Journal of biomedical informatics
-
There is a surge of research interest in protein-protein interaction (PPI) extraction from biomedical literature. While most of the state-of-the-art PPI extraction systems focus on dependency-based structured information, the rich structured information inherent in constituent parse trees has not been extensively explored for PPI extraction. ⋯ Compared with previously used constituent tree setups, our dependency-motivated constituent tree setup achieves the best results across five commonly used PPI corpora. Moreover, our tree kernel-based method outperforms other single kernel-based ones and performs comparably with some multiple kernel ones on the most commonly tested AIMed corpus.
-
Handoff among healthcare providers has been recognized as a major source of medical errors. Most prior research has often focused on the communication aspects of handoff, with limited emphasis on the overall handoff process, especially from a clinician workflow perspective. Such a workflow perspective that is based on the continuity of care model provides a framework required to identify and support an interconnected trajectory of care events affecting handoff communication. ⋯ The iterative development of clinician-centered approach was realized using a multi-faceted study conducted in the Medical Intensive Care Unit (MICU) of an academic hospital. Using the clinician-centered approach, we (a) identify the nature, inherent characteristics and the interdependencies between three phases of the handoff process and (b) develop a descriptive framework of handoff communication in critical care that captures the non-linear, recursive and interactive nature of collaboration and decision-making. The results reported in this paper serve as a "proof of concept" of our approach, emphasizing the importance of capturing a coordinated and uninterrupted succession of clinician information management and transfer activities in relation to patient care events.
-
Mobile phones are becoming an increasingly important platform for the delivery of health interventions. In recent years, researchers have used mobile phones as tools for encouraging physical activity and healthy diets, for symptom monitoring in asthma and heart disease, for sending patients reminders about upcoming appointments, for supporting smoking cessation, and for a range of other health problems. ⋯ We describe the features of mobile phones that make them a particularly promising platform for health interventions, and we identify five basic intervention strategies that have been used in mobile-phone health applications across different health conditions. Finally, we outline the directions for future research that could increase our understanding of functional and design requirements for the development of highly effective mobile-phone health interventions.
-
The current volume and complexity of genetic tests, and the molecular genetics knowledge and health knowledge related to interpretation of the results of those tests, are rapidly outstripping the ability of individual clinicians to recall, understand and convey to their patients information relevant to their care. The tailoring of molecular genetics knowledge and health knowledge in clinical settings is important both for the provision of personalized medicine and to reduce clinician information overload. In this paper we describe the incorporation, customization and demonstration of molecular genetic data (mainly sequence variants), molecular genetics knowledge and health knowledge into a standards-based electronic health record (EHR) prototype developed specifically for this study. ⋯ This research shows a feasible model for delivering patient sequence variants and presenting tailored molecular genetics knowledge and health knowledge via a standards-based EHR system prototype. EHR standards can be extended to include the necessary patient data (as we have demonstrated in the case of the CCR), while knowledge can be obtained from external knowledge bases that are created and maintained independently from the EHR. This approach can form the basis for a personalized medicine framework, a more comprehensive standards-based EHR system and a potential platform for advancing translational research by both disseminating results and providing opportunities for new insights into phenotype-genotype relationships.
-
Comparative Effectiveness Research (CER) is designed to provide research evidence on the effectiveness and risks of different therapeutic options on the basis of data compiled from subpopulations of patients with similar medical conditions. Electronic Health Record (EHR) system contain large volumes of patient data that could be used for CER, but the data contained in EHR system are typically accessible only in formats that are not conducive to rapid synthesis and interpretation of therapeutic outcomes. In the time-pressured clinical setting, clinicians faced with large amounts of patient data in formats that are not readily interpretable often feel 'information overload'. ⋯ We developed a 'VisualDecisionLinc' (VDL) tool prototype that uses visual analytics to provide summarized CER-derived data views to facilitate rapid interpretation of large amounts of data. We highlight the flexibility that visual analytics offers to gain an overview of therapeutic options and outcomes and if needed, to instantly customize the evidence to the needs of the patient or clinician. The VDL tool uses visual analytics to help the clinician evaluate and understand the effectiveness and risk of different therapeutic options for different subpopulations of patients.