背景:ML预测模型已显示出其改善风险预测和辅助医疗决策的能力,然而,在哥伦比亚甚至南美,缺乏早期识别未来CKD快速进展者的准确性系统。
目的:本研究的目的是开发一系列可解释的机器学习模型,以预测6个月时的GFR。9个月,和12个月。
方法:超过29,000名CKD患者1至3b期(估计GFR,<60ml/min/1.73m2),平均3年随访数据。我们使用机器学习极限梯度提升(XGBoost)构建了三个模型来预测下一个eGFR。模型进行了内部和外部验证。此外,我们纳入了Shapley加法扩张(SHAP)值,以提供可解释的全球和局部预测模型。
结果:所有模型在开发和外部验证中都表现出良好的性能。然而,6个月XGBoost预测模型在内部表现最好(MAE平均值=6.07;RSME=78.87),和外部验证(MAE平均值=6.45,RSME=18.94)。将预测的eGFR值推到较低值的前3个最有影响力的特征是eGFR和肌酐的内插值,和基线时的eGFR。
结论:在当前研究中,我们开发并验证了机器学习模型,以预测不同间隔的下一个eGFR值。此外,我们试图通过提供透明的预测来解决预测解释的必要性。
BACKGROUND: ML predictive models have shown their capability to improve risk prediction and assist medical decision-making, nevertheless, there is a lack of accuracy systems to early identify future rapid CKD progressors in Colombia and even in South America.
OBJECTIVE: The purpose of this study was to develop a series of interpretable machine learning models that predict GFR at 6-months, 9-months, and 12-months.
METHODS: Over 29,000 CKD patients stages 1 to 3b (estimated GFR, <60 ml/min / 1.73 m2) with an average of 3-year follow-up data were included. We used the machine learning extreme gradient boosting (XGBoost) to build three models to predict the next eGFR. Models were internally and externally validated. In addition, we included SHapley Additive exPlanation (SHAP) values to offer interpretable global and local prediction models.
RESULTS: All models showed a good performance in development and external validation. However, the 6-months XGBoost prediction model showed the best performance in internal (MAE average= 6.07; RSME= 78.87), and in external validation (MAE average= 6.45, RSME= 18.94). The top 3 most influential features that pushed the predicted eGFR value to lower values were the interpolated values for eGFR and creatinine, and eGFR at baseline.
CONCLUSIONS: In the current study we have developed and validated machine learning models to predict the next eGFR value at different intervals. Furthermore, we attempted to approach the need for prediction explanation by offering transparent predictions.