MIMIC-Sepsis: A Curated Benchmark for Modeling and Learning from Sepsis Trajectories in the ICU

TL;DR

MIMIC-Sepsis provides a comprehensive, reproducible benchmark derived from MIMIC-IV for modeling sepsis trajectories in ICU patients, supporting improved predictive modeling and clinical decision-making.

Contribution

It introduces a curated, standardized dataset and benchmark framework for sepsis modeling, including preprocessing pipelines and multiple predictive tasks, enhancing reproducibility and comparability.

Findings

Including treatment data improves model accuracy.

Transformer models outperform traditional approaches.

Benchmark facilitates evaluation of sepsis prediction methods.

Abstract

Sepsis is a leading cause of mortality in intensive care units (ICUs), yet existing research often relies on outdated datasets, non-reproducible preprocessing pipelines, and limited coverage of clinical interventions. We introduce MIMIC-Sepsis, a curated cohort and benchmark framework derived from the MIMIC-IV database, designed to support reproducible modeling of sepsis trajectories. Our cohort includes 35,239 ICU patients with time-aligned clinical variables and standardized treatment data, including vasopressors, fluids, mechanical ventilation and antibiotics. We describe a transparent preprocessing pipeline-based on Sepsis-3 criteria, structured imputation strategies, and treatment inclusion-and release it alongside benchmark tasks focused on early mortality prediction, length-of-stay estimation, and shock onset classification. Empirical results demonstrate that incorporating treatment variables substantially improves model performance, particularly for Transformer-based architectures. MIMIC-Sepsis serves as a robust platform for evaluating predictive and sequential models in critical care research.