Hierarchical Neyman-Pearson Classification for Prioritizing Severe Disease Categories in COVID-19 Patient Data

COVID-19 has a spectrum of disease severity, ranging from asymptomatic to requiring hospitalization. Providing appropriate medical care to severe patients is crucial to reduce mortality risks. Hence, in classifying patients into severity categories, the more important classification errors are "under-diagnosis", in which patients are misclassified into less severe categories and thus receive insufficient medical care. The Neyman-Pearson (NP) classification paradigm has been developed to prioritize the designated type of error. However, current NP procedures are either for binary classification or do not provide high probability controls on the prioritized errors in multi-class classification. Here, we propose a hierarchical NP (H-NP) framework and an umbrella algorithm that generally adapts to popular classification methods and controls the under-diagnosis errors with high probability. On an integrated collection of single-cell RNA-seq (scRNA-seq) datasets for 740 patients, we explore ways of featurization and demonstrate the efficacy of the H-NP algorithm in controlling the under-diagnosis errors regardless of featurization. Beyond COVID-19 severity classification, the H-NP algorithm generally applies to multi-class classification problems, where classes have a priority order.