June 2022
Volume 63, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2022
Predictive Modeling of Long-Term Glaucoma Progression Based on Systemic Data in the Electronic Medical Record
Author Affiliations & Notes
  • Richul Oh
    Ophthalmology, Seoul National University College of Medicine, Seoul, Korea (the Republic of)
    Ophthalmology, Seoul National University Bundang Hospital, Seongnam, Korea (the Republic of)
  • Hyunjoong Kim
    Applied Statistics, Yonsei University, Seodaemun-gu, Seoul, Korea (the Republic of)
  • Tae-Woo Kim
    Ophthalmology, Seoul National University College of Medicine, Seoul, Korea (the Republic of)
    Ophthalmology, Seoul National University Bundang Hospital, Seongnam, Korea (the Republic of)
  • Eun Ji Lee
    Ophthalmology, Seoul National University College of Medicine, Seoul, Korea (the Republic of)
    Ophthalmology, Seoul National University Bundang Hospital, Seongnam, Korea (the Republic of)
  • Footnotes
    Commercial Relationships   Richul Oh None; Hyunjoong Kim None; Tae-Woo Kim None; Eun Ji Lee None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2022, Vol.63, 2051 – A0492. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Richul Oh, Hyunjoong Kim, Tae-Woo Kim, Eun Ji Lee; Predictive Modeling of Long-Term Glaucoma Progression Based on Systemic Data in the Electronic Medical Record. Invest. Ophthalmol. Vis. Sci. 2022;63(7):2051 – A0492.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To determine the baseline systemic features predictive of rapid retinal nerve fiber layer (RNFL) thinning over future 5 years in primary open-angle glaucoma (POAG)

Methods : Database in the electronic medical record (EMR) was searched to include patients diagnosed with POAG between 2009 and 2016, and had been followed up for > 5 years with annual evaluation of RNFL thickness using spectral-domain optical coherence tomography (OCT). Systemic data obtained within 6 months from the time of glaucoma diagnosis were extracted from the EMR and incorporated into the model to predict the rate of progressive RNFL thinning. After training and testing a predictive model using a random forest (RF) method, the model was interpreted by the Shapley additive explanation plots (SHAP) method. The features that can explain the rate of progressive RNFL thinning were identified and interpreted.

Results : Data from 1256 eyes of 696 patients and 1107 eyes of 607 patients were included in the training and test sets, respectively. The R square value for the RF model was 0.88. The prediction model showed that higher serum aspartate aminotransferase, lower blood glucose, higher systolic blood pressure, higher high-density lipoprotein were the four most determinant systemic features predicting faster RNFL thinning over 5 years. Partial interaction plots showed interactions between some systemic features influencing the rate of RNFL thinning; the interactions between aspartate aminotransferase and Alkaline Phosphatase, systemic blood pressure and diastolic blood pressure, high-density lipoprotein and low-density lipoprotein, blood urea nitrogen and creatinine were associated features. Among ophthalmic features, higher global RNFL thickness and higher intraocular pressure were the most important factors predicting rapid RNFL thinning.

Conclusions : Baseline systemic features of POAG patients had predictive value in identifying those at risk of faster progression

This abstract was presented at the 2022 ARVO Annual Meeting, held in Denver, CO, May 1-4, 2022, and virtually.

 

×
×

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.

×