Article

Performance drift is a major barrier to the safe use of machine learning in cardiac surgery

2023-01-22

Abstract excerpt

<h4>ABSTRACT</h4> <h4>Objectives</h4> The Society of Thoracic Surgeons (STS), and EuroSCORE II (ES II) risk scores, are the most commonly used risk prediction models for adult cardiac surgery post-operative in-hospital mortality. However, they are prone to miscalibration over time, and poor generalisation across datasets and their use remain controversial. It has been suggested that using Machine Learning (ML) tec...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: a16e7061-ac78-532c-82e6-7002c97f586c
DOI: 10.1101/2023.01.21.23284795

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Performance drift is a major barrier to the safe use of machine learning in cardiac surgeryDOI 10.1101/2023.01.21.23284795Read

Evaluation of Domain Generalization and Adaptation on Improving Model Robustness to Temporal Dataset Shift in Clinical MedicineSemantic proximity Read

Development and external validation of a machine learning model for predicting immediate postoperative instability in adults undergoing cardiac surgerySemantic proximity Read

Unsupervised Cluster-Augmented Mortality Prediction in MIMIC-IV Using Tabular ICU Time-Series Aggregation and Gradient Boosted LearningSemantic proximity Read

Performance Drift in a Mortality Prediction Algorithm during the SARS-CoV-2 PandemicSemantic proximity Read

Machine Learning for Predicting Medical Error Risks in Greek Surgery DepartmentsSemantic proximity Read

Low Responsiveness of Machine Learning Models to Critical or Deteriorating Health ConditionsSemantic proximity Read

Improved Sensitivity For Detection Of Clinical Deterioration When Diagnostic Pathology And Patient Trends Are Included In Machine Learning ModelsSemantic proximity Read

Clinical Risk-Weighted Evaluation of ICU Mortality Prediction Models on MIMIC-IVSemantic proximity Read

Model Generalizability Considerations in Development and Evaluation of SaMDSemantic proximity Read

Reference-Class Failure in Mortality Prediction: A Synthetic Study of Irreducible Uncertainty in End-of-Life Prognostic ModelsSemantic proximity Read

Dynamic AI Risk Loop (DARL): A Continuous Risk Management Framework for AI-Enabled Health Information Systems in Medical Device SoftwareSemantic proximity Read

Evaluating Deep Learning Sepsis Prediction Models in ICUs Under Distribution Shift: A Multi-Centre Retrospective Cohort StudySemantic proximity Read