Multivariable risk modelling and survival analysis with machine learning in SARS-CoV-2 infection

Abstract

AbstractAimWe evaluated the performance of a machine learning model based on demographic variables, blood tests, pre-existing comorbidities, and CT-based radiomic features to predict critical outcome in patients with acute respiratory syndrome coronavirus 2 (SARS-CoV-2).MethodsWe retrospectively enrolled 694 SARS-CoV-2 positive patients. Clinical and demographic data were extracted from clinical records. Radiomic data were extracted from CT. Patients were randomized to the training (80%, n=556) or test (20%, n=138) dataset. The training set was used to define the association between severity of disease and comorbidities, laboratory tests, demographic and CT-based radiomic variables, and to implement a risk prediction model. Models were evaluated using the C statistic and Brier scores. The test set was used for external validation.ResultsPatients who died (n=157) were predominantly male (66%) over the age of 50 with (median [range] C-reactive protein (CRP)=5 [1, 37] mg/dL, lactate dehydrogenase (LDH)=494 [141, 3,631] U/I and D-dimer=6.006 [168, 152.015] ng/ml). Surviving patients (n=537) had (median [range]) CRP=3 [0, 27] mg/dL, LDH=484 [78, 3.745] U/I, and D-dimer=1.133 [96, 55.660]ng/ml. The strongest risk factors were D-dimer, age, and cardiovascular disease.The model implemented using the variables identified by the LASSO Cox regression analysis classified 152 of the 157 (97%) non-survivors as high risk individuals (Odd ratio=54.2 [21.9, 134.4]). Median survival in this group (14 [12, 19] days) was not different from that observed in non-survivors (12 [10, 14] days).ConclusionsA machine learning model based on combined data available on the first days of hospitalization (demographics, CT-radiomics, comorbidities, and blood biomarkers), can identify SARS-CoV-2 patients at risk of serious illness and death.