Video-based eye tracking performance for computer-assisted diagnostic support of diabetic neuropathy
作者：
Highlights：
• A computer-assisted diagnosis method of diabetic neuropathy is presented.
• The method is based on tracking of eye trajectories while the patient follows a target on screen.
• Eye tracking dynamics captured via heteroscedastic ARX models on control and diabetic individuals.
• 11 control and 20 diabetic individuals with complications including neuropathy used in the study.
• The method can detect with high accuracy differences between control and diabetic populations.
摘要
•A computer-assisted diagnosis method of diabetic neuropathy is presented.•The method is based on tracking of eye trajectories while the patient follows a target on screen.•Eye tracking dynamics captured via heteroscedastic ARX models on control and diabetic individuals.•11 control and 20 diabetic individuals with complications including neuropathy used in the study.•The method can detect with high accuracy differences between control and diabetic populations.
论文关键词：Video-based eye tracking,Diabetic neuropathy,Computer-assisted diagnosis,Heteroscedastic ARX (H-ARX) models
论文评审过程：Received 27 January 2020, Revised 16 February 2021, Accepted 21 February 2021, Available online 5 March 2021, Version of Record 12 March 2021.
论文官网地址：https://doi.org/10.1016/j.artmed.2021.102050
