We propose a cognitive system for patient-centric care that leverages and combines natural language processing, semantics, and learning from users over time to support care professionals working with large volumes of patient notes. The proposed methods highlight the entities embedded in the unstructured data to provide a holistic semantic view of an individual. A user-based evaluation is presented, showing consensus between the users and the system.
In order to cover the requirements for interoperability in the Norwegian context, we studied the terminology binding of archetypes to terminology expressions created with the SNOMED-CT compositional grammar. As a result we identified important challenges categorized as technical, expressivity, human, and models mismatch.
We created the Terminology Status Application Programming Interface (API) to assist users in mapping obsolete codes to current RxNorm, SNOMED CT and LOINC concepts. Use cases include support for information retrieval, maintenance of value sets, and analytics of legacy clinical databases. Our terminology status APIs typically receive over 4 million calls per month on average.
Jean-Marie Rodrigues, Sukil Kim, Syed Aljunid, Jae Jin Lee, Huib Ten Napel, Béatrice Trombert
1334 - 1334
The International Classification of Health Interventions (ICHI) alpha2 2016 Section 1 Interventions on Body Systems and Functions is based on ISO 1828 international standard named categorial Structure (CAST). This is not sufficient to represent the meaning of ICD9-CM Volume 3 labels. We propose to modify it by using the SNOMED CT concept model.
Arash Shaban-Nejad, Anya Okhmatovskaia, Eun Kyong Shin, Robert L. Davis, David L. Buckeridge
1335 - 1335
The major goal of our study is to provide an automatic evaluation framework that aligns the results generated through semantic reasoning with the best available evidence regarding effective interventions to support the logical evaluation of public health policies. To this end, we have designed the POLicy EVAlUation & Logical Testing (POLE.VAULT) Framework to assist different stakeholders and decision-makers in making informed decisions about different health-related interventions, programs and ultimately policies, based on the contextual knowledge and the best available evidence at both individual and aggregate levels.
Fadi Shamoon, Harald Leitich, Jeroen S. de Bruin, Andrea Rappelsberger, Klaus-Peter Adlassnig
1336 - 1336
Evidence-based clinical guidelines positively effect physician decision-making. Actionable clinical guidelines that actively trigger alerts, reminders, and instructive texts will increase effectiveness. We applied Activiti, a Business Process Model and Notation language system to model a clinical guideline for the prevention of mother-to-child transmission of hepatitis B as a computerized clinical workflow. Furthermore, we implemented an interconnected Arden-Syntax-based medical rule engine, which is part of the ARDENSUITE software.
Mark R. Stöhr, Gudrun Helm, Raphael W. Majeed, Andreas Günther
1337 - 1337
The German Center for Lung Research (DZL) is a research network with the aim of researching respiratory diseases. To perform consortium-wide queries through one single interface, it requires a uniform conceptual structure. No single terminology covers all our concepts. To achieve a broadly accepted and complete ontology, we developed a platform for collaborative metadata management “CoMetaR”. Anyone can browse and discuss the ontology while editing can be performed by authenticated users.
Haixia Sun, Junlian Li, Yingjie Wu, Lei Wang, Kin Wah Fung
1338 - 1338
To handle differences in affiliation names submitted with biomedical journal articles, we build an affiliation knowledge base named Authority File for Affiliations (AFA) based on ontology principles. There are currently 113,700 affiliation concepts with about 583,700 affiliation names. The AFA becomes an essential tool in managing citation information and data analysis.
Nurses as the largest Health Care Workers group, are extrememly important in promoting eHealth. Before promoting eHealth in a structured system, personal use of eHealth like as for Health Information Seeking; is important. Therefore study was done on the use of electronic health information sources among the Sri Lankan Nursing students. It showed that though they do use a wide range of sources, but they are unable to use them specifically and reliably.
This pilot study investigated problems of electronic health records (EHR), which have been used by nurses as a clinical decision tool. The investigation was conducted based on case records retrieved from the national database of medical adverse events. Detailed data related to nursing services must continue to be collected to establish a clearer linkage of EHR data and scholary information.
The objective of this research is to propose to develop an innovative distance function, called SNOMED distance, which captures the nature of the semantic distance within the topological structure of SNOMED, to identify semantic similarity between clinical trials.
A proposal on terminology adoption for the Problem and Encounter Reason capturing in the Hong Kong Hospital Authority Family Medicine Module was suggested. Given the complexity of the project, mapping had been conducted as preparatory work in the early phase of development.
In a hierarchical diagnosis and treatment policy local tertiary hospitals assume the majority of clinic service, improving patient medical experience and enhancing service quality. Information technologies such as comprehensive self-services, and palm medical APPs can help solve these problems.
China has issued and implemented standard clinical pathways (Chinese standard CPs) since 2009; however, they are still paper-based CPs. The aim of the study is to reorganize Chinese standard CPs based on related Chinese medical standards, by using archetype approach, and develop an Open platform for CP (openCP) in China.
The purpose of this study is to integrate Japanese medical device adverse event terminologies for evaluating terminological consistency. We represented hierarchy and relations among terms using Resource Description Framework (RDF). There were 3521 classes and 14650 properties. As a result of evaluating the consistency of the description in SPARQL, it was evident that the same notations existed within different terminologies (category terms and terms) and some terms had plural definitions.
Javier Zelechower, José Astudillo, Francisco Traversaro, Francisco Redelico, Daniel Luna, Fernan Quiros, Eduardo San Roman, Marcelo Risk
1346 - 1346
The Big Data paradigm can be applied in intensive care unit, in order to improve the treatment of the patients, with the aim of customized decisions. This poster is about the infrastructure necessary to built a Big Data system for the ICU. Together with the infrastructure, the conformation of a multidisciplinary team is essential to develop Big Data to use in critical care medicine.
To build evidence-based medicine (EBM) databases in China, we developed a semantic structure of EBM database information model by top-level, middle-level, and bottom-level structure. Top-level structure was composed of three modules including Literature Characteristics, Treatment Process and Evidence Levels. We further specified each top-level module based on international and national metadata and health related standards. Finally, we developed a complete information semantic model of EBM resources by an ontology tool. It can provide a reference for semantic construction of Chinese EBM database.
Based on the System Development Life Cycle, a hospital based nursing adverse event reporting system was developed and implemented which integrated with the current Hospital Information System (HIS). Besides the potitive outcomes in terms of timeliness and efficiency, this approach has brought an enormous change in how the nurses report, analyze and respond to the adverse events.
Thirty-nine electronic English and Chinese articles on data quality assessment of the Chinese AIDS information system were critically reviewed. Some performance assessment related indicators of data quality have improved since the system was launched in 2008. After a thematic analysis of the factors that may affect data quality, four domains were identified. They are data management, data collector, information system, and data collection environment. The findings are useful to guide data quality improvement effort.
The purpose of this study was to evaluate the Clinical Nursing Information System (CNIS) in Taiwan regional hospital. In 2016, a total of 333 nurses responded to the Technology Acceptance Model-based questionnaire after 15 months of CNIS implementation. The results showed positive acceptance toward CNI, especially among those nurses who were younger, those who worked as administrative managers or in non-critical care units, and had advanced computer skills.
Theresa A. Cullen, Suranga N. Kasthurirathne, Jenna M. Norton, Andrew S. Narva
1354 - 1354
Chronic care coordination efforts often focus on the needs of the healthcare team and not on the individual needs of each patient. However, developing a personalized care plan for patients with Chronic Kidney Disease (CKD) requires individual patient engagement with the health care team. We describe the development of a CKD e-care plan that focuses on patient specific needs and life goals, and can be personalized according to provider needs.
Mario A. Cypko, Matthaeus Stoehr, Steffen Oeltze-Jafra, Andreas Dietz, Heinz U. Lemke
1355 - 1355
In complex cancer cases, Bayesian networks can support clinical experts in finding the best patient-specific therapeutic decisions. However, the development of decision networks requires teamwork of at least one domain expert and one knowledge engineer making the process expensive, time-consuming, and prone to misunderstandings. We present a novel method for guided modeling. This method enables domain experts to model collaboratively without the need of knowledge engineers, increasing both the development speed and model quality.
The purpose of this research is to make the medical report generation process more practical, fast and reliable, both for the health professional and for the patient. We created an ontology and modeling of a structured report (SR) Standard DICOM SR.
Event notifications are real-time, electronic alerts that have the promise of improving population health by exchanging critical information to a patient's extended care team. In a trial of event noficiations in U.S. Veterans Affairs facilities, we seek to understand the impact of notifications on health care utilization within 30 and 90-days. Lessons from the trial have implications beyond the evidence by informing strategies to develop and implement event notifications in other health systems.