Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning.

The implementation of clinical-decision support algorithms for medical imaging faces challenges with reliability and interpretability. Here, we establish a diagnostic tool based on a deep-learning framework for the screening of patients with common treatable blinding retinal diseases. Our framework utilizes transfer learning, which trains a neural network with a fraction of the data of conventional approaches. Applying this approach to a dataset of optical coherence tomography images, we demonstrate performance comparable to that of human experts in classifying age-related macular degeneration and diabetic macular edema. We also provide a more transparent and interpretable diagnosis by highlighting the regions recognized by the neural network. We further demonstrate the general applicability of our AI system for diagnosis of pediatric pneumonia using chest X-ray images. This tool may ultimately aid in expediting the diagnosis and referral of these treatable conditions, thereby facilitating earlier treatment, resulting in improved clinical outcomes. VIDEO ABSTRACT.

Deep-learning models for the detection and incidence prediction of chronic kidney disease and type 2 diabetes from retinal fundus images.

Regular screening for the early detection of common chronic diseases might benefit from the use of deep-learning approaches, particularly in resource-poor or remote settings. Here we show that deep-learning models can be used to identify chronic kidney disease and type 2 diabetes solely from fundus images or in combination with clinical metadata (age, sex, height, weight, body-mass index and blood pressure) with areas under the receiver operating characteristic curve of 0.85-0.93. The models were trained and validated with a total of 115,344 retinal fundus photographs from 57,672 patients and can also be used to predict estimated glomerulal filtration rates and blood-glucose levels, with mean absolute errors of 11.1-13.4 ml min-1 per 1.73 m2 and 0.65-1.1 mmol l-1, and to stratify patients according to disease-progression risk. We evaluated the generalizability of the models for the identification of chronic kidney disease and type 2 diabetes with population-based external validation cohorts and via a prospective study with fundus images captured with smartphones, and assessed the feasibility of predicting disease progression in a longitudinal cohort.

The effects of temporary intraocular pressure spikes after intravitreal dexamethasone implantation on the retinal nerve fiber layer.

Background and objective: The dexamethasone (DEX) implant is known to cause temporary intraocular pressure (IOP) spikes after implantation. The purpose of this study is to determine if IOP spikes after DEX implant cause significant thinning in the retinal nerve fiber layer (RNFL). Study design, patients, and methods: A total of 306 charts were reviewed with 48 and 21 patients meeting inclusion criteria for the cross-sectional and prospective groups, respectively. Cross-sectional inclusion criteria: IOP spike ≥22 mmHg up to 16 weeks after DEX implant, DEX implant in only 1 eye per patient, and spectral-domain optical coherence tomography (OCT) RNFL imaging of both eyes ≥3 months after IOP spike. Prospective inclusion criteria: OCT RNFL performed within 1 year prior to DEX implantation, IOP spike ≥22 mmHg up to 16 weeks after DEX implant, and OCT RNFL performed ≥3 months after IOP spike. The average RNFL thickness in the contralateral eye was used as the control in the cross-sectional group. Institutional review board approval was obtained. Results: In the cross-sectional group, there was no statistically significant difference in the mean RNFL thicknesses in the treated vs untreated eyes (80.4±15.5 µm and 82.6±15.8 µm, respectively; P=0.33) regardless of treatment diagnosis, magnitude of IOP spike, or history of glaucoma. In the prospective group, mean RNFL thicknesses before and after IOP spikes ≥22 mmHg were similar (78.0±14.8 µm and 75.6±13.6 µm, respectively; P=0.13). Conclusion and relevance: Temporary elevation of IOP after DEX implantation when treated with topical IOP lowering drops does not appear to lead to a meaningful change in RNFL thickness.

Evaluation and accurate diagnoses of pediatric diseases using artificial intelligence.

Artificial intelligence (AI)-based methods have emerged as powerful tools to transform medical care. Although machine learning classifiers (MLCs) have already demonstrated strong performance in image-based diagnoses, analysis of diverse and massive electronic health record (EHR) data remains challenging. Here, we show that MLCs can query EHRs in a manner similar to the hypothetico-deductive reasoning used by physicians and unearth associations that previous statistical methods have not found. Our model applies an automated natural language processing system using deep learning techniques to extract clinically relevant information from EHRs. In total, 101.6 million data points from 1,362,559 pediatric patient visits presenting to a major referral center were analyzed to train and validate the framework. Our model demonstrates high diagnostic accuracy across multiple organ systems and is comparable to experienced pediatricians in diagnosing common childhood diseases. Our study provides a proof of concept for implementing an AI-based system as a means to aid physicians in tackling large amounts of data, augmenting diagnostic evaluations, and to provide clinical decision support in cases of diagnostic uncertainty or complexity. Although this impact may be most evident in areas where healthcare providers are in relative shortage, the benefits of such an AI system are likely to be universal.

Appointment Compliance in Patients With Diabetic Macular Edema and Exudative Macular Degeneration.

BACKGROUND AND OBJECTIVE: The purpose of this study is to compare cancellation and no-show rates in patients with diabetic macular edema (DME) and exudative macular degeneration (wet AMD). PATIENTS AND METHODS: An anonymous survey was sent to 1,726 retina specialists inquiring as to the number of appointments their patients with DME and wet AMD attended, cancelled, or did not show up for in 2014 and 2015. RESULTS: Data were obtained on 109,599 appointments. Patients with DME in the U.S. had a 1.591-times increased odds of cancelling or no-showing to their appointments than patients with wet AMD (P < .0001). Patients with DME in Europe had a 1.918-times increased odds of cancelling or no showing to their appointments than patients with wet AMD (P < .0001). CONCLUSION: Patients with DME in the U.S. and Europe cancelled and no-showed to their appointments significantly more often than patients with wet AMD. These findings can be taken into consideration when establishing treatment plans for patients with DME. [Ophthalmic Surg Lasers Imaging Retina. 2018;49:186-190.].

Clinical applications of retinal gene therapies.

Retinal degenerative diseases are a major cause of blindness. Retinal gene therapy is a trail-blazer in the human gene therapy field, leading to the first FDA approved gene therapy product for a human genetic disease. The application of Clustered Regularly Interspaced Short Palindromic Repeat/Cas9 (CRISPR/Cas9)-mediated gene editing technology is transforming the delivery of gene therapy. We review the history, present, and future prospects of retinal gene therapy.

Diabetic macular edema: it is more than just VEGF.

Diabetic macular edema is a serious visual complication of diabetic retinopathy. This article reviews the history of previous and current therapies, including laser therapy, anti-vascular endothelial growth factor agents, and corticosteroids, that have been used to treat this condition. In addition, it proposes new ways to use them in combination in order to decrease treatment burden and potentially address other causes besides vascular endothelial growth factor for diabetic macular edema.