A non-invasive XGBoost model using estimated cardiac output and body measurements detected albuminuria risk with an AUC of 0.75 (95% CI 0.67-0.84), outperforming existing non-invasive risk scores.
Observational
Yes
Does a non-invasive XGBoost model using estimated cardiac output and body measurements improve the detection of microalbuminuria in people with diabetes compared to existing risk scores?
A non-invasive XGBoost model incorporating estimated cardiac output and simple clinical measures can effectively detect early diabetic kidney disease risk without laboratory tests.
Effect estimate: AUC 0.75 (95% CI 0.67-0.84)
Absolute Event Rate: 0.75% vs 0.58%
INTRODUCTION: Moderately increased (micro) albuminuria serves as a critical early indicator of Diabetic Kidney Disease (DKD). However, traditional screening methods that rely on laboratory-based analyses face significant challenges in enabling timely and continuous monitoring. This study addresses these limitations by introducing a non-invasive approach for albuminuria risk detection, allowing real-time estimation of mild albuminuria increases using vital signs and body measurements. METHODS: We developed a non-invasive model for albuminuria risk detection using vital signs and body measurements. Data were drawn from the NHANES cohort (USA) and a Bangladeshi cohort of people with diabetes (PwD). Feature selection identified four non-laboratory predictors - estimated cardiac output (eCO), body mass index, waist circumference, and diabetes duration - as the most informative inputs. The proposed models were benchmarked against baseline machine learning approaches and existing methods developed over the past decade, with model interpretability assessed via SHapely Additive exPlanation (SHAP) contributions. RESULTS: Our best model, an XGBoost classifier, achieved an AUC of 0.75 0.67-0.84, an accuracy of 0.70, and a macro F1 score of 0.68, outperforming other non-invasive risk scores (0.58) and machine learning baselines. Validation against an external reference risk score confirmed superior precision-recall balance for both positive (microalbuminuria) and negative classes. CONCLUSION: This study demonstrates that a fine-tuned, non-invasive XGBoost model using simple clinical measures can support albuminuria monitoring and early DKD detection without laboratory tests. While the selected predictors may not represent the definitive or optimal feature set, their strong performance highlights the potential of leveraging easily obtainable, clinically relevant measures. In particular, the contribution of eCO underscores a promising direction for exploring heart-kidney-metabolism interactions in DKD risk assessment. Together, these findings highlight a scalable, non-invasive tool for resource-limited settings, an interpretable framework for clinical trust, and a pathway to refining feature sets for both accuracy and biological insight.
To et al. (Sat,) conducted a observational in Diabetic Kidney Disease. Non-invasive XGBoost model vs. Other non-invasive risk scores and machine learning baselines was evaluated on Albuminuria risk detection (AUC 0.75, 95% CI 0.67-0.84). A non-invasive XGBoost model using estimated cardiac output and body measurements detected albuminuria risk with an AUC of 0.75 (95% CI 0.67-0.84), outperforming existing non-invasive risk scores.