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

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

42
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
42

You might also read

Related Articles

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

Sort by
Same author

Restorative materials for direct coronal restoration of permanent posterior teeth: an overview of systematic reviews.

The Cochrane database of systematic reviews·2026
Same author

Detecting Adverse Events Following Acute Care Encounters among Veterans Prescribed Non-Steroidal Anti-Inflammatory Drugs.

Journal of the American College of Emergency Physicians open·2026
Same author

Development of the authentication and authorization processes for the iAgree portal, a platform for patient-controlled data sharing across health systems.

JAMIA open·2026
Same author

Privacy-enhancing sequential learning under heterogeneous selection bias in multi-site electronic health records data.

Journal of the American Medical Informatics Association : JAMIA·2026
Same author

Detecting Uncoded Self-Harm in Veterans' Electronic Health Records Using Positive and Unlabeled Learning: Retrospective Cohort Study.

Journal of medical Internet research·2026
Same author

Explainability in context: calibrating appropriate trust and reliance in artificial intelligence.

Journal of the American Medical Informatics Association : JAMIA·2026

Related Experiment Video

Updated: Jun 9, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

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

Published on: October 10, 2018

8.2K

A machine learning framework to adjust for learning effects in medical device safety evaluation.

Jejo D Koola1, Karthik Ramesh2, Jialin Mao3

  • 1Department of Medicine, University of California San Diego, San Diego, CA 92093, United States.

Journal of the American Medical Informatics Association : JAMIA
|October 29, 2024
PubMed
Summary

This study introduces a machine learning (ML) framework to accurately assess medical device safety by detecting and adjusting for operator learning effects, improving upon traditional methods.

Keywords:
learning curvelearning effectsmachine learningmedical devicespost-market safety surveillance

More Related Videos

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.5K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

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

Published on: August 16, 2020

6.7K

Related Experiment Videos

Last Updated: Jun 9, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

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

Published on: October 10, 2018

8.2K
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.5K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

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

Published on: August 16, 2020

6.7K

Area of Science:

  • Medical Device Safety
  • Machine Learning Applications
  • Post-Market Surveillance

Background:

  • Traditional medical device post-market surveillance methods struggle to account for operator learning effects, leading to biased safety assessments.
  • Complex factors like non-linearity, learning curves, and physician experience introduce challenges for existing surveillance techniques.
  • There is a need for advanced methods to accurately evaluate device safety in the presence of operator learning.

Purpose of the Study:

  • To develop a machine learning (ML) framework for detecting and adjusting operator learning effects in medical device post-market surveillance.
  • To address the limitations of traditional methods in handling non-linear learning curves and time-varying covariates.
  • To enhance the accuracy of medical device safety evaluations by accounting for operator experience.

Main Methods:

  • Utilized a gradient-boosted decision tree ML method on synthetic datasets mimicking clinical scenarios.
  • Employed a risk-adjusted cumulative sum method to detect learning effects and quantify excess adverse events due to inexperience.
  • Adjusted for operator learning effects alongside patient factors in evaluating device safety signals, using data from the Department of Veterans Affairs.

Main Results:

  • The ML framework accurately identified learning effects in 93.6% of datasets and determined device safety signals in 93.4% of cases.
  • Device odds ratio confidence intervals were accurately aligned with specified ratios in 94.7% of datasets.
  • The framework achieved 100% specificity for clinically relevant safety signal thresholds, outperforming comparative models that excluded learning effects.

Conclusions:

  • A tailored ML framework offers superior performance over standard parametric techniques for post-market device evaluation when operator learning is present.
  • This ML framework effectively addresses limitations of traditional statistical methods in post-market surveillance.
  • The developed framework can significantly improve medical device safety evaluation by reliably detecting and adjusting for learning effects.