Machine Learning Models for Prediction of Response to Therapeutic Plasma Exchange in Pediatric Acute Liver Failure.

Of the 511 pediatric acute liver failure patients admitted during the study period, 139 underwent therapeutic plasma exchange.

The machine learning classifiers had maximum accuracy at T2 (12-18 h post-first therapeutic plasma exchange) and T4 (12-18 h post the second therapeutic plasma exchange).

The AUCs of these three machine learning models were slightly lower at T4 (0.722-0.783).

These sets of models, trained separately for real-time prediction of therapeutic plasma exchange response at baseline, T2, and T4, were incorporated into a web-based tool to guide decision-making in pediatric acute liver failure.