# Associations of serum sTREM-1 and sTREM-2 with mortality and neurological prognosis in patients resuscitated from cardiac arrest: a machine learning-based approach

## TL;DR

This study explores how blood levels of sTREM-1 and sTREM-2, along with machine learning models, can predict survival and neurological recovery in patients revived after cardiac arrest.

## Contribution

The study introduces novel machine learning models using sTREM biomarkers to improve prediction of mortality and neurological outcomes after cardiac arrest.

## Key findings

- sTREM-1 and sTREM-2 levels were higher in non-survivors compared to survivors after cardiac arrest.
- XGBoost and Random Forest models outperformed traditional clinical systems in predicting mortality and neurological outcomes.
- sTREM-1 showed better predictive power than sTREM-2 for patient outcomes.

## Abstract

Patients resuscitated from cardiac arrest (CA) commonly have poor outcomes with a high mortality rate. We aimed to determine the predictive values of serum soluble triggering receptor expressed on myeloid cells 1 and 2 (sTREM-1 and sTREM-2) in patients after return of spontaneous circulation (ROSC) and to develop machine learning (ML) prediction models.

We prospectively enrolled adult CA patients successfully resuscitated after cardiopulmonary resuscitation between November, 2021 to December, 2023. Serum sTREM-1, sTREM-2 and other biomarkers were measured on days 1, 3 and 5 after ROSC. The primary outcome was 28-day all-cause mortality. The secondary outcome was 3-month neurological prognosis. The performance of serum sTREM-1, sTREM-2, as well as the developed ML prediction models, to predict 28-day all-cause mortality and 3-month neurological prognosis were studied.

The study enrolled 120 patients, including 32 survivors and 88 non-survivors, with 30 healthy volunteers. Both sTREM-1 and sTREM-2 levels increased in patients after ROSC, with a larger increase in the non-survivors than survivors. Moreover, eleven features, including sTREM-1 and sTREM-2, were ultimately identified to build ML models. Among other ML models, the eXtreme Gradient Boosting (XGBoost) and Random Forest (RF) models showed strong performances for predicting 28-day all-cause mortality and 3-month neurological prognosis, respectively.

Serum sTREM-1 performed better than sTREM-2 to predict mortality and neurological outcome after ROSC. Furthermore, the newly developed XGBoost and RF models incorporating sTREM-1 and/or sTREM-2 demonstrated superior predictive accuracy compared to conventional clinical scoring systems.