Lee Te-Won

Racette Lyne, Chiou Christine Y, Hao Jiucang, Bowd Christopher, Goldbaum Michael H, Zangwill Linda M et al.

Combining optic disc topography (HRT) and visual field (SWAP) data improved glaucoma diagnostic accuracy using machine learning (RVM), outperforming individual tests. This suggests better glaucoma detection.

Bowd Christopher, Hao Jiucang, Tavares Ivan M, Medeiros Felipe A, Zangwill Linda M, Lee Te-Won et al.

Combining OCT and SAP with machine learning slightly improved glaucoma diagnosis over using either alone, offering a more robust diagnostic approach.

Goldbaum Michael H, Sample Pamela A, Zhang Zuohua, Chan Kwokleung, Hao Jiucang, Lee Te-Won et al.

Unsupervised learning identified two visual field clusters (normal/glaucoma), with six independent axes in glaucoma. This method effectively captures clinically meaningful defect patterns and severity, aiding glaucoma diagnosis and monitoring.

Sample Pamela A, Boden Catherine, Zhang Zuohua, Pascual John, Lee Te-Won, Zangwill Linda M et al.

Unsupervised machine learning identified glaucoma progression patterns more effectively than standard methods, potentially improving early detection and monitoring of visual field loss.

Bowd Christopher, Medeiros Felipe A, Zhang Zuohua, Zangwill Linda M, Hao Jiucang, Lee Te-Won et al.

Machine learning (RVM/SVM) analysis of SLP RNFL data accurately classified glaucoma, outperforming standard parameters. This shows promise for improved glaucoma diagnosis.

Zangwill Linda M, Chan Kwokleung, Bowd Christopher, Hao Jicuang, Lee Te-Won, Weinreb Robert N et al.

HRT disc margin measurements, especially inferior sectors, detected early/moderate glaucoma better than parapapillary measurements using machine learning, offering improved diagnostic accuracy.

Sample Pamela A, Chan Kwokleung, Boden Catherine, Lee Te-Won, Blumenthal Eytan Z, Weinreb Robert N et al.

Unsupervised machine learning identified four distinct glaucoma visual field patterns and one normal pattern, mirroring patterns recognized by clinical experience, offering an objective classification method.

Bowd Christopher, Zangwill Linda M, Medeiros Felipe A, Hao Jiucang, Chan Kwokleung, Lee Te-Won et al.

This study found that HRT analysis (especially SVM) and stereophotographs predict visual field loss in glaucoma suspects, emphasizing optic disc examination for early diagnosis.

Bowd Christopher, Chan Kwokleung, Zangwill Linda M, Goldbaum Michael H, Lee Te-Won, Sejnowski Terrence J et al.

Neural networks using HRT optic disc parameters better discriminate glaucoma from healthy eyes than traditional methods, showing promise for improving glaucoma diagnostic accuracy.

Sample Pamela A, Goldbaum Michael H, Chan Kwokleung, Boden Catherine, Lee Te-Won, Vasile Christiana et al.

Machine learning classifiers predicted glaucomatous visual field changes in ocular hypertensive eyes nearly four years earlier than traditional methods, offering potential for earlier glaucoma diagnosis and intervention.

Goldbaum Michael H, Sample Pamela A, Chan Kwokleung, Williams Julia, Lee Te-Won, Blumenthal Eytan et al.

Machine learning (MoG) classified glaucoma from visual fields better than standard indices and experts. This suggests ML can improve glaucoma diagnosis from perimetry.