Background International recommendations promote a strict potassium diet in order to avoid hyperkalemia in chronic kidney disease patients. However, efficiency of such a dietary counseling has never been demonstrated. The objectives of this study were to define the relationship between kalemia, dietary potassium intake estimated by kaliuresis and renal function and to define the factors associated with kalemia in patients using artificial intelligence. Methods To this extent, data from patients followed in a nephrology unit, included in the UniverSel study and whose kalemia (measured on the day of urine collection; n = 367) were analyzed. Results The patients included had a wide range of estimated glomerular filtration rate, but few had stage 5 chronic kidney disease (CKD). Kalemia was negatively and linearly correlated to estimated glomerular filtration rate (p<0.001) but was not correlated to kaliuresis (p = 0.55). Kaliuresis was not correlated to estimated glomerular filtration rate (p = 0.08). Factors associated with kalemia were analyzed using a Bayesian network. The 5 variables most associated with kalemia were, in descending order, estimated glomerular filtration rate, original nephropathy, age, diabetes, and plasma bicarbonate level. Conclusion The results of this study do not support a strict dietary potassium control to regulate kalemia in stage 1 to 4 CKD patients