Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

Telemedicine Service Experience Questionnaire for Chinese Outpatients: Development and Validation Study.

JMIR human factors·2026

Same author

A layered standards framework for integrating single-cell and spatial omics data into brain cell atlases.

bioRxiv : the preprint server for biology·2026

Same author

Speech-to-Speech Voice-Cloning Care (SVCC) for improving ICU-acquired anxiety for critically ill patients in a tertiary hospital in Beijing, China: protocol of a randomised, controlled trial.

BMJ open·2026

Same author

Mycelial growth in the bronchial lumen of a patient with acute promyelocytic leukaemia.

Thorax·2025

Same author

Multitemporal single-cell profiling uncovers alveolar IL1β<sup>hi</sup> neutrophils: A significant indicator of CARDS progression.

Clinical and translational medicine·2025

Same author

Multicentre, parallel, open-label, two-arm, randomised controlled trial on the prognosis of electrical impedance tomography-guided versus low PEEP/FiO2 table-guided PEEP setting: a trial protocol.

BMJ open·2024

Search research articles

Related Experiment Video

Updated: Nov 11, 2025

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Noninvasive Real-Time Mortality Prediction in Intensive Care Units Based on Gradient Boosting Method: Model

Huizhen Jiang¹, Longxiang Su², Hao Wang²

¹Department of Information Center, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, China.

JMIR Medical Informatics

|March 25, 2021

Summary

This study developed a noninvasive gradient boosting model for real-time mortality prediction in intensive care units (ICUs). The RMM model demonstrated efficiency and practicality, improving patient comfort and clinical decision-making.

Keywords:

intensive care unit mortality prediction noninvasive real time

More Related Videos

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

Related Experiment Videos

Last Updated: Nov 11, 2025

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

Area of Science:

Critical care medicine
Machine learning in healthcare
Predictive analytics

Background:

Real-time monitoring of critically ill patients in ICUs is crucial.
Traditional scoring systems for mortality prediction lack precision and efficiency.
Current methods are often time-consuming and invasive.

Purpose of the Study:

To integrate diverse medical data for noninvasive, real-time mortality prediction in ICU patients.
To develop a gradient boosting model that minimizes patient discomfort.
To enhance the precision of mortality risk assessment.

Main Methods:

Five real-time mortality prediction models were developed using LightGBM and tested with XGBoost.
Models utilized features from monitoring, laboratory, and scoring data (APACHE, SOFA).
Focus was placed on the noninvasive RMM model (monitoring features only).

Main Results:

The noninvasive RMM model achieved an AUC of 0.8264, outperforming RMA and RMS models.
Noninvasive prediction proved efficient and practical, avoiding extra interventions like blood draws.
Key features identified include blood pressure, heart rate, oxygen saturation, and fluid balance.

Conclusions:

The developed noninvasive method offers a practical and patient-friendly approach to real-time ICU mortality prediction.
This method enhances clinical decision-making and patient care.
The findings highlight the significance of monitoring vital signs and fluid balance for mortality risk assessment.