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

Relative Risk

Relative Risk

Relative risk (RR) is a statistical measure commonly used in epidemiology to compare the likelihood of a particular event occurring between two groups. This metric is important for evaluating the relationship between exposure to a specific risk factor and the probability of a particular outcome. It plays a crucial role in medical research, public health studies, and risk assessment. Relative risk quantifies how much more (or less) likely an event is to occur in an exposed group compared to an...

Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches

Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches

Biopharmaceutical studies constitute a vital field aiming to enhance drug delivery methods and refine therapeutic approaches, drawing upon diverse interdisciplinary knowledge. In research methodologies, the choice between controlled and non-controlled studies significantly influences the study's reliability and accuracy.
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...

You might also read

Related Articles

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

Sort by

Same author

MRDsteer: quality-aware AI-driven closed-loop optimization enhances ctDNA-based minimal residual disease detection.

Briefings in bioinformatics·2026

Same author

STGBench: sequencing-level spatial DNA-RNA simulation for multimodal and virtual cell-oriented benchmarking of genomic alterations.

Briefings in bioinformatics·2026

Same author

Genome-wide analysis of the LAR gene family and the role of OvLAR71 in proanthocyanidin biosynthesis in Onobrychis viciifolia.

Plant physiology and biochemistry : PPB·2026

Same author

A comparative study of machine learning models for microbiome-based diagnosis and multi-class staging of colorectal cancer.

Scientific reports·2026

Same author

Jujube Polysaccharide Promotes Neuroprotection and Longevity in <i>Caenorhabditis elegans</i> Through Oxidative Stress Resistance and Stress-Response Signaling.

International journal of molecular sciences·2026

Same author

Relationship Between Prognostic Nutritional Index and Stroke-Associated Pneumonia in Elderly Patients: A Two-Center Study of Spontaneous Intracerebral Hemorrhage.

Food science & nutrition·2026

Search research articles

Related Experiment Video

Updated: Oct 26, 2025

An R-Based Landscape Validation of a Competing Risk Model

An R-Based Landscape Validation of a Competing Risk Model

Published on: September 16, 2022

A non-linear ensemble model-based surgical risk calculator for mixed data from multiple surgical fields.

Ruoyu Liu¹, Xin Lai^2,3, Jiayin Wang¹

¹School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, China.

BMC Medical Informatics and Decision Making

|July 31, 2021

Summary

This study introduces a new non-linear surgical risk calculator that improves patient safety by accurately predicting postoperative risks, outperforming traditional linear models. The Gradient Boosting Decision Tree (GBDT) model enhances accuracy and identifies key risk factors.

Keywords:

Clinical decision support system Gradient boosting decision tree Machine learning Surgical risk calculator

More Related Videos

Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery

Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery

Published on: September 27, 2024

Establishing a Competing Risk Regression Nomogram Model for Survival Data

Establishing a Competing Risk Regression Nomogram Model for Survival Data

Published on: October 23, 2020

Related Experiment Videos

Last Updated: Oct 26, 2025

An R-Based Landscape Validation of a Competing Risk Model

An R-Based Landscape Validation of a Competing Risk Model

Published on: September 16, 2022

Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery

Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery

Published on: September 27, 2024

Establishing a Competing Risk Regression Nomogram Model for Survival Data

Establishing a Competing Risk Regression Nomogram Model for Survival Data

Published on: October 23, 2020

Area of Science:

Medical Informatics
Clinical Decision Support
Predictive Analytics

Background:

Surgical risk misestimation poses a significant threat to patient safety.
Existing linear models struggle to capture complex non-linear interactions among risk factors, limiting predictive accuracy.
Improving postoperative risk prediction is crucial for effective surgical planning and patient care.

Purpose of the Study:

To develop and validate a novel non-linear surgical risk calculator.
To enhance the accuracy of postoperative risk prediction using advanced machine learning.
To address the limitations of linear models in capturing complex physiological interactions.

Main Methods:

Development of a surgical risk calculator utilizing the Gradient Boosting Decision Tree (GBDT) non-linear ensemble algorithm.
Implementation of three distinct modes for handling varied data scenarios and feature reduction based on GBDT importance.
Comparison with baseline and similar models using three-year clinical data from Hong Kong's Surgical Outcome Monitoring and Improvement Program (SOMIP).

Main Results:

The GBDT-based approach achieved excellent performance, with the best Area Under Curve (AUC) reaching 0.902, Hosmer-Lemeshow test ([Formula: see text]) of 7.398, and Brier Score (BS) of 0.047.
Even after feature reduction, the model maintained high accuracy, with AUC at 0.894, [Formula: see text] at 7.638, and BS at 0.060.
Consistent performance advantage across all evaluation metrics in comparative experiments.

Conclusions:

The developed non-linear surgical risk calculator (NL-SRC) significantly improves patient risk prediction accuracy.
The model effectively identifies critical risk factors and their complex interactions, crucial for understanding surgical outcomes.
Demonstrated excellent performance with mixed data from diverse surgical fields, highlighting its clinical applicability.