Because of the large scale of the ISARIC-4C study, we were able to detect robust groupings of patients with different patterns of symptoms. We found four patterns that are strikingly differnet from the core symptom groups: gastro-intestinal disease, productive cough, confusion, and pauci-symptomatic presentations. Each of these has a different clinical course and a different chance of death. These observations deepen our understanding of COVID-19 and will influence clinical diagnosis, risk prediction, and future mechanistic and clinical studies.