Convex Representations Using Deep Archetypal Analysis for Predicting Glaucoma
Goal: The purpose of this study was to identify clinically relevant patterns of glaucomatous vision loss through convex representation to predict glaucoma several years prior to disease onset. Methods: We developed a deep archetypal analysis to identify patterns of glaucomatous vision loss, and then...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Journal of Translational Engineering in Health and Medicine |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9102996/ |
| _version_ | 1818410558763827200 |
|---|---|
| author | Anshul Thakur Michael Goldbaum Siamak Yousefi |
| author_facet | Anshul Thakur Michael Goldbaum Siamak Yousefi |
| author_sort | Anshul Thakur |
| collection | DOAJ |
| description | Goal: The purpose of this study was to identify clinically relevant patterns of glaucomatous vision loss through convex representation to predict glaucoma several years prior to disease onset. Methods: We developed a deep archetypal analysis to identify patterns of glaucomatous vision loss, and then projected visual fields over the identified patterns. Projections provided a representation that was more accurate in detecting glaucomatous vision loss, thus, more appropriate for recognizing preclinical signs of glaucoma prior to disease development. To overcome the class imbalance in prediction, we implemented a class-balanced bagging with neural networks. Results: Using original visual field as features of the class-balanced bagging classification provided an area under the receiver-operating characteristic curve (AUC) of 0.55 for predicting glaucoma approximately four years prior to disease development. Using convex representation of the visual fields as input features provided an AUC of 0.61 while using deep convex representation as input features improved the AUC to 0.71. Relevance vector machine (RVM) achieved an AUC of 0.64. Conclusion: Deep archetypal analysis representation of visual functional features with balanced bagging classification could serve as an automated tool for predicting glaucoma. Significance: Glaucoma is the second leading cause of worldwide blindness. Most people with glaucoma have no early symptoms or pain, delaying diagnosis in many patients until they reach late irreversible vision loss stages. In fact, about 50% of people with glaucoma are unaware they have the disease. Deep archetypal analysis models may impact clinical practice in effectively identifying at-risk glaucoma patients well prior to disease development. |
| first_indexed | 2024-12-14T10:17:26Z |
| format | Article |
| id | doaj.art-909d86b140ef4da49fbcb5ec8a9bdfb3 |
| institution | Directory Open Access Journal |
| issn | 2168-2372 |
| language | English |
| last_indexed | 2024-12-14T10:17:26Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Translational Engineering in Health and Medicine |
| spelling | doaj.art-909d86b140ef4da49fbcb5ec8a9bdfb32022-12-21T23:06:45ZengIEEEIEEE Journal of Translational Engineering in Health and Medicine2168-23722020-01-0181710.1109/JTEHM.2020.29821509102996Convex Representations Using Deep Archetypal Analysis for Predicting GlaucomaAnshul Thakur0Michael Goldbaum1Siamak Yousefi2School of Computing and Electrical Engineering, Indian Institute of Technology Mandi, Mandi, IndiaDepartment of Ophthalmology, University of California San Diego, San Diego, CA, USADepartment of Ophthalmology, The University of Tennessee Health Science Center, Memphis, TN, USAGoal: The purpose of this study was to identify clinically relevant patterns of glaucomatous vision loss through convex representation to predict glaucoma several years prior to disease onset. Methods: We developed a deep archetypal analysis to identify patterns of glaucomatous vision loss, and then projected visual fields over the identified patterns. Projections provided a representation that was more accurate in detecting glaucomatous vision loss, thus, more appropriate for recognizing preclinical signs of glaucoma prior to disease development. To overcome the class imbalance in prediction, we implemented a class-balanced bagging with neural networks. Results: Using original visual field as features of the class-balanced bagging classification provided an area under the receiver-operating characteristic curve (AUC) of 0.55 for predicting glaucoma approximately four years prior to disease development. Using convex representation of the visual fields as input features provided an AUC of 0.61 while using deep convex representation as input features improved the AUC to 0.71. Relevance vector machine (RVM) achieved an AUC of 0.64. Conclusion: Deep archetypal analysis representation of visual functional features with balanced bagging classification could serve as an automated tool for predicting glaucoma. Significance: Glaucoma is the second leading cause of worldwide blindness. Most people with glaucoma have no early symptoms or pain, delaying diagnosis in many patients until they reach late irreversible vision loss stages. In fact, about 50% of people with glaucoma are unaware they have the disease. Deep archetypal analysis models may impact clinical practice in effectively identifying at-risk glaucoma patients well prior to disease development.https://ieeexplore.ieee.org/document/9102996/Glaucoma predictionarchetypal analysisdeep archetypal analysisartificial intelligencemachine learning |
| spellingShingle | Anshul Thakur Michael Goldbaum Siamak Yousefi Convex Representations Using Deep Archetypal Analysis for Predicting Glaucoma IEEE Journal of Translational Engineering in Health and Medicine Glaucoma prediction archetypal analysis deep archetypal analysis artificial intelligence machine learning |
| title | Convex Representations Using Deep Archetypal Analysis for Predicting Glaucoma |
| title_full | Convex Representations Using Deep Archetypal Analysis for Predicting Glaucoma |
| title_fullStr | Convex Representations Using Deep Archetypal Analysis for Predicting Glaucoma |
| title_full_unstemmed | Convex Representations Using Deep Archetypal Analysis for Predicting Glaucoma |
| title_short | Convex Representations Using Deep Archetypal Analysis for Predicting Glaucoma |
| title_sort | convex representations using deep archetypal analysis for predicting glaucoma |
| topic | Glaucoma prediction archetypal analysis deep archetypal analysis artificial intelligence machine learning |
| url | https://ieeexplore.ieee.org/document/9102996/ |
| work_keys_str_mv | AT anshulthakur convexrepresentationsusingdeeparchetypalanalysisforpredictingglaucoma AT michaelgoldbaum convexrepresentationsusingdeeparchetypalanalysisforpredictingglaucoma AT siamakyousefi convexrepresentationsusingdeeparchetypalanalysisforpredictingglaucoma |