Sleep apnea phenotyping and relationship to disease in a large clinical biobank

Abstract

Objective Sleep apnea is associated with a broad range of pathophysiology. While electronic health record (EHR) information has the potential for revealing relationships between sleep apnea and associated risk factors and outcomes, practical challenges hinder its use. Our objectives were to develop a sleep apnea phenotyping algorithm that improves the precision of EHR case/control information using natural language processing (NLP); identify novel associations between sleep apnea and comorbidities in a large clinical biobank; and investigate the relationship between polysomnography statistics and comorbid disease using NLP phenotyping. Materials and Methods We performed clinical chart reviews on 300 participants putatively diagnosed with sleep apnea and applied International Classification of Sleep Disorders criteria to classify true cases and noncases. We evaluated 2 NLP and diagnosis code-only methods for their abilities to maximize phenotyping precision. The lead algorithm was used to identify incident and cross-sectional associations between sleep apnea and common comorbidities using 4876 NLP-defined sleep apnea cases and 3× matched controls. Results The optimal NLP phenotyping strategy had improved model precision (≥0.943) compared to the use of one diagnosis code (≤0.733). Of the tested diseases, 170 disorders had significant incidence odds ratios (ORs) between cases and controls, 8 of which were confirmed using polysomnography (n = 4544), and 281 disorders had significant prevalence OR between sleep apnea cases versus controls, 41 of which were confirmed using polysomnography data. Discussion and Conclusion An NLP-informed algorithm can improve the accuracy of case-control sleep apnea ascertainment and thus improve the performance of phenome-wide, genetic, and other EHR analyses of a highly prevalent disorder.

Discovery of genomic loci associated with sleep apnoea risk through multi-trait GWAS analysis with snoring

“…While combining multiple sources for phenotype definition is warranted to achieve the required sample sizes for GWAS, minimal phenotyping might introduce heterogeneity. Future studies should explore using novel advances in natural language processing 74 of electronic health records to increase the accuracy of biobank-based phenotyping and compare the accuracy and genetic concordance of the different phenotyping approaches used here. We found the combined effect of the SNPs in our meta-analysis to explain ∼13% of the variance of sleep apnoea on the observed scale.…”

The Causal Effects of Lipid Profiles on Sleep Apnea

“…We chose the largest sample size datasets of SA in the MRC Integrative Epidemiology Unit (MRC-IEU) consortium 3 from the UKB ( 18 ) (dataset ID: ukb-b-7853, N = 463,010, diagnosis: sleep apnea). Apnea-hypopnea index (AHI) is defined as the frequency of obstructive or mixed apnea or hypopnea per hour and is the disease-defining threshold for laboratory diagnosis of sleep apnea obtained by laboratory polysomnography test ( 24 , 25 ). The diagnosis of SA is determined by AHI > 5/h for adults ( 26 ).…”

Predictive Modeling and Deep Phenotyping of Obstructive Sleep Apnea and Associated Comorbidities through Natural Language Processing and Large Language Models

“…To enhance model validation, we will consider incorporating two or more instances of diagnostic codes for a specific health condition when labeling (Keenan et al, 2020) or collaborating with physicians in this study to create a ground truth dataset (Cade et al, 2022).…”