Journal of Endourology · 2024 · 12 citations · 17 references
MedicineNephrologyUrologyMachine LearningUrolithiasisUrologic SurgeryPredictive Health ModelingRecurrent Stone DiseaseRenal Function TestsUrolithiasis Surgery24-Hour Urine CollectionKidney Stone PassageKidney Stone RecurrenceMachine Learning ClassificationMedical Chart ReviewPrediction Model DevelopmentPrognostic Prediction ModelsUrine Biomarkers
Objectives: The absence of predictive markers for kidney stone recurrence poses a challenge for the clinical management of stone disease. The unpredictability of stone events is also a significant limitation for clinical trials, where many patients must be enrolled to obtain sufficient stone events for analysis. In this study, we sought to use machine learning methods to identify a novel algorithm to predict stone recurrence. Subjects/Patients and Methods: Patients enrolled in the Registry for Stones of the Kidney and Ureter (ReSKU), a registry of nephrolithiasis patients collected between 2015–2020, with at least one prospectively collected 24-hour urine test (Litholink 24-hour urine test; Labcorp) were included in the training set. A validation set was obtained from chart review of stone patients not enrolled in ReSKU with 24-hour urine data. Stone events were defined as either an office visit where a patient reports symptomatic passage of stones or a surgical procedure for stone removal. Seven prediction classification methods were evaluated. Predictive analyses and receiver operator characteristics (ROC) curve generation were performed in R. Results: A training set of 423 kidney stone patients with stone event data and 24-hour urine samples were trained using the prediction classification methods. The highest performing prediction model was a Logistic Regression with ElasticNet machine learning model (area under curve [AUC] = 0.65). Restricting analysis to high confidence predictions significantly improved model accuracy (AUC = 0.82). The prediction model was validated on a validation set of 172 stone patients with stone event data and 24-hour urine samples. Prediction accuracy in the validation set demonstrated moderate discriminative ability (AUC = 0.64). Repeat modeling was performed with four of the highest scoring features, and ROC analyses demonstrated minimal loss in accuracy (AUC = 0.63). Conclusion: Machine-learning models based on 24-hour urine data can predict stone recurrences with a moderate degree of accuracy.
17
Prevalence of Kidney Stones in the United States
Charles D. Scales, Alexandria Smith, Janet Hanley et al. · European Urology · 2012 · 2.6K citations · Full text
Medicine, Nephrology, Urology +9
Medical Management of Kidney Stones: AUA Guideline
Margaret S. Pearle, David S. Goldfarb, Dean G. Assimos et al. · The Journal of Urology · 2014 · 1.1K citations
Medicine, Nephrology, Urology +17
Kidney stones and kidney function loss: a cohort study
R. Todd Alexander, Brenda R. Hemmelgarn, Natasha Wiebe et al. · BMJ · 2012 · 368 citations · Full text
Medicine, Nephrology, Urology +16
The ROKS Nomogram for Predicting a Second Symptomatic Stone Episode
Andrew D. Rule, John C. Lieske, Xujian Li et al. · Journal of the American Society of Nephrology · 2014 · 299 citations · Full text
Medicine, Nephrology, Urology +11
A PROSPECTIVE STUDY OF RECURRENCE RATE AND RISK FACTORS FOR RECURRENCE AFTER A FIRST RENAL STONE
Alberto Trinchieri, F Ostini, R. Nespoli et al. · The Journal of Urology · 1999 · 248 citations
Medicine, Nephrology, Urology +10