# Development of a Predictive Model for Cardiac Dysfunction in MIS-C Patients Utilizing Laboratory Biomarkers

## TL;DR

This study developed a model using early lab data to predict heart dysfunction in children with MIS-C, helping identify high-risk patients quickly.

## Contribution

A novel predictive model using admission biomarkers to identify cardiac dysfunction in MIS-C patients.

## Key findings

- The model achieved a cross-validated AUC of 0.845 for predicting left ventricular systolic dysfunction.
- C-reactive protein, fibrinogen, and procalcitonin were the most predictive biomarkers early in the disease.
- The model for coronary artery abnormalities performed poorly with an AUC of 0.57.

## Abstract

Background and Objectives: Early identification of cardiac dysfunction in multi-system inflammatory syndrome in children (MIS-C) is crucial for effective management. Our primary objective was to predict left ventricular systolic dysfunction (LVSD) through a multicenter collaborative assessing admission laboratory data and echocardiogram findings. Methods: Laboratory and clinical data were collected by retrospective chart review from a cohort of pediatric patients admitted and treated for MIS-C in our institutions. Laboratory data including absolute lymphocyte count, albumin, sedimentation rate, C-reactive protein, procalcitonin, d-dimer, fibrinogen, ferritin, interleukin-6 level, and lymphocyte subsets (T, B and NK quantitation, TBNK) were collected. We built a LASSO logistic regression model to predict which MIS-C patients would have left ventricular systolic dysfunction LVSD using only laboratory data obtained within the first 24 h of admission. Results: Of the 1474 MIS-C patients evaluated, 297 had LVSD. The linear kinetic analysis found differences in albumin, lymphocyte count, C-reactive proteins and fibrinogen for systolic dysfunction patients, and of these C-reactive proteins, fibrinogen and procalcitonin were more predictive earlier. The best model for coronary artery abnormalities (CAAs) performed poorly, with a mean cross-validated AUC of 0.57. The model performed well with a cross-validated AUC of 0.845. Conclusions: This model identified widely available biomarkers to successfully predict systolic dysfunction in MIS-C patients. Those at high risk of systolic dysfunction had higher peak laboratory values for C-reactive protein, fibrinogen, and procalcitonin early on. A regularized logistic regression model was validated to provide excellent discrimination for LVSD.