Genetic validation of bipolar disorder identified by automated phenotyping using electronic health records

Abstract

Bipolar disorder (BD) is a heritable mood disorder characterized by episodes of mania and depression. Although genomewide association studies (GWAS) have successfully identified genetic loci contributing to BD risk, sample size has become a rate-limiting obstacle to genetic discovery. Electronic health records (EHRs) represent a vast but relatively untapped resource for high-throughput phenotyping. As part of the International Cohort Collection for Bipolar Disorder (ICCBD), we previously validated automated EHR-based phenotyping algorithms for BD against in-person diagnostic interviews (Castro et al. Am J Psychiatry 172:363–372, 2015). Here, we establish the genetic validity of these phenotypes by determining their genetic correlation with traditionally ascertained samples. Case and control algorithms were derived from structured and narrative text in the Partners Healthcare system comprising more than 4.6 million patients over 20 years. Genomewide genotype data for 3330 BD cases and 3952 controls of European ancestry were used to estimate SNP-based heritability (h2g) and genetic correlation (rg) between EHR-based phenotype definitions and traditionally ascertained BD cases in GWAS by the ICCBD and Psychiatric Genomics Consortium (PGC) using LD score regression. We evaluated BD cases identified using 4 EHR-based algorithms: an NLP-based algorithm (95-NLP) and three rule-based algorithms using codified EHR with decreasing levels of stringency—“coded-strict”, “coded-broad”, and “coded-broad based on a single clinical encounter” (coded-broad-SV). The analytic sample comprised 862 95-NLP, 1968 coded-strict, 2581 coded-broad, 408 coded-broad-SV BD cases, and 3 952 controls. The estimated h2g were 0.24 (p = 0.015), 0.09 (p = 0.064), 0.13 (p = 0.003), 0.00 (p = 0.591) for 95-NLP, coded-strict, coded-broad and coded-broad-SV BD, respectively. The h2g for all EHR-based cases combined except coded-broad-SV (excluded due to 0 h2g) was 0.12 (p = 0.004). These h2g were lower or similar to the h2g observed by the ICCBD + PGCBD (0.23, p = 3.17E−80, total N = 33,181). However, the rg between ICCBD + PGCBD and the EHR-based cases were high for 95-NLP (0.66, p = 3.69 × 10–5), coded-strict (1.00, p = 2.40 × 10−4), and coded-broad (0.74, p = 8.11 × 10–7). The rg between EHR-based BD definitions ranged from 0.90 to 0.98. These results provide the first genetic validation of automated EHR-based phenotyping for BD and suggest that this approach identifies cases that are highly genetically correlated with those ascertained through conventional methods. High throughput phenotyping using the large data resources available in EHRs represents a viable method for accelerating psychiatric genetic research.

Machine Learning for Violence Risk Assessment Using Dutch Clinical Notes

“…Indeed, machine learning approaches trained on English-language psychiatric notes have shown promising results with values of the Receiver Operating Characteristic (ROC) Area Under the Curve (AUC) of 0.85 and higher [6][7][8][9][10].…”

Comparing Deep Learning and Classical Machine Learning Approaches for Predicting Inpatient Violence Incidents from Clinical Text

“…The structured data in a patient record (e.g., diagnosis, medication, lab measurements) are relatively straightforward to analyze using well-known and well-researched statistical methods, in practice however, a lot of information in EHR is captured in an unstructured free text form that is more difficult to analyze [9,10]. Despite this difficulty, the merits of utilizing clinical text for research purposes are currently being discovered in many areas of research, such as adverse event detection, phenotyping, and predictive analysis (e.g., [11][12][13][14]). These approaches use well established methods for classification of text like bag-of-words and n-grams for representing text, and Naive Bayes and Support Vector Machine models for classifying text.…”

Defining major depressive disorder cohorts using the EHR: Multiple phenotypes based on ICD-9 codes and medication orders

“…Additionally, antidepressants may be prescribed for a variety of comorbid mental (Shah and Han, 2015) and non-mental health indications (Wong et al, 2017), such as tobacco use cessation (Reid et al, 2016) or chronic pain (Chong and Bajwa, 2003), which complicates its use for reliably identifying depression (Gill et al, 2010). Lastly, the use of natural language processing (NLP) on clinical notes has great promise for classifying psychiatric disorders (Castro et al, 2015;Chen et al, 2018;Kho et al, 2011;Perlis et al, 2012;Zhou et al, 2015). However, the generalizability of these methods may be limited due to data sets that do not have the number or types of notes required or contain only deidentified structured data.…”