Generative Image Reconstruction From Gradients.

In this article, we propose a method, generative image reconstruction from gradients (GIRG), for recovering training images from gradients in a federated learning (FL) setting, where privacy is preserved by sharing model weights and gradients rather than raw training data. Previous studies have shown the potential for revealing clients' private information or even pixel-level recovery of training images from shared gradients. However, existing methods are limited to low-resolution images and small batch sizes (BSs) or require prior knowledge about the client data. GIRG utilizes a conditional generative model to reconstruct training images and their corresponding labels from the shared gradients. Unlike previous generative model-based methods, GIRG does not require prior knowledge of the training data. Furthermore, GIRG optimizes the weights of the conditional generative model to generate highly accurate "dummy" images instead of optimizing the input vectors of the generative model. Comprehensive empirical results show that GIRG is able to recover high-resolution images with large BSs and can even recover images from the aggregation of gradients from multiple participants. These results reveal the vulnerability of current FL practices and call for immediate efforts to prevent inversion attacks in gradient-sharing-based collaborative training.

Clinical efficacy of Shugan granule in the treatment of mixed anxiety-depressive disorder: A multicenter, randomized, double-blind, placebo-controlled trial.

ETHNOPHARMACOLOGICAL RELEVANCE: Shugan granule is derived from Xiaoyao powder, a traditional Chinese medicine that has been shown to be effective in treating emotional disorders. At present, there is no standard drug treatment for mixed anxiety-depressive disorder (MADD), and no evidence-based clinical trial has been performed for any drug, meaning MADD patients are unable to obtain standardized treatment. AIM OF THE STUDY: The purpose of this clinical trial was to test the clinical efficacy and safety of Shugan granules in the treatment of MADD, and to provide clinical trial-based support along with drug recommendations for the treatment of MADD. MATERIALS AND METHODS: A multicenter, randomized, double-blind, placebo-controlled study was conducted on 400 patients with MADD recruited from January 1, 2019 to December 31, 2020, and they were randomly divided into test and placebo groups with a 1:1 ratio. Subjects in the test group (n = 200) received oral administration of Shugan granules, while subjects in the placebo group (n = 200) received oral administration of a Shugan granule simulator. The treatment lasted for 8 weeks. The Hamilton Anxiety Scale (HAMA), Hamilton Depression Scale-17 (HAMD-17), Clinical Global Impression Scale (CGIS), Self-rating Anxiety Scale (SAS), and Self-rating Depression Scale (SDS) were used to evaluate efficacy. In addition, the traditional Chinese medicine (TCM) syndrome scale for MADD was developed to observe improvements of related symptoms in patients after treatment based on the disease guidelines of TCM and the clinical manifestations of depression. Furthermore, the safety of Shugan granules was evaluated during and after treatment. RESULTS: After 8 weeks of treatment, the total scores for HAMA, HAMD, SAS, and SDS in the test group were significantly lower than those in the placebo group (P < 0.01). The proportion of patients with efficacy index (EI) > 1 for the CGIS score in the test group was significantly higher than that in the placebo group (P < 0.01). The efficacy of treatment in the test group based on the TCM syndrome scale was 70.16% and 88.27% after 4 weeks and 8 weeks, respectively, which was significantly higher than that in the placebo group (44.27% and 66.67% after 4 weeks and 8 weeks, respectively; P < 0.01). The disappearance rate of single symptoms in the test group was 20-30% higher than that in the placebo group, with a significant difference between groups (P < 0.05). During the treatment period, the incidence of adverse reactions was 2.05% in the test group and 2.06% in the placebo group, with no significant differences noted (P = 1.0000). CONCLUSION: Shugan granule was more effective than placebo in the treatment of MADD. Moreover, there was no significant difference between the two groups in terms of safety. This paper provides a clinical therapeutic regime using Shugan granule for the treatment of MADD.

Retinal photograph-based deep learning algorithms for myopia and a blockchain platform to facilitate artificial intelligence medical research: a retrospective multicohort study.

BACKGROUND: By 2050, almost 5 billion people globally are projected to have myopia, of whom 20% are likely to have high myopia with clinically significant risk of sight-threatening complications such as myopic macular degeneration. These are diagnoses that typically require specialist assessment or measurement with multiple unconnected pieces of equipment. Artificial intelligence (AI) approaches might be effective for risk stratification and to identify individuals at highest risk of visual loss. However, unresolved challenges for AI medical studies remain, including paucity of transparency, auditability, and traceability. METHODS: In this retrospective multicohort study, we developed and tested retinal photograph-based deep learning algorithms for detection of myopic macular degeneration and high myopia, using a total of 226 686 retinal images. First we trained and internally validated the algorithms on datasets from Singapore, and then externally tested them on datasets from China, Taiwan, India, Russia, and the UK. We also compared the performance of the deep learning algorithms against six human experts in the grading of a randomly selected dataset of 400 images from the external datasets. As proof of concept, we used a blockchain-based AI platform to demonstrate the real-world application of secure data transfer, model transfer, and model testing across three sites in Singapore and China. FINDINGS: The deep learning algorithms showed robust diagnostic performance with areas under the receiver operating characteristic curves [AUC] of 0·969 (95% CI 0·959-0·977) or higher for myopic macular degeneration and 0·913 (0·906-0·920) or higher for high myopia across the external testing datasets with available data. In the randomly selected dataset, the deep learning algorithms outperformed all six expert graders in detection of each condition (AUC of 0·978 [0·957-0·994] for myopic macular degeneration and 0·973 [0·941-0·995] for high myopia). We also successfully used blockchain technology for data transfer, model transfer, and model testing between sites and across two countries. INTERPRETATION: Deep learning algorithms can be effective tools for risk stratification and screening of myopic macular degeneration and high myopia among the large global population with myopia. The blockchain platform developed here could potentially serve as a trusted platform for performance testing of future AI models in medicine. FUNDING: None.

Leveraging Machine Learning Techniques and Engineering of Multi-Nature Features for National Daily Regional Ambulance Demand Prediction.

The accurate prediction of ambulance demand provides great value to emergency service providers and people living within a city. It supports the rational and dynamic allocation of ambulances and hospital staffing, and ensures patients have timely access to such resources. However, this task has been challenging due to complex multi-nature dependencies and nonlinear dynamics within ambulance demand, such as spatial characteristics involving the region of the city at which the demand is estimated, short and long-term historical demands, as well as the demographics of a region. Machine learning techniques are thus useful to quantify these characteristics of ambulance demand. However, there is generally a lack of studies that use machine learning tools for a comprehensive modeling of the important demand dependencies to predict ambulance demands. In this paper, an original and novel approach that leverages machine learning tools and extraction of features based on the multi-nature insights of ambulance demands is proposed. We experimentally evaluate the performance of next-day demand prediction across several state-of-the-art machine learning techniques and ambulance demand prediction methods, using real-world ambulatory and demographical datasets obtained from Singapore. We also provide an analysis of this ambulatory dataset and demonstrate the accuracy in modeling dependencies of different natures using various machine learning techniques.