Scholarlink

<p>Urinary calculi recurrence substantially exacerbates healthcare resource consumption and socioeconomic burdens, yet the underlying mechanisms remain unclear. This study aimed to identify critical risk factors for calculi recurrence, develop a machine learning (ML) algorithm-based predictive model, and evaluate its predictive performance. This retrospective cohort study analyzed 1,146 urinary calculi patients treated at the Department of Urology, the Second Affiliated Hospital of Zhengzhou University (2019–2024). Key risk factors were identified using least absolute shrinkage and selection operator (LASSO) regression combined with multivariate logistic regression, and a binary predictive model for recurrence risk was developed. Model performance was validated via the area under the curve (AUC), with SHAP (Shapley Additive Explanations) values applied to interpret predictions. This study ultimately included 708 patients. The Random Forest model was selected as the optimal algorithm, demonstrating the following performance in the validation set: AUC 0.741 (95% CI: 0.664–0.818), sensitivity 0.552 (0.426–0.674), specificity 0.828 (0.756–0.885), positive predictive value 0.597 (0.464–0.719), negative predictive value 0.800 (0.727–0.861), F1-score 0.574, and Brier score 0.186, indicating satisfactory model calibration. SHAP feature attribution analysis identified the top four factors associated with recurrence: 24-hour urinary calcium excretion, hypertension status, serum creatinine level, and 24-hour urinary oxalate excretion. This study innovatively integrated metabolic data with imaging characteristics to establish a machine learning-based predictive model for quantitative recurrence risk assessment in urinary calculi. The integration of key metabolic parameters with imaging features has enhanced the predictive performance of the model, providing an evidence-based decision-making tool for personalized metabolic intervention and recurrent stone prevention strategies.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Development and validation of a machine learning-based prediction model for urinary calculi recurrence

  • 期刊论文

  • 发表日期：

    2025年6月19日

查看全文
  • Jiangkun Guo,
  • Jinhang Zhang,
  • Jinxiao Zhang,
  • Changbao Xu,
  • Xikun Wang,
  • Changwei Liu

摘要

Urinary calculi recurrence substantially exacerbates healthcare resource consumption and socioeconomic burdens, yet the underlying mechanisms remain unclear. This study aimed to identify critical risk factors for calculi recurrence, develop a machine learning (ML) algorithm-based predictive model, and evaluate its predictive performance. This retrospective cohort study analyzed 1,146 urinary calculi patients treated at the Department of Urology, the Second Affiliated Hospital of Zhengzhou University (2019–2024). Key risk factors were identified using least absolute shrinkage and selection operator (LASSO) regression combined with multivariate logistic regression, and a binary predictive model for recurrence risk was developed. Model performance was validated via the area under the curve (AUC), with SHAP (Shapley Additive Explanations) values applied to interpret predictions. This study ultimately included 708 patients. The Random Forest model was selected as the optimal algorithm, demonstrating the following performance in the validation set: AUC 0.741 (95% CI: 0.664–0.818), sensitivity 0.552 (0.426–0.674), specificity 0.828 (0.756–0.885), positive predictive value 0.597 (0.464–0.719), negative predictive value 0.800 (0.727–0.861), F1-score 0.574, and Brier score 0.186, indicating satisfactory model calibration. SHAP feature attribution analysis identified the top four factors associated with recurrence: 24-hour urinary calcium excretion, hypertension status, serum creatinine level, and 24-hour urinary oxalate excretion. This study innovatively integrated metabolic data with imaging characteristics to establish a machine learning-based predictive model for quantitative recurrence risk assessment in urinary calculi. The integration of key metabolic parameters with imaging features has enhanced the predictive performance of the model, providing an evidence-based decision-making tool for personalized metabolic intervention and recurrent stone prevention strategies.