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.

Clinical longitudinal evaluation of COVID-19 patients and prediction of organ-specific recovery using artificial intelligence.

Within COVID-19 there is an urgent unmet need to predict at the time of hospital admission which COVID-19 patients will recover from the disease, and how fast they recover to deliver personalized treatments and to properly allocate hospital resources so that healthcare systems do not become overwhelmed. To this end, we have combined clinically salient CT imaging data synergistically with laboratory testing data in an integrative machine learning model to predict organ-specific recovery of patients from COVID-19. We trained and validated our model in 285 patients on each separate major organ system impacted by COVID-19 including the renal, pulmonary, immune, cardiac, and hepatic systems. To greatly enhance the speed and utility of our model, we applied an artificial intelligence method to segment and classify regions on CT imaging, from which interpretable data could be directly fed into the predictive machine learning model for overall recovery. Across all organ systems we achieved validation set area under the receiver operator characteristic curve (AUC) values for organ-specific recovery ranging from 0.80 to 0.89, and significant overall recovery prediction in Kaplan-Meier analyses. This demonstrates that the synergistic use of an artificial intelligence (AI) framework applied to CT lung imaging and a machine learning model that integrates laboratory test data with imaging data can accurately predict the overall recovery of COVID-19 patients from baseline characteristics.

EyeHealer: A large-scale anterior eye segment dataset with eye structure and lesion annotations.

Anterior segment eye diseases account for a significant proportion of presentations to eye clinics worldwide, including diseases associated with corneal pathologies, anterior chamber abnormalities (e.g. blood or inflammation), and lens diseases. The construction of an automatic tool for segmentation of anterior segment eye lesions would greatly improve the efficiency of clinical care. With research on artificial intelligence progressing in recent years, deep learning models have shown their superiority in image classification and segmentation. The training and evaluation of deep learning models should be based on a large amount of data annotated with expertise; however, such data are relatively scarce in the domain of medicine. Herein, the authors developed a new medical image annotation system, called EyeHealer. It is a large-scale anterior eye segment dataset with both eye structures and lesions annotated at the pixel level. Comprehensive experiments were conducted to verify its performance in disease classification and eye lesion segmentation. The results showed that semantic segmentation models outperformed medical segmentation models. This paper describes the establishment of the system for automated classification and segmentation tasks. The dataset will be made publicly available to encourage future research in this area.

The SARS-CoV-2 spike L452R-E484Q variant in the Indian B.1.617 strain showed significant reduction in the neutralization activity of immune sera.

To assess the impact of the key non-synonymous amino acid substitutions in the RBD of the spike protein of SARS-CoV-2 variant B.1.617.1 (dominant variant identified in the current India outbreak) on the infectivity and neutralization activities of the immune sera, L452R and E484Q (L452R-E484Q variant), pseudotyped virus was constructed (with the D614G background). The impact on binding with the neutralizing antibodies was also assessed with an ELISA assay. Pseudotyped virus carrying a L452R-E484Q variant showed a comparable infectivity compared with D614G. However, there was a significant reduction in the neutralization activity of the immune sera from non-human primates vaccinated with a recombinant receptor binding domain (RBD) protein, convalescent patients, and healthy vaccinees vaccinated with an mRNA vaccine. In addition, there was a reduction in binding of L452R-E484Q-D614G protein to the antibodies of the immune sera from vaccinated non-human primates. These results highlight the interplay between infectivity and other biologic factors involved in the natural evolution of SARS-CoV-2. Reduced neutralization activities against the L452R-E484Q variant will have an impact on health authority planning and implications for the vaccination strategy/new vaccine development.

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.

Mutation spectrum in GNAQ and GNA11 in Chinese uveal melanoma.

Uveal melanoma is the most common intraocular cancer in the adult eye. R183 and Q209 were found to be mutational hotspots in exon 4 and exon 5 of GNAQ and GNA11 in Caucasians. However, only a few studies have reported somatic mutations in GNAQ or GNA11 in uveal melanoma in Chinese. We extracted somatic DNA from paraffin-embedded biopsies of 63 Chinese uveal melanoma samples and sequenced the entire coding regions of exons 4 and 5 in GNAQ and GNA11. The results showed that 33% of Chinese uveal melanoma samples carried Q209 mutations while none had R183 mutation in GNAQ or GNA11. In addition, seven novel missense somatic mutations in GNAQ (Y192C, F194L, P170S, D236N, L232F, V230A, and M227I) and four novel missense somatic mutations in GNA11 (R166C, I200T, S225F, and V206M) were found in our study. The high mutation frequency of Q209 and the novel missense mutations detected in this study suggest that GNAQ and GNA11 are common targets for somatic mutations in Chinese uveal melanoma.

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.

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.