Forecasting stock price trends accurately appears a huge challenge because the environment of stock markets is extremely stochastic and complicated. This challenge persistently motivates us to seek reliable pathways to guide stock trading. While the Long Short-Term Memory (LSTM) network has the dedicated gate structure quite suitable for the prediction based on contextual features, we propose a novel LSTM-based model. Also, we devise a multiscale convolutional feature fusion mechanism for the model to extensively exploit the contextual relationships hidden in consecutive time steps. The significance of our designed scheme is twofold. (1) Benefiting from the gate structure designed for both long- and short-term memories, our model can use the given stock history data more adaptively than traditional models, which greatly guarantees the prediction performance in financial time series (FTS) scenarios and thus profits the prediction of stock trends. (2) The multiscale convolutional feature fusion mechanism can diversify the feature representation and more extensively capture the FTS feature essence than traditional models, which fairly facilitates the generalizability. Empirical studies conducted on three classic stock history data sets, i.e., S&P 500, DJIA, and VIX, demonstrated the effectiveness and stability superiority of the suggested method against a few state-of-the-art models using multiple validity indices. For example, our method achieved the highest average directional accuracy (around 0.71) on the three employed stock data sets.

Clinical pathway (CP) is a plan for diagnosis, treatment, and nursing, having strict work order and exacting requirements on time, formulated by medical staff and other relevant personnel for the inspection, diagnosis, treatment, nursing, and rehabilitation guidance of some diseases, in order to improve the medical quality, standardize the medical behavior and reduce the medical cost. It is also a medical management tool [1] enabling patients to get the best quality of treatment. CP is an eff ective way to guarantee the medical quality and medical safety, while the electronic medical record (EMR) is both a business support system and an eff ective carrier and an important part of pathway information source. In the basic structure and data standard of electronic medical record published by the Ministry of Health, the CP is classifi ed as one of the groups for standard data on clinical documents, which lays a foundation for the normalization and standardization of clinical data, produces structured and standardized medical data for the EMR system, and provides a basis for the implementation of CP, thereby achieving the integration and intelligence of CP management, and achieving a CP which can be defi ned and confi gured, with an implementation that can be recorded and controlled, and eff ects that can be evaluated [2]. With the deepening of information construction in our hospital, the semi-structured EMR based on CP is a more practical construction scheme. Its construction is summarized below, so that the clinical staff can easily recognize and understand the process. CP design of EMRTh e CP framework in our hospital refers to the clinical pathway management guidelines (Trial) issued by the Ministry of Health, which mainly employs Chinese Medical Record English Edition, 2013; 1(8): 338-342 AbstractTo explore the basic idea, fl ow and functional modules in the construction of a semi-structured electronic medical record (EMR) based on a clinical pathway (CP), and to evaluate both the eff ects of its implementation and the existing problems. The adoption of a semi-structured EMR favors promoting the CP management, improving the medical quality, standardizing the medical behavior, and reducing the medical cost. Considering the great and far-reaching signifi cance in constructing a semi-structured EMR based on CP, we should increase the coverage of diseases implementing CP and rapidly develop a patient-centered, novel, semi-structured EMR at the same time.

No abstract