Search

There has been increasing interest in modeling survival data using deep learning methods in medical research. In this paper, we proposed a Bayesian hierarchical deep neural networks model for modeling and prediction of survival data. Compared with previously studied methods, the new proposal can provide not only point estimate of survival probability but also quantification of the corresponding uncertainty, which can be of crucial importance in predictive modeling and subsequent decision making. The favorable statistical properties of point and uncertainty estimates were demonstrated by simulation studies and real data analysis. The Python code implementing the proposed approach was provided.

Vaccine safety is a concerning problem of the public, and many signal detecting methods have been developed to identify relative risks between vaccines and adverse events (AEs). Those methods usually focus on individual AEs, where the randomness of data is high. The results often turn out to be inaccurate and lack of clinical meaning. The AE ontology contains information about biological similarity of AEs. Based on this, we extend the concept of relative risks (RRs) to AE group level, which allows the possibility of more accurate and meaningful estimation by utilizing data from the whole group. In this paper, we propose the method zGPS.AO (Zero Inflated Gamma Poisson Shrinker with AE ontology) based on the zero inflated negative binomial distribution. This model has two purples: a regression model estimating group level RRs, and a empirical bayes framework to evaluate AE level RRs. The regression part can handle both excess zeros and over dispersion in the data, and the empirical method borrows information from both group level and AE level to reduce data noise and stabilize the AE level result. We have demonstrate the unbiaseness and low variance features of our model with simulated data, and obtained meaningful results coherent with previous studies on the VAERS (Vaccine Adverse Event Reporting System) database. The proposed methods are implemented in the R package zGPS.AO, which can be installed from the Comprehensive R Archive Network, CRAN. The results on VAERS data are visualized using the interactive web app Rshiny., Comment: 10 pages, 3 figures

In regression models, predictor variables with inherent ordering, such as tumor staging ranging and ECOG performance status, are commonly seen in medical settings. Statistically, it may be difficult to determine the functional form of an ordinal predictor variable. Often, such a variable is dichotomized based on whether it is above or below a certain cutoff. Other methods conveniently treat the ordinal predictor as a continuous variable and assume a linear relationship with the outcome. However, arbitrarily choosing a method may lead to inaccurate inference and treatment. In this paper, we propose a Bayesian mixture model to simultaneously assess the appropriate form of the predictor in regression models by considering the presence of a changepoint through the lens of a threshold detection problem. By using a mixture model framework to consider both dichotomous and linear forms for the variable, the estimate is a weighted average of linear and binary parameterizations. This method is applicable to continuous, binary, and survival outcomes, and easily amenable to penalized regression. We evaluated the proposed method using simulation studies and apply it to two real datasets. We provide JAGS code for easy implementation.

Vaccination safety is critical for individual and public health. Many existing methods have been used to conduct safety studies with the VAERS (Vaccine Adverse Event Reporting System) database. However, these methods frequently identify many adverse event (AE) signals and they are often hard to interpret in a biological context. The AE ontology introduces biologically meaningful structures to the VAERS database by connecting similar AEs, which provides meaningful interpretation for the underlying safety issues. In this paper, we develop rigorous statistical methods to identify "interesting" AE groups by performing AE enrichment analysis. We extend existing gene enrichment tests to perform AE enrichment analysis. Unlike the continuous gene expression data, AE data are counts. Therefore, AE data has many zeros and ties. We propose two enrichment tests, AEFisher and AEKS. AEFisher is a modified Fisher's exact test based on pre-selected significant AEs, while AEKS is based on a modified Kolmogorov-Smirnov statistic. Both tests incorporate the special features of the AE data. The proposed methods were evaluated using simulation studies and were further illustrated on two studies using VAERS data. By appropriately addressing the issues of ties and excessive zeros in AE count data, our enrichment tests performed well as demonstrated by simulation studies and analyses of VAERS data. The proposed methods were implemented in R package AEenrich and can be installed from the Comprehensive R Archive Network, CRAN., Comment: 7 pages, 1 figure

Efficient and effective learning is one of the ultimate goals of the deep reinforcement learning (DRL), although the compromise has been made in most of the time, especially for the application of robot manipulations. Learning is always expensive for robot manipulation tasks and the learning effectiveness could be affected by the system uncertainty. In order to solve above challenges, in this study, we proposed a simple but powerful reward shaping method, namely Dense2Sparse. It combines the advantage of fast convergence of dense reward and the noise isolation of the sparse reward, to achieve a balance between learning efficiency and effectiveness, which makes it suitable for robot manipulation tasks. We evaluated our Dense2Sparse method with a series of ablation experiments using the state representation model with system uncertainty. The experiment results show that the Dense2Sparse method obtained higher expected reward compared with the ones using standalone dense reward or sparse reward, and it also has a superior tolerance of system uncertainty.

There has been increasing interest in modelling survival data using deep learning methods in medical research. Current approaches have focused on designing special cost functions to handle censored survival data. We propose a very different method with two steps. In the first step, we transform each subject's survival time into a series of jackknife pseudo conditional survival probabilities and then use these pseudo probabilities as a quantitative response variable in the deep neural network model. By using the pseudo values, we reduce a complex survival analysis to a standard regression problem, which greatly simplifies the neural network construction. Our two-step approach is simple, yet very flexible in making risk predictions for survival data, which is very appealing from the practice point of view. The source code is freely available at http://github.com/lilizhaoUM/DNNSurv., Comment: 12 pages, 4 figures

There are substantial instructional videos on the Internet, which enables us to acquire knowledge for completing various tasks. However, most existing datasets for instructional video analysis have the limitations in diversity and scale,which makes them far from many real-world applications where more diverse activities occur. Moreover, it still remains a great challenge to organize and harness such data. To address these problems, we introduce a large-scale dataset called "COIN" for COmprehensive INstructional video analysis. Organized with a hierarchical structure, the COIN dataset contains 11,827 videos of 180 tasks in 12 domains (e.g., vehicles, gadgets, etc.) related to our daily life. With a new developed toolbox, all the videos are annotated effectively with a series of step descriptions and the corresponding temporal boundaries. Furthermore, we propose a simple yet effective method to capture the dependencies among different steps, which can be easily plugged into conventional proposal-based action detection methods for localizing important steps in instructional videos. In order to provide a benchmark for instructional video analysis, we evaluate plenty of approaches on the COIN dataset under different evaluation criteria. We expect the introduction of the COIN dataset will promote the future in-depth research on instructional video analysis for the community., Comment: CVPR2019, project page: https://coin-dataset.github.io/

The conformal properties of complex Finsler metrics are studied. We give a characterization of a compact complex Finsler manifold to be globally conformal K\"ahler. The critical points of the total holomorphic curvature and total Ricci curvature in the volume preserved conformal classes are studied. The stability of critical K\"ahler Finsler metrics is obtained. A Yamabe type problem for mean Ricci curvature is considered.