University Hospital Southampton NHS Foundation Trust Reports Findings in Uretero scopy (A machine learning approach using stone volume to predict stone-free stat us at ureteroscopy)
University Hospital Southampton NHS Foundation Trust Reports Findings in Uretero scopy (A machine learning approach using stone volume to predict stone-free stat us at ureteroscopy)
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Surgical Procedures - Ureteroscopy is the subject of a report. According to news originating from Sout hampton, United Kingdom, by NewsRx correspondents, research stated, “To develop a predictive model incorporating stone volume along with other clinical and radi ological factors to predict stone-free (SF) status at ureteroscopy (URS). Retros pective analysis of patients undergoing URS for kidney stone disease at our inst itution from 2012 to 2021.” Our news journalists obtained a quote from the research from University Hospital Southampton NHS Foundation Trust, “SF status was defined as stone fragments <2 mm at the end of the procedure confirmed endoscopically and no evidence of st one fragments > 2 mm at XR KUB or US KUB at 3 months fol low up. We specifically included all non-SF patients to optimise our algorithm f or identifying instances with residual stone burden. SF patients were also rando mly sampled over the same time period to ensure a more balanced dataset for ML p rediction. Stone volumes were measured using preprocedural CT and combined with 19 other clinical and radiological factors. A bagged trees machine learning mode l with cross-validation was used for this analysis. 330 patients were included ( SF: n = 276, not SF: n = 54, mean age 59.5 ± 16.1 years). A fivefold cross valid ated RUSboosted trees model has an accuracy of 74.5% and AUC of 0. 82. The model sensitivity and specificity were 75% and 72.2% respectively. Variable importance analysis identified total stone volume (17.7% of total importance), operation time (14.3%), age (12.9% ) and stone composition (10.9%) as important factors in predicting non-SF patients. Single and cumulative stone size which are commonly used in cur rent practice to guide management, only represented 9.4% and 4.7% of total importance, respectively. Machine learning can be used to predict patie nts that will be SF at the time of URS. Total stone volume appears to be more im portant than stone size in predicting SF status.”
Key words
Southampton/United Kingdom/Europe/Cyb orgs/Emerging Technologies/Health and Medicine/Machine Learning/Surgery/Ure teroscopy/Urologic Surgical Procedures
NETL
NSTL