June 2023
Volume 64, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2023
Automated machine learning to predict anatomical outcomes in pneumatic retinopexy
Author Affiliations & Notes
  • Arina Nisanova
    School of Medicine, University of California Davis, California, United States
  • Arefeh Yavary
    Department of Computer Science, University of California Davis, Davis, California, United States
  • Jordan Deaner
    Mid Atlantic Retina, Wills Eye Hospital, Philadelphia, Pennsylvania, United States
  • Ferhina S. Ali
    New York Medical College, Valhalla, New York, United States
  • Priyanka Gogte
    Associated Retinal Consultants, Royal Oak, Michigan, United States
  • Richard Kaplan
    New York Eye and Ear Infirmary of Mount Sinai, New York, New York, United States
  • Kevin C Chen
    Vantage Eye Center, Salinas, California, United States
  • Eric Nudleman
    Shiley Eye Center, University of California San Diego, La Jolla, California, United States
  • Dilraj Grewal
    Eye Center, Duke University, Durham, North Carolina, United States
  • Meenakashi Gupta
    New York Eye and Ear Infirmary of Mount Sinai, New York, New York, United States
  • Jeremy Wolfe
    Associated Retinal Consultants, Royal Oak, Michigan, United States
  • Michael Klufas
    Wills Eye Hospital, Thomas Jefferson University, Philadelphia, Pennsylvania, United States
  • Glenn Yiu
    Tschannen Eye Institute, University of California Davis, Sacramento, California, United States
  • Iman Soltani-Bozchalooi
    College of Engineering, University of California Davis, Davis, California, United States
  • Parisa Emami-Naeini
    Tschannen Eye Institute, University of California Davis, Sacramento, California, United States
  • Footnotes
    Commercial Relationships   Arina Nisanova J. William Kohl Summer Scholarship for Medical Students, Code F (Financial Support); Arefeh Yavary None; Jordan Deaner Alimera Sciences Inc, Eyepoint Pharmaceuticals Inc, Code C (Consultant/Contractor); Ferhina Ali Genentech, Allergan, Code C (Consultant/Contractor), Genentech, Allergan, EyePoint, Genentech, Code S (non-remunerative); Priyanka Gogte None; Richard Kaplan None; Kevin Chen None; Eric Nudleman None; Dilraj Grewal Regeneron, Unity Biotechnology, Iveric Bio, EyePoint, RegenxBio, Code C (Consultant/Contractor); Meenakashi Gupta None; Jeremy Wolfe Alcon, Apellis, Kodiak, RegenexBio, Genentech, Gyroscope, Novartis, Regeneron, Adverum, Allergan/Abvie,, Code C (Consultant/Contractor), Aviceda, Caeregen, Vortex, Code I (Personal Financial Interest), Allergan/Abvie, Genentech, Regeneron, Code S (non-remunerative); Michael Klufas Regeneron, Genentech, Allergan, RegenexBio, Code C (Consultant/Contractor); Glenn Yiu Abbvie, Adverum, Alimera, Anlong, Bausch & Lomb, Cholgene, Clearside, Endogena, Genentech, Gyroscope, Intergalactic, Iridex, Janssen, NGM Bio, Regeneron, Thea, Topcon, Zeiss., Code C (Consultant/Contractor); Iman Soltani-Bozchalooi None; Parisa Emami-Naeini Eyepoint, Bausch+Lomb, Code C (Consultant/Contractor)
  • Footnotes
    Support  Arina Nisanova was supported by training funds from the J. William Kohl Summer Scholarship for Medical Students.
Investigative Ophthalmology & Visual Science June 2023, Vol.64, 223. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Arina Nisanova, Arefeh Yavary, Jordan Deaner, Ferhina S. Ali, Priyanka Gogte, Richard Kaplan, Kevin C Chen, Eric Nudleman, Dilraj Grewal, Meenakashi Gupta, Jeremy Wolfe, Michael Klufas, Glenn Yiu, Iman Soltani-Bozchalooi, Parisa Emami-Naeini; Automated machine learning to predict anatomical outcomes in pneumatic retinopexy. Invest. Ophthalmol. Vis. Sci. 2023;64(8):223.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : Pneumatic retinopexy (PR) is a minimally invasive procedure for retinal detachment (RD) repair with a variable anatomic success rate. However, no definitive measures exist to reliably predict the anatomical success of the procedure. Machine learning (ML) models have been previously developed by computer scientists to predict outcomes of various medical procedures. We sought to evaluate the feasibility of implementing fully automated ML algorithms developed by medical professionals without coding experience and evaluate the models’ discriminative performance for predicting success in PR.

Methods : This is a retrospective multicenter study of 539 consecutive patients with primary RD (between 2002 and 2022). Medical professionals without coding background used two autoML platforms, MATLAB Classification Learner App and Google Cloud AutoML Vertex AI, to develop models. We used single-procedure anatomic success as the outcome of interest and included patients’ baseline clinical characteristics in the models. Additional ML models were developed by computer scientists in Python (v3.8) to evaluate the accuracy and area under ROC curves (AUC). The ML experts were free to adopt any data pre-processing steps (e.g. augmentation or imputation) and ML algorithms.

Results : The dataset was divided into a training set (n=483) and a test set (n=56). We used this training set (Dataset 1) to train the MATLAB model. Given Google Cloud AutoML minimum data threshold (n>1000), the training set was tripled to make Dataset prime1 (n=1449) with a similar 2:1 success-to-failure ratio. Additional imputed and augmented datasets were generated in Python: Dataset 2 (n=660) and Dataset 3 (n=1313) with 1:1 success:failure ratio. The autoML models showed test accuracy of 53.6%, AUC=0.87 (MATLAB) and 57.4%, AUC=0.61 (Google autoML) on the imbalanced datasets (1 and prime1, respectively). Use of pre-processed datasets improved accuracy of autoML models to 80.4% (AUC=0.87, MATLAB) and 60.7% (AUC=0.69, Google AutoML), which were comparable to the models developed by the ML experts (accuracy 86%, AUC=0.86).

Conclusions : AutoML platforms have great potential in predicting procedure outcomes and can be used by clinicians without prior coding knowledge. However, limitations exist especially if datasets contain missing variables or are highly imbalanced. Proper data pre-processing, including augmentation techniques, can improve usability of autoML tools.

This abstract was presented at the 2023 ARVO Annual Meeting, held in New Orleans, LA, April 23-27, 2023.

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×