Showing papers in "Journal of Biomedical Informatics in 2019"

TL;DR: The Research Electronic Data Capture (REDCap) data management platform was developed in 2004 to address an institutional need at Vanderbilt University, then shared with a limited number of adopting sites beginning in 2006, and a broader consortium sharing and support model was created.

TL;DR: This survey will examine the recent works on stress detection in daily life which are using smartphones and wearable devices and investigate the works according to used physiological modality and their targeted environment such as office, campus, car and unrestricted daily life conditions.

TL;DR: A community-based federated machine learning (CBFL) algorithm was introduced and evaluated on non-IID ICU EMRs and results show that CBFL outperformed the baseline federatedMachine learning algorithm in terms of Area Under the Receiver Operating Characteristic Curve (ROC AUC), Area under the Precision-Recall Curve (PR AUC) and communication cost between hospitals and the server.

TL;DR: An interdisciplinary approach to wearable activity trackers is taken to attempt to understand the rich human-information interaction that is enabled by WAT adoption, and to propose several new research questions.

TL;DR: A comprehensive study on the consequences of imbalanced data problem on the data of cancer patients for the first time, examining the impact of class imbalance on the function of classifiers, a general comparing of thefunction of pre-processing techniques and classifying all data sets and finally determining the best balancer and classifier for each kind of cancer data set.

TL;DR: This paper provides a guide for training word representations on clinical text data, using a survey of relevant research, and discusses different types of word representations, clinical text corpora, available pre-trained clinical word vector embeddings, intrinsic and extrinsic evaluation, applications, and limitations of these approaches.

TL;DR: This research explores and critically analyzes HL7 FHIR to design and prototype an interoperable mobile PHR that conforms to the HL7 PHR Functional Model and allows bi-directional communication with OpenEMR.

TL;DR: The performance results indicated that data distributed via a blockchain could be recovered with low average response time and high availability in the scenarios the authors tested and demonstrated how OmniPHR model implementation can integrate distributed data into a unified view of health records.

TL;DR: A cost-sensitive formulation of Long Short-Term Memory (LSTM) neural network using expert features and contextual embedding of clinical concepts is presented using both expert and machine derived features, incorporating sequential patterns and addressing the class imbalance problem.

TL;DR: Differences between the applicability of those algorithms and the results obtained with them were a function of the software platforms used in the data analysis.

TL;DR: In this article, a new model which combines data-driven deep learning approaches and knowledge-driven dictionary approaches was proposed to handle the clinical named entity recognition task, and two different architectures that extend the bi-directional long short-term memory neural network and five different feature representation schemes were also proposed.

TL;DR: This is the first comprehensive review focusing only on feature based methods of drug target interaction, and provides a comprehensive overview of the various techniques, datasets, tools and metrics.

TL;DR: It is argued that biomedical informatics research would benefit from shifting attention from these theories to multi-dimensional approaches that can better capture the complexity of issues surrounding implementation and use of HIT.

TL;DR: Assessing the available literature on big data analytics and artificial intelligence in healthcare will help understand the needs in application of these technologies in healthcare by identifying the areas that require additional research and will provide the researchers and industry experts with a base for future work.

TL;DR: A smartwatch-based framework for real-time and online assessment and mobility monitoring (ROAMM) with the integration of sensor-based and user-reported data collection, the ROAMM framework allows for data visualization and summary statistics in real- time.

TL;DR: In this article, a deep multi-scale convolutional architecture trained on the Medical Information Mart for Intensive Care III (MIMIC-III) for mortality prediction, and the use of concepts from coalitional game theory to construct visual explanations aimed to show how important these inputs are deemed by the network.

TL;DR: The results suggested the usefulness of the methods in developing the specialized NER tools for identifying ADR-related information from Chinese ADERs.

TL;DR: A policy viewpoint on how the new European Interoperability Framework (EIF) may benefit the implementation of eHealth systems for the management of personal health information for citizens and practical implications relate to the need of multi-disciplinary cooperation and European level compatibility and sustainability of the underlying infrastructures.

TL;DR: The main contributions of this paper focus on defining a recommender system based on different difficulty levels and user skills, which offers the ability to provide the user with a personalized game mode based on his own history and preferences.

TL;DR: A BiLSTM-CRF model based on the radical-level feature and self-attention mechanism that aims to capture the intrinsic and internal relevances of characters and achieves F1-score 93.00% and 86.34% on CCKS-2017 and TP_CNER dataset respectively.

TL;DR: The recent advancement of neural network-based approaches for classifying biomedical relations is described, including convolutional neural networks (CNNs) and recurrent neural Networks (RNNs), and the remaining challenges are described and the future directions are outlined.

TL;DR: It is demonstrated that anxiety-related stress levels can be predicted using combined features extracted from smartphone log data using a method to extract a co-occurring combination of a user's real-world and online behavioral features by converting raw sensor data into categorical features.

TL;DR: Results of a case study aimed at classifying fall-related information (including fall history, fall prevention interventions, and fall risk) in homecare visit notes indicate that clinical text mining can be implemented without the need for large labeled datasets necessary for other types of machine learning.

TL;DR: Blation analysis indicates that the multilevel attention mechanism plays a decisive role in the system for dealing with Chinese clinical notes and the proposed multilayer attention bidirectional recurrent neural network model outperforms the baseline neural network models and achieves the lowest Hamming loss value.

TL;DR: An analytic framework is formulated, which integrates the random-effects structure of GLMM into non-linear machine learning models capable of exploiting temporal heterogeneous effects, sparse and varying-length patient characteristics inherent in longitudinal data, and predicts change of a longitudinal clinical outcome in real-world clinical settings with high accuracy.

TL;DR: The annotation methodology developed in order to create a new manually annotated wide-coverage corpus for clinical concept normalization, the Medical Concept Normalization (MCN) corpus, which will be publicly released to the research community in a shared task in 2019.

TL;DR: Using a common data model can dramatically speed phenotype implementation at the cost of having to populate that data model, though this will produce a net benefit as the number of phenotype implementations increases.

TL;DR: A novel adversarial training based lattice LSTM with a conditional random field layer (AT-lattice L STM-CRF) for Chinese CNER achieves a highly competitive performance compared to other prevalent neural models, which can be a reinforced baseline for further research in this field.

TL;DR: This survey attempts to consolidate and present the evolution of techniques in literature Based Discovery, and introduces the various methodologies currently employed and also the challenges yet to be tackled.

TL;DR: An interactive and low-cost full body rehabilitation framework for the generation of 3D immersive serious games is proposed, which combines two Natural User Interfaces (NUIs), for hand and body modeling, respectively, and a Head Mounted Display to provide the patient with an interactive and highly defined Virtual Environment for playing with stimulating rehabilitation exercises.