Investigative Ophthalmology & Visual Science Cover Image for Volume 60, Issue 9
July 2019
Volume 60, Issue 9
Open Access
ARVO Annual Meeting Abstract  |   July 2019
A universal artificial intelligence platform for collaborative management of cataracts
Author Affiliations & Notes
  • Xiaohang Wu
    State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China
  • Lijian Chen
    Beijing Tulip Partners Technology Co., Ltd, Beijing, China
  • Zhenzhen Liu
    State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China
  • Weiyi Lai
    State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China
  • Kai Zhang
    School of Computer Science and Technology, Xidian University, Xi’an, China
  • Duoru Lin
    State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China
  • Kexin Chen
    Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou, China
  • Tongyong Yu
    Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou, China
  • Dongxuan Wu
    Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou, China
  • Cong Li
    Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou, China
  • Chuan Chen
    Department of Molecular and Cellular Pharmacology, University of Miami Miller School of Medicine, China
  • Yi Zhu
    Department of Molecular and Cellular Pharmacology, University of Miami Miller School of Medicine, China
  • Haotian Lin
    State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China
  • Footnotes
    Commercial Relationships   Xiaohang Wu, None; Lijian Chen, None; Zhenzhen Liu, None; Weiyi Lai, None; Kai Zhang, None; Duoru Lin, None; Kexin Chen, None; Tongyong Yu, None; Dongxuan Wu, None; Cong Li, None; Chuan Chen, None; Yi Zhu, None; Haotian Lin, None
  • Footnotes
    Support  1. The National Natural Science Foundation of China (81800810); 2. The Natural Science Foundation of Guangdong Province (2018A030310104)
Investigative Ophthalmology & Visual Science July 2019, Vol.60, 1477. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Xiaohang Wu, Lijian Chen, Zhenzhen Liu, Weiyi Lai, Kai Zhang, Duoru Lin, Kexin Chen, Tongyong Yu, Dongxuan Wu, Cong Li, Chuan Chen, Yi Zhu, Haotian Lin; A universal artificial intelligence platform for collaborative management of cataracts. Invest. Ophthalmol. Vis. Sci. 2019;60(9):1477.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : The current healthcare system is unsatisfactory for the management of high incidence diseases, such as cataract, due to inadequate medical resources and limited accessibility. Artificial intelligence (AI) holds great promises, meanwhile, remains to be improved to integrate into primary healthcare services for increased patient coverage. This study was to establish and validate a universal AI platform for collaborative management of cataracts involving multilevel clinical scenarios and explored an AI-based medical referral pattern to improve collaborative efficiency and resource coverage.

Methods : The training and validation datasets were derived from the Chinese Medical Alliance for Artificial Intelligence (CMAAI), covering multilevel healthcare facilities and capture modes. The datasets were labeled using a three-step strategy: (1) capture mode recognition; (2) cataract diagnosis as a normal lens, cataract or a postoperative eye; and (3) detection of referable cataracts with respect to etiology and severity. Moreover, we integrated the cataract AI agent with a real-world multilevel referral pattern involving self-monitoring at home, primary healthcare, and specialized hospital services.

Results : The universal AI platform and multilevel collaborative pattern showed robust diagnostic performance in three-step tasks: (1) capture mode recognition (AUC 99.28%-99.71%), (2) cataract diagnosis (normal lens, cataract or postoperative eye with AUCs of 99.96%, 99.99%, and 100.00%; AUCs >99% for other capture modes), and (3) detection of referable cataracts (AUC>85% in all tests). In the real-world tertiary referral pattern, the agent suggested 30.3% of people be “referred”, substantially increasing the ophthalmologist-to-population service ratio for 10.2 times compared to the traditional pattern.

Conclusions : The universal AI platform and multilevel collaborative pattern showed robust diagnostic performance and effective service for cataracts. The context of our AI based medical referral pattern will be extended to other common disease conditions and resource-intensive situations to provide cost-effective health care for an increasing number of patients.

This abstract was presented at the 2019 ARVO Annual Meeting, held in Vancouver, Canada, April 28 - May 2, 2019.

 

The overall training pipeline for the cataract AI agent

The overall training pipeline for the cataract AI agent

 

The novel tertiary healthcare referral system based on the cataract AI agent and comparison with the traditional healthcare system.

The novel tertiary healthcare referral system based on the cataract AI agent and comparison with the traditional healthcare system.

×
×

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.

×