A deep learning model incorporating spatial and temporal information successfully detects visual field worsening using a consensus based approach
Abstract Glaucoma is a leading cause of irreversible blindness, and its worsening is most often monitored with visual field (VF) testing. Deep learning models (DLM) may help identify VF worsening consistently and reproducibly. In this study, we developed and investigated the performance of a DLM on...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-01-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-28003-6 |
| _version_ | 1797945971371409408 |
|---|---|
| author | Jasdeep Sabharwal Kaihua Hou Patrick Herbert Chris Bradley Chris A. Johnson Michael Wall Pradeep Y. Ramulu Mathias Unberath Jithin Yohannan |
| author_facet | Jasdeep Sabharwal Kaihua Hou Patrick Herbert Chris Bradley Chris A. Johnson Michael Wall Pradeep Y. Ramulu Mathias Unberath Jithin Yohannan |
| author_sort | Jasdeep Sabharwal |
| collection | DOAJ |
| description | Abstract Glaucoma is a leading cause of irreversible blindness, and its worsening is most often monitored with visual field (VF) testing. Deep learning models (DLM) may help identify VF worsening consistently and reproducibly. In this study, we developed and investigated the performance of a DLM on a large population of glaucoma patients. We included 5099 patients (8705 eyes) seen at one institute from June 1990 to June 2020 that had VF testing as well as clinician assessment of VF worsening. Since there is no gold standard to identify VF worsening, we used a consensus of six commonly used algorithmic methods which include global regressions as well as point-wise change in the VFs. We used the consensus decision as a reference standard to train/test the DLM and evaluate clinician performance. 80%, 10%, and 10% of patients were included in training, validation, and test sets, respectively. Of the 873 eyes in the test set, 309 [60.6%] were from females and the median age was 62.4; (IQR 54.8–68.9). The DLM achieved an AUC of 0.94 (95% CI 0.93–0.99). Even after removing the 6 most recent VFs, providing fewer data points to the model, the DLM successfully identified worsening with an AUC of 0.78 (95% CI 0.72–0.84). Clinician assessment of worsening (based on documentation from the health record at the time of the final VF in each eye) had an AUC of 0.64 (95% CI 0.63–0.66). Both the DLM and clinician performed worse when the initial disease was more severe. This data shows that a DLM trained on a consensus of methods to define worsening successfully identified VF worsening and could help guide clinicians during routine clinical care. |
| first_indexed | 2024-04-10T21:03:29Z |
| format | Article |
| id | doaj.art-bbb482f53cc640029775396b0d50a2d4 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-10T21:03:29Z |
| publishDate | 2023-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-bbb482f53cc640029775396b0d50a2d42023-01-22T12:09:30ZengNature PortfolioScientific Reports2045-23222023-01-011311910.1038/s41598-023-28003-6A deep learning model incorporating spatial and temporal information successfully detects visual field worsening using a consensus based approachJasdeep Sabharwal0Kaihua Hou1Patrick Herbert2Chris Bradley3Chris A. Johnson4Michael Wall5Pradeep Y. Ramulu6Mathias Unberath7Jithin Yohannan8Wilmer Eye Institute, Johns Hopkins University School of MedicineMalone Center for Engineering, Johns Hopkins UniversityMalone Center for Engineering, Johns Hopkins UniversityWilmer Eye Institute, Johns Hopkins University School of MedicineDepartment of Ophthalmology and Visual Sciences, University of IowaDepartment of Ophthalmology and Visual Sciences, University of IowaWilmer Eye Institute, Johns Hopkins University School of MedicineMalone Center for Engineering, Johns Hopkins UniversityWilmer Eye Institute, Johns Hopkins University School of MedicineAbstract Glaucoma is a leading cause of irreversible blindness, and its worsening is most often monitored with visual field (VF) testing. Deep learning models (DLM) may help identify VF worsening consistently and reproducibly. In this study, we developed and investigated the performance of a DLM on a large population of glaucoma patients. We included 5099 patients (8705 eyes) seen at one institute from June 1990 to June 2020 that had VF testing as well as clinician assessment of VF worsening. Since there is no gold standard to identify VF worsening, we used a consensus of six commonly used algorithmic methods which include global regressions as well as point-wise change in the VFs. We used the consensus decision as a reference standard to train/test the DLM and evaluate clinician performance. 80%, 10%, and 10% of patients were included in training, validation, and test sets, respectively. Of the 873 eyes in the test set, 309 [60.6%] were from females and the median age was 62.4; (IQR 54.8–68.9). The DLM achieved an AUC of 0.94 (95% CI 0.93–0.99). Even after removing the 6 most recent VFs, providing fewer data points to the model, the DLM successfully identified worsening with an AUC of 0.78 (95% CI 0.72–0.84). Clinician assessment of worsening (based on documentation from the health record at the time of the final VF in each eye) had an AUC of 0.64 (95% CI 0.63–0.66). Both the DLM and clinician performed worse when the initial disease was more severe. This data shows that a DLM trained on a consensus of methods to define worsening successfully identified VF worsening and could help guide clinicians during routine clinical care.https://doi.org/10.1038/s41598-023-28003-6 |
| spellingShingle | Jasdeep Sabharwal Kaihua Hou Patrick Herbert Chris Bradley Chris A. Johnson Michael Wall Pradeep Y. Ramulu Mathias Unberath Jithin Yohannan A deep learning model incorporating spatial and temporal information successfully detects visual field worsening using a consensus based approach Scientific Reports |
| title | A deep learning model incorporating spatial and temporal information successfully detects visual field worsening using a consensus based approach |
| title_full | A deep learning model incorporating spatial and temporal information successfully detects visual field worsening using a consensus based approach |
| title_fullStr | A deep learning model incorporating spatial and temporal information successfully detects visual field worsening using a consensus based approach |
| title_full_unstemmed | A deep learning model incorporating spatial and temporal information successfully detects visual field worsening using a consensus based approach |
| title_short | A deep learning model incorporating spatial and temporal information successfully detects visual field worsening using a consensus based approach |
| title_sort | deep learning model incorporating spatial and temporal information successfully detects visual field worsening using a consensus based approach |
| url | https://doi.org/10.1038/s41598-023-28003-6 |
| work_keys_str_mv | AT jasdeepsabharwal adeeplearningmodelincorporatingspatialandtemporalinformationsuccessfullydetectsvisualfieldworseningusingaconsensusbasedapproach AT kaihuahou adeeplearningmodelincorporatingspatialandtemporalinformationsuccessfullydetectsvisualfieldworseningusingaconsensusbasedapproach AT patrickherbert adeeplearningmodelincorporatingspatialandtemporalinformationsuccessfullydetectsvisualfieldworseningusingaconsensusbasedapproach AT chrisbradley adeeplearningmodelincorporatingspatialandtemporalinformationsuccessfullydetectsvisualfieldworseningusingaconsensusbasedapproach AT chrisajohnson adeeplearningmodelincorporatingspatialandtemporalinformationsuccessfullydetectsvisualfieldworseningusingaconsensusbasedapproach AT michaelwall adeeplearningmodelincorporatingspatialandtemporalinformationsuccessfullydetectsvisualfieldworseningusingaconsensusbasedapproach AT pradeepyramulu adeeplearningmodelincorporatingspatialandtemporalinformationsuccessfullydetectsvisualfieldworseningusingaconsensusbasedapproach AT mathiasunberath adeeplearningmodelincorporatingspatialandtemporalinformationsuccessfullydetectsvisualfieldworseningusingaconsensusbasedapproach AT jithinyohannan adeeplearningmodelincorporatingspatialandtemporalinformationsuccessfullydetectsvisualfieldworseningusingaconsensusbasedapproach AT jasdeepsabharwal deeplearningmodelincorporatingspatialandtemporalinformationsuccessfullydetectsvisualfieldworseningusingaconsensusbasedapproach AT kaihuahou deeplearningmodelincorporatingspatialandtemporalinformationsuccessfullydetectsvisualfieldworseningusingaconsensusbasedapproach AT patrickherbert deeplearningmodelincorporatingspatialandtemporalinformationsuccessfullydetectsvisualfieldworseningusingaconsensusbasedapproach AT chrisbradley deeplearningmodelincorporatingspatialandtemporalinformationsuccessfullydetectsvisualfieldworseningusingaconsensusbasedapproach AT chrisajohnson deeplearningmodelincorporatingspatialandtemporalinformationsuccessfullydetectsvisualfieldworseningusingaconsensusbasedapproach AT michaelwall deeplearningmodelincorporatingspatialandtemporalinformationsuccessfullydetectsvisualfieldworseningusingaconsensusbasedapproach AT pradeepyramulu deeplearningmodelincorporatingspatialandtemporalinformationsuccessfullydetectsvisualfieldworseningusingaconsensusbasedapproach AT mathiasunberath deeplearningmodelincorporatingspatialandtemporalinformationsuccessfullydetectsvisualfieldworseningusingaconsensusbasedapproach AT jithinyohannan deeplearningmodelincorporatingspatialandtemporalinformationsuccessfullydetectsvisualfieldworseningusingaconsensusbasedapproach |