Showing papers in "Journal of Biomedical Informatics in 2017"

TL;DR: Most of the e-Health applications and serious games investigated have been proven to yield solely short-term engagement through extrinsic rewards and it is therefore necessary to build e- health solutions on well-founded theories that exploit the core experience and psychological effects of game mechanics.

TL;DR: DeepCare is introduced, an end-to-end deep dynamic neural network that reads medical records, stores previous illness history, infers current illness states and predicts future medical outcomes, demonstrating the efficacy of DeepCare for disease progression modeling, intervention recommendation, and future risk prediction.

TL;DR: This review has identified many NLP systems capable of processing clinical free text and generating structured output, and the information collected and evaluated here will be important for prioritizing development of new approaches for clinical NLP.

TL;DR: This work proposes a model named OmniPHR, a distributed model to integrate PHRs, and demonstrates the feasibility of the model in maintaining health records distributed in an architecture model that promotes a unified view of PHR with elasticity and scalability of the solution.

TL;DR: This work explores the problem of stress detection using machine learning and signal processing techniques in laboratory conditions, and then applies the extracted laboratory knowledge to real-life data to propose a novel context-based stress-detection method.

TL;DR: This paper introduces a novel neural network architecture that benefits from both word- and character-level representations automatically, by using a combination of bidirectional long short-term memory (LSTM) and conditional random field (CRF) eliminating the need for most feature engineering tasks.

TL;DR: Experimental results reveal that the proposed system besides being completely reversible is capable of providing high quality watermarked images for fairly high payload and a comparison of the observed results with some state-of-art schemes show that the scheme performs better.

TL;DR: A hybrid system is developed that achieves the highest micro F1-scores under the "token, "strict" and "binary token" criteria respectively, ranking first in the 2016 CEGS N-GRID NLP challenge and outperforming other state-of-the-art systems.

TL;DR: The first models based on recurrent neural networks (more specifically Long Short-Term Memory - LSTM) for classifying relations from clinical notes show comparable performance to previously published systems while requiring no manual feature engineering.

TL;DR: The current method is proposed as a robust, yet simple and fast, universal in silico approach for identification of DDIs and it is envisioned that this proposed method can be used as a practical technique for the detection of possible DDIs based on the functional similarities of drugs.

TL;DR: This work presents a state-of-the-art system for DNR and CCE that avoids conventional, time-consuming feature engineering, and outperformed all previously proposed systems with the Bidirectional LSTM-CRF model.

TL;DR: The unsupervised machine learning model using user, textual, and temporal information in social media data, along with sentiment analysis, identifies latent infectious diseases in a given location quicker than when the disease is formalized by national public health institutes.

TL;DR: Overall, de-identification is still not a solved problem, though it is important to the future of clinical NLP, and unmodified existing systems do not generalize well to new data without the benefit of training data.

TL;DR: The various foci of CDS are reviewed and aspects in which theoretical models and frameworks for CDS have been explored or could be explored and where they might be expected to be most useful are identified.

TL;DR: The experiments indicated that BRWH can achieve better performances compared with several popular methods on prioritizing disease-related miRNA candidates, and case studies of some common diseases further demonstrated the superior performance of the proposed method.

TL;DR: Navigating between multiple screens was frequently identified as a usability barrier in usability evaluations of electronic health record (EHR) as discussed by the authors, which may increase potential for errors, reduce efficiency, and increase fatigue.

TL;DR: The novelty of the approach, stems from the integration of sequence-based physiological pattern markers with the sequential CHMM model to learn dynamic physiological behavior, as well as from the coupling of such patterns to build powerful risk stratification models for septic shock patients.

TL;DR: Results from a pilot implementation of the method suggests that it is feasible to develop a scalable alternative to the time-and-resource-intensive, manual curation exercise previously applied to develop reference sets of positive and negative controls to be used in drug safety research.

TL;DR: A novel gene selection method based on the neighborhood rough set model is proposed, which has the ability of dealing with real-value data whilst maintaining the original gene classification information, and an entropy measure is addressed under the frame of neighborhood rough sets for tackling the uncertainty and noisy of gene expression data.

TL;DR: Missing data imputation appears to be an effective means for improving postoperative SSI detection using EHR clinical data.

TL;DR: This paper introduces the reader to modern and historical LBD models, key system components, evaluation methodologies, and current trends, and describes a unifying framework for LBD systems.

TL;DR: The Whale Optimization Algorithm (WOA) has been proposed to optimize the parameters of SVM, so that the classification error can be reduced and the experimental results proved that the proposed model achieved high sensitivity to all toxic effects.

TL;DR: Novel representations of temporal data in electronic health records are explored based on symbolic sequence representations of time series data that better account for the temporality of clinical events, which is often key to prediction tasks in the biomedical domain.

TL;DR: Graphical abstract 3-D representation of high dimensional data following ESOM projection and visualization of group (cluster) structures using the U-matrix, which employs a geographical map analogy of valleys where members of the same cluster are located, separated by mountain ranges marking cluster borders.

TL;DR: Comparative performance assessment of the proposed MRMR-COA-HS gene selection method with other evolutionary algorithms suggested that the proposed algorithm significantly outperforms other methods in selecting a fewer number of genes while maintaining the highest classification accuracy.

TL;DR: It is believed that real-time representation of the status of the entire emergency department and each patient within it through information visualizations will better support clinical decision-making in-the-moment and provide for rapid intervention to improve ED flow.

TL;DR: The new proposed sampling method, S-C4.5-SMOTE, is not only able to overcome the problem of data distortion, but also improves overall system performance because its mechanism aims at effectively reducing the data size without distortion, by keeping datasets balanced and technically smooth.

TL;DR: How a pathologist's diagnosis is influenced by fixed case-level factors, their prior clinical experience, and their patterns of visual inspection is examined to provide new insights into the medical interpretive process and demonstrate the complex interactions between pathologists and cases that guide diagnostic decision-making.

TL;DR: Two independent deep neural network models are proposed: one based on convolutional neural networks (CNN) and another based on recurrent neural networks with hierarchical attention (ReHAN), the latter of which allows for interpretation of model decisions.

TL;DR: Clinical usefulness analyses provided optimal risk thresholds, which varied by reason for readmission, outcome prevalence, and calibration algorithm, and decision-makers must understand underlying utilities or costs inherent in the use-case at hand to assess usefulness and will obtain the optimal risk threshold to trigger intervention with intervention cost limits.