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

Kaplan-Meier Approach01:24

Kaplan-Meier Approach

484
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,...
484

You might also read

Related Articles

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

Sort by
Same author

Trends in Women Authoring Editorials in Cardiothoracic Surgery Journals.

Brazilian journal of cardiovascular surgery·2026
Same author

Marine Microplastic Levels and the Prevalence of Cardiometabolic Diseases in US Coastline Counties.

Journal of the American Heart Association·2025
Same author

Impact of Marine Microplastics on Neurologic and Functional Disabilities: A Population-Level Study.

European journal of neurology·2025
Same author

Robotic Belsey fundoplication: How I do it.

JTCVS techniques·2025
Same author

Exercise capacity and cardiac allograft ischemic time in recent heart transplant recipients.

JHLT open·2025
Same author

Robotic lobectomy with en bloc chest wall resection and reconstruction: How I do it.

JTCVS techniques·2025

Related Experiment Video

Updated: Dec 21, 2025

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
06:22

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Published on: September 19, 2025

355

Exploration of critical care data by using unsupervised machine learning.

Sookyung Hyun1, Pacharmon Kaewprag2, Cheryl Cooper3

  • 1College of Nursing, Pusan National University, 49 Busandaehak-ro Mulgeum-eup, Yangsan-si, 50612, South Korea.

Computer Methods and Programs in Biomedicine
|May 14, 2020
PubMed
Summary

Unsupervised machine learning identified three distinct patient subgroups in the intensive care unit (ICU). These patient clusters exhibited significant differences in lab results, treatments, and mortality rates, aiding in personalized care strategies.

Keywords:
Critical careElectronic health recordK-means clusteringUnsupervised machine learning

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.6K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.3K

Related Experiment Videos

Last Updated: Dec 21, 2025

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
06:22

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Published on: September 19, 2025

355
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.6K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.3K

Area of Science:

  • Intensive care medicine
  • Data science
  • Machine learning

Background:

  • Understanding clinical heterogeneity in intensive care unit (ICU) patients is crucial.
  • Subgroup identification can inform tailored treatment strategies and outcome prediction.

Purpose of the Study:

  • To apply unsupervised machine learning to ICU patient data for subgroup discovery.
  • To characterize identified subgroups based on clinical features, treatments, and outcomes.

Main Methods:

  • K-means clustering algorithm utilized.
  • Analysis based on 1503 observations and 9 laboratory test results.

Main Results:

  • Three distinct patient clusters were identified.
  • Significant differences observed in blood urea nitrogen, creatinine, potassium, hemoglobin, and red blood cell counts.
  • Cluster Three showed higher blood product transfusion rates (19.8%) and mortality (30.4%), with more frequent hemodialysis.
  • Clusters One and Two had lower transfusion rates and mortality, with bronchoscopy more common.

Conclusions:

  • The study successfully identified three distinct ICU patient subgroups using unsupervised machine learning.
  • Clinical characteristics, treatments, and outcomes varied significantly across subgroups.
  • These findings support the use of machine learning for organizing complex ICU data to guide personalized treatment and anticipate patient outcomes.