Victor Manuel Castro

This study uses EHR data to estimate TRD probability and identifies two genome-wide significant loci linked to metabolic traits, suggesting shared biology with related conditions.

Neptune delivers structured genomic data to EHR systems through customizable reports and variant reanalysis, supporting over 15,000 clinical reports.

The paper develops a model to identify patients likely to have a genetic disease using EHR data, achieving high accuracy in predicting genetic testing needs.

sureLDA automates phenotype labeling in EHR data using topic modeling, achieving high accuracy and robustness across various phenotypes.

This study evaluates polygenic risk scores for schizophrenia in electronic health records, finding strong associations with schizophrenia and pleiotropic effects on other psychiatric and medical conditions.

This paper develops an automated high-throughput phenotyping method (MAP) that improves phenotype accuracy and scalability for PheWAS studies.

This paper validates EHR-based BD phenotyping algorithms by showing their genetic correlation with traditional BD cases, suggesting they identify genetically similar cases.