Rxivist logo

Phenotype Risk Scores: moving beyond cases and controls to classify psychiatric disease in hospital-based biobanks.

By Dannielle S. Lebovitch, Jessica S Johnson, Hillary Ruhl Duenas, Laura M Huckins

Posted 26 Jan 2021
medRxiv DOI: 10.1101/2021.01.25.21249615

Current phenotype classifiers for large biobanks with coupled electronic health records EHR and multi-omic data rely on ICD-10 codes for definition. However, ICD-10 codes are primarily designed for billing purposes, and may be insufficient for research. Nuanced phenotypes composed of a patients' experience in the EHR will allow us to create precision psychiatry to predict disease risk, severity, and trajectories in EHR and clinical populations. Here, we create a phenotype risk score (PheRS) for major depressive disorder (MDD) using 2,086 cases and 31,000 individuals from Mount Sinai's biobank BioMe. Rather than classifying individuals as 'cases' and 'controls', PheRS provide a whole-phenome estimate of each individual's likelihood of having a given complex trait. These quantitative scores substantially increase power in EHR analyses and may identify individuals with likely missing diagnoses (for example, those with large numbers of comorbid diagnoses and risk factors, but who lack explicit MDD diagnoses). Our approach applied ten-fold cross validation and elastic net regression to select comorbid ICD-10 codes for inclusion in our PheRS. We identified 158 ICD-10 codes significantly associated with Moderate MDD (F33.1). Phenotype Risk Score were significantly higher among individuals with ICD-10 MDD diagnoses compared to the rest of the population (Kolgorov-Smirnov p<2.2e-16), and were significantly correlated with MDD polygenic risk scores (R2>0.182). Accurate classifiers are imperative for identification of genetic associations with psychiatric disease; therefore, moving forward research should focus on algorithms that can better encompass a patient's phenome.

Download data

  • Downloaded 289 times
  • Download rankings, all-time:
    • Site-wide: 87,312
    • In psychiatry and clinical psychology: 307
  • Year to date:
    • Site-wide: 6,405
  • Since beginning of last month:
    • Site-wide: 12,456

Altmetric data


Downloads over time

Distribution of downloads per paper, site-wide


PanLingua

Sign up for the Rxivist weekly newsletter! (Click here for more details.)


News