Application of neural network model in assisting device fitting for low vision patients

Bingfa Dai; Yang Yu; Lijuan Huang; Zhiyong Meng; Liang Chen; Hongxia Luo; Ting Chen; Xuelan Chen; Wenwen Ye; Yuyuan Yan; Chi Cai; Jianqing Zheng; Jun Zhao; Liquan Dong; Jianmin Hu

doi:10.21037/atm.2020.02.161

Application of neural network model in assisting device fitting for low vision patients

Ann Transl Med. 2020 Jun;8(11):702. doi: 10.21037/atm.2020.02.161.

Authors

Bingfa Dai^{1

2}, Yang Yu^{1

2}, Lijuan Huang^{1

2}, Zhiyong Meng^{1

2}, Liang Chen³, Hongxia Luo³, Ting Chen^{1

2}, Xuelan Chen^{1

2}, Wenwen Ye^{1

2}, Yuyuan Yan^{1

2}, Chi Cai^{2

4}, Jianqing Zheng^{2

5}, Jun Zhao⁶, Liquan Dong⁷, Jianmin Hu^{1

2}

Affiliations

¹ Department of Ophthalmology, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, China.
² Fujian Province University Engineering Research Center of Assistive Technology for Visual Impairment, Quanzhou, China.
³ Fujian Assistive Devices and Technology Resource Centre for Persons with Disabilities, Fuzhou, China.
⁴ Department of Radiology, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, China.
⁵ Department of Radiation Oncology, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, China.
⁶ Department of Ophthalmology, Shenzhen Eye Hospital Affiliated to Jinan University, Shenzhen, China.
⁷ China Assistive Devices and Technology Centre for Persons with Disabilities, Beijing, China.

Abstract

Background: To explore the application of neural network models in artificial intelligence (AI)-aided devices fitting for low vision patients.

Methods: The data of 836 visually impaired people were collected in southwestern Fujian from May 2014 to May 2017. After a full eye examination, 629 low vision patients were selected from this group. Based on the visual functions, rehabilitation needs, and living quality scores of the selected patients, the professionals chose assistive devices that were the best fit for the patients. The data of these three factors were then subjected to the quantitative analysis, and the results were digitized and labeled. The final datasets were used to train a fully connected deep neural networks to obtain an AI-aided model for assistive device fitting.

Results: In this study, the main causes of low vision in southwestern Fujian were congenital diseases, among which congenital cataract was the most common. During the low vision AI-aided devices fitting, we found that the intermediate distance magnifier was suitable for the largest number of patients. Through quantitative analysis of the research results, it was found that AI-aided devices fitting was closely related to visual function, rehabilitation needs and quality of life. If this complex relationship can be mapped into the neural network model, AI-aided device fitting can be realized. We built a fully connected neural network model for AI-aided device fitting. The input of the model was the characteristic data of low vision patients, and the output was the forecast of suitable devices. When the threshold of the model was 0.4, the accuracy was about 80% and the F1 value was about 0.31. This threshold can be used as the classification judgment threshold of the model.

Conclusions: Low vision AI-aided device fitting is closely related to visual function, rehabilitation needs, and quality of life scores. The neural network model based on full connection can achieve high accuracy in AI-aided devices fitting. It has a great impact on clinical application.

Keywords: Low vision; artificial intelligence-aided assistive device fitting (AI-aided assistive device fitting); neural network model.