June 2022
Volume 63, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2022
Retinal photograph-based deep learning predicts biological age, and stratifies morbidity and mortality risk
Author Affiliations & Notes
  • Ching-Yu Cheng
    Ocular Epidemiology Research Group, Singapore Eye Research Institute, Singapore, Singapore, Singapore
    Ophthalmology & Visual Sciences Academic Clinical Program, Duke-NUS Medical School, Singapore, Singapore
  • Simon Nusinovici
    Ocular Epidemiology Research Group, Singapore Eye Research Institute, Singapore, Singapore, Singapore
  • Marco Yu
    Data Science Unit, Singapore Eye Research Institute, Singapore, Singapore
  • Geunyoung Lee
    Medi Whale Inc., Korea (the Republic of)
  • Yih Chung Tham
    Ocular Epidemiology Research Group, Singapore Eye Research Institute, Singapore, Singapore, Singapore
    Ophthalmology & Visual Sciences Academic Clinical Program, Duke-NUS Medical School, Singapore, Singapore
  • Ning Cheung
    Singapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore, Singapore
    Ophthalmology & Visual Sciences Academic Clinical Program, Duke-NUS Medical School, Singapore, Singapore
  • Zhi Da Soh
    Ocular Epidemiology Research Group, Singapore Eye Research Institute, Singapore, Singapore, Singapore
  • Sahil Thakur
    Ocular Epidemiology Research Group, Singapore Eye Research Institute, Singapore, Singapore, Singapore
  • Joo Lee Chan
    Division of Cardiology; Severance Hospital, Yonsei University College of Medicine, Severance Cardiovascular Hospital, Seodaemun-gu, Seoul, Korea (the Republic of)
  • Charumathi Sabanayagam
    Ocular Epidemiology Research Group, Singapore Eye Research Institute, Singapore, Singapore, Singapore
    Ophthalmology & Visual Sciences Academic Clinical Program, Duke-NUS Medical School, Singapore, Singapore
  • Byoung Kwon Lee
    Division of Cardiology; Gangnam Severance Hospital; Yonsei University Medical College of Medicine, Severance Cardiovascular Hospital, Seodaemun-gu, Seoul, Korea (the Republic of)
  • Sungha Park
    Division of Cardiology; Integrated Research Center for Cerebrovascular and Cardiovascular disease, Severance Hospital, Yonsei University College of Medicine, Severance Cardiovascular Hospital, Seodaemun-gu, Seoul, Korea (the Republic of)
  • Sung Soo Kim
    Department of Ophthalmology; Yonsei University College of Medicine, Severance Hospital, Seodaemun-gu, Seoul, Korea (the Republic of)
  • Hyeon Chang Kim
    Department of Preventive Medicine, Yonsei University College of Medicine, Seodaemun-gu, Seoul, Korea (the Republic of)
  • Tien Yin Wong
    Singapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore, Singapore
    Ophthalmology & Visual Sciences Academic Clinical Program, Duke-NUS Medical School, Singapore, Singapore
  • Tyler Hyungtaek Rim
    Ocular Epidemiology Research Group, Singapore Eye Research Institute, Singapore, Singapore, Singapore
    Ophthalmology & Visual Sciences Academic Clinical Program, Duke-NUS Medical School, Singapore, Singapore
  • Footnotes
    Commercial Relationships   Ching-Yu Cheng None; Simon Nusinovici None; Marco Yu None; Geunyoung Lee None; Yih Chung Tham None; Ning Cheung None; Zhi Da Soh None; Sahil Thakur None; Joo Lee Chan None; Charumathi Sabanayagam None; Byoung Lee None; Sungha Park None; Sung Soo Kim None; Hyeon Kim None; Tien Yin Wong None; Tyler Hyungtaek Rim None
  • Footnotes
    Support  MOH-HLCA21Jan-0004
Investigative Ophthalmology & Visual Science June 2022, Vol.63, 2097 – F0086. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Ching-Yu Cheng, Simon Nusinovici, Marco Yu, Geunyoung Lee, Yih Chung Tham, Ning Cheung, Zhi Da Soh, Sahil Thakur, Joo Lee Chan, Charumathi Sabanayagam, Byoung Kwon Lee, Sungha Park, Sung Soo Kim, Hyeon Chang Kim, Tien Yin Wong, Tyler Hyungtaek Rim; Retinal photograph-based deep learning predicts biological age, and stratifies morbidity and mortality risk. Invest. Ophthalmol. Vis. Sci. 2022;63(7):2097 – F0086.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Ageing is an important risk factor for a variety of human pathologies. Biological age (BA) may better capture ageing-related physiological changes, compared to chronological age (CA). We developed a deep-learning (DL) algorithm to predict BA based on retinal photographs and evaluated the performance of our new ageing marker in the risk stratification of mortality and major morbidity in general populations.

Methods : We first trained a DL algorithm using 129,236 retinal photographs from 40,480 participants in the Korean Health Screening study to predict the probability of age being ≥65 years (“RetiAGE”) and then evaluated the ability of RetiAGE to stratify the risk of mortality and major morbidity among 56,301 participants in the UK Biobank. Cox proportional hazards model was used to estimate the hazard ratios (HRs).

Results : In the UK Biobank, over a 10-year follow up, 2,236 (4.0%) died; of them, 636 [28.4%] were due to cardiovascular diseases (CVDs) and 1,276 [57.1%] due to cancers. Compared to the participants in the RetiAGE first quartile, those in the RetiAGE fourth quartile had a 67% higher risk of 10-year all-cause mortality (HR=1.67 [1.42-1.95]; Figure), a 142% higher risk of CVD mortality (HR=2.42 [1.69-3.48]), and a 60% higher risk of cancer mortality (HR=1.60 [1.31-1.96]), independent of CA and established ageing phenotypic biomarkers. Likewise, compared to the first quartile group, the risk of CVD and cancer events in the fourth quartile group increased by 39% (HR=1.39 [1.14-1.69]) and 18% (HR=1.18 [1.10-1.26]), respectively. The best discrimination ability for RetiAGE alone was found for CVD mortality (c-index=0.70, sensitivity=0.76, specificity=0.55). Furthermore, adding RetiAGE increased the discrimination ability of the model beyond CA and phenotypic biomarkers (increment in c-index between 1 and 2%).

Conclusions : The DL-derived RetiAGE provides a novel, alternative approach to measure ageing.

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.

×