Health Information Managers (HIMs) are responsible for overseeing health information. The change management necessary during the transition to electronic health records (EHR) is substantial, and ongoing. Archetype-based EHRs are a core health information system component which solve many of the problems that arise during this period of change. Archetypes are models of clinical content, and they have many beneficial properties. They are interoperable, both between settings and through time. They are more amenable to change than conventional paradigms, and their design is congruent with clinical practice. This paper is an overview of the current archetype literature relevant to Health Information Managers. The literature was sourced in the English language sections of ScienceDirect, IEEE Explore, Pubmed, Google Scholar, ACM Digital library and other databases on the usage of archetypes for electronic health record storage, looking at the current areas of archetype research, appropriate usage, and future research. We also used reference lists from the cited papers, papers referenced by the openEHR website, and the recommendations from experts in the area. Criteria for inclusion were (a) if studies covered archetype research and (b) were either studies of archetype use, archetype system design, or archetype effectiveness. The 47 papers included show a wide and increasing worldwide archetype usage, in a variety of medical domains. Most of the papers noted that archetypes are an appropriate solution for future-proof and interoperable medical data storage. We conclude that archetypes are a suitable solution for the complex problem of electronic health record storage and interoperability.

Abstract-Data originating from some specific fields, for instance tourist arrivals, may exhibit a high degree of fluctuations as well as non-linear characteristics due to time varying behaviors. This paper proposes a new hybrid method to perform prediction for such data. The proposed hybrid model of wavelet transform and long-short-term memory (LSTM) recurrent neural network (RNN) is able to capture non-linear attributes in tourist arrival time series. Firstly, data is decomposed into constitutive series through wavelet transform. The decomposition is expressed as a function of a combination of wavelet coefficients, which have different levels of resolution. Then, LSTM neural network is used to train and simulate the value at each level to find the bias vectors and weighting coefficients for the prediction value. A sliding windows model is employed to capture the time series nature of the data. An evaluation is conducted to compare the proposed model with other RNN algorithms, i.e., Elman RNN and Jordan RNN, as well as the combination of wavelet transform with each of them. The result shows that the proposed model has better performance in terms of training time than the original LSTM RNN, while the accuracy is better than the hybrid of wavelet-Elman and the hybrid of wavelet-Jordan.

No abstract

Twitter is one of the social medias that are widely used at the moment. Tweet conversations can be classified according to their sentiments. The existence of sarcasm contained in a tweet sometimes causes incorrect determination of the tweet’s sentiment because sarcasm is difficult to analyze automatically, even by humans. Hence, sarcasm detection needs to be conducted, which is expected to improve the results of sentiment analysis. The effect of sarcasm detection on sentiment analysis can be seen in terms of accuracy, precision and recall. In this paper, detection of sarcasm is applied to Indonesian tweets. The feature extraction of sarcasm detection uses unigram and 4 Boazizi feature sets which consist of sentiment-relate features, punctuation-relate features, lexical and syntactic features, and top word features. Detection of sarcasm uses the Random Forest algorithm. The feature extraction of sentiment analysis uses TF-IDF, while the classification uses Naïve Bayes algorithm. The evaluation shows that sentiment analysis with sarcasm detection improves the  accuracy of sentiment analysis about 5.49%. The accuracy of the model is 80.4%, while the precision is 83.2%, and the recall is 91.3%.

No abstract