CAD) variants for association with incident CVD. RESULTS: Among 49,230 participants with T2D, 8,956 had incident CVD events (event rate 18.2%). We identified three novel genetic loci for incident CVD: rs147138607 (near CACNA1E/ZNF648, hazard ratio [HR] 1.23, P = 3.6 × 10-9), rs77142250 (near HS3ST1, HR 1.89, P = 9.9 × 10-9), and rs335407 (near TFB1M/NOX3, HR 1.25, P = 1.5 × 10-8). Among 204 known CAD loci, 5 were associated with incident CVD in T2D (multiple comparison-adjusted P < 0.00024, 0.05/204). A standardized polygenic score of these 204 variants was associated with incident CVD with HR 1.14 (P = 1.0 × 10-16). CONCLUSIONS: The data point to novel and known genomic regions associated with incident CVD among individuals with T2D.

Large-scale cross-ancestry genome-wide meta-analysis of serum urate.

Hyperuricemia is an essential causal risk factor for gout and is associated with cardiometabolic diseases. Given the limited contribution of East Asian ancestry to genome-wide association studies of serum urate, the genetic architecture of serum urate requires exploration. A large-scale cross-ancestry genome-wide association meta-analysis of 1,029,323 individuals and ancestry-specific meta-analysis identifies a total of 351 loci, including 17 previously unreported loci. The genetic architecture of serum urate control is similar between European and East Asian populations. A transcriptome-wide association study, enrichment analysis, and colocalization analysis in relevant tissues identify candidate serum urate-associated genes, including CTBP1, SKIV2L, and WWP2. A phenome-wide association study using polygenic risk scores identifies serum urate-correlated diseases including heart failure and hypertension. Mendelian randomization and mediation analyses show that serum urate-associated genes might have a causal relationship with serum urate-correlated diseases via mediation effects. This study elucidates our understanding of the genetic architecture of serum urate control.

Development of a human genetics-guided priority score for 19,365 genes and 399 drug indications.

Studies have shown that drug targets with human genetic support are more likely to succeed in clinical trials. Hence, a tool integrating genetic evidence to prioritize drug target genes is beneficial for drug discovery. We built a genetic priority score (GPS) by integrating eight genetic features with drug indications from the Open Targets and SIDER databases. The top 0.83%, 0.28% and 0.19% of the GPS conferred a 5.3-, 9.9- and 11.0-fold increased effect of having an indication, respectively. In addition, we observed that targets in the top 0.28% of the score were 1.7-, 3.7- and 8.8-fold more likely to advance from phase I to phases II, III and IV, respectively. Complementary to the GPS, we incorporated the direction of genetic effect and drug mechanism into a directional version of the score called the GPS with direction of effect. We applied our method to 19,365 protein-coding genes and 399 drug indications and made all results available through a web portal.

Prediction of Venous Thromboembolism in Diverse Populations Using Machine Learning and Structured Electronic Health Records.

BACKGROUND: Venous thromboembolism (VTE) is a major cause of morbidity and mortality worldwide. Current risk assessment tools, such as the Caprini and Padua scores and Wells criteria, have limitations in their applicability and accuracy. This study aimed to develop machine learning models using structured electronic health record data to predict diagnosis and 1-year risk of VTE. METHODS: We trained and validated models on data from 159 001 participants in the Mount Sinai Data Warehouse. We then externally tested them on 401 723 participants in the UK Biobank and 123 039 participants in All of Us. All data sets contain populations of diverse ancestries and clinical histories. We used these data sets to develop small, medium, and large models with increasing features on a range of optimizing portability to maximizing performance. We make trained models publicly available in click-and-run format at https://doi.org/10.17632/tkwzysr4y6.6. RESULTS: In the holdout and external test sets, respectively, models achieved areas under the receiver operating characteristic curve of 0.80 to 0.83 and 0.72 to 0.82 for VTE diagnosis prediction and 0.76 to 0.78 and 0.64 to 0.69 for 1-year risk prediction, significantly outperforming the Padua score. Models also demonstrated robust performance across different VTE types and patient subsets, including ethnicity, age, and surgical and hospitalization status. Models identified both established and novel clinical features contributing to VTE risk, offering valuable insights into its underlying pathophysiology. CONCLUSIONS: Machine learning models using structured electronic health record data can significantly improve VTE diagnosis and 1-year risk prediction in diverse populations. Model probability scores exist on a continuum, affecting mortality risk in both healthy individuals and VTE cases. Integrating these models into electronic health record systems to generate real-time predictions may enhance VTE risk assessment, early detection, and preventative measures, ultimately reducing the morbidity and mortality associated with VTE.

Quantitative Prediction of Right Ventricular Size and Function From the ECG.

BACKGROUND: Right ventricular ejection fraction (RVEF) and end-diastolic volume (RVEDV) are not readily assessed through traditional modalities. Deep learning-enabled ECG analysis for estimation of right ventricular (RV) size or function is unexplored. METHODS AND RESULTS: We trained a deep learning-ECG model to predict RV dilation (RVEDV >120 mL/m2), RV dysfunction (RVEF ≤40%), and numerical RVEDV and RVEF from a 12-lead ECG paired with reference-standard cardiac magnetic resonance imaging volumetric measurements in UK Biobank (UKBB; n=42 938). We fine-tuned in a multicenter health system (MSHoriginal [Mount Sinai Hospital]; n=3019) with prospective validation over 4 months (MSHvalidation; n=115). We evaluated performance with area under the receiver operating characteristic curve for categorical and mean absolute error for continuous measures overall and in key subgroups. We assessed the association of RVEF prediction with transplant-free survival with Cox proportional hazards models. The prevalence of RV dysfunction for UKBB/MSHoriginal/MSHvalidation cohorts was 1.0%/18.0%/15.7%, respectively. RV dysfunction model area under the receiver operating characteristic curve for UKBB/MSHoriginal/MSHvalidation cohorts was 0.86/0.81/0.77, respectively. The prevalence of RV dilation for UKBB/MSHoriginal/MSHvalidation cohorts was 1.6%/10.6%/4.3%. RV dilation model area under the receiver operating characteristic curve for UKBB/MSHoriginal/MSHvalidation cohorts was 0.91/0.81/0.92, respectively. MSHoriginal mean absolute error was RVEF=7.8% and RVEDV=17.6 mL/m2. The performance of the RVEF model was similar in key subgroups including with and without left ventricular dysfunction. Over a median follow-up of 2.3 years, predicted RVEF was associated with adjusted transplant-free survival (hazard ratio, 1.40 for each 10% decrease; P=0.031). CONCLUSIONS: Deep learning-ECG analysis can identify significant cardiac magnetic resonance imaging RV dysfunction and dilation with good performance. Predicted RVEF is associated with clinical outcome.

Machine Learning Enables Single-Score Assessment of MASLD Presence and Severity.

Metabolic dysfunction-associated steatotic liver disease (MASLD) affects 30% of the global population but is often underdiagnosed. To fill this diagnostic gap, we developed a digital score reflecting presence and severity of MASLD. We fitted a machine learning model to electronic health records from 37,212 UK Biobank participants with proton density fat fraction measurements and/or a MASLD diagnosis to generate a "MASLD score". In holdout testing, our model achieved areas under the receiver-operating curve of 0.83-0.84 for MASLD diagnosis and 0.90-0.91 for identifying MASLD-associated advanced fibrosis. MASLD score was significantly associated with MASLD risk factors, progression to cirrhosis, and mortality. External testing in 252,725 diverse American participants demonstrated consistent results, and hepatologist chart review showed MASLD score identified probable MASLD underdiagnosis. The MASLD score could improve early diagnosis and intervention of chronic liver disease by providing a non-invasive, low-cost method for population-wide screening of MASLD.

Severe hypertriglyceridemia: Existing and emerging therapies.

Severe hypertriglyceridemia (sHTG), defined as a triglyceride (TG) concentration ≥ 500 mg/dL (≥ 5.7 mmol/L) is an important risk factor for acute pancreatitis. Although lifestyle, some medications, and certain conditions such as diabetes may lead to HTG, sHTG results from a combination of major and minor genetic defects in proteins that regulate TG lipolysis. Familial chylomicronemia syndrome (FCS) is a rare disorder caused by complete loss of function in lipoprotein lipase (LPL) or LPL activating proteins due to two homozygous recessive traits or compound heterozygous traits. Multifactorial chylomicronemia syndrome (MCS) and sHTG are due to the accumulation of rare heterozygous variants and polygenic defects that predispose individuals to sHTG phenotypes. Until recently, treatment of sHTG focused on lifestyle interventions, control of secondary factors, and nonselective pharmacotherapies that had modest TG-lowering efficacy and no corresponding reductions in atherosclerotic cardiovascular disease events. Genetic discoveries have allowed for the development of novel pathway-specific therapeutics targeting LPL modulating proteins. New targets directed towards inhibition of apolipoprotein C-III (apoC-III), angiopoietin-like protein 3 (ANGPTL3), angiopoietin-like protein 4 (ANGPTL4), and fibroblast growth factor-21 (FGF21) offer far more efficacy in treating the various phenotypes of sHTG and opportunities to reduce the risk of acute pancreatitis and atherosclerotic cardiovascular disease events.

Deep learning on electronic medical records identifies distinct subphenotypes of diabetic kidney disease driven by genetic variations in the Rho pathway.

Kidney disease affects 50% of all diabetic patients; however, prediction of disease progression has been challenging due to inherent disease heterogeneity. We use deep learning to identify novel genetic signatures prognostically associated with outcomes. Using autoencoders and unsupervised clustering of electronic health record data on 1,372 diabetic kidney disease patients, we establish two clusters with differential prevalence of end-stage kidney disease. Exome-wide associations identify a novel variant in ARHGEF18, a Rho guanine exchange factor specifically expressed in glomeruli. Overexpression of ARHGEF18 in human podocytes leads to impairments in focal adhesion architecture, cytoskeletal dynamics, cellular motility, and RhoA/Rac1 activation. Mutant GEF18 is resistant to ubiquitin mediated degradation leading to pathologically increased protein levels. Our findings uncover the first known disease-causing genetic variant that affects protein stability of a cytoskeletal regulator through impaired degradation, a potentially novel class of expression quantitative trait loci that can be therapeutically targeted.

An atlas of associations between 14 micronutrients and 22 cancer outcomes: Mendelian randomization analyses.

BACKGROUND: Micronutrients, namely vitamins and minerals, are associated with cancer outcomes; however, their reported effects have been inconsistent across studies. We aimed to identify the causally estimated effects of micronutrients on cancer by applying the Mendelian randomization (MR) method, using single-nucleotide polymorphisms associated with micronutrient levels as instrumental variables. METHODS: We obtained instrumental variables of 14 genetically predicted micronutrient levels and applied two-sample MR to estimate their causal effects on 22 cancer outcomes from a meta-analysis of the UK Biobank (UKB) and FinnGen cohorts (overall cancer and 21 site-specific cancers, including breast, colorectal, lung, and prostate cancer), in addition to six major cancer outcomes and 20 cancer subset outcomes from cancer consortia. We used sensitivity MR methods, including weighted median, MR-Egger, and MR-PRESSO, to assess potential horizontal pleiotropy or heterogeneity. Genome-wide association summary statistical data of European descent were used for both exposure and outcome data, including up to 940,633 participants of European descent with 133,384 cancer cases. RESULTS: In total, 672 MR tests (14 micronutrients × 48 cancer outcomes) were performed. The following two associations met Bonferroni significance by the number of associations (P < 0.00016) in the UKB plus FinnGen cohorts: increased risk of breast cancer with magnesium levels (odds ratio [OR] = 1.281 per 1 standard deviation [SD] higher magnesium level, 95% confidence interval [CI] = 1.151 to 1.426, P < 0.0001) and increased risk of colorectal cancer with vitamin B12 level (OR = 1.22 per 1 SD higher vitamin B12 level, 95% CI = 1.107 to 1.345, P < 0.0001). These two associations remained significant in the analysis of the cancer consortia. No significant heterogeneity or horizontal pleiotropy was observed. Micronutrient levels were not associated with overall cancer risk. CONCLUSIONS: Our results may aid clinicians in deciding whether to regulate the intake of certain micronutrients, particularly in high-risk groups without nutritional deficiencies, and may help in the design of future clinical trials.

Time-to-Event Genome-Wide Association Study for Incident Cardiovascular Disease in People with Type 2 Diabetes Mellitus.

BACKGROUND: Type 2 diabetes mellitus (T2D) confers a two- to three-fold increased risk of cardiovascular disease (CVD). However, the mechanisms underlying increased CVD risk among people with T2D are only partially understood. We hypothesized that a genetic association study among people with T2D at risk for developing incident cardiovascular complications could provide insights into molecular genetic aspects underlying CVD. METHODS: From 16 studies of the Cohorts for Heart & Aging Research in Genomic Epidemiology (CHARGE) Consortium, we conducted a multi-ancestry time-to-event genome-wide association study (GWAS) for incident CVD among people with T2D using Cox proportional hazards models. Incident CVD was defined based on a composite of coronary artery disease (CAD), stroke, and cardiovascular death that occurred at least one year after the diagnosis of T2D. Cohort-level estimated effect sizes were combined using inverse variance weighted fixed effects meta-analysis. We also tested 204 known CAD variants for association with incident CVD among patients with T2D. RESULTS: A total of 49,230 participants with T2D were included in the analyses (31,118 European ancestries and 18,112 non-European ancestries) which consisted of 8,956 incident CVD cases over a range of mean follow-up duration between 3.2 and 33.7 years (event rate 18.2%). We identified three novel, distinct genetic loci for incident CVD among individuals with T2D that reached the threshold for genome-wide significance (P<5.0×10-8): rs147138607 (intergenic variant between CACNA1E and ZNF648) with a hazard ratio (HR) 1.23, 95% confidence interval (CI) 1.15 - 1.32, P=3.6×10-9, rs11444867 (intergenic variant near HS3ST1) with HR 1.89, 95% CI 1.52 - 2.35, P=9.9×10-9, and rs335407 (intergenic variant between TFB1M and NOX3) HR 1.25, 95% CI 1.16 - 1.35, P=1.5×10-8. Among 204 known CAD loci, 32 were associated with incident CVD in people with T2D with P<0.05, and 5 were significant after Bonferroni correction (P<0.00024, 0.05/204). A polygenic score of these 204 variants was significantly associated with incident CVD with HR 1.14 (95% CI 1.12 - 1.16) per 1 standard deviation increase (P=1.0×10-16). CONCLUSIONS: The data point to novel and known genomic regions associated with incident CVD among individuals with T2D.

Prioritization of therapeutic targets for dyslipidemia using integrative multi-omics and multi-trait analysis.

Drug targets with genetic support are several-fold more likely to succeed in clinical trials. We introduce a genetic-driven approach based on causal inferences that can inform drug target prioritization, repurposing, and adverse effects of using lipid-lowering agents. Given that a multi-trait approach increases the power to detect meaningful variants/genes, we conduct multi-omics and multi-trait analyses, followed by network connectivity investigations, and prioritize 30 potential therapeutic targets for dyslipidemia, including SORT1, PSRC1, CELSR2, PCSK9, HMGCR, APOB, GRN, HFE2, FJX1, C1QTNF1, and SLC5A8. 20% (6/30) of prioritized targets from our hypothesis-free drug target search are either approved or under investigation for dyslipidemia. The prioritized targets are 22-fold higher in likelihood of being approved or under investigation in clinical trials than genome-wide association study (GWAS)-curated targets. Our results demonstrate that the genetic-driven approach used in this study is a promising strategy for prioritizing targets while informing about the potential adverse effects and repurposing opportunities.

Carriers of rare damaging CCR2 genetic variants are at lower risk of atherosclerotic disease.

Background: The CCL2/CCR2 axis governs monocyte trafficking and recruitment to atherosclerotic lesions. Human genetic analyses and population-based studies support an association between circulating CCL2 levels and atherosclerosis. Still, it remains unknown whether pharmacological targeting of CCR2, the main CCL2 receptor, would provide protection against human atherosclerotic disease. Methods: In whole-exome sequencing data from 454,775 UK Biobank participants (40-69 years), we identified predicted loss-of-function (LoF) or damaging missense (REVEL score >0.5) variants within the CCR2 gene. We prioritized variants associated with lower monocyte count (p<0.05) and tested associations with vascular risk factors and risk of atherosclerotic disease over a mean follow-up of 14 years. The results were replicated in a pooled cohort of three independent datasets (TOPMed, deCODE and Penn Medicine BioBank; total n=441,445) and the effect of the most frequent damaging variant was experimentally validated. Results: A total of 45 predicted LoF or damaging missense variants were identified in the CCR2 gene, 4 of which were also significantly associated with lower monocyte count, but not with other white blood cell counts. Heterozygous carriers of these variants were at a lower risk of a combined atherosclerosis outcome, showed a lower burden of atherosclerosis across four vascular beds, and were at a lower lifetime risk of coronary artery disease and myocardial infarction. There was no evidence of association with vascular risk factors including LDL-cholesterol, blood pressure, glycemic status, or C-reactive protein. Using a cAMP assay, we found that cells transfected with the most frequent CCR2 damaging variant (3:46358273:T:A, M249K, 547 carriers, frequency: 0.14%) show a decrease in signaling in response to CCL2. The associations of the M249K variant with myocardial infarction were consistent across cohorts (ORUKB: 0.62 95%CI: 0.39-0.96; ORexternal: 0.64 95%CI: 0.34-1.19; ORpooled: 0.64 95%CI: 0.450.90). In a phenome-wide association study, we found no evidence for higher risk of common infections or mortality among carriers of damaging CCR2 variants. Conclusions: Heterozygous carriers of damaging CCR2 variants have a lower burden of atherosclerosis and lower lifetime risk of myocardial infarction. In conjunction with previous evidence from experimental and epidemiological studies, our findings highlight the translational potential of CCR2-targeting as an atheroprotective approach.

Common- and rare-variant genetic architecture of heart failure across the allele frequency spectrum.

Heart failure (HF) is a complex trait, influenced by environmental and genetic factors, that affects over 30 million individuals worldwide. Historically, the genetics of HF have been studied in Mendelian forms of disease, where rare genetic variants have been linked to familial cardiomyopathies. More recently, genome-wide association studies (GWAS) have successfully identified common genetic variants associated with risk of HF. However, the relative importance of genetic variants across the allele-frequency spectrum remains incompletely characterized. Here, we report the results of common- and rare-variant association studies of all-cause heart failure, applying recently developed methods to quantify the heritability of HF attributable to different classes of genetic variation. We combine GWAS data across multiple populations including 207,346 individuals with HF and 2,151,210 without, identifying 176 risk loci at genome-wide significance (p < 5×10-8). Signals at newly identified common-variant loci include coding variants in Mendelian cardiomyopathy genes (MYBPC3, BAG3), as well as regulators of lipoprotein (LPL) and glucose metabolism (GIPR, GLP1R), and are enriched in cardiac, muscle, nerve, and vascular tissues, as well as myocyte and adipocyte cell types. Gene burden studies across three biobanks (PMBB, UKB, AOU) including 27,208 individuals with HF and 349,126 without uncover exome-wide significant (p < 3.15×10-6) associations for HF and rare predicted loss-of-function (pLoF) variants in TTN, MYBPC3, FLNC, and BAG3. Total burden heritability of rare coding variants (2.2%, 95% CI 0.99-3.5%) is highly concentrated in a small set of Mendelian cardiomyopathy genes, and is lower than heritability attributable to common variants (4.3%, 95% CI 3.9-4.7%) which is more diffusely spread throughout the genome. Finally, we demonstrate that common-variant background, in the form of a polygenic risk score (PRS), significantly modifies the risk of HF among carriers of pathogenic truncating variants in the Mendelian cardiomyopathy gene TTN. These findings suggest a significant polygenic component to HF exists that is not captured by current clinical genetic testing.

Genome-wide association study of thoracic aortic aneurysm and dissection in the Million Veteran Program.

The current understanding of the genetic determinants of thoracic aortic aneurysms and dissections (TAAD) has largely been informed through studies of rare, Mendelian forms of disease. Here, we conducted a genome-wide association study (GWAS) of TAAD, testing ~25 million DNA sequence variants in 8,626 participants with and 453,043 participants without TAAD in the Million Veteran Program, with replication in an independent sample of 4,459 individuals with and 512,463 without TAAD from six cohorts. We identified 21 TAAD risk loci, 17 of which have not been previously reported. We leverage multiple downstream analytic methods to identify causal TAAD risk genes and cell types and provide human genetic evidence that TAAD is a non-atherosclerotic aortic disorder distinct from other forms of vascular disease. Our results demonstrate that the genetic architecture of TAAD mirrors that of other complex traits and that it is not solely inherited through protein-altering variants of large effect size.

Quantitative prediction of right ventricular and size and function from the electrocardiogram.

Background: Right ventricular ejection fraction (RVEF) and end-diastolic volume (RVEDV) are not readily assessed through traditional modalities. Deep-learning enabled 12-lead electrocardiogram analysis (DL-ECG) for estimation of RV size or function is unexplored. Methods: We trained a DL-ECG model to predict RV dilation (RVEDV>120 mL/m2), RV dysfunction (RVEF≤40%), and numerical RVEDV/RVEF from 12-lead ECG paired with reference-standard cardiac MRI (cMRI) volumetric measurements in UK biobank (UKBB; n=42,938). We fine-tuned in a multi-center health system (MSHoriginal; n=3,019) with prospective validation over 4 months (MSHvalidation; n=115). We evaluated performance using area under the receiver operating curve (AUROC) for categorical and mean absolute error (MAE) for continuous measures overall and in key subgroups. We assessed association of RVEF prediction with transplant-free survival with Cox proportional hazards models. Results: Prevalence of RV dysfunction for UKBB/MSHoriginal/MSHvalidation cohorts was 1.0%/18.0%/15.7%, respectively. RV dysfunction model AUROC for UKBB/MSHoriginal/MSHvalidation cohorts was 0.86/0.81/0.77, respectively. Prevalence of RV dilation for UKBB/MSHoriginal/MSHvalidation cohorts was 1.6%/10.6%/4.3%. RV dilation model AUROC for UKBB/MSHoriginal/MSHvalidation cohorts 0.91/0.81/0.92, respectively. MSHoriginal MAE was RVEF=7.8% and RVEDV=17.6 ml/m2. Performance was similar in key subgroups including with and without left ventricular dysfunction. Over median follow-up of 2.3 years, predicted RVEF was independently associated with composite outcome (HR 1.37 for each 10% decrease, p=0.046). Conclusions: DL-ECG analysis can accurately identify significant RV dysfunction and dilation both overall and in key subgroups. Predicted RVEF is independently associated with clinical outcome.

A machine learning model identifies patients in need of autoimmune disease testing using electronic health records.

Systemic autoimmune rheumatic diseases (SARDs) can lead to irreversible damage if left untreated, yet these patients often endure long diagnostic journeys before being diagnosed and treated. Machine learning may help overcome the challenges of diagnosing SARDs and inform clinical decision-making. Here, we developed and tested a machine learning model to identify patients who should receive rheumatological evaluation for SARDs using longitudinal electronic health records of 161,584 individuals from two institutions. The model demonstrated high performance for predicting cases of autoantibody-tested individuals in a validation set, an external test set, and an independent cohort with a broader case definition. This approach identified more individuals for autoantibody testing compared with current clinical standards and a greater proportion of autoantibody carriers among those tested. Diagnoses of SARDs and other autoimmune conditions increased with higher model probabilities. The model detected a need for autoantibody testing and rheumatology encounters up to five years before the test date and assessment date, respectively. Altogether, these findings illustrate that the clinical manifestations of a diverse array of autoimmune conditions are detectable in electronic health records using machine learning, which may help systematize and accelerate autoimmune testing.