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.

Accurate prediction of myopic progression and high myopia by machine learning.

Background: Myopia is a leading cause of visual impairment in Asia and worldwide. However, accurately predicting the progression of myopia and the high risk of myopia remains a challenge. This study aims to develop a predictive model for the development of myopia. Methods: We first retrospectively gathered 612 530 medical records from five independent cohorts, encompassing 227 543 patients ranging from infants to young adults. Subsequently, we developed a multivariate linear regression algorithm model to predict the progression of myopia and the risk of high myopia. Result: The model to predict the progression of myopia achieved an R2 value of 0.964 vs a mean absolute error (MAE) of 0.119D [95% confidence interval (CI): 0.119, 1.146] in the internal validation set. It demonstrated strong generalizability, maintaining consistent performance across external validation sets: R2 = 0.950 vs MAE = 0.119D (95% CI: 0.119, 1.136) in validation study 1, R2 = 0.950 vs MAE = 0.121D (95% CI: 0.121, 1.144) in validation study 2, and R2 = 0.806 vs MAE = -0.066D (95% CI: -0.066, 0.569) in the Shanghai Children Myopia Study. In the Beijing Children Eye Study, the model achieved an R2 of 0.749 vs a MAE of 0.178D (95% CI: 0.178, 1.557). The model to predict the risk of high myopia achieved an area under the curve (AUC) of 0.99 in the internal validation set and consistently high area under the curve values of 0.99, 0.99, 0.96 and 0.99 in the respective external validation sets. Conclusion: Our study demonstrates accurate prediction of myopia progression and risk of high myopia providing valuable insights for tailoring strategies to personalize and optimize the clinical management of myopia in children.

A deep-learning pipeline for the diagnosis and discrimination of viral, non-viral and COVID-19 pneumonia from chest X-ray images.

Common lung diseases are first diagnosed using chest X-rays. Here, we show that a fully automated deep-learning pipeline for the standardization of chest X-ray images, for the visualization of lesions and for disease diagnosis can identify viral pneumonia caused by coronavirus disease 2019 (COVID-19) and assess its severity, and can also discriminate between viral pneumonia caused by COVID-19 and other types of pneumonia. The deep-learning system was developed using a heterogeneous multicentre dataset of 145,202 images, and tested retrospectively and prospectively with thousands of additional images across four patient cohorts and multiple countries. The system generalized across settings, discriminating between viral pneumonia, other types of pneumonia and the absence of disease with areas under the receiver operating characteristic curve (AUCs) of 0.94-0.98; between severe and non-severe COVID-19 with an AUC of 0.87; and between COVID-19 pneumonia and other viral or non-viral pneumonia with AUCs of 0.87-0.97. In an independent set of 440 chest X-rays, the system performed comparably to senior radiologists and improved the performance of junior radiologists. Automated deep-learning systems for the assessment of pneumonia could facilitate early intervention and provide support for clinical decision-making.

DNA methylation markers in the diagnosis and prognosis of common leukemias.

The ability to identify a specific type of leukemia using minimally invasive biopsies holds great promise to improve the diagnosis, treatment selection, and prognosis prediction of patients. Using genome-wide methylation profiling and machine learning methods, we investigated the utility of CpG methylation status to differentiate blood from patients with acute lymphocytic leukemia (ALL) or acute myelogenous leukemia (AML) from normal blood. We established a CpG methylation panel that can distinguish ALL and AML blood from normal blood as well as ALL blood from AML blood with high sensitivity and specificity. We then developed a methylation-based survival classifier with 23 CpGs for ALL and 20 CpGs for AML that could successfully divide patients into high-risk and low-risk groups, with significant differences in clinical outcome in each leukemia type. Together, these findings demonstrate that methylation profiles can be highly sensitive and specific in the accurate diagnosis of ALL and AML, with implications for the prediction of prognosis and treatment selection.