Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 17, 2025

A Data-Driven Approach to Quantifying Immune States in Sepsis

A Data-Driven Approach to Quantifying Immune States in Sepsis

Published on: February 7, 2025

Continuous sepsis trajectory prediction using tensor-reduced physiological signals.

Olivia P Alge¹, Joshua Pickard², Winston Zhang²

¹Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, USA. oialge@umich.edu.

Scientific Reports

|August 5, 2024

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Integrated proteogenomic and metabolomic profiling of acute myeloid leukemias to identify molecular subtypes and associated therapy targets.

Nature cancer·2026

Same author

Translational bottlenecks in blood-based proteomics.

EMBO molecular medicine·2026

Same author

The rheological properties of <i>Candida albicans</i> colony biofilms are impacted by matrix production and cell wall structure.

Biofilm·2026

Same author

VO: The Vaccine Ontology.

Scientific data·2026

Same author

A 15-layer multi-omics analysis of gastric cancer ecotypes provides therapeutic insights.

Cell reports. Medicine·2026

Same author

Genetic Insights into the Rheological Phenotype of Candida albicans Biofilms.

Research square·2026

Same journal

Turbulent flow in a vortex separator with a directed pipe inlet.

Scientific reports·2026

Same journal

Systematic characteristic evaluation of clay-based cementitious material derived from calcium carbide residue and waste tile powder.

Scientific reports·2026

Same journal

Retraction Note: Improvement of a rapid diagnostic application of monoclonal antibodies against avian influenza H7 subtype virus using Europium nanoparticles.

Scientific reports·2026

Same journal

Applying large language models to spam detection in the Kazakh low-resource language setting.

Scientific reports·2026

Same journal

An open-source 3D printing system enabling in-situ freeze-thaw processing of hydrogels.

Scientific reports·2026

Same journal

An enhanced EfficientNet framework for automated waste classification using cosine annealing and label smoothing.

Scientific reports·2026

See all related articles

This summary is machine-generated.

Predicting sepsis progression using machine learning models shows promise. Tensor decomposition of physiological signals enhances prediction accuracy, offering real-time insights independent of electronic health record data availability.

Area of Science:

Critical Care Medicine
Biomedical Engineering
Data Science

Background:

The quick Sequential Organ Failure Assessment (qSOFA) system is crucial for identifying patients at risk of poor sepsis-related outcomes.
Accurate and timely prediction of qSOFA score increases is vital for effective clinical intervention.
Traditional methods often rely on electronic health record (EHR) data, which may not be continuously available.

Purpose of the Study:

To develop and evaluate machine learning models for predicting increases in qSOFA scores.
To investigate the utility of tensor decomposition for feature reduction in physiological signals (ECG, arterial line).
To compare the performance of models using EHR data versus physiological signals.

Main Methods:

Utilized Support Vector Machine, Learning Using Concave and Convex Kernels, and Random Forest algorithms.

More Related Videos

A Reproducible Intensive Care Unit-Oriented Endotoxin Model in Rats

A Reproducible Intensive Care Unit-Oriented Endotoxin Model in Rats

Published on: February 20, 2021

Use of a Wireless Video-EEG System to Monitor Epileptiform Discharges Following Lateral Fluid-Percussion Induced Traumatic Brain Injury

Use of a Wireless Video-EEG System to Monitor Epileptiform Discharges Following Lateral Fluid-Percussion Induced Traumatic Brain Injury

Published on: June 21, 2019

Related Experiment Videos

Last Updated: Jun 17, 2025

A Data-Driven Approach to Quantifying Immune States in Sepsis

A Data-Driven Approach to Quantifying Immune States in Sepsis

Published on: February 7, 2025

A Reproducible Intensive Care Unit-Oriented Endotoxin Model in Rats

A Reproducible Intensive Care Unit-Oriented Endotoxin Model in Rats

Published on: February 20, 2021

Use of a Wireless Video-EEG System to Monitor Epileptiform Discharges Following Lateral Fluid-Percussion Induced Traumatic Brain Injury

Use of a Wireless Video-EEG System to Monitor Epileptiform Discharges Following Lateral Fluid-Percussion Induced Traumatic Brain Injury

Published on: June 21, 2019

Structured physiological signals data (ECG, arterial line) in a tensor format.

Applied Canonical Polyadic/Parallel Factors (CP) decomposition for feature reduction.

Integrated EHR data with signal-derived features.

Main Results:

Random Forests trained on tensor-decomposed ECG data improved prediction performance (AUROC 0.67 ± 0.06).
Incorporating arterial line data further enhanced performance, especially with tensor decomposition (AUROC 0.71 ± 0.07).
Combining EHR data with tensor-reduced signal models yielded the highest performance (AUROC 0.77 ± 0.06).

Conclusions:

Tensor decomposition of physiological signals improves predictive model performance for qSOFA score increases.
Signal-based models offer real-time, continuous prediction capabilities independent of EHR data availability.
Machine learning models integrating diverse data sources show significant potential for early sepsis risk identification.