Development and validation of a federated learning framework for detection of subphenotypes of multisystem inflammatory syndrome in children (preprint)

Background: Multisystem inflammatory syndrome in children (MIS-C) is a severe post-acute sequela of SARS-CoV-2 infection. The highly diverse clinical features of MIS-C necessities characterizing its features by subphenotypes for improved recognition and treatment. However, jointly identifying subphenotypes in multi-site settings can be challenging. We propose a distributed multi-site latent class analysis (dMLCA) approach to jointly learn MIS-C subphenotypes using data across multiple institutions. Methods We used data from the electronic health records (EHR) systems across nine U.S. childrens hospitals. Among the 3,549,894 patients, we extracted 864 patients < 21 years of age who had received a diagnosis of MIS-C during an inpatient stay or up to one day before admission. Using MIS-C conditions, laboratory results, and procedure information as input features for the patients, we applied our dMLCA algorithm and identified three MIS-C subphenotypes. As validation, we characterized and compared more granular features across subphenotypes. To evaluate the specificity of the identified subphenotypes, we further compared them with the general subphenotypes identified in the COVID-19 infected patients. Findings Subphenotype 1 (46.1%) represents patients with a mild manifestation of MIS-C not requiring intensive care, with minimal cardiac involvement. Subphenotype 2 (25.3%) is associated with a high risk of shock, cardiac and renal involvement, and an intermediate risk of respiratory symptoms. Subphenotype 3 (28.6%) represents patients requiring intensive care, with a high risk of shock and cardiac involvement, accompanied by a high risk of >4 organ system being impacted. Importantly, for hospital-specific clinical decision-making, our algorithm also revealed a substantial heterogeneity in relative proportions of these three subtypes across hospitals. Properly accounting for such heterogeneity can lead to accurate characterization of the subphenotypes at the patient-level. Interpretation Our identified three MIS-C subphenotypes have profound implications for personalized treatment strategies, potentially influencing clinical outcomes. Further, the proposed algorithm facilitates federated subphenotyping while accounting for the heterogeneity across hospitals.

Clinical Subphenotypes of Multisystem Inflammatory Syndrome in Children: An EHR-based cohort study from the RECOVER program (preprint)

Background: Multi-system inflammatory syndrome in children (MIS-C) represents one of the most severe post-acute sequelae of SARS-CoV-2 infection in children, and there is a critical need to characterize its disease patterns for improved recognition and management. Our objective was to characterize subphenotypes of MIS-C based on presentation, demographics and laboratory parameters. Methods: We conducted a retrospective cohort study of children with MIS-C from March 1, 2020 - April 30, 2022 and cared for in 8 pediatric medical centers that participate in PEDSnet. We included demographics, symptoms, conditions, laboratory values, medications and outcomes (ICU admission, death), and grouped variables into eight categories according to organ system involvement. We used a heterogeneity-adaptive latent class analysis model to identify three clinically-relevant subphenotypes. We further characterized the sociodemographic and clinical characteristics of each subphenotype, and evaluated their temporal patterns. Findings: We identified 1186 children hospitalized with MIS-C. The highest proportion of children (44.4%) were aged between 5-11 years, with a male predominance (61.0%), and non-Hispanic white ethnicity (40.2%). Most (67.8%) children did not have a chronic condition. Class 1 represented children with a severe clinical phenotype, with 72.5% admitted to the ICU, higher inflammatory markers, hypotension/shock/dehydration, cardiac involvement, acute kidney injury and respiratory involvement. Class 2 represented a moderate presentation, with 4-6 organ systems involved, and some overlapping features with acute COVID-19. Class 3 represented a mild presentation, with fewer organ systems involved, lower CRP, troponin values and less cardiac involvement. Class 1 initially represented 51.1% of children early in the pandemic, which decreased to 33.9% from the pre-delta period to the omicron period. Interpretation: MIS-C has a spectrum of clinical severity, with degree of laboratory abnormalities rather than the number of organ systems involved providing more useful indicators of severity. The proportion of severe/critical MIS-C decreased over time.