The infection post flexible UreteroreNoscopy (I-FUN) predictive model based on machine learning: a new clinical tool to assess the risk of sepsis post retrograde intrarenal surgery for kidney stone disease

• Published in: World journal of urology Vol. 42; no. 1; p. 612
• Main Authors: Castellani, Daniele, De Stefano, Virgilio, Brocca, Carlo, Mazzon, Giorgio, Celia, Antonio, Bosio, Andrea, Gozzo, Claudia, Alessandria, Eugenio, Cormio, Luigi, Ratnayake, Runeel, Vismara Fugini, Andrea, Morena, Tonino, Tanidir, Yiloren, Sener, Tarik Emre, Choong, Simon, Ferretti, Stefania, Pescuma, Andrea, Micali, Salvatore, Pavan, Nicola, Simonato, Alchiede, Miano, Roberto, Orecchia, Luca, Pirola, Giacomo Maria, Naselli, Angelo, Emiliani, Esteban, Hernandez-Peñalver, Pedro, Di Dio, Michele, Bisegna, Claudio, Campobasso, Davide, Serafin, Emauele, Antonelli, Alessandro, Rubilotta, Emanuele, Ragoori, Deepak, Balloni, Emanuele, Paolanti, Marina, Gauhar, Vineet, Galosi, Andrea Benedetto
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.11.2024; Springer Nature B.V
• Subjects: Antibiotics; Bacteriuria; Calculi; Comorbidity; Computed tomography; Implants; Kidney stones; Kidneys; Learning algorithms; Lithiasis; Machine learning; Medicine; Medicine & Public Health; Nephrolithiasis; Nephrology; Oncology; Patients; Prediction models; Prophylaxis; Sepsis; Septic shock; Surgery; Ureter; Urology; Flexible ureteroscopy; Retrograde intrarenal surgery; Sepsis; Complications; Machine learning; Kidney stones
• ISSN: 0724-4983; 1433-8726; 1433-8726
• DOI: 10.1007/s00345-024-05314-5

Purpose To create a machine-learning model for estimating the likelihood of post-retrograde intrarenal surgery (RIRS) sepsis. Methods All consecutive patients with kidney stone(s) only undergoing RIRS in 16 centers were prospectively included (January 2022–August 2023). Inclusion criteria: adult, renal stone(s) only, CT scan (within three months), mid-stream urine culture (within 10 days). Exclusion criteria: concomitant ureteral stone, bilateral procedures. In case of symptomatic infection/asymptomatic bacteriuria, patients were given six days of antibiotics according to susceptibility profiles. All patients had antibiotics prophylaxis. Variables selected for the model: age, gender, age-adjusted Charlson Comorbidity Index, stone volume, indwelling preoperative bladder catheter, urine culture, single/multiple stones, indwelling preoperative stent/nephrostomy, ureteric access sheath, surgical time. Analysis was conducted using Python programming language, with Pandas library and machine learning models implemented using the Scikit-learn library. Machine learning algorithms tested: Decision Tree, Random Forest, Gradient Boosting. Overall performance was accurately estimated by K-Fold cross-validation with three folds. Results 1552 patients were included. There were 20 (1.3%) sepsis cases, 16 (1.0%) septic shock cases, and three more cases (0.2%) of sepsis-related deaths. Random Forest model showed the best performance (precision = 1.00; recall = 0.86; F1 score = 0.92; accuracy = 0.92). A web-based interface of the predictive model was built and is available at https://emabal.pythonanywhere.com/ Conclusions Our model can predict post-RIRS sepsis with high accuracy and might facilitate patient selection for day-surgery procedures and identify patients at higher risk of sepsis who deserve extreme attention for prompt identification and treatment.