Pereira, Naveen

Abstract Patients with rare genetic disorders often wait years for a correct diagnosis, highlighting the urgent need for early and efficient triage for those at risk. Electronic health records (EHRs) are rich in useful information, yet the extent to which this data is sufficient to generate prediagnostic signals is uncertain. We trained machine learning models on billing codes and phenotypes extracted from clinical notes and applied these across eight conditions in a longitudinal cohort of roughly 3 million patient records from the Mayo Clinic, seeking early identification of conditions. The number of patients identified early varied by condition, ranging from 10% to 89% at 99% specificity. Median lead times exceeded one year prior to the first diagnostic billing code for most conditions, including Fabry disease (1,408 days), hereditary angioedema (2,755 days), neurofibromatosis type 1 (1,067 days), and hereditary hemorrhagic telangiectasia (2,320 days). We show that ML models trained on EHR data can prioritize patients for clinician review and confirmatory genetic testing and that the integration of diverse phenotypic data sources provides superior predictive value.

Abstract Human genomic studies link reduced CUB domain-containing protein 1 (CDCP1) expression with myocardial recovery in heart failure. While CDCP1 regulates cardiac fibroblast proliferation in vitro, it’s in vivo role in cardiac fibrosis remains unclear. Using a Cdcp1 -knockout (KO) angiotensin II/phenylephrine mouse model, we show that Cdcp1 deletion reduces echocardiographic left ventricular mass, histologic cardiac fibrosis, and pro-fibrotic gene expression, along with decreased fibroblast activation and inflammatory markers. Spatial transcriptomics identified a pressure overload–expanded fibroblast subpopulation enriched for growth factor and TGF-β signaling (FB5), which was markedly attenuated in Cdcp1 -KO hearts, alongside reduction of a pro-inflammatory cardiomyocyte subtype (CM4). Complementary studies in human ventricular fibroblasts demonstrate that CDCP1 knockdown reduced extracellular matrix gene expression and collagen I deposition. These findings establish CDCP1 as a regulator of cardiac fibrotic remodeling in vivo and open avenues for its further investigation as a potential therapeutic target.

Abstract Pathogenic variants in cardiomyopathy genes confer substantial disease risk, yet clinical penetrance varies widely. The population-level prevalence, age-specific penetrance, and the extent to which polygenic susceptibility modifies disease risk across diverse ancestries remain poorly defined. This population-based cohort study leveraged genome sequencing and linked electronic health record data from the All of Us Research Program (n=414,830). This study found that P/LP variants in cardiomyopathy-associated genes were present in 0.91% of participants (95% CI, 0.88%–0.94%), with similar prevalence across ancestry groups. Compared with non-carriers, variant carriers had significantly higher odds of all-cause heart failure (ACHF, OR, 2.58; 95% CI, 2.31–2.89), non-ischemic heart failure (NIHF, OR, 2.74; 95% CI, 2.42–3.10), and non-ischemic cardiomyopathy (NICM, OR, 4.99; 95% CI, 4.44–5.63). Among carriers, by age 50 years, 24.5% (95% CI, 14.5%–33.4%) developed ACHF, 17.2% (95% CI, 8.8%–24.8%) developed NIHF, and 30.1% (95% CI, 19.5%–40.2%) developed NICM. Higher polygenic risk for heart failure was independently associated with increased risk of ACHF (OR, 1.81; 95% CI, 1.74–1.89), NIHF (OR, 1.66; 95% CI, 1.58–1.75), and NICM (OR, 1.69; 95% CI, 1.59–1.80). Among carriers with elevated polygenic risk, odds of disease were substantially higher than among non-carriers at average polygenic risk (ACHF: OR, 4.71; 95% CI, 4.17–5.32; NIHF: OR, 4.56; 95% CI, 3.99–5.22; NICM: OR, 8.51; 95% CI, 7.44–9.73). Results showed that P/LP variants in cardiomyopathy genes were relatively common in this large, ancestrally diverse cohort, and conferred increased risk of cardiomyopathy and HF, with incomplete but clinically meaningful penetrance. Polygenic risk for HF independently and additively increased disease risk across ancestries. Integrating both may improve risk stratification and enable more precise, equitable care.