EUVIMEDEUVIMED entdecken
Open Access

A Novel Machine-Learning Algorithm to Predict Stone Recurrence with 24-Hour Urine Data

Kevin Shee, Andrew W Liu, Carter Chan, Heiko Yang, Wilson Sui, Manoj Desai, Sunita Ho, Thomas Chi, Marshall L Stoller

Journal of Endourology · 2024

DOI: 10.1089/end.2023.0457 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Endourology, 2024. Verfasst von Kevin Shee und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Urology, UCSF, San Francisco, California, USA. Hauptthemen laut MEDLINE: Machine Learning, Kidney Calculi, Recurrence, Algorithms. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIDDK NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningKidney CalculiRecurrenceAlgorithmsHumansFemaleMaleMiddle AgedAdultUrinalysisROC CurveAged

Stichwörter der Autor:innen

24-hour urinekidney stonemachine learningnephrolithiasisoutcomes

Autor:innen und Institutionen

  • Department of Urology, UCSF, San Francisco, California, USA.

Förderung

  • NIDDK NIH HHS

Zitieren

APA

Shee, K., Liu, A. W., Chan, C., Yang, H., Sui, W., Desai, M., Ho, S., Chi, T., & Stoller, M. L. (2024). A Novel Machine-Learning Algorithm to Predict Stone Recurrence with 24-Hour Urine Data. Journal of Endourology. https://doi.org/10.1089/end.2023.0457

Vancouver

Shee K, Liu AW, Chan C, Yang H, Sui W, Desai M, et al. A Novel Machine-Learning Algorithm to Predict Stone Recurrence with 24-Hour Urine Data. Journal of Endourology. 2024. doi:10.1089/end.2023.0457

BibTeX
@article{Shee2024,
  author = {Shee, Kevin and Liu, Andrew W and Chan, Carter and Yang, Heiko and Sui, Wilson and Desai, Manoj and Ho, Sunita and Chi, Thomas and Stoller, Marshall L},
  title = {A Novel Machine-Learning Algorithm to Predict Stone Recurrence with 24-Hour Urine Data},
  journal = {Journal of Endourology},
  year = {2024},
  doi = {10.1089/end.2023.0457}
}
Kostenlos starten →