Paraphrase generation (PG) is important in plenty of NLP applications. However, the research of PG is far from enough. In this paper, we propose a novel method for statistical paraphrase generation (SPG), which can (1) achieve various applications based on a uniform statistical model, and (2) naturally combine multiple resources to enhance the PG performance. In our experiments, we use the proposed method to generate paraphrases for three different applications. The results show that the method can be easily transformed from one application to another and generate valuable and interesting paraphrases.

Artificial intelligence (AI) has proven successful for the detection and diagnosis of pathological conditions on medical images. Images, such as radiographs and computed tomography scans in Digital Imaging and Communications in Medicine (DICOM) format, are used by AI to selflearn and identify patterns that allow for the derivation of reasonable predictions. Even without the input of standard image-processing rules by medical experts, network algorithms can learn from raw images, and ultimately provide highly accurate and consistent output. Furthermore, AI has demonstrated the potential to assist radiologists in performing computer-aided analysis and diagnosis. For example, Stanford University published a convolutional neural network with 121 layers, CheXNet, that outperformed four radiologists after learning on a dataset of 112,120 frontal-view chest radiographs (Chest X-ray14) (1). Likewise, Li et al.(2) presented a retrospective

In PhysioNet/Computing in Cardiology Challenge 2020, we developed an ensembled model based on SE-ResNet to classify cardiac abnormalities from 12-lead electrocardiogram (ECG) signals. We employed two residual neural network modules with squeeze-and-excitation blocks to learn from the first 10-second and 30-second segments of the signals. We used external open-source data for validation and fine-tuning during the model development phase. We designed a multi-label loss to emphasize the impact of wrong predictions during training. We built a rule-based bradycardia model based on clinical knowledge to correct the output. All these efforts helped us to achieve a robust classification performance. Our final model achieved a challenge validation score of 0.682 and a full test score of 0.514, placing our team HeartBeats 3rd out of 41 in the official ranking. We believed that our model has a great potential to be applied in the actual clinical practice, and planned to further extend the research after the challenge.

In data-driven medical research, multi-center studies have long been preferred over single-center ones due to a single institute sometimes not having enough data to obtain sufficient statistical power for certain hypothesis testings as well as predictive and subgroup studies. The wide adoption of electronic health records (EHRs) has made multi-institutional collaboration much more feasible. However, concerns over infrastructures, regulations, privacy and data standardization present a challenge to data sharing across healthcare institutions. Federated Learning (FL), which allows multiple sites to collaboratively train a global model without directly sharing data, has become a promising paradigm to break the data isolation. In this study, we surveyed existing works on FL applications in EHRs and evaluated the performance of current state-of-the-art FL algorithms on two EHR machine learning tasks of significant clinical importance on a real world multi-center EHR dataset.