Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Nursing Interventions II: Selecting and Classifying the Nursing Interventions01:29

Nursing Interventions II: Selecting and Classifying the Nursing Interventions

2.1K
Creating and executing a nursing diagnosis helps nurses plan care and guide patient, family, and community interventions. They are developed based on a patient's physical evaluation and support measuring the outcomes. It is not recommended to select random interventions throughout the planning process. Instead, consider the following six essential factors when choosing interventions:
2.1K
Clinical Trials01:16

Clinical Trials

6.6K
Clinical trials are prospective experimental studies conducted on humans to determine the safety and efficacy of treatments, drugs, diet methods, and medical devices. Using statistics in clinical trials enables researchers to derive reasonable and accurate conclusions from the collected data, allowing them to make wise decisions in uncertain situations. In medical research, statistical methods are crucial for preventing errors and bias.
There are four phases in a clinical trial. A phase one...
6.6K

You might also read

Related Articles

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

Sort by
Same author

Large language models in emergency and critical care medicine: a comprehensive review of applications, challenges, and future directions.

Burns & trauma·2026
Same author

Systematic evaluation of the DeepSeek large language model for clinical diagnostic reasoning.

PloS one·2026
Same author

EEG-RCPNet: a cross-subject cognitive impairment detection model based on limited-channel eeg signals.

Medical & biological engineering & computing·2026
Same author

Research Progress on Sepsis Diagnosis and Monitoring Based on Omics Technologies: A Review.

Diagnostics (Basel, Switzerland)·2025
Same author

Deriving consensus sepsis clusters via goal-directed subgroup identification in multi-omics study.

Nature communications·2025
Same author

Variation in global trauma care: a survey of 187 hospitals across 51 countries.

BMJ global health·2025

Related Experiment Video

Updated: Jun 14, 2025

A Data-Driven Approach to Quantifying Immune States in Sepsis
07:42

A Data-Driven Approach to Quantifying Immune States in Sepsis

Published on: February 7, 2025

150

Enhancing Patient Selection in Sepsis Clinical Trials Design Through an AI Enrichment Strategy: Algorithm Development

Meicheng Yang1, Jinqiang Zhuang2,3, Wenhan Hu4

  • 1State Key Laboratory of Digital Medical Engineering, School of Instrument Science and Engineering, Southeast University, Nanjing, China.

Journal of Medical Internet Research
|September 4, 2024
PubMed
Summary

This study developed an AI model to identify persistently ill sepsis patients for clinical trials, improving patient selection and reducing trial heterogeneity. Conformal prediction enhanced model reliability by quantifying output uncertainty.

Keywords:
artificial intelligenceconformal predictiondisease progression trajectoriesenrichment strategypredictive modelingsepsis

More Related Videos

A Protocol for Using Gene Set Enrichment Analysis to Identify the Appropriate Animal Model for Translational Research
09:35

A Protocol for Using Gene Set Enrichment Analysis to Identify the Appropriate Animal Model for Translational Research

Published on: August 16, 2017

17.8K
Standardized Colon Ascendens Stent Peritonitis in Rats - a Simple, Feasible Animal Model to Induce Septic Acute Kidney Injury
07:03

Standardized Colon Ascendens Stent Peritonitis in Rats - a Simple, Feasible Animal Model to Induce Septic Acute Kidney Injury

Published on: February 15, 2022

1.4K

Related Experiment Videos

Last Updated: Jun 14, 2025

A Data-Driven Approach to Quantifying Immune States in Sepsis
07:42

A Data-Driven Approach to Quantifying Immune States in Sepsis

Published on: February 7, 2025

150
A Protocol for Using Gene Set Enrichment Analysis to Identify the Appropriate Animal Model for Translational Research
09:35

A Protocol for Using Gene Set Enrichment Analysis to Identify the Appropriate Animal Model for Translational Research

Published on: August 16, 2017

17.8K
Standardized Colon Ascendens Stent Peritonitis in Rats - a Simple, Feasible Animal Model to Induce Septic Acute Kidney Injury
07:03

Standardized Colon Ascendens Stent Peritonitis in Rats - a Simple, Feasible Animal Model to Induce Septic Acute Kidney Injury

Published on: February 15, 2022

1.4K

Area of Science:

  • Artificial Intelligence in Medicine
  • Clinical Trial Design
  • Sepsis Pathophysiology

Background:

  • Sepsis is a complex syndrome requiring homogeneous patient cohorts for effective clinical trials.
  • Artificial intelligence (AI) aids in identifying patient subgroups but lacks uncertainty estimation for clinical decision-making.

Purpose of the Study:

  • To design an AI model for purposeful patient enrollment in sepsis trials, identifying persistently ill individuals.
  • To ensure the AI model provides interpretable factors and estimates output uncertainty at a specified confidence level.

Main Methods:

  • Retrospective analysis of 9135 sepsis patients for model development and 3743 for external validation.
  • Stratification of patients into rapid death, recovery, or persistent illness trajectories using 148 variables.
  • Utilized machine learning algorithms, conformal prediction (CP) for uncertainty estimation, and Shapley Additive Explanations for interpretability.

Main Results:

  • A gradient boosting machine model demonstrated strong performance in predicting sepsis trajectories across validation cohorts.
  • Key predictors included maximum norepinephrine equivalence, urine output, and physiological scores.
  • Conformal prediction reduced prediction errors by up to 30.7% and improved identification of persistently ill patients.

Conclusions:

  • The AI model can decrease heterogeneity in sepsis clinical trials by enabling more precise patient enrollment.
  • Conformal prediction enhances the reliability of AI-driven predictions, supporting informed clinical decisions.