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

Survival Tree

Survival Tree

Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...

You might also read

Related Articles

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

Sort by

Same author

Hospital costs attributable to further fracture, reoperation, and death during the first year following hip fracture in England : a nationwide cohort study.

The bone & joint journal·2026

Same author

Impact of socioeconomic deprivation on early and long-term outcomes after major aortic surgery: insights from a 20-year single-centre cohort.

Open heart·2026

Same author

National patient-reported outcome measures data and the National Joint Registry : a report on the data completeness and quality.

The bone & joint journal·2026

Same author

Perioperative Outcomes and Complications of Laparoscopic Cholecystectomy in End-Stage Renal Disease Patients: A Prospective Comparative Study.

World journal of surgery·2026

Same author

PCI after SVG failure-native vessel or graft?

Indian journal of thoracic and cardiovascular surgery·2026

Same author

Towards individualised multi-morbidity predictions: a new frontier for AI-enabled diagnostics in thrombotic disease.

Indian journal of thoracic and cardiovascular surgery·2026

Search research articles

Related Experiment Video

Updated: Apr 12, 2026

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

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

Published on: October 10, 2018

Performance Drift in Machine Learning Models for Cardiac Surgery Risk Prediction: Retrospective Analysis.

Tim Dong¹, Shubhra Sinha¹, Ben Zhai²

¹Bristol Heart Institute, Translational Health Sciences, University of Bristol, Bristol, United Kingdom.

|June 18, 2024

Summary

Machine learning models for cardiac surgery risk prediction show performance decline over time due to dataset drift. Extreme gradient boosting and random forest models outperformed traditional scores like EuroSCORE II.

Keywords:

United Kingdom adult artificial intelligence cardiac cardiac surgery cardiology data data set drift heart machine learning model mortality national data set operative mortality performance performance drift prediction risk risk prediction surgery

More Related Videos

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

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

Published on: August 16, 2020

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

Related Experiment Videos

Last Updated: Apr 12, 2026

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

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

Published on: October 10, 2018

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

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

Published on: August 16, 2020

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

Area of Science:

Cardiovascular Surgery
Medical Informatics
Machine Learning in Healthcare

Background:

Traditional risk scores (e.g., EuroSCORE II) for adult cardiac surgery mortality are prone to miscalibration and poor generalization.
Dataset drift, where deployed ML models encounter data different from their training data, hinders ML adoption in clinical practice.
Understanding performance drift in ML models is crucial for their reliable application in real-world healthcare settings.

Purpose of the Study:

To assess the extent of performance drift in machine learning (ML) models for cardiac surgery risk prediction over time.
To investigate the influence of dataset drift and variable importance drift on model performance.
To compare the performance drift of ML models against the EuroSCORE II risk score.

Main Methods:

Retrospective analysis of prospectively collected UK cardiac surgery data (2012-2019) from 227,087 adult patients.
Development and temporal validation of five novel ML mortality prediction models alongside EuroSCORE II.
Assessment of relationships between variable importance drift, performance drift, and dataset drift using a consensus metric.

Main Results:

A significant decrease in overall performance was observed across all models (P<.0001).
Extreme gradient boosting (CEM 0.728) and random forest (CEM 0.727) demonstrated the best performance.
EuroSCORE II exhibited the poorest performance; sharp changes in variable importance and dataset drift correlated with performance decreases.

Conclusions:

All evaluated models experienced performance degradation over time, highlighting the impact of dataset drift.
Variable importance drift detection underscores limitations of logistic regression and the effects of dataset drift in cardiac surgery risk prediction.
Further research is needed to explore ensemble ML models for potentially improved performance and robustness.