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

You might also read

Related Articles

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

Sort by
Same author

Properties of the threshold stimulus exposure duration (TSED) measure of visual search efficiency.

Attention, perception & psychophysics·2026
Same author

Spontaneous Branch Retinal Artery Occlusion Secondary to Aneurysmal Fibrosis in an Adult with Coats Disease: A Case Report.

Retinal cases & brief reports·2026
Same author

Characterization of vascular tortuosity throughout the murine oxygen-induced retinopathy model of ischemic retinopathy.

JCI insight·2026
Same author

Predictors of Good Visual Recovery in Patients With Spontaneously Resolved Acute CSCR - MICRoN Report Number Thirteen.

American journal of ophthalmology·2026
Same author

A Matching-Adjusted Comparison of Faricimab and Aflibercept 8 mg in Neovascular Age-Related Macular Degeneration and Diabetic Macular Edema.

Ophthalmic research·2026
Same author

RWC Update: Modern One Health Approaches to Novel Challenges in Infectious Uveitis-Parasitic, Fungal and Mycobacterial Uveitis (Part 2); Management of 180° Iridodialysis With Aphakia and Total Hyphema; Retinal Astrocytic Hamartoma.

Ophthalmic surgery, lasers & imaging retina·2026

Related Experiment Video

Updated: Jun 24, 2025

A Spine Robotic-Assisted Navigation System for Pedicle Screw Placement
06:24

A Spine Robotic-Assisted Navigation System for Pedicle Screw Placement

Published on: May 11, 2020

8.8K

Performance of Automated Machine Learning in Predicting Outcomes of Pneumatic Retinopexy.

Arina Nisanova1, Arefeh Yavary2, Jordan Deaner3

  • 1School of Medicine, University of California Davis, Davis, California.

Ophthalmology Science
|June 3, 2024
PubMed
Summary

Automated machine learning (AutoML) shows promise for predicting pneumatic retinopexy success in retinal detachment. Careful data balancing is crucial for reliable outcomes, preventing misleading results from imbalanced datasets.

Keywords:
Automated machine learning (AutoML)Machine learningMedical outcome predictionPneumatic retinopexyRhegmatogenous retinal detachment

More Related Videos

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
An Experimental Paradigm for the Prediction of Post-Operative Pain PPOP
14:56

An Experimental Paradigm for the Prediction of Post-Operative Pain PPOP

Published on: January 27, 2010

21.4K

Related Experiment Videos

Last Updated: Jun 24, 2025

A Spine Robotic-Assisted Navigation System for Pedicle Screw Placement
06:24

A Spine Robotic-Assisted Navigation System for Pedicle Screw Placement

Published on: May 11, 2020

8.8K
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
An Experimental Paradigm for the Prediction of Post-Operative Pain PPOP
14:56

An Experimental Paradigm for the Prediction of Post-Operative Pain PPOP

Published on: January 27, 2010

21.4K

Area of Science:

  • Ophthalmology
  • Medical Informatics
  • Machine Learning

Background:

  • Automated machine learning (AutoML) offers a coding-free solution for medical professionals to build predictive models.
  • Pneumatic retinopexy (PR) is a treatment for rhegmatogenous retinal detachment (RRD), and predictive modeling can aid treatment success assessment.

Purpose of the Study:

  • To evaluate the performance of AutoML tools in predicting PR success for RRD.
  • To compare AutoML-developed models against those created by machine learning (ML) experts.

Main Methods:

  • A retrospective multicenter study included 539 patients undergoing PR for RRD.
  • MATLAB Classification Learner and Google Cloud AutoML were used. Models were trained on balanced and imbalanced datasets.
  • Performance was assessed using F2 scores and area under the receiver operating curve (AUROC).

Main Results:

  • The best AutoML model (MATLAB) achieved an F2 score of 0.85 and AUROC of 0.90 on balanced data, comparable to expert models.
  • Imbalanced data training resulted in a misleadingly high AUROC (0.81) but a low F2 score (0.2) and sensitivity (0.17).

Conclusions:

  • AutoML is a feasible tool for clinicians to develop predictive models from clinical data.
  • Proper data preprocessing and model selection are essential to ensure the reliability of AutoML tools.
  • Naive use of AutoML with imbalanced or incomplete data can lead to unreliable predictions.