人工智能预测肾结石成分(KiSCAI)研究
该回顾性队列纳入442例接受腔内泌尿外科治疗或自行排石且结石主要成分>50%的患者,构建可解释机器学习模型预测五大类结石成分。仅用临床变量模型宏观AUC最高0.809;加入形态学特征后CatBoost验证集宏观AUC达0.983,但联合模型依赖术中术后描述,宜作术中/术后决策支持。
要点
- 临床变量模型可预测主要结石成分,宏观AUC最高0.809。
- 加入Daudon形态学特征后CatBoost验证集宏观AUC达0.983。
- 联合模型依赖术中术后描述,不宜作为术前工具。
核心结论
- 仅用临床变量可预测结石主要成分并可能支持术前决策;加入形态学特征后性能显著提升,但联合模型宜作术中或术后决策支持工具。
研究设计与样本
- 回顾性队列纳入2019至2024年接受腔内泌尿外科治疗或自行排石、实验室分析显示结石主要成分超过50%的连续患者442例。
- 结局为优势结石成分,分为草酸钙一水合物、草酸钙二水合物、磷酸钙、尿酸和胱氨酸五类;数据按80%和20%分层分为训练集与验证集。
主要发现
- 442例患者中位年龄51岁、男性67%;草酸钙一水合物占41.0%(n=181),草酸钙二水合物占24.9%(n=110),磷酸钙占19.7%(n=87),尿酸占10.9%(n=49),胱氨酸占3.6%(n=16)。
- LASSO稳定性分析显示可重复预测因子包括年龄、遗传性疾病类型、结石密度、最大直径和位置。
- 仅临床变量模型宏观AUC最高达0.809;加入形态学特征后集成模型验证集宏观AUC最高达0.983(CatBoost)。
- SHAP分析显示形态学变量位列最强贡献因素。
临床怎么用
- 临床变量模型可用于术前预测结石主要成分,辅助决策。
- 联合形态学特征的模型应在术中获得描述后用于术中或术后决策支持,而非术前。
- 临床实施前需外部前瞻性验证。
局限性
- 回顾性设计。
- 联合模型依赖术中及术后描述,无法用于术前。
- 需外部前瞻性验证后方可临床实施。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
OBJECTIVES: To develop and validate explainable machine learning (ML) models predicting urinary stone composition from routinely available clinical variables and standardised morphological features, and to quantify the incremental value of morphology. PATIENTS AND METHODS: This retrospective cohort study included consecutive patients undergoing endourological treatment or spontaneous stone expulsion, with laboratory analysis showing a major component exceeding 50% of stone composition, between 2019 and 2024. The outcome was dominant stone composition, classified into five categories: calcium oxalate monohydrate (COM), calcium oxalate dihydrate (COD), calcium phosphate, uric acid, and cystine. Predictors included demographics, comorbidities, stone metrics, procedural details, and Daudon-based morphological descriptors. Data were split into stratified training and validation cohorts (80% and 20%, respectively). Predictor stability was assessed using repeated-resampling multiclass Least Absolute Shrinkage and Selection Operator (LASSO). Multiple supervised classifiers (logistic regression, support vector machine, random forest, ExtraTrees, Adaptive Boosting [AdaBoost] variants, Extreme Gradient Boosting [XGBoost], Categorical Boosting [CatBoost]) were fine-tuned using GridSearch. Discrimination was assessed using macro-averaged one-vs-rest area under the curve (AUC) and accuracy. Explainability relied on SHapley Additive exPlanations (SHAP). RESULTS: Among 442 patients (median age 51 years; 67% male), stone composition was COM in 41.0% (n = 181), COD in 24.9% (n = 110), calcium phosphate in 19.7% (n = 87), uric acid in 10.9% (n = 49), and cystine in 3.6% (n = 16). LASSO stability highlighted reproducible predictors, including age, hereditary disease type, stone density, maximal diameter, and location. Clinical-only models achieved good discrimination (macro-AUC up to 0.809). Adding morphological features markedly improved performance, with ensemble models achieving excellent discrimination in validation (macro-AUC up to 0.983 with CatBoost). Morphological variables ranked among the strongest contributors on SHAP. CONCLUSIONS: A clinical-only model can predict the major stone component and may support preoperative decision-making. Performance further improved when morpho-constitutional features were added, confirming Daudon's classification as the ground truth; however, this combined model relies on intra- and postoperative descriptors and is best regarded as an intra- or postoperative decision-support tool rather than a preoperative one. External prospective validation is needed before clinical implementation.
引用
- Duffaut L, Scilipoti P, Khene ZE, et al. Kidney stones composition prediction using artificial intelligence (KiSCAI) study. BJU Int. 2026. PMID: 42670720. doi:10.1111/bju.70442
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。