The long awaited work on developing a precision research cohort for Long COVID, Precision phenotyping for curating research cohorts of patients with unexplained post-acute sequelae of COVID-19, is finally out in Cell Med – (link to open access publication).

Context and significance

Identifying cohorts of patients with post-acute sequelae of COVID-19 (PASC), or long COVID, using real-world data is complex. The absence of precise definitions for PASC poses significant challenges in clinical research and patient care. Utilizing electronic health records from a large integrated healthcare system, Azhir et al. developed a precision phenotyping algorithm incorporating a novel attention mechanism that accounts for both infection-related chronic conditions and differential diagnoses. This approach demonstrated superior accuracy in identifying PASC cases compared to the existing ICD-10-CM code U09.9 while also mitigating demographic biases in diagnosis. The implications are profound, offering a refined tool for constructing research cohorts to explore the genetics and metabolomics of long COVID, thereby enhancing the health systems’ capacity to manage it.

Abstract

Scalable identification of patients with post-acute sequelae of COVID-19 (PASC) is challenging due to a lack of reproducible precision phenotyping algorithms, which has led to suboptimal accuracy, demographic biases, and underestimation of the PASC. In a retrospective case-control study, we developed a precision phenotyping algorithm for identifying cohorts of patients with PASC. We used longitudinal electronic health records data from over 295,000 patients from 14 hospitals and 20 community health centers in Massachusetts. The algorithm employs an attention mechanism to simultaneously exclude sequelae that prior conditions can explain and include infection-associated chronic conditions. We performed independent chart reviews to tune and validate the algorithm. The PASC phenotyping algorithm improves precision and prevalence estimation and reduces bias in identifying PASC cohorts compared to the ICD-10-CM code U09.9. The algorithm identified a cohort of over 24,000 patients with 79.9% precision. Our estimated prevalence of PASC was 22.8%, which is close to the national estimates for the region. We also provide in-depth analyses, encompassing identified lingering effects by organ, comorbidity profiles, and temporal differences in the risk of PASC. PASC precision phenotyping boasts superior precision and prevalence estimation while exhibiting less bias in identifying patients with PASC. The cohort derived from this algorithm will serve as a springboard for delving into the genetic, metabolomic, and clinical intricacies of PASC, surmounting the constraints of prior PASC cohort studies.