# AI-Powered Early Detection of Sepsis in Emergency Medicine

## TL;DR

This paper explores using machine learning to detect sepsis early in emergency settings, comparing models that are easy to interpret with those that are more accurate but harder to understand.

## Contribution

The study evaluates white-box and black-box machine learning models for early sepsis detection across various emergency care stages.

## Key findings

- White-box models like logistic regression and decision trees offer interpretability but may lack accuracy.
- Black-box models such as deep neural networks achieve higher accuracy but struggle with clinical transparency.
- The study identifies effective computational strategies for early sepsis recognition in diverse healthcare settings.

## Abstract

Sepsis remains a critical medical emergency caused by a dysregulated immune response to infection, with timely detection and intervention being essential for improving survival rates. Traditional methods often rely on clinician intuition and structured scoring systems, which may be time-intensive and prone to variability. To address these limitations, Machine Learning (ML) offers a powerful alternative, bringing precision and efficiency to sepsis detection. This study investigates both white-box and complex black-box ML models applied to patient data collected across the continuum of care, including monitoring at the urgent care, en route in ambulances, and diagnostics conducted within hospital emergency department settings themselves. White-box models, such as logistic regression and decision trees, are valued for their interpretability, allowing healthcare providers to understand and trust the reasoning behind predictions. Meanwhile, black-box models like deep neural networks and support vector machines deliver superior accuracy but pose challenges in clinical transparency. This trade-off between explainability and performance is explored in detail, supported by experimental results aimed at identifying the most effective computational strategies for early sepsis recognition across diverse healthcare environments.