Judith W. Dexheimer, Lijun Gu, Yuping Guo, Carolyn Kercsmar
1004 - 1004
Asthma is one of the most common chronic pediatric conditions. Providing evidence-based, guideline-appropriate care for asthma is complex. A computerized system may help providers with guideline compliance. The AsthmaTreatSmart application is a stand-alone web-based system developed in Pulmonary medicine with a multidisciplinary team based on national asthma guidelines. The application collects history and symptom information to assign a severity categorization. Medication reconciliation of asthma medications is performed with input from the patient. Severity and medication recommendation are provided for the provider. A personalized action plan and medication summary including medications, etc. is created. The system is successfully used in 6 outpatient clinics and current work is focused on integration with the electronic health record.
How to report and summarize a user's health or wellness status from the Electronic Health Records (EHR) is a important topic since a well-designed health report can provide not only a valued information source for users to exam their physical health status but also a guidance to a better health level. Existing health reports are not totally satisfying and easily bores a user by words and numeral data in them. Facial complexion is one of important indicator in the clinical diagnosis. The pathological changes of health status could often be diagnosed by inspecting the changes of facial complexion. Based on this facial complexion idea, a visualized health report, which reversely visualizes a user's health status directly on his/her outside appearance, is proposed to provide a better alternative than conventional text-based report. Due to its unique characteristic, the proposed visualized health information and guidance is expected to provide valued personalized health information and also effectively encourage users toward healthier lifestyle.
This study aims to provide both a quantitative and a qualitative analysis of the usability of the most popular electronic dental records in Brazil regarding its clinical and administrative features. The softwares not only will be evaluated regarding their usage among the Brazilian dental professionals but also regarding their functionalities (present, used and desired) and the difficulties encountered by the dentists during their use.
Lina F. Soualmia, Catherine Letord, Tayeb Merabti, Nicolas Griffon, Jacques Manel, Stéfan J. Darmoni
1007 - 1007
The concept-oriented structure of the MeSH® thesaurus is not yet in common use. Nevertheless, it has been shown that a concept-based querying of PubMed may be of interest. To take full advantage of the concept-oriented structure of MeSH in the information retrieval tool associated with the CISMeF catalogue, it was necessary to translate such concepts into French.
Randi Karlsen, Jose Enrique Borrás Morell, Luis Fernández Luque, Vicente Traver Salcedo
1008 - 1008
Health information retrieval and YouTube can be used as powerful tools to improve user's health knowledge. However, YouTube videos must be carefully analysed in order to avoid misleading, inaccurate, obsolete and incorrect health content.
We present an approach for re-ranking health videos obtained from YouTube, called Domain-based ranking. Our system automatically identifies videos coming from trusted sources (channels), such as hospitals and health organizations, and re-ranks YouTube results so that such videos are presented first in the ranking list. Video and channel metadata are used to automatically determine if a video is provided by a trusted source. The approach is tested and results show that the amount of relevant and reliable videos ranked within top-10 increase when using Domain-based ranking, compared with the original YouTube ranking.
Eirik Årsand, Stein Olav Skrøvseth, Ole Hejlesen, Alexander Horsch, Fred Godtliebsen, Astrid Grøttland, Gunnar Hartvigsen
1010 - 1010
Patient diaries as apps on mobile phones are becoming increasingly common, and can be a good support tool for patients who need to organize information relevant for their disease. Self-management is important to achieving diabetes treatment goals and can be a tool for lifestyle changes for patients with Type 2 diabetes. The autoimmune disease Type 1 diabetes requires a more intensive management than Type 2 – thus more advanced functionalities is desirable for users. Both simple and easy-to-use and more advanced diaries have their respective benefits, depending on the target user group and intervention. In this poster we summarize main findings and experience from more than a decade of research and development in the diabetes area. Several versions of the mobile health research platform—the Few Touch Application (FTA) are presented to illustrate the different approaches and results.
Laszlo Balkanyi, Stefan Schulz, Ronald Cornet, Olivier Bodenreider
1011 - 1011
This work aims at understanding the state of the art in the broad contextual research area of “medical concept representation”. Our data support the general understanding that the focus of research has moved toward medical ontologies, which we interpret as a paradigm shift. Both the opinion of socially active groups of researchers and changes in bibliometric data since 1988 support this opinion. Socially active researchers mention the OBO foundry, SNOMED CT, and the UMLS as anchor activities.
Alexa Love, Corey W. Arnold, Suzie El-Saden, David S. Liebeskind, Lewellyn Andrada, Jeffrey Saver, Alex A.T. Bui
1012 - 1012
With the large number of clinical practice guidelines available, there is an increasing need for a comprehensive unified model for acute ischemic stroke treatment to assist in clinical decision making. We present a unified treatment model derived through review of existing clinical practice guidelines, meta-analyses, and clinical trials. Using logic from the treatment model, a Bayesian belief network was defined and fitted to data from our institution's observational quality improvement database for acute stroke patients. The resulting network validates known relationships between variables, treatment decisions and outcomes, and enables the exploration of new correlative relationships not defined in current guidelines.
Daniel Capurro, Matthias Ganzinger, José E. Pérez-Lu
1013 - 1013
This work explores a) the use of e-health systems in the context of palliative care and b) the information needs of patients, care givers and healthcare professionals in palliative care. To achieve this we conducted a systematic literature review and interviewed health professionals in Germany, Peru, and Chile. All countries have in common that specific e-health systems are rarely used in this context and the presence of a gradient of available care between rural and urban areas.
The purpose of this study is to extract genes that could distinguish between two subtypes (diffuse and intestinal) of gastric cancer (GC) from their gene expression profile, to build a classifier based on the genes and to investigate the relationships among the selected genes, because there are big differences in the survival curve and the medical treatment between the subtypes. First, we applied Wilcoxon test, independent component analysis (ICA) and multiple logistic regression (MLR) to the profile, and conducted a classifier consisting of only three genes. We validated the classifier using test data with new 9 samples (blind test). The classifier yielded the accuracy of 100%. Finally, using the 18 genes selected by MLR and specific to each subtype, Bayesian Network was constructed, and compared with the network from GeneMANIA. Consequently, these networks were very similar each other.
Sooyoung Yoo, Seok Kim, Kee-Hyuck Lee, Rong-Min Baek, Hee Hwang
1015 - 1015
Although the adoption rates for Electronic Health Records (EHRs) are growing, significant opportunities for further advances in EHR system design remain. The goal of this study was to identify issues that should be considered in the design process for the successful development of future systems by analyzing end users' service requests gathered during a recent three-year period after a comprehensive EHR system was implemented at Seoul National University's Bundang Hospital (SNUBH) in South Korea. Data on service requests from end users of the EHR system made from 2008 through 2010 were analyzed and categorized. From our study, we found that the EHR system has evolved to optimize ease of use and special functionalities for particular groups of users and particular subspecialties.
Rex Yiu, Vicky Fung, Karen Szeto, Veronica Hung, Ricky Siu, Johnny Lam, Daniel Lai, Christina Maw, Adah Cheung, Raman Shea, Anna Choy
1016 - 1016
In Hong Kong, elderly patients discharged from hospital are at high risk of unplanned readmission. The Integrated Care Model (ICM) program is introduced to provide continuous and coordinated care for high risk elders from hospital to community to prevent unplanned readmission.
A multidisciplinary working group was set up to address the requirements on developing the electronic forms for ICM program. Six (6) forms were developed. These forms can support ICM service delivery for the high risk elders, clinical documentation, statistical analysis and information sharing.
The Community Medical ICT Network service at the Nagasaki, Japan was established in 2009. Medical information network for sharing patients data was investigated focused on the access log data from April of 2009 and October of 2010. The total number of the access to the medical information was 30,914 of 2,213 patients. And the total number of access of the image including diagnostic imaging report, medical examination, treatment and medical documents was 10,278(33.2%), 8,949(28.9%), 6,896(22.3%) and 4,791(15.5%) respectively. These results showed that these medical information had enough valued for sharing in the regional medicine. In conclusion, many types of medical information should be required for sharing in the community medical ICT network in Japan.
When children undergo surgery, the parents waiting for them outside the room feel extreme anxiety. SNUH was a full EMR hospital. But nurses had to manually operate an electronic display board which provided information regarding the progresses of the operations. The parents had to be located in front of the board. It was a unilateral and passive system.
Therefore, we were about to improve the system to provide efficient information satisfying both parents and nurses. This service, which connected to the EMR system to provide real time location of patients undergoing operations, provide information through an electronic display board outside the operating room and SMS messages. We could reduce uneasiness of patients' families, increase satisfactions, and further, not only contribute to establishing the improved service of SNUH but also lessening unnecessary duties of nurses.
Seung Kwon Hong, Mi Sun Lim, Kyung Hwan Kim, Jin Wook Choi, Ju Han Kim, Jung Wook Seo
1019 - 1019
The Purpose of this study is to investigate factors affecting satisfaction of the Electronic Health Records (EHRs) in Seoul National University of Korea, from a physicians' perspectives. Administration of a survey instrument containing 6 items to cover characteristics of the user's population in hospital. A sample of 327 users was selected including medical sectors for the study. The Overall response rate was 16.5%. It is mores satisfaction with EHRs that pharmacy and technician sector than physician sector after implementing the EHRs system. Of the total respondents, there was a significant association between performance ‘System functionality and performance of EHRs’ and ‘overall satisfaction level with EHRs’ (p < 0.01). In addition, physicians stated other factors that actually affected satisfaction of the EHRs systems in Hospital. Among these factors, summary note of discharge and operation factors are most correlation with satisfaction.
An electrocardiogram (ECG) is an indispensable tool to diagnose cardiac diseases, such as ischemic heart disease, myocarditis, arrhythmia, and cardiomyopathy. Since ECG patterns vary depend on patient status, it is also used to monitor patients during treatment and comparison with ECGs with previous results is important for accurate diagnosis. However, the comparison requires connection to ECG data server in a hospital and the availability of data connection among hospitals is limited. To improve the portability and availability of ECG data regardless of server connection, we here introduce conversion of ECG data into 2D barcodes as text data and decode of the QR code for drawing ECG with Google Chart API. Fourteen cardiologists and six general physicians evaluated the system using iPhone and iPad. Overall, they were satisfied with the system in usability and accuracy of decoded ECG compared to the original ECG. This new coding system may be useful in utilizing ECG data irrespective of server connections.
Standard Japanese electronic medical record (EMR) systems are associated with major shortcomings. For example, they do not assure lifelong readability of records because each document requires its own viewing software program, a system that is difficult to maintain over long periods of time. It can also be difficult for users to comprehend a patient's clinical history because different classes of documents can only be accessed from their own window. To address these problems, we developed a document-based electronic medical record that aggregates all documents for a patient in a PDF or DocuWorks format. We call this system the Document Archiving and Communication System (DACS). There are two types of viewers in the DACS: the Matrix View, which provides a time line of a patient's history, and the Tree View, which stores the documents in hierarchical document classes. We placed 2,734 document classes into 11 categories. A total of 22,3972 documents were entered per month. The frequency of use of the DACS viewer was 268,644 instances per month. The DACS viewer was used to assess a patient's clinical history.
The ratio of correct diagnosis for primary headache has always been relatively low for general practitioners due to the unacquaintance with headache guideline in Chinese primary hospitals. This study proposed a computerized headache guideline method using SAGE module and developed a decision support system for headache diagnosis, which could be expected to help general practitioners of primary hospitals improve diagnostic accuracy. 282 previously diagnosed cases from EMR were used to evaluate the diagnostic accuracy of the system, the result is: migraine 144/153 (94.1%), tension-type headache 89/100 (89.0%), cluster headache 10/11 (90.9%) and chronic daily headache 53/57(93.0%). The proposed system is in the starting phase of the implementation at the outpatient department of Neurology in Chinese PLA general hospital.
Clinical Guidelines (CG) are recommendations on the appropriate treatment and care of people with specific diseases and conditions. CG should be used by both physicians and patients to make the informed decision. However, the CGs are not well used due to their complexity and because they are frequently updated. The computerized CGs are proposed to make use of the computer to do the decision making. However, it needs a lot of human effort to transform the narrative CG into computerized CG. In this paper, we proposed a method to use the NLP techniques to extract the fine-grained information from the text based CG automatically. Such information could be easily converted to the computer interpretable models.
John Strauss, Arturo Martinez Peguero, Graeme Hirst
1024 - 1024
In preparation for a clinical information system implementation, the Centre for Addiction and Mental Health (CAMH) Clinical Information Transformation project completed multiple preparation steps. An automated process was desired to supplement the onerous task of manual analysis of clinical forms. We used natural language processing (NLP) and machine learning (ML) methods for a series of 266 separate clinical forms. For the investigation, documents were represented by feature vectors. We used four ML algorithms for our examination of the forms: cluster analysis, k-nearest neigh-bours (kNN), decision trees and support vector machines (SVM). Parameters for each algorithm were optimized. SVM had the best performance with a precision of 64.6%. Though we did not find any method sufficiently accurate for practical use, to our knowledge this approach to forms has not been used previously in mental health.
Most electronic medical record (EMR) systems in Japan are equipped with nursing documentation functions. Electronic nursing records (ENRs) are much more accessible to doctors and paramedical staff than paper-based record systems. Face-to-face communication might be used less often to acquire patient information collected by nurses if EMR systems were effectively used. We conducted a questionnaire survey to investigate the methods used by other health professionals to acquire patient information collected by nurses under EMR implementation at two university hospitals. There were 153 responses, which showed that 51% of doctors and 16% of paramedical staff still often used face-to-face communication even though more than 70% of them often accessed the ENR. Only 35% of doctors and paramedical staff recognized that the EMR system helped reduce the time needed to acquire patient information; furthermore, 32% thought that using the EMR system to acquire patient information was bothersome. These results indicate that the operability of EMR systems is still insufficient for health professionals.
We developed a tele-health consultation system that combines a sphygmomanometer with a tele-conference system. These were placed in pharmacies and the University. We selected five pharmacies to set up a consultation room; one in a local area, two in a suburban area, and the remaining two in an urban area. Nurses with more than 5 years of clinical experience were assigned as consultants. These consultants offer health consultation but do not practice medicine. Some researchers have indicated the economic viability of at-home health management systems, but nothing has been researched on the economic viability of tele-health consultation. The objective of present study was estimated Willingness to Payment (WTP) of Tele-health consultation service. The WTP was estimated by Double-Bounded Dichotomous-Choice model. We performed logistic-regression analysis to confirm factors to affect WTP. The number of the respondent was 480. Mean WTP was calculated 495 yen and the median was 367 yen. There was significant difference for factor of “annual income”, “have a willingness to use this system”, and “have a child/children”.
Today, the number of foreign residents in Japan is increasingdue to globalization. However, Japan is behind other advanced countries in accepting oversea patients. Japan has to improve medical institutions' readiness to accept foreign patients, and nurture medical interpreters. To address these issues, we developed a language support application for smart phones. Anyone can download it freely.