# Guideline-based strategies to identify severe cytokine release syndrome in COVID-19 and cancer immunotherapy using large-scale electronic health records

## TL;DR

This study explores how to identify severe cytokine release syndrome in EHR data using guidelines, enabling better risk prediction for patients with cancer and COVID-19.

## Contribution

A novel EHR-based strategy for identifying CRS using grading guidelines rather than diagnosis codes.

## Key findings

- CRS diagnosis codes were underutilized and insufficient for severity assessment.
- Using grading guidelines identified 3.7% of 2.5 million COVID-19 patients and 31.5% of blinatumomab-treated patients with grade 2 or higher CRS.
- Severe CRS in COVID-19 patients showed varied inflammatory levels.

## Abstract

Cytokine Release Syndrome (CRS) is a life-threatening adverse event of cancer immunotherapies and a complication of infections. Predicting which patients are at risk for severe CRS would inform mitigation decisions and drug development, but requires large, reliably labeled datasets.

This study evaluates the feasibility of disease-agnostic case identification of CRS patterns in large-scale Electronic Health Records (EHR) to generate high-quality cohorts of CRS-positive and CRS-negative patients.

Using the Optum® de-identified COVID-19 EHR dataset, we isolated 2.5 million patients with active COVID-19 and 171 individuals treated with the T-cell Engager (TCE) blinatumomab. Diagnosis codes for CRS were underutilized and provided limited information on severity. Instead, we implemented the consensus CRS grading guidelines, which identified 92,541 COVID-19 patients (3.7%) and 54 blinatumomab patients (31.5%) with grade 2 or higher CRS, respectively. Severe CRS COVID-19 patients showed heterogeneous inflammatory levels.

Our EHR-based CRS case identification strategy is suitable for risk factor analysis and developing CRS risk prediction models.