Electronic health records (EHR) are rich heterogeneous collections of patient health information, whose broad adoption provides clinicians and researchers unprecedented opportunities for health informatics, disease-risk prediction, actionable clinical recommendations, and precision medicine. However, EHRs present several modeling challenges, including highly sparse data matrices, noisy irregular clinical notes, arbitrary biases in billing code assignment, diagnosis-driven lab tests, and heterogeneous data types. To address these challenges, we present MixEHR, a multi-view Bayesian topic model. We demonstrate MixEHR on MIMIC-III, Mayo Clinic Bipolar Disorder, and Quebec Congenital Heart Disease EHR datasets. Qualitatively, MixEHR disease topics reveal meaningful combinations of clinical features across heterogeneous data types. Quantitatively, we observe superior prediction accuracy of diagnostic codes and lab test imputations compared to the state-of-art methods. We leverage the inferred patient topic mixtures to classify target diseases and predict mortality of patients in critical conditions. In all comparison, MixEHR confers competitive performance and reveals meaningful disease-related topics.
This study investigates an extended version of the combined compromise solution method with grey numbers, named CoCoSo-G for short, to measure the performance of suppliers in a construction company in Madrid. Seven criteria from a relevant previous study are the basis for assessing the performance of suppliers, while ten suppliers are composing our decision matrix. To initiate the decision-making process, we invite experts to aid us in the qualitative evaluation of the suppliers using grey interval values. Two weighting methods, including the DEMATEL (Decision Making Trial and Evaluation Laboratory) and BWM (best worst method) are used to achieve the importance of supplier criteria in a combined manner. The DEMATEL method is used to realise the best and worst criteria, and the BWM is used to sort the criteria according to a linear programming formulation. The CoCoSo-G method used to release the score of each supplier and rank them. We compare the results obtained by the CoCoSo-G with those obtained by the Complex Proportional Assessment method. It is evident that offering grey values for supplier qualification, using the combined weighting tool and proposing the new CoCoSo-G approach facilitate the evaluation process while indicating trustable outcomes.
Our simple thermodynamic model, free of any adjustable parameters, has predicted the size-dependent and dimension-dependent melting temperatures of molecular nanocrystals whose diameters are at the lower bound of the mesoscopic size range, of 2 to 10 nm. In this size range, the depression of the melting temperature is no longer proportional to the reciprocal of the diameter of the nanocrystals. The model predictions are supported by experimental and molecular dynamics simulation results for cyclohexane, benzene, n-decane, methyl chloride, oxygen, neon, argon, and krypton nanocrystals.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.