Search

Medical device technology develops rapidly, and the life cycle of a medical device is much shorter than drugs. It is necessary to evaluate the safety and effectiveness of a medical device in a timely manner to keep up with technology flux. Bayesian methods provides an efficient approach to addressing this challenge. In this article, we review the characteristics of the Bayesian approach and some Bayesian designs that were commonly used in medical device regulatory setting, including Bayesian adaptive design, Bayesian diagnostic design, Bayesian multiregional design, and Bayesian label expansion study. We illustrate these designs with medical devices approved by the US Food and Drug Administration (FDA). We also review several innovative Bayesian information borrowing methods, and briefly discuss the challenges and future directions of the Bayesian application in medical device trials. Our objective is to promote the use of the Bayesian approach to accelerate the development of innovative medical devices and their accessibility to patients for effective disease diagnoses and treatments.

BACKGROUND Identifying the occurrence form of iodine in soil and the law of iodine migration and transformation in soil is of great significance for evaluating the biogeochemical behavior of iodine and preventing human iodine deficiency diseases. OBJECTIVES To review the source, content, speciation, transportation, and transformation of iodine in soils; and briefly summarize the transportation of iodine between soil and plants. METHODS The source, content, speciation, transportation, and transformation characteristics of iodine in soils were reviewed. The influences of soil types, environmental factors, organic matter, microbial activity, pH, and Eh on iodine dynamics were summarized. Great emphasis was laid on the main factors affecting the sorption of iodine in soil, which is the key process regulating soil iodine mobility and bioavailability. RESULTS The dry and wet deposition of the atmosphere, the weathering of the soil parent rock, and the absorption and release of plants are the main sources of iodine in soil. Iodine contents in soil typically range from 1 to 5mg/kg. Organic iodine is the dominant form of iodine in soil due to the close association of iodine with organic matter, which is the critical factor affecting soil iodine dynamics. Sorption is the key process regulating soil iodine mobility and bioavailability. Under acidic conditions, hydroxyl groups on soil mineral surface are protonated, and thus facilitating iodine sorption via electrostatic interaction. CONCLUSIONS Due to the complex composition of soil, establishing a complete soil iodine database is the basis for exploring soil iodine related aspects. It is necessary to further seek better soil iodine analysis methods. Studying the adsorption mechanism of soil iodine and the effect of organic matter and microorganisms on iodine in soil are also an important direction for future research.

BackgroundThe polygenic nature of Alzheimer's disease (AD) suggests that multiple variants jointly contribute to disease susceptibility. As an individual's genetic variants are constant throughout life, evaluating the combined effects of multiple disease-associated genetic risks enables reliable AD risk prediction. Because of the complexity of genomic data, current statistical analyses cannot comprehensively capture the polygenic risk of AD, resulting in unsatisfactory disease risk prediction. However, deep learning methods, which capture nonlinearity within high-dimensional genomic data, may enable more accurate disease risk prediction and improve our understanding of AD etiology. Accordingly, we developed deep learning neural network models for modeling AD polygenic risk.MethodsWe constructed neural network models to model AD polygenic risk and compared them with the widely used weighted polygenic risk score and lasso models. We conducted robust linear regression analysis to investigate the relationship between the AD polygenic risk derived from deep learning methods and AD endophenotypes (i.e., plasma biomarkers and individual cognitive performance). We stratified individuals by applying unsupervised clustering to the outputs from the hidden layers of the neural network model.ResultsThe deep learning models outperform other statistical models for modeling AD risk. Moreover, the polygenic risk derived from the deep learning models enables the identification of disease-associated biological pathways and the stratification of individuals according to distinct pathological mechanisms.ConclusionOur results suggest that deep learning methods are effective for modeling the genetic risks of AD and other diseases, classifying disease risks, and uncovering disease mechanisms.

In this study, we propose a MOOC Analytic Statistical Visual model (MOOC-ASV) to explore students' engagement in MOOC courses and predict their performance on the basis of their behaviors logged as big data in MOOC platforms. The model has multifunctions, which performs on visually analyzing learners' data by state-of-the-art techniques. The model presents several visual analyses, which exhibit learners' interaction patterns with course videos and also statistical summaries of associated events for each video. The results showed positive indicators that would enable instructors to identify learners dropping out based on their interactions with videos. The model gives feedback into course instructors and developers to review and modify the course content, especially video content, which ultimately lead to improving the course quality and outcomes.

Online learning has become more popular in higher education since it adds convenience and flexibility to students' schedule. But, it has faced difficulties in the retention of the continuity of students and ensure continual growth in course. Dropout is a concerning factor in online course continuity. Therefore, it has sparked great interest among educators and researchers to offer many models and strategies to reduce online course students' dropout by analyzing students' behavior and their individual and academic information. However, online education platforms still face challenges of high dropout rate and the difficulty of accurate prediction to reduce it. The key aim of the present study is to construct a predictive model to early predict students who are at-risk of dropout. This model is useful to the course instructors to make effective and timely interventions. We have noticed that dropout prediction is basically a sequence labeling or time series prediction problem. For these reasons, we proposed two models; the Logistic Regression by adding a regularization term and the Input-Output Hidden Markov Model (IOHMM). Results showed that the proposed models achieved an accuracy of 84% compared to the baseline of Machine Learning Models for prediction of the students at-risk of dropping out.