Antibiotic resistance is an increasing problem, especially in children with urinary tract infections. Rates of drug-specific resistant pathogens were reported, and an easy prediction model to guide the clinical decision-making process for antibiotic treatment was proposed. Data on microbiological isolation from urinoculture, between January 2007–December 2018 at Istituto Gaslini, Italy, in patients aged <19 years were extracted. Logistic regression-based prediction scores were calculated. Discrimination was determined by the area under the receiver operating characteristic curve; calibration was assessed by the Hosmer and Lemeshow test and the Spiegelhalterz test. A total of 9449 bacterial strains were isolated in 6207 patients; 27.2% were <6 months old at the first episode. Enterobacteriales (Escherichia coli and other Enterobacteriales) accounted for 80.4% of all isolates. Amoxicillin-clavulanate (AMC) and cefixime (CFI) Enterobacteriales resistance was 32.8% and 13.7%, respectively, and remained quite stable among the different age groups. On the contrary, resistance to ciprofloxacin (CIP) (overall 9.6%) and cotrimoxazole (SXT) (overall 28%) increased with age. After multivariable analysis, resistance to AMC/CFI could be predicted by the following: sex; age at sampling; department of admission; previous number of bacterial pathogens isolated. Resistance to CIP/SXT could be predicted by the same factors, excluding sex. The models achieved very good calibration but moderate discrimination performance. Specific antibiotic resistance among Enterobacteriales could be predicted using the proposed scoring system to guide empirical antibiotic choice. Further studies are needed to validate this tool.