medical

ICU Mortality

3260 papers • 126 benchmarks • 313 datasets

Prediction of a patient mortality in the Intensive Care Unit (ICU) given its first hours of Electronic Health Record (EHR).

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in icu-mortality

Trend

Dataset

Best Model

Actions

HiRID

Libraries

i

Use these libraries to find icu-mortality models and implementations

Datasets

eICU-CRD

HiRID

Subtasks

No subtasks available.

Most implemented papers

ISeeU2: Visually Interpretable ICU mortality prediction using deep learning and free-text medical notes

William Caicedo-Torres, Jairo Gutiérrez•Mon May 18 2020

A Deep Learning model trained on MIMIC-III is shown to predict mortality using raw nursing notes, together with visual explanations for word importance, outperforming the traditional SAPS-II score and providing enhanced interpretability when compared with similar Deep Learning approaches.

3

Content

0

Paper Graph

FLICU: A Federated Learning Workflow for Intensive Care Unit Mortality Prediction

Lena Mondrejevski, Ioanna Miliou, Annaclaudia Montanino, David Pitts, Jaakko Hollmén, P. Papapetrou•Sun May 29 2022

Federated Learning can be seen as a valid and privacy-preserving alternative to Centralized Machine Learning for classifying Intensive Care Unit mortality when the sharing of sensitive patient data between hospitals is not possible.

15 0

Paper Graph

Early prediction of the risk of ICU mortality with Deep Federated Learning

Korbinian Randl, Lena Mondrejevski, Ioanna Miliou, N'uria Llad'os Armengol•Wed Nov 30 2022

This study compares the predictive performance of Federated, Centralized, and Local Machine Learning in terms of AUPRC, F1-score, and AUROC and shows that Federated Learning performs equally well as the centralized approach and is substantially better than the local approach, thus providing a viable solution for early Intensive Care Unit mortality prediction.

9 0

Paper Graph

HiRID-ICU-Benchmark - A Comprehensive Machine Learning Benchmark on High-resolution ICU Data

M. Faltys, Matthias Hüser, Xinrui Lyu, M. Zimmermann, G. Rätsch, Hugo Yèche, Rita Kuznetsova•Mon Nov 15 2021

This work provides a benchmark covering a large spectrum of ICU-related tasks using the HiRID dataset, and provides an in-depth analysis of current state-of-the-art sequence modeling methods, highlighting some limitations of deep learning approaches for this type of data.

58 0

Paper Graph

Dynamic Measurement Scheduling for Event Forecasting using Deep RL

A. Goldenberg, C. Chang, Mingjie Mai•Wed Jan 23 2019

Deep reinforcement learning is used to answer the question of what and when to be measured to forecast detrimental events, by scheduling strategically-timed measurements that jointly minimizes the measurement cost and maximizes predictive gain.

19 0

Paper Graph

Adding a benchmark result helps the community track progress.