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

Steps in Outbreak Investigation01:18

Steps in Outbreak Investigation

101
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
101
Kaplan-Meier Approach01:24

Kaplan-Meier Approach

67
The Kaplan-Meier estimator is a non-parametric method used to estimate the survival function from time-to-event data. In medical research, it is frequently employed to measure the proportion of patients surviving for a certain period after treatment. This estimator is fundamental in analyzing time-to-event data, making it indispensable in clinical trials, epidemiological studies, and reliability engineering. By estimating survival probabilities, researchers can evaluate treatment effectiveness,...
67
Actuarial Approach01:20

Actuarial Approach

50
The actuarial approach, a statistical method originally developed for life insurance risk assessment, is widely used to calculate survival rates in clinical and population studies. This method accounts for participants lost to follow-up or those who die from causes unrelated to the study, ensuring a more accurate representation of survival probabilities.
Consider the example of a high-risk surgical procedure with significant early-stage mortality. A two-year clinical study is conducted,...
50

You might also read

Related Articles

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

Sort by
Same author

Artificial Extracellular Matrices Containing Bioactive Glass Nanoparticles Promote Osteogenic Differentiation in Human Mesenchymal Stem Cells.

International journal of molecular sciences·2021
Same author

FDG PET/CT of Primary Ewing Sarcoma of the Peritoneum.

Clinical nuclear medicine·2021
Same author

A new zinc-ion battery cathode with high-performance: Loofah-like lanthanum manganese perovskite.

Journal of colloid and interface science·2021
Same author

Chromosome-level genome assembly of the Chinese three-keeled pond turtle (Mauremys reevesii) provides insights into freshwater adaptation.

Molecular ecology resources·2021
Same author

Oxidative stress transforms 3CLpro into an insoluble and more active form to promote SARS-CoV-2 replication.

Redox biology·2021
Same author

Porous bioactive glass micro- and nanospheres with controlled morphology: developments, properties and emerging biomedical applications.

Materials horizons·2021

Related Experiment Video

Updated: May 20, 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

127

Physician documentation matters. Using natural language processing to predict mortality in sepsis.

Keaton Cooley-Rieders1, Kai Zheng2

  • 1School of Medicine, University of California Irvine, 1001 Health Sciences Road, Irvine, CA, 92617, USA.

Intelligence-Based Medicine
|March 24, 2025
PubMed
Summary
This summary is machine-generated.

Natural language processing (NLP) improves sepsis mortality prediction. An NLP model analyzing physician notes outperformed SOFA and qSOFA scores in predicting in-hospital mortality for sepsis patients.

Keywords:
Early RecognitionMortalityNLPNatural language processingScreeningSepsis

More Related Videos

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

15.7K
Use of Animal Model of Sepsis to Evaluate Novel Herbal Therapies
07:34

Use of Animal Model of Sepsis to Evaluate Novel Herbal Therapies

Published on: April 11, 2012

19.3K

Related Experiment Videos

Last Updated: May 20, 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

127
A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

15.7K
Use of Animal Model of Sepsis to Evaluate Novel Herbal Therapies
07:34

Use of Animal Model of Sepsis to Evaluate Novel Herbal Therapies

Published on: April 11, 2012

19.3K

Area of Science:

  • Medical Informatics
  • Clinical Decision Support
  • Artificial Intelligence in Healthcare

Background:

  • Sepsis mortality prediction remains a challenge.
  • Technological advancements, particularly natural language processing (NLP), offer novel approaches.
  • Existing prediction methods lack optimal accuracy.

Purpose of the Study:

  • To develop and validate an NLP-based model for predicting sepsis-related in-hospital mortality.
  • To compare the performance of the NLP model against established scoring systems (SOFA, qSOFA).

Main Methods:

  • Utilized the MIMIC III dataset for initial model development (2008-2013).
  • Analyzed physician progress notes from the first 24 hours of sepsis patient admission using NLP.
  • Retrospectively validated the model on sepsis admissions at UCIMC (2013-2018).

Main Results:

  • An 80-concept NLP model achieved an AUC of 0.687 for severe sepsis, outperforming SOFA (0.571).
  • For simple sepsis, the NLP model demonstrated an AUC of 0.696, exceeding qSOFA (0.590).
  • The model was validated on 7117 UCIMC admissions.

Conclusions:

  • NLP-extracted clinical judgment from physician notes shows superior performance in predicting sepsis mortality.
  • The NLP model offers a more accurate prediction tool compared to SOFA and qSOFA.
  • This approach enhances clinical decision-making for sepsis management.