Machine learning prediction of childhood nephrotic syndrome outcomes.
Machine learning models weakly predict frequent relapses or steroid dependence in childhood nephrotic syndrome
Machine learning prediction of childhood nephrotic syndrome outcomes.
Children with steroid-resistant, frequently relapsing, and steroid-dependent nephrotic syndrome experience high disease and treatment-related morbidity.
We analyzed data from Insight into Nephrotic Syndrome: Investigating Genes, Health, and Therapeutics, a prospective observational childhood nephrotic syndrome cohort.
AUROC, barely better than chance at predicting frequent relapse or steroid dependence
We included 515 children diagnosed with nephrotic syndrome.
Of these, 484 (94%) were steroid-sensitive and 31 (6%) were steroid-resistant.
Nine machine learning models were developed and optimized by hyperparameter tuning for each outcome.
Machine learning models also had weak predictive ability for relapse occurrence (AUC 0.62; logistic regression with recursive feature elimination), steroid-sparing medication initiation (AUC 0.61; XGBoost), and steroid resistance (AUC 0.64; XGBoost).
Routinely collected sociodemographic, clinical, and laboratory features at nephrotic syndrome diagnosis are weakly predictive of subsequent relapses and treatment response, using machine learning methods.
Discovery of novel biomarkers may improve future prediction and proactive treatment.