Diversity of symptom phenotypes in SARS-CoV-2 community infections observed in multiple large datasets

TL;DR

This study uses advanced machine learning techniques to identify diverse symptom patterns in SARS-CoV-2 community infections across large datasets, revealing underlying structures and age-related differences.

Contribution

It introduces a novel unsupervised classification approach to characterize COVID-19 symptom phenotypes across multiple datasets and age groups.

Findings

Symptoms cluster into gastrointestinal, respiratory, and other types.

Distinct symptom co-occurrence patterns at different ages.

Deep structure of COVID-19 symptoms identified without study bias.

Abstract

Through the use of cutting-edge unsupervised classification techniques from statistics and machine learning, we characterise symptom phenotypes among symptomatic SARS-CoV-2 PCR-positive community cases. We first analyse each dataset in isolation and across age bands, before using methods that allow us to compare multiple datasets. While we observe separation due to the total number of symptoms experienced by cases, we also see a separation of symptoms into gastrointestinal, respiratory and other types, and different symptom co-occurrence patterns at the extremes of age. In this way, we are able to demonstrate the deep structure of symptoms of COVID-19 without usual biases due to study design. This is expected to have implications for the identification and management of community SARS-CoV-2 cases and could be further applied to symptom-based management of other diseases and syndromes.