No abstract

Around five percent of the population is affected by a rare disease, most often due to genetic variation. A genetic test is the quickest path to a diagnosis, yet most suffer through years of diagnostic odyssey before getting a test, if they receive one at all. Identifying patients that are likely to have a genetic disease and therefore need genetic testing is paramount to improving diagnosis and treatment. While there are thousands of previously described genetic diseases with specific phenotypic presentations, a common feature among them is the presence of multiple rare phenotypes which often span organ systems. Here, we hypothesize that these patients can be identified from longitudinal clinical data in the electronic health record (EHR). We used diagnostic information from the EHRs of 2,286 patients that received a chromosomal microarray and 9,144 matched controls to train and test a prediction model. We identified high prediction accuracy (AUROC = 0.97, AUPR = 0.92) in a held-out test sample and in 172,265 hospital patients where cases were defined broadly as interacting with a genetics provider (AUROC = 0.9, AUPR = 0.63). High probabilities (median = 0.97) were associated with 46 patients carrying a known pathogenic copy number variant (CNV) among a subset of 6,445 genotyped patients. Our model identified many more patients needing a genetic test while increasing the proportion having a putative genetic disease compared to the current nonsytematic approach. Taken together, we demonstrate that phenotypic patterns representative of a genetic disease can be captured from EHR data and provide an opportunity to systematize decision making on genetic testing to speed up diagnosis, improve care, and reduce costs.

Treatment-resistant depression (TRD), often defined by absence of symptomatic remission following at least two adequate treatment trials, occurs in roughly a third of all individuals with major depressive disorder (MDD). Prior work has suggested a significant common variant genetic component of liability to TRD, with heritability estimates of 8% when comparing to non-treatment resistant MDD. Despite this evidence of heritability, no replicated genetic loci have been identified and the genetic architecture of TRD remains unclear. A key barrier to this work has been the paucity of adequately powered cohorts for investigation, largely because of the challenge in prospectively investigating this phenotype. Using electroconvulsive therapy (ECT) as a surrogate for TRD, we applied standard machine learning methods to electronic health record (EHR) data to derive predicted probabilities of receiving ECT. We applied these probabilities as a quantitative trait in a genome-wide association study (GWAS) over 154,433 genotyped patients across four large biobanks. With this approach, we demonstrate heritability ranging from 2% to 4.2% and significant genetic overlap with cognition, attention deficit hyperactivity disorder, schizophrenia, alcohol and smoking traits and body mass index. We identify two genome-wide significant loci, both previously implicated in metabolic traits, suggesting shared biology and potential pharmacological implications. This work provides support for the utility of estimation of disease probability for genomic investigation and provides insights into the genetic architecture and biology of TRD.

Around five percent of the population is affected by a rare disease, most often due to genetic variation. A genetic test is the quickest path to a diagnosis, yet most suffer through years of diagnostic odyssey before getting a test, if they receive one at all. Identifying patients that are likely to have a genetic disease and therefore need genetic testing is paramount to improving diagnosis and treatment. While there are thousands of previously described genetic diseases with specific phenotypic presentations, a common feature among them is the presence of multiple rare phenotypes which often span organ systems. Here, we hypothesize that these patients can be identified from longitudinal clinical data in the electronic health record (EHR). We used diagnostic information from the EHRs of 2,286 patients that received a chromosomal microarray and 9,144 matched controls to train and test a prediction model. We identified high prediction accuracy (AUROC = 0.97, AUPR = 0.92) in a held-out test sample and in 172,265 hospital patients where cases were defined broadly as interacting with a genetics provider (AUROC = 0.9, AUPR = 0.63). High probabilities (median = 0.97) were associated with 46 patients carrying a known pathogenic copy number variant (CNV) among a subset of 6,445 genotyped patients. Our model identified many more patients needing a genetic test while increasing the proportion having a putative genetic disease compared to the current nonsytematic approach. Taken together, we demonstrate that phenotypic patterns representative of a genetic disease can be captured from EHR data and provide an opportunity to systematize decision making on genetic testing to speed up diagnosis, improve care, and reduce costs.

No abstract