Abstract
Electronic access to patient's medication history (PMH) in the emergency department (ED) in Portugal is not widely granted, nor has the importance of such access been clearly assessed. Given the known association between poor PMH and medication errors, the goal of this study was to gather requirements for such a system, assessing physicians' opinions regarding the importance of having access to PMH in the ED. A questionnaire was sent to all Portuguese public hospitals which approved the study, and forwarded by email by the internal services of each hospital to ED physicians. Fourteen hospitals authorized the study, from which 83 ED physicians answered the questionnaire. PMH-related information considered most important focused on medication name and posology (> 90%) and date and dose of prescription (> 80%), but also date of dispensing of medications (> 40%). Other information such as allergies (99%) and adverse reactions (96%) were similarly considered important, and physicians agree with the inclusion of nonprescription medications (85%) as well as homeopathic medicines (64%). Overall, access to PMH in the ED appears to be important and present benefits to patients' care. Given this, electronic access to PHM should be settled in Portuguese ED.

Abstract
Most streaming decision models evolve continuously over time, run in resource-aware environments, and detect and react to changes in the environment generating data. One important issue, not yet convincingly addressed, is the design of experimental work to evaluate and compare decision models that evolve over time. This paper proposes a general framework for assessing predictive stream learning algorithms. We defend the use of prequential error with forgetting mechanisms to provide reliable error estimators. We prove that, in stationary data and for consistent learning algorithms, the holdout estimator, the prequential error and the prequential error estimated over a sliding window or using fading factors, all converge to the Bayes error. The use of prequential error with forgetting mechanisms reveals to be advantageous in assessing performance and in comparing stream learning algorithms. It is also worthwhile to use the proposed methods for hypothesis testing and for change detection. In a set of experiments in drift scenarios, we evaluate the ability of a standard change detection algorithm to detect change using three prequential error estimators. These experiments point out that the use of forgetting mechanisms (sliding windows or fading factors) are required for fast and efficient change detection. In comparison to sliding windows, fading factors are faster and memoryless, both important requirements for streaming applications. Overall, this paper is a contribution to a discussion on best practice for performance assessment when learning is a continuous process, and the decision models are dynamic and evolve over time.

Abstract

Abstract
The goal of the OPTIM project is to optimize the graphical user interface of an electronic health record (EHR) by predicting clinical documents' relevance and provide a ranked list of relevant documents for the given user at a certain time. This paper describes the architecture of the relevance assignment and ranking prototype and some implementation issues. The prototype's design is based on two components: OPTIM Core, with logical representation, estimation server's integration and the webservice layer, and the OPTIM WebUI, with the user interface for presenting the results. The prototype was tested in integration with an EHR using a simulated environment. The results were encouraging but yet they revealed a certain lack of security (confidentiality). It has now the capacity of rating 10 documents per second. Nonetheless, the integration of features such as rating clinical relevance based on mathematical models can be included in existing EHR potentially improving their usability.

Abstract
Obstructive Sleep Apnea (OSA) is a disease that affects approximately 4% of men and 2% of women worldwide but is still underestimated and underdiagnosed. The standard method for assessing this index, and therefore defining the OSA diagnosis, is polysomnography (PSG). Previous work developed relevant Bayesian network models but those were based only on variables univariatedly associated with the outcome, yielding a bias on the possible knowledge representation of the models. The aim of this work was to develop and validate new Bayesian network decision support models that could be used during sleep consult to assess the need for PSG. Bayesian models were developed using a) expert opinion, b) hill-climbing, c) naive Bayes and d) TAN structures. Resulting models validity was assessed with in-sample AUC and stratified cross-validation, also comparing with previously published model. Overall, models achieved good discriminative power (AUC>70%) and validity (measures consistently above 70%). Main conclusions are a) the need to integrate a wider range of variables in the final models and b) the support of using Bayesian networks in the diagnosis of obstructive sleep apnea.

Abstract
Anomalies in data can cause a lot of problems in the data analysis processes. Thus, it is necessary to improve data quality by detecting and eliminating errors and inconsistencies in the data, known as the data cleaning process [1]. Since detection and correction of anomalies requires detailed domain knowledge, the involvement of experts in the field is essential to the success of the process of cleaning the data. However, considering the size of data to be processed, this process should be as automatic as possible so as to minimize the time spent [1]. © 2013 IEEE.