No abstract

The COVID-19 pandemic has drastically affected the traditional methods residency programs use to train their residents. Chief residents serve a unique role as part of the residency leadership to foster the education and development of the residents. Given the rapid shift in demands on physicians in the face of the pandemic, the responsibilities of the chief residents have also shifted to help prepare the residents to meet these demands as frontline providers. There is not a precedent for how residency programs respond to this crisis while maintaining their primary role to develop and train physicians. The authors have identified 5 questions chief residents can ask to guide their program’s response to the demands of COVID-19 during this uncertain time in health care.

In this paper, we propose multi-band MelGAN, a much faster waveform generation model targeting to high-quality text-to-speech. Specifically, we improve the original MelGAN by the following aspects. First, we increase the receptive field of the generator, which is proven to be beneficial to speech generation. Second, we substitute the feature matching loss with the multi-resolution STFT loss to better measure the difference between fake and real speech. Together with pre-training, this improvement leads to both better quality and better training stability. More importantly, we extend MelGAN with multiband processing: the generator takes mel-spectrograms as input and produces sub-band signals which are subsequently summed back to full-band signals as discriminator input. The proposed multi-band MelGAN has achieved high MOS of 4.34 and 4.22 in waveform generation and TTS, respectively. With only 1.91M parameters, our model effectively reduces the total computational complexity of the original MelGAN from 5.85 to 0.95 GFLOPS. Our Pytorch implementation, which will be open-resourced shortly, can achieve a real-time factor of 0.03 on CPU without hardware specific optimization.

OBJECTIVES: Although it is widely believed that China is facing a major shortage of pediatricians, the real situation of the current national status of pediatric human resources and their working conditions has not been evaluated to date. METHODS: We administered a survey to 54 214 hospitals from all 31 provinces in mainland China from 2015 to 2016. Hospital directors of all secondary and tertiary hospitals with pediatric services and a random sample (10%) of primary hospitals provided information on number of pediatricians and their educational levels, specialties, workloads, dropout rates, and other hospital characteristics. A data set of medical resources and socioeconomic information regarding each region (1997–2016) was constructed from the Chinese National Statistics Bureau. The Gini coefficient was used to describe the geographical distributions of pediatricians and hospitals. RESULTS: There were 135 524 pediatricians in China or ∼4 pediatricians per 10 000 children. Pediatricians’ average educational level was low, with ∼32% having only 3 years of junior college training after high school. The distribution of pediatricians was extremely skewed (Gini coefficient 0.61), and the imbalance of highly educated pediatricians was even more skewed (Gini coefficient 0.68). The dropout rate of pediatricians was 12.6%. Despite an increase in the Chinese government’s financial investment in health over the last decade, physicians have been burdened with a greater workload. CONCLUSIONS: Uneven development of the pediatric care system, inadequately trained pediatricians, low job satisfaction, and unmet demand for pediatric care are the major challenges facing China’s pediatric health care system.

No abstract

Many life activities and key functions in organisms are maintained by different types of protein–protein interactions (PPIs). In order to accelerate the discovery of PPIs for different species, many computational methods have been developed. Unfortunately, even though computational methods are constantly evolving, efficient methods for predicting PPIs from protein sequence information have not been found for many years due to limiting factors including both methodology and technology. Inspired by the similarity of biological sequences and languages, developing a biological language processing technology may provide a brand new theoretical perspective and feasible method for the study of biological sequences. In this paper, a pure biological language processing model is proposed for predicting protein–protein interactions only using a protein sequence. The model was constructed based on a feature representation method for biological sequences called bio-to-vector (Bio2Vec) and a convolution neural network (CNN). The Bio2Vec obtains protein sequence features by using a “bio-word” segmentation system and a word representation model used for learning the distributed representation for each “bio-word”. The Bio2Vec supplies a frame that allows researchers to consider the context information and implicit semantic information of a bio sequence. A remarkable improvement in PPIs prediction performance has been observed by using the proposed model compared with state-of-the-art methods. The presentation of this approach marks the start of “bio language processing technology,” which could cause a technological revolution and could be applied to improve the quality of predictions in other problems.

Background The key to modern drug discovery is to find, identify and prepare drug molecular targets. However, due to the influence of throughput, precision and cost, traditional experimental methods are difficult to be widely used to infer these potential Drug-Target Interactions (DTIs). Therefore, it is urgent to develop effective computational methods to validate the interaction between drugs and target. Methods We developed a deep learning-based model for DTIs prediction. The proteins evolutionary features are extracted via Position Specific Scoring Matrix (PSSM) and Legendre Moment (LM) and associated with drugs molecular substructure fingerprints to form feature vectors of drug-target pairs. Then we utilized the Sparse Principal Component Analysis (SPCA) to compress the features of drugs and proteins into a uniform vector space. Lastly, the deep long short-term memory (DeepLSTM) was constructed for carrying out prediction. Results A significant improvement in DTIs prediction performance can be observed on experimental results, with AUC of 0.9951, 0.9705, 0.9951, 0.9206, respectively, on four classes important drug-target datasets. Further experiments preliminary proves that the proposed characterization scheme has great advantage on feature expression and recognition. We also have shown that the proposed method can work well with small dataset. Conclusion The results demonstration that the proposed approach has a great advantage over state-of-the-art drug-target predictor. To the best of our knowledge, this study first tests the potential of deep learning method with memory and Turing completeness in DTIs prediction.

The use of artificial intelligence (AI) is a powerful tool for image analysis that is increasingly being evaluated by radiology professionals. However, due to the fact that these methods have been developed for the analysis of nonmedical image data and data structure in radiology departments is not “AI ready”, implementing AI in radiology is not straightforward. The purpose of this review is to guide the reader through the pipeline of an AI project for automated image analysis in radiology and thereby encourage its implementation in radiology departments. At the same time, this review aims to enable readers to critically appraise articles on AI-based software in radiology.