We constructed an automated predictive analytics framework for machine-learning algorithm with high discriminatory ability for assessing the risk of surgical complications and death using readily available preoperative electronic health records data. The feasibility of this novel algorithm implemented in real time clinical workflow requires further testing.

Funding has been viewed in the literature as one of the main determinants of scientific activities. Also, at an individual level, securing funding is one of the most important factors for a researcher, enabling him/her to carry out research projects. However, not everyone is successful in obtaining the necessary funds. The main objective of this work is to measure the effect of several important factors such as past productivity, scientific collaboration or career age of researchers, on the amount of funding that is allocated to them. For this purpose, the paper estimates a temporal non-linear multiple regression model. According to the results, although past productivity of researchers positively affects the funding level, our findings highlight the significant role of networking and collaboration. It was observed that being a member of large scientific teams and getting connected to productive researchers who have also a good control over the collaboration network and the flow of information can increase the chances for securing more money. In fact, our results show that in the quest for the research money it is more important how researchers build their collaboration network than what publications they produce and whether they are cited.

No abstract

Electronic Health Records (EHR) are mainly designed to record relevant patient information during their stay in the hospital for administrative purposes. They additionally provide an efficient and inexpensive source of data for medical research, such as patient outcome prediction. In this study, we used preoperative Electronic Health Records to predict postoperative delirium. We compared the performance of seven machine learning models on delirium prediction: linear models, generalized additive models, random forests, support vector machine, neural networks, and extreme gradient boosting. Among the models evaluated in this study, random forests and generalized additive model outperformed the other models in terms of the overall performance metrics for prediction of delirium, particularly with respect to sensitivity. We found that age, alcohol or drug abuse, socioeconomic status, underlying medical issue, severity of medical problem, and attending surgeon can affect the risk of delirium.