Predictors and associations of complications in ureteroscopy for stone disease using AI: outcomes from the FLEXOR registry.

Journal: Urolithiasis
PMID:

Abstract

We aimed to develop machine learning(ML) algorithms to evaluate complications of flexible ureteroscopy and laser lithotripsy(fURSL), providing a valid predictive model. 15 ML algorithms were trained on a large number fURSL data from > 6500 patients from the international FLEXOR database. fURSL complications included pelvicalyceal system(PCS) bleeding, ureteric/PCS injury, fever and sepsis. Pre-treatment characteristics served as input for ML training and testing. Correlation and logistic regression analysis were carried out by a multi-task neural network, while explainable AI was used for the predictive model. ML algorithms performed excellently. For intraoperative PCS bleeding, Extra Tree Classifier achieved the best accuracy at 95.03% (precision 80.99%), and greatest correlation with stone diameter(0.21) and residual fragments(0.26). PCS injury was best predicted by RandomForest (accuracy 97.72%, precision 63.50%). XGBoost performed best for ureteric injury (accuracy 96.88%, precision 60.67%). Both demonstrated moderate correlation with preoperative characteristics. Postoperative fever was predicted by Extra Tree Classifier with 91.34% accuracy (precision 58.20%). Cat Boost Classifier predicted postoperative sepsis with 99.15% accuracy (precision 66.38%), and the best overall performance. At logistic regression, postoperative fever/sepsis positively correlated with preoperative urine culture(p = 0.001). ML represents a powerful tool for automatic prediction of outcomes. Our study showed promises in algorithms training and validation on a very large database of patients treated for urolithiasis, with excellent accuracy for prediction of complications. With further research, reliable predictive nomograms could be created based on ML analysis, to serve as aid to urologists and patients in the decision making and treatment planning process.

Authors

  • Carlotta Nedbal
    ASST Fatebenefratelli Sacco, Urology, Milan, Italy. carlottanedbal@gmail.com.
  • Vineet Gauhar
    Endourology Section, European Association of Urology, Arnhem, The Netherlands.
  • Sairam Adithya
    Symbiosis Institute of Technology, Engineering, Pune, India.
  • Pietro Tramanzoli
    Azienda Ospedaliero-Universitaria Ospedali Riuniti di Ancona, Polytechnic University Le Marche, Ancona, Italy.
  • Nithesh Naik
    Manipal Academy of Higher Education, Engineering, Manipal, India.
  • Shilpa Gite
    Symbiosis Institute of Technology, Engineering, Pune, India.
  • Het Sevalia
    Symbiosis Institute of Technology, Engineering, Pune, India.
  • Daniele Castellani
    Endourology Section, European Association of Urology, Arnhem, The Netherlands.
  • Frédéric Panthier
    Endolase lab, GRC20, Sorbonne Université and PIMM-Arts et Métiers Paris Tech, Paris, France.
  • Jeremy Y C Teoh
    The Chinese University of Hong Kong, Urology, Hong Kong, China.
  • Ben H Chew
    University of British Columbia, Urology, Vancouver, Canada.
  • Khi Yung Fong
    Yong Loo Lin School of Medicine, National University of Singapore, Urology, Singapore, Singapore.
  • Mohammed Boulmani
    Boston Scientific - Urology and Pelvic Health, Paris, France.
  • Nariman Gadzhiev
    Pavlov First Saint Petersburg State Medical University, Saint Petersburg, Russia.
  • Thomas R W Herrmann
    Kantonspital Frauenfeld, Spital Thurgau AG, Frauenfeld, Switzerland.
  • Olivier Traxer
    Endolase lab, GRC20, Sorbonne Université and PIMM-Arts et Métiers Paris Tech, Paris, France.
  • Bhaskar K Somani
    University Hospital Southampton NHS Trust, Southampton, Hampshire, UK.