Purpose Fundus images are typically used as the sole training input for automated diabetic retinopathy (DR) classification. In this study, we considered several well-known DR risk factors and attempted to improve the accuracy of DR screening. Metphods Fusing nonimage data (e.g., age, gender, smoking status, International Classification of Disease code, and laboratory tests) with data from fundus images can enable an end-to-end deep learning architecture for DR screening. We propose a neural network that simultaneously trains heterogeneous data and increases the performance of DR classification in terms of sensitivity and specificity. In the current retrospective study, 13,410 fundus images and their corresponding nonimage data were collected from the Chung Shan Medical University Hospital in Taiwan. The images were classified as either nonreferable or referable for DR by a panel of ophthalmologists. Cross-validation was used for the training models and to evaluate the classification performance. Results The proposed fusion model achieved 97.96% area under the curve with 96.84% sensitivity and 89.44% specificity for determining referable DR from multimodal data, and significantly outperformed the models that used image or nonimage information separately. Conclusions The fusion model with heterogeneous data has the potential to improve referable DR screening performance for earlier referral decisions. Translational Relevance Artificial intelligence fused with heterogeneous data from electronic health records could provide earlier referral decisions from DR screening.

The ICH E5 Guidance facilitates the registration of medicine among ICH regions by recommending a framework for evaluating the impact of ethnic factors upon a medicine's effect. It further describes the use of bridging studies, when necessary, to allow extrapolation of foreign clinical data to a new region. Bridging studies are performed in a new region for medicines already approved in the original region. The conventional noninferiority criterion requires the treatment effect (adjusted for placebo) attained in the new region preserves a prespecified proportion of the treatment effect attained in the original region. Such a bridging criterion, however, is often impractical. Hsiao et al. (2007) proposed a Bayesian approach that borrows the strength of the original trial to establish the treatment effect in the bridging region through using a weighted prior distribution. The weight, however, is often difficult to prespecify. In this presentation, we consider the overall treatment effect by combining the weighted effects attained in the original and bridging regions. The maximum weight allowed to be placed on the estimate of bridging region in order to show a significant overall treatment effect represents the strength of the treatment effect in the bridging region. Regional approval will be evaluated either by comparing the weight estimate with the prespecified limit or by benefit-risk evaluation of the medicine. Sample size requirements for the approaches are derived. The simulation results of type I error rate and power for the proposed methods are given. An example illustrates the application of the proposed procedures.

In recent years, developing pharmaceutical products via multiregional clinical trials (MRCTs) has become standard. Traditionally, an MRCT would assume that a treatment effect is uniform across regions. However, heterogeneity among regions may have impact upon the evaluation of a medicine's effect. In this study, we consider a random effects model using discrete distribution (DREM) to account for heterogeneous treatment effects across regions for the design and evaluation of MRCTs. We derive an power function for a treatment that is beneficial under DREM and illustrate determination of the overall sample size in an MRCT. We use the concept of consistency based on Method 2 of the Japanese Ministry of Health, Labour, and Welfare's guidance to evaluate the probability for treatment benefit and consistency under DREM. We further derive an optimal sample size allocation over regions to maximize the power for consistency. Moreover, we provide three algorithms for deriving sample size at the desired level of power for benefit and consistency. In practice, regional treatment effects are unknown. Thus, we provide some guidelines on the design of MRCTs with consistency when the regional treatment effect are assumed to fall into a specified interval. Numerical examples are given to illustrate applications of the proposed approach. Copyright © 2016 John Wiley & Sons, Ltd.