Frontiers of Data and Computing ›› 2024, Vol. 6 ›› Issue (2): 117-133.

CSTR: 32002.14.jfdc.CN10-1649/TP.2024.02.011

doi: 10.11871/jfdc.issn.2096-742X.2024.02.011

• Technology and Application • Previous Articles     Next Articles

Application of Machine Learning Technology in the Field of Eye Health

YE Xu1(),DU Yi1,CUI Wenjuan1,SHEN Junjie2,XIE Jing2,WANG Ludi1,*()   

  1. 1. Computer Network Information Center, Chinese Academy of Sciences, Beijing 100083, China
    2. Changsha Aier Eye Hospital, Changsha, Hunan 410015, China
  • Received:2023-04-06 Online:2024-04-20 Published:2024-04-26


[Background] With the explosive growth of data, continuous improvement of algorithms, and rapid development of computing power, machine learning has been widely used in education, finance, manufacturing, and medical fields. In the field of eye health, machine learning has also achieved preliminary applications in many tasks such as disease diagnosis, disease grading, medical examination, and early screening of diseases. [Methods] Based on the investigation of relevant domestic and foreign literature in the field of eye health, this paper sorts out and analyzes the application of the field from four different dimensions of ophthalmic disease category, treatment stage, data type, and technology type, and makes corresponding prospects for the next research. [Results] Based on the results of research and analysis, it can be seen that in the field of eye health, machine learning technology mainly uses image data, focusing on disease diagnosis and grading. At the same time, it has also achieved good performance in tasks such as early disease screening and disease risk prediction that are in the early stages of disease development. [Conclusion] By applying machine learning technology to all stages of the ophthalmology diagnosis and treatment process, it is expected to reduce the burden on ophthalmologists, improve the work efficiency of ophthalmologists, help control the development of patients' diseases, improve the quality of life of the patients, and reduce the economic and time costs of patient treatment.

Key words: eye health, machine learning, big data