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

Comparing the Survival Analysis of Two or More Groups01:20

Comparing the Survival Analysis of Two or More Groups

725
Survival analysis is a cornerstone of medical research, used to evaluate the time until an event of interest occurs, such as death, disease recurrence, or recovery. Unlike standard statistical methods, survival analysis is particularly adept at handling censored data—instances where the event has not occurred for some participants by the end of the study or remains unobserved. To address these unique challenges, specialized techniques like the Kaplan-Meier estimator, log-rank test, and...
725
Blood Studies for Cardiovascular System I: Cardiac Biomarkers01:20

Blood Studies for Cardiovascular System I: Cardiac Biomarkers

1.2K
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...
1.2K

You might also read

Related Articles

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

Sort by
Same author

Development and validation of the quiet quitting behavior scale: a mixed-methods study with primary healthcare workers in China.

Frontiers in public health·2026
Same author

Vasoactive-Inotropic Score Reduction Rate Is Highly Associated With Prognosis for Critically Ill Patients With Cardiogenic Shock: Insights From the Real-World Dynamic Data.

Cardiovascular therapeutics·2026
Same author

Lecithin supplementation to HFD improves largemouth bass liver health: Implications for regulating lipid homeostasis, antioxidant responses and endoplasmic reticulum stress.

Fish physiology and biochemistry·2026
Same author

Targeting the JAK2/STAT3 Axis and Remodeling the Tumour Microenvironment: The Dual Anti-Tumour Mechanism of Total Glucosides of Paeony in Gallbladder Cancer.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2026
Same author

Effectiveness of an educational intervention based on the common-sense model of self-regulation for lung cancer patients after thoracoscopic surgery.

Scientific reports·2025
Same author

[Accumulation and Application Potentials of Dominant Plants on Pb-Zn Mines in Karst Region， Guangxi].

Huan jing ke xue= Huanjing kexue·2025

Related Experiment Video

Updated: Apr 16, 2026

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

793

Machine Learning Interpretability to Assess the Association Between Time in Tight Range and Mortality in Cardiogenic

Yang Jiang1, Qing-Lin Li2, Yan-Ling Huang3

  • 1Department of Rehabilitation, Shenzhen Bao'an Chinese Medicine Hospital, Guangzhou University of Chinese Medicine, Shenzhen, China.

Nursing in Critical Care
|April 15, 2026
PubMed
Summary

Maintaining a higher Time In Tight Range (TITR) for blood glucose is linked to reduced mortality in cardiogenic shock patients. Machine learning models effectively predict outcomes, highlighting TITR as a key factor for intervention.

Keywords:
cardiogenic shockmachine learningmortalitytime in tight range

Related Experiment Videos

Last Updated: Apr 16, 2026

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

793

Area of Science:

  • Critical Care Medicine
  • Endocrinology
  • Data Science in Healthcare

Background:

  • Cardiogenic shock (CS) presents high mortality due to end-organ hypoperfusion.
  • Glycemic variability, measured by Time In Tight Range (TITR), may worsen instability in critically ill patients.
  • The prognostic impact of TITR on CS mortality is not well-established.

Purpose of the Study:

  • To investigate the association between TITR and mortality in patients with CS.
  • To provide evidence for early intervention and personalized glucose management strategies.
  • To evaluate the performance and interpretability of machine learning (ML) models in predicting CS mortality.

Main Methods:

  • Retrospective multi-cohort study analyzing TITR and in-hospital mortality in CS patients.
  • Statistical analyses included restricted cubic spline (RCS) models, Cox regression, and logistic regression.
  • Developed and compared multiple ML models (XGBoost, LightGBM, CatBoost, etc.) against traditional scoring systems, using SHAP for interpretability.

Main Results:

  • An inverse, L-shaped association was found between TITR and in-hospital mortality (p < 0.001) in both MIMIC-IV and eICU cohorts.
  • Patients with TITR > 57% (High TITR group) exhibited significantly lower in-hospital mortality compared to the Low TITR group.
  • ML models, particularly CatBoost, Gradient Boosting, and XGBoost, outperformed traditional scoring systems in mortality prediction (AUCs ranging from 0.74 to 0.77).

Conclusions:

  • Higher TITR is a critical predictor of improved outcomes in CS patients, emphasizing the need for dynamic glucose control.
  • Interpretable ML models demonstrate superiority in risk stratification and decision support for CS management.
  • Findings provide evidence-based guidance for ICU interventions, identifying TITR as a key modifiable factor for improving patient outcomes.