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

Blood Studies for Cardiovascular System I: Cardiac Biomarkers01:20

Blood Studies for Cardiovascular System I: Cardiac Biomarkers

1.1K
Cardiac biomarkers are enzymes, proteins, and hormones released into the blood when cardiac cells are injured. They are powerful tools for triaging.
The essential diagnostic tools for detecting myocardial necrosis and monitoring individuals suspected of having acute coronary syndrome (ACS) include:
Troponins
Troponins, particularly cardiac troponins I and T, are the most precise and sensitive markers of myocardial injury. They are detectable within 4-6 hours of myocardial injury and remain...
1.1K
Acute Coronary Syndrome III: Diagnostic Studies01:30

Acute Coronary Syndrome III: Diagnostic Studies

421
Diagnosing acute coronary syndrome or ACS begins with a thorough patient history. Notable symptoms include central, crushing chest pain radiating to the left arm, neck, jaw, or back, along with shortness of breath, sweating (diaphoresis), nausea, vomiting, dizziness, and palpitations.It is crucial to note any history of cardiac illnesses and assess risk factors, including age, gender, smoking, hypertension, diabetes, hyperlipidemia, and a sedentary lifestyle.During physical examination, vital...
421

You might also read

Related Articles

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

Sort by
Same author

The Impact of CoronaVac Vaccination on 28-day Mortality Rate of Critically Ill Patients with COVID-19 in Türkiye.

Balkan medical journal·2023
Same author

Gene-expression programming for flip-bucket spillway scour.

Water science and technology : a journal of the International Association on Water Pollution Research·2012
See all related articles

Related Experiment Video

Updated: Mar 29, 2026

Technical Refinement of a Bilateral Renal Ischemia-Reperfusion Mouse Model for Acute Kidney Injury Research
03:13

Technical Refinement of a Bilateral Renal Ischemia-Reperfusion Mouse Model for Acute Kidney Injury Research

Published on: November 3, 2023

3.2K

Early Risk Stratification for 30-Day Mortality After In-Hospital Cardiac Arrest: SHAP Interpretable CatBoost Model

Gülseren Elay1, Aytaç Güven2

  • 1Department of Internal Medicine, Faculty of Medicine, Gaziantep University, Gaziantep 27310, Turkey.

Journal of Clinical Medicine
|March 28, 2026
PubMed
Summary

Predicting 30-day mortality after in-hospital cardiac arrest (IHCA) is difficult. A new CatBoost model, using m-NUTRIC score, age, and micronutrients, shows improved prediction accuracy over logistic regression.

Keywords:
30-day mortalityCatBoostSHAPin-hospital cardiac arrestm-NUTRICmachine learningrisk stratification

More Related Videos

Author Spotlight: A Unique Mouse Model of Asphyxia-Induced Cardiac Arrest
07:18

Author Spotlight: A Unique Mouse Model of Asphyxia-Induced Cardiac Arrest

Published on: April 14, 2023

2.4K
Cutoff Value of Phase Angle by Bioelectrical Impedance Analysis at Admission as a Prognostic Factor in Patients with Acute Heart Failure
05:16

Cutoff Value of Phase Angle by Bioelectrical Impedance Analysis at Admission as a Prognostic Factor in Patients with Acute Heart Failure

Published on: June 10, 2025

772

Related Experiment Videos

Last Updated: Mar 29, 2026

Technical Refinement of a Bilateral Renal Ischemia-Reperfusion Mouse Model for Acute Kidney Injury Research
03:13

Technical Refinement of a Bilateral Renal Ischemia-Reperfusion Mouse Model for Acute Kidney Injury Research

Published on: November 3, 2023

3.2K
Author Spotlight: A Unique Mouse Model of Asphyxia-Induced Cardiac Arrest
07:18

Author Spotlight: A Unique Mouse Model of Asphyxia-Induced Cardiac Arrest

Published on: April 14, 2023

2.4K
Cutoff Value of Phase Angle by Bioelectrical Impedance Analysis at Admission as a Prognostic Factor in Patients with Acute Heart Failure
05:16

Cutoff Value of Phase Angle by Bioelectrical Impedance Analysis at Admission as a Prognostic Factor in Patients with Acute Heart Failure

Published on: June 10, 2025

772

Area of Science:

  • Critical Care Medicine
  • Machine Learning in Healthcare
  • Biomarker Research

Background:

  • Predicting 30-day mortality following in-hospital cardiac arrest (IHCA) presents a significant clinical challenge.
  • Existing models often lack interpretability or fail to integrate key prognostic factors effectively.
  • The role of micronutrient status in IHCA outcomes requires further elucidation.

Purpose of the Study:

  • To develop and validate an interpretable machine learning model for predicting 30-day mortality in IHCA patients.
  • To incorporate the m-NUTRIC score, age, and specific micronutrient biomarkers into the predictive model.
  • To compare the performance of the developed CatBoost model against traditional logistic regression.

Main Methods:

  • A cohort of 880 IHCA patients admitted to a medical intensive care unit was analyzed.
  • Electronic medical records were used to extract data on demographics, clinical variables, m-NUTRIC score, and micronutrient levels (magnesium, zinc, vitamin D, vitamin B12).
  • A CatBoost model and logistic regression model were trained on an 80/20 data split, with performance evaluated using ROC-AUC, precision-recall curves, and decision curve analysis. SHAP values were used for interpretability.

Main Results:

  • The CatBoost model achieved a superior ROC-AUC of 0.850 (training) and 0.827 (test) compared to logistic regression (0.797).
  • Key performance metrics on the test set included accuracy (0.761), precision (0.847), recall (0.790), and F1-score (0.817).
  • SHAP analysis highlighted the m-NUTRIC score and age as primary predictors, with micronutrients providing supplementary predictive value.

Conclusions:

  • The interpretable CatBoost model demonstrates enhanced performance in predicting 30-day mortality post-IHCA compared to logistic regression.
  • The model's ability to integrate clinical scores, demographics, and micronutrient data offers a more comprehensive prognostic approach.
  • Prospective, multicenter validation is recommended to confirm the generalizability and clinical utility of this CatBoost model.