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.
Complications
Flexible ureteroscopy
Kidney stones
Machine learning
Retrograde intrarenal surgery
Sepsis
Journal
World journal of urology
ISSN: 1433-8726
Titre abrégé: World J Urol
Pays: Germany
ID NLM: 8307716
Informations de publication
Date de publication:
01 Nov 2024
01 Nov 2024
Historique:
received:
05
06
2024
accepted:
07
10
2024
medline:
1
11
2024
pubmed:
1
11
2024
entrez:
1
11
2024
Statut:
epublish
Résumé
To create a machine-learning model for estimating the likelihood of post-retrograde intrarenal surgery (RIRS) sepsis. All consecutive patients with kidney stone(s) only undergoing RIRS in 16 centers were prospectively included (January 2022-August 2023). adult, renal stone(s) only, CT scan (within three months), mid-stream urine culture (within 10 days). 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. 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.
Identifiants
pubmed: 39485570
doi: 10.1007/s00345-024-05314-5
pii: 10.1007/s00345-024-05314-5
doi:
Types de publication
Journal Article
Multicenter Study
Langues
eng
Sous-ensembles de citation
IM
Pagination
612Informations de copyright
© 2024. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.
Références
Gauhar V, Chew BH, Traxer O et al (2023) Indications, preferences, global practice patterns and outcomes in retrograde intrarenal surgery (RIRS) for renal stones in adults: results from a multicenter database of 6669 patients of the global FLEXible ureteroscopy outcomes Registry (FLEXOR). World J Urol 41:567–574. https://doi.org/10.1007/s00345-022-04257-z
doi: 10.1007/s00345-022-04257-z
pubmed: 36536170
Geraghty RM, Davis NF, Tzelves L et al (2023) Best practice in interventional management of Urolithiasis: an update from the European Association of Urology Guidelines Panel for Urolithiasis 2022. Eur Urol Focus 9:199–208. https://doi.org/10.1016/j.euf.2022.06.014
doi: 10.1016/j.euf.2022.06.014
pubmed: 35927160
Assimos D, Krambeck A, Miller NL et al (2016) Surgical management of stones: American urological association/endourological society guideline, PART II. J Urol 196:1161–1169. https://doi.org/10.1016/j.juro.2016.05.091
doi: 10.1016/j.juro.2016.05.091
pubmed: 27238615
Tonyali S, Haberal HB, Esperto F et al (2023) The prime time for flexible ureteroscopy for large renal stones is coming: is percutaneous nephrolithotomy no longer needed? Urol Res Pract 49:280–284. https://doi.org/10.5152/tud.2023.23142
doi: 10.5152/tud.2023.23142
pubmed: 37877875
pmcid: 10646796
Corrales M, Sierra A, Doizi S, Traxer O (2022) Risk of sepsis in retrograde intrarenal surgery: a systematic review of the literature. Eur Urol open Sci 44:84–91. https://doi.org/10.1016/j.euros.2022.08.008
doi: 10.1016/j.euros.2022.08.008
pubmed: 36071820
pmcid: 9442387
Cindolo L, Castellan P, Scoffone CM et al (2016) Mortality and flexible ureteroscopy: analysis of six cases. World J Urol 34:305–310. https://doi.org/10.1007/s00345-015-1642-0
doi: 10.1007/s00345-015-1642-0
pubmed: 26210344
Bonkat G, Cai T, Veeratterapillay R et al (2019) Management of urosepsis in 2018. Eur Urol Focus 5:5–9. https://doi.org/10.1016/j.euf.2018.11.003
doi: 10.1016/j.euf.2018.11.003
pubmed: 30448051
Bhanot R, Pietropaolo A, Tokas T et al (2022) Predictors and strategies to avoid Mortality following ureteroscopy for stone disease: a systematic review from European Association of Urologists Sections of Urolithiasis (EULIS) and uro-technology (ESUT). Eur Urol Focus 8:598–607. https://doi.org/10.1016/j.euf.2021.02.014
doi: 10.1016/j.euf.2021.02.014
pubmed: 33674255
Bi Q, Goodman KE, Kaminsky J, Lessler J (2019) What is Machine Learning? A primer for the epidemiologist. Am J Epidemiol 188:2222–2239. https://doi.org/10.1093/aje/kwz189
doi: 10.1093/aje/kwz189
pubmed: 31509183
Skolarikos A, Neisius A, Petřík A et al (2023) A, European Association of Urology Guidelines on Urolithiasis. https://d56bochluxqnz.cloudfront.net/documents/full-guideline/EAU-Guidelines-on-Urolithiasis-2023.pdf . Accessed 14 Feb 2024
Singer M, Deutschman CS, Seymour C et al (2016) The third international consensus definitions for sepsis and septic shock (sepsis-3). JAMA 315:801–810. https://doi.org/10.1001/jama.2016.0287
doi: 10.1001/jama.2016.0287
pubmed: 26903338
pmcid: 4968574
Giusti G, Proietti S, Villa L et al (2016) Current standard technique for modern flexible ureteroscopy: tips and tricks. Eur Urol 70:188–194. https://doi.org/10.1016/j.eururo.2016.03.035
doi: 10.1016/j.eururo.2016.03.035
pubmed: 27086502
Tam A (2021) Training-validation-test split and cross-validation done right. In: Mach. Learn., Process https://machinelearningmastery.com/training-validation-test-split-and-cross-validation-done-right/ . Accessed 3 Mar 2024
Brownlee J (2023) A Gentle Introduction to k-fold Cross-Validation. In: Statistics (Ber). https://machinelearningmastery.com/k-fold-cross-validation/ . Accessed 3 Mar 2024
Figueroa RL, Zeng-Treitler Q, Kandula S, Ngo LH (2012) Predicting sample size required for classification performance. BMC Med Inf Decis Mak. https://doi.org/10.1186/1472-6947-12-8
doi: 10.1186/1472-6947-12-8
Talekar B (2020) A detailed review on decision tree and random forest. Biosci Biotechnol Res Commun 13:245–248. https://doi.org/10.21786/bbrc/13.14/57
doi: 10.21786/bbrc/13.14/57
Chen T, Guestrin C (2016) XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD ’16). Association for Computing Machinery, New York, USA, pp 785–794. https://doi.org/10.1145/2939672.2939785
Rokach L (2010) Ensemble-based classifiers. Artif Intell Rev 33:1–39. https://doi.org/10.1007/s10462-009-9124-7
doi: 10.1007/s10462-009-9124-7
Breiman L (2001) Random forests. Mach Learn 45:5–32. https://doi.org/10.1023/A:1010933404324
doi: 10.1023/A:1010933404324
Xuan Z, Yu Z, Tan G et al (2022) Development and validation of a novel nomogram for predicting systemic inflammatory response syndrome’s occurrence in patients undertaking flexible ureteroscopy. Transl Androl Urol 11:228–237. https://doi.org/10.21037/tau-22-34
doi: 10.21037/tau-22-34
pubmed: 35280653
pmcid: 8899144
Pietropaolo A, Geraghty RM, Veeratterapillay R et al (2021) A machine learning predictive model for post-ureteroscopy urosepsis needing intensive care unit admission: a case-control YAU endourology study from nine european centres. J Clin Med. https://doi.org/10.3390/jcm10173888
doi: 10.3390/jcm10173888
pubmed: 34501335
pmcid: 8432042
Sabbagh A, Washington SL 3rd, Tilki D et al (2023) Development and external validation of a machine learning model for prediction of Llymph Node metastasis in patients with prostate cancer. Eur Urol Oncol 6:501–507. https://doi.org/10.1016/j.euo.2023.02.006
doi: 10.1016/j.euo.2023.02.006
pubmed: 36868922
Ngiam KY, Khor IW (2019) Big data and machine learning algorithms for health-care delivery. Lancet Oncol 20:e262–e273. https://doi.org/10.1016/S1470-2045(19)30149-4
doi: 10.1016/S1470-2045(19)30149-4
pubmed: 31044724
Zhang Y, Xu W, Yang P, Zhang A (2023) Machine learning for the prediction of sepsis-related death: a systematic review and meta-analysis. BMC Med Inf Decis Mak. https://doi.org/10.1186/s12911-023-02383-1
doi: 10.1186/s12911-023-02383-1
Castellani D, Teoh JY, Pavia MP et al (2022) Assessing the optimal urine culture for predicting systemic inflammatory response syndrome after percutaneous nephrolithotomy and retrograde intrarenal surgery: results from a systematic review and meta-analysis. J Endourol 36:158–168. https://doi.org/10.1089/end.2021.0386
doi: 10.1089/end.2021.0386
pubmed: 34314245
Croghan SM, Cunnane EM, O’Meara S et al (2023) In vivo ureteroscopic intrarenal pressures and clinical outcomes: a multi-institutional analysis of 120 consecutive patients. BJU Int 132:531–540. https://doi.org/10.1111/bju.16169
doi: 10.1111/bju.16169
pubmed: 37656050
Gauhar V, Traxer O, Castellani D et al (2024) Could use of a flexible and navigable suction ureteral access sheath be a potential game-changer in retrograde intrarenal surgery? Outcomes at 30 days from a large, prospective, multicenter, real-world study by the European association of urology urolithiasis section. European Urology Focus. https://doi.org/10.1016/j.euf.2024.05.010
doi: 10.1016/j.euf.2024.05.010
pubmed: 38897872