“…Using hierarchical clustering, we could identify two clusters of COVID-19 patients based on their socio-demographic and clinical characteristics: one, including younger patients with lower circulating inflammation levels and better renal function, and the other composed of generally older and more co-morbid subjects, more prevalently men and smokers. Interestingly, HCQ appeared to be associated with reduced mortality only in the low (hazard ratio 0.46, 95%CI: 0.39 to 0.54) but not in the high-risk cluster (hazard ratio 0.89, 95%CI: 0.65 to 1.22; P for difference P<0.001), suggesting a selective beneficial effect of HCQ in low risk COVID-19 patients ( 11 ). This was in line with the findings of the IDENTIFY study, a multicentre US clinical trial ( 12 ); in that study, HCQ treatment was associated with higher survival in the treated harm, especially in those patients that were predicted to benefit most, based on a supervised machine learning algorithm applied to their characteristics.…”