COVID-19 is strongly influenced by age and comorbidities. Acute kidney injury (AKI) is a frequent finding in COVID-19 patients and seems to be associated to mortality and severity. On the other hand, the role of kidney dysfunction in COVID-19 is still debated. We performed a retrospective study in a cohort of 174 hospitalized COVID-19 patients in Italy from March 3rd to May 21st 2020, to investigate the role of kidney dysfunction on COVID-19 severity and mortality. Moreover, we examined in depth the relationship between kidney function, age, and progression of COVID-19, also using different equations to estimate the glomerular filtration rate (GFR). We performed logistic regressions, while a predictive analysis was made through a machine learning approach. AKI and death occurred respectively in 10.2% and 19.5%, in our population. The major risk factors for mortality in our cohort were age adjusted HR, 6.2; 95% confidence interval (CI) 1.8-21.4 and AKI 3.36 (1.44-7.87), while, in these relationships, GFR at baseline mitigated the role of age. The occurrence of AKI was influenced by baseline kidney function, D-dimer, procalcitonin and hypertension. Our predictive analysis for AKI and mortality reached an accuracy of ≥ 94% and ≥ 91%, respectively. Our study scales down the role of kidney function impairment on hospital admission , especially in elderly patients. BIS-1 formula demonstrated a worse performance to predict the outcomes in COVID-19 patients when compared with MDRD and CKD-EPI.