The Experts below are selected from a list of 10692 Experts worldwide ranked by ideXlab platform
Kenghung Lin - One of the best experts on this subject based on the ideXlab platform.
-
epiretinal membrane detection at the Ophthalmologist level using deep learning of optical coherence tomography
Scientific Reports, 2020Co-Authors: Kenghung Lin, Henry Bair, Wayne Hueyherng Sheu, Chisen Chang, Yingcheng Shen, Chelun HungAbstract:Purpose: Previous deep learning studies on optical coherence tomography (OCT) mainly focused on diabetic retinopathy and age-related macular degeneration. We proposed a deep learning model that can identify epiretinal membrane (ERM) in OCT with Ophthalmologist-level performance. Design: Cross-sectional study. Participants: A total of 3,618 central fovea cross section OCT images from 1,475 eyes of 964 patients. Methods: We retrospectively collected 7,652 OCT images from 1,197 patients. From these images, 2,171 were normal and 1,447 were ERM OCT. A total of 3,141 OCT images was used as training dataset and 477 images as testing dataset. DL algorithm was used to train the interpretation model. Diagnostic results by four board-certified non-retinal specialized Ophthalmologists on the testing dataset were compared with those generated by the DL model. Main Outcome Measures: We calculated for the derived DL model the following characteristics: sensitivity, specificity, F1 score and area under curve (AUC) of the receiver operating characteristic (ROC) curve. These were calculated according to the gold standard results which were parallel diagnoses of the retinal specialist. Performance of the DL model was finally compared with that of non-retinal specialized Ophthalmologists. Results: Regarding the diagnosis of ERM in OCT images, the trained DL model had the following characteristics in performance: sensitivity: 98.7%, specificity: 98.0%, and F1 score: 0.945. The accuracy on the training dataset was 99.7% (95% CI: 99.4 - 99.9%), and for the testing dataset, diagnostic accuracy was 98.1% (95% CI: 96.5 - 99.1%). AUC of the ROC curve was 0.999. The DL model slightly outperformed the average non-retinal specialized Ophthalmologists. Conclusions: An Ophthalmologist-level DL model was built here to accurately identify ERM in OCT images. The performance of the model was slightly better than the average non-retinal specialized Ophthalmologists. The derived model may play a role to assist clinicians to promote the efficiency and safety of healthcare in the future.
Marie Lynn Miranda - One of the best experts on this subject based on the ideXlab platform.
-
access to Ophthalmologists in states where optometrists have expanded scope of practice
JAMA Ophthalmology, 2018Co-Authors: Joshua D Stein, Christopher A Andrews, Kapil G Kapoor, Joshua Tootoo, Alan L Wagner, Marie Lynn MirandaAbstract:Importance As the United States considers how to best structure its health care services, specialty care availability is receiving increased focus. This study assesses whether patients lack reasonable access to Ophthalmologists in states where optometrists have been granted expanded scope of practice. Objective To determine the estimated travel time (ETT) to the nearest Ophthalmologist office for persons residing in states that have expanded scope of practice for optometrists, and to quantify ETT to the nearest Ophthalmologist for Medicare beneficiaries who received surgical care from optometrists in those states between 2008 and 2014. Design, Setting, and Participants This study used data from the 2010 US census, a 2016 American Academy of Ophthalmology member database, and a data set of claims data for a random sample of 20% of beneficiaries enrolled in Medicare nationwide from 2008 to 2014 (n=14 063 725). Combining these sources with geographic information systems analysis, the ETT to the nearest Ophthalmologist office was calculated for every resident of Kentucky, Oklahoma, and New Mexico. This study also assessed ETT to the nearest Ophthalmologist for Medicare beneficiaries in those states who had received surgery from an optometrist from 2008 to 2014. Data analyses were conducted from July 2016 to July 2017. Main Outcomes and Measures The proportion of residents of Kentucky, Oklahoma, and New Mexico who live within an ETT of 10, 30, 45, 60, or 90 minutes of the nearest Ophthalmologist office. Results The study included 4 339 367 Kentucky residents, 3 751 351 Oklahoma residents, and 2 059 179 New Mexico residents. Of these, 5 140 547 (50.6%) were female. Racial/ethnic composition included 7 154 847 people (70.5%) who were white, 640 608 (6.3%) who were black, and 1 418 246 (14.0%) who were Hispanic. The mean (SD) age was 37.8 (22.8) years. More than 75% of residents in the 3 states lived within an ETT of 30 minutes to the nearest ophthalmology office, and 94% to 99% of residents lived within an ETT of 60 minutes to the nearest ophthalmology office. Among Medicare beneficiaries who received surgery by optometrists, 58.3%, 51.1%, and 46.9% in Kentucky, Oklahoma, and New Mexico, respectively, lived within an ETT of 30 minutes from the nearest Ophthalmologist office. Conclusions and Relevance In the states where optometrists have expanded scope of practice, most residents lived within an ETT of 30 minutes of the nearest Ophthalmologist office, as do half of Medicare beneficiaries who received surgical care from optometrists. These results can help inform policy makers when weighing the pros and cons of scope of practice expansion for optometrists.
Daniel S W Ting - One of the best experts on this subject based on the ideXlab platform.
-
interpretation of artificial intelligence studies for the Ophthalmologist
Current Opinion in Ophthalmology, 2020Co-Authors: Tienen Tan, Zhaoran Wang, Yong Liu, Daniel S W TingAbstract:Purpose of review The use of artificial intelligence (AI) in ophthalmology has increased dramatically. However, interpretation of these studies can be a daunting prospect for the Ophthalmologist without a background in computer or data science. This review aims to share some practical considerations for interpretation of AI studies in ophthalmology. Recent findings It can be easy to get lost in the technical details of studies involving AI. Nevertheless, it is important for clinicians to remember that the fundamental questions in interpreting these studies remain unchanged - What does this study show, and how does this affect my patients? Being guided by familiar principles like study purpose, impact, validity, and generalizability, these studies become more accessible to the Ophthalmologist. Although it may not be necessary for nondomain experts to understand the exact AI technical details, we explain some broad concepts in relation to AI technical architecture and dataset management. Summary The expansion of AI into healthcare and ophthalmology is here to stay. AI systems have made the transition from bench to bedside, and are already being applied to patient care. In this context, 'AI education' is crucial for Ophthalmologists to be confident in interpretation and translation of new developments in this field to their own clinical practice.
Chelun Hung - One of the best experts on this subject based on the ideXlab platform.
-
epiretinal membrane detection at the Ophthalmologist level using deep learning of optical coherence tomography
Scientific Reports, 2020Co-Authors: Kenghung Lin, Henry Bair, Wayne Hueyherng Sheu, Chisen Chang, Yingcheng Shen, Chelun HungAbstract:Purpose: Previous deep learning studies on optical coherence tomography (OCT) mainly focused on diabetic retinopathy and age-related macular degeneration. We proposed a deep learning model that can identify epiretinal membrane (ERM) in OCT with Ophthalmologist-level performance. Design: Cross-sectional study. Participants: A total of 3,618 central fovea cross section OCT images from 1,475 eyes of 964 patients. Methods: We retrospectively collected 7,652 OCT images from 1,197 patients. From these images, 2,171 were normal and 1,447 were ERM OCT. A total of 3,141 OCT images was used as training dataset and 477 images as testing dataset. DL algorithm was used to train the interpretation model. Diagnostic results by four board-certified non-retinal specialized Ophthalmologists on the testing dataset were compared with those generated by the DL model. Main Outcome Measures: We calculated for the derived DL model the following characteristics: sensitivity, specificity, F1 score and area under curve (AUC) of the receiver operating characteristic (ROC) curve. These were calculated according to the gold standard results which were parallel diagnoses of the retinal specialist. Performance of the DL model was finally compared with that of non-retinal specialized Ophthalmologists. Results: Regarding the diagnosis of ERM in OCT images, the trained DL model had the following characteristics in performance: sensitivity: 98.7%, specificity: 98.0%, and F1 score: 0.945. The accuracy on the training dataset was 99.7% (95% CI: 99.4 - 99.9%), and for the testing dataset, diagnostic accuracy was 98.1% (95% CI: 96.5 - 99.1%). AUC of the ROC curve was 0.999. The DL model slightly outperformed the average non-retinal specialized Ophthalmologists. Conclusions: An Ophthalmologist-level DL model was built here to accurately identify ERM in OCT images. The performance of the model was slightly better than the average non-retinal specialized Ophthalmologists. The derived model may play a role to assist clinicians to promote the efficiency and safety of healthcare in the future.
Madeleine Zetterberg - One of the best experts on this subject based on the ideXlab platform.
-
amaurosis fugax delay between symptoms and surgery by specialty
Clinical Ophthalmology, 2016Co-Authors: Pia Kvickström, Bertil Lindblom, Göran Bergström, Madeleine ZetterbergAbstract:PURPOSE To describe the time course of management of patients with amaurosis fugax and analyze differences in management by different specialties. METHODS Patients diagnosed with amaurosis fugax and subjected to carotid ultrasound in 2004-2010 at the Sahlgrenska University Hospital, Gothenburg, Sweden (n=302) were included in this retrospective cohort study, and data were collected from medical records. RESULTS The prevalence of significant carotid stenosis was 18.9%, and 14.2% were subjected to carotid endarterectomy. A trend of longer delay for surgery was noted for patients first consulting a general practitioner (P=0.069) as compared to hospital-based specialties. For 46.3% of the patients, an Ophthalmologist was their first medical contact. No significant difference in time interval to endarterectomy was seen between Ophthalmologists and neurologists/internists. Only 31.8% of the patients with significant carotid stenosis had carotid endarterectomy within 2 weeks from the debut of symptoms, and this proportion was smaller for patients residing outside the Gothenburg city area (P=0.038). CONCLUSION Initially consulting an Ophthalmologist does not delay the time to ultrasound or carotid endarterectomy. The overall time from symptoms to surgery is longer than recommended for a majority of the patients, especially for patients from rural areas and for patients initially consulting a general practitioner.
