Ebook: Integrating Information Technology and Management for Quality of Care

The current volume presents the papers of the ICIMTH (International Conference on Informatics, Management, and Technology in Healthcare). The Organising Committee and the Scientific Programme Committee would like to present to the academic community the scientific outcomes of the ICIMTH 2014 Conference, which is being held from 10 to 13 July, 2014 in Athens, Greece.

The ICIMTH 2014 Conference is the 12th Annual Conference in this series of scientific events, gathering scientists from all continents as well as from the hosting country in the field of Biomedical and Health Informatics.

The Conference has a major focus on the integration of the applications of Biomedical Informatics from Clinical Informatics, Health Informatics to Public Health Informatics as well as on ICT applications in the Healthcare domain. Considering that Management and Organisational Issues play an important role in the implementation phase of Biomedical Informatics applications, topics related to the above themes are also included as an integral part to the overall theme of the Conference. We are treating the field of Biomedical Informatics in a very broad framework examining the research and applications outcomes of Informatics from cell to populations, including a number of Technologies such as Imaging, Sensors, and Biomedical Equipment and Management and Organisational subjects, such as such as legal and social issues and setting research priorities in Health Informatics.

However, in this volume we have incorporated only the papers and posters accepted for presentation, whereas all other scientific events within the Conference are incorporated within the local electronic version of the proceedings. It should be noted that the Proceedings are published for the first time in this series of the Conference as an e-book for ease of use and browsing without losing any of the advantages of indexing and citation in the biggest Scientific Literature Databases, such as Medline and Scopus that this Series, Studies in Health Technology and Informatics (SHTI) of IOS Press, provides.

At the end of the deadline we have gathered 125 submissions, from which after reviewing we have accepted 79 as full papers and 12 poster presentations to be included in the volume proceedings, as well as 2 workshops and 3 tutorials.

It goes without saying that the compilation of the proceedings is a huge task and this effort could not have been done without the dedication, accuracy, persistence, and tiresome contribution of our two Assistant Editors, mainly performed by Miss Katia Kolokathi but also with the work of Mr. Parisis Gallos both members of the research staff of the Health Informatics Laboratory of the University of Athens.

The Organising Committee working along with the Scientific Programme Committee is dedicated to organise a successful scientific event and will arrange also to have an excellent stay for you and your fellows in Athens.

Athens, 15 06 2014

The Editors

John Mantas, Mowafa S. Househ, Arie Hasman

This contribution introduces the Technology Acceptance model. Since information systems are still underutilized, application of models of user acceptance can provide important clues about what can be done to increase system usage.

The improved understanding of the whole healthcare and wellbeing pathway for individuals depends on the power of healthcare information, being made readily available and easily interpretable by both humans and machines. In the centre of this challenge lies the concept of interoperability, as a way to provide fundamental linkage, integration and meaningful use of healthcare data between systems, organisations and users. In particular, semantic interoperability can offer a way of enriching healthcare data with context and meaning, in order to achieve enhanced understanding and better evidence-based interpretation of disease and wellbeing for an individual, within the context of healthcare provision and clinical research. In this keynote paper, the concept of semantic interoperability, for healthcare data linkage and exchange, is critically discussed. An emphasis is given on the importance of clinical terminologies and associated services, as means for adding meaning to routinely collected clinical data.

Mobile Health is fast becoming one of the fastest growing sectors of health as health tries to shift to patient-centric solutions. Putting the patients in the centre of care also forces them to take control of their wellbeing, health management and/or disease management. This is especially relevant when the management is constant as it is the case with chronic diseases

We were told at school, “If you want to solve a problem you have to identify it first”, you are then halfway towards the solution. This implied of course that the other half of the solution is a straight forward exercise, or it can be provided by a standard predetermined procedure which can be found on a shelf of ready-made solutions. This procedure, even though it has limitations, was followed extensively in solving medical problems and proved to be successful especially in cases where the available options for the solution were limited, and the only criteria to determine the final solution were cost, convenience, time, availability, etc. In other words the solution-treatment was primarily based on predetermined options, and not patient based.

Biomedical vocabularies vary in scope, and it is often necessary to utilize multiple vocabularies simultaneously in order to cover the full range of concepts relevant to a given biomedical application. However, as the number and size of these resources grow both redundancy (i.e., different vocabularies containing similar terms) and inconsistency (i.e., different terms in multiple vocabularies referring to the same entity) between the vocabularies increase. Therefore, there is a need for automatically aligning vocabularies. In this paper, we explore and propose new methods for detecting probable matches between two vocabularies. The methods build upon existing string similarity functions, enhancing these functions for the context of semi-automated vocabulary matching.

There is an open controversy in the use of the terms personalised and precision medicine and what they refer to in different contexts. In the present work we have considered the data types managed by each of them rather than their application and we have been able to identify commonalities but also differences in the types of data addressed in both approaches that would ultimately lead to include, from a data perspective, personalised medicine within the broader precision medicine term.

Interpretation-only providers are becoming increasingly prominent in the field of Direct-To-Consumer genomics. We examined the information obtained from two different providers (Interpretome and Promethease) when analysing the same personal genome. We found large discrepancies between the results from these services for the list of SNPs included in the analysis, but a high level of concordance in their interpretation when the SNPs were coincident.

Nowadays pervasive health care monitoring environments, as well as business activity monitoring environments, gather information from a variety of data sources. However it includes new challenges because of the use of body and wireless sensors, nontraditional operational and transactional sources. This makes the health data more difficult to monitor. Decision making in this environment is typically complex and unstructured as clinical work is essentially interpretative, multitasking, collaborative, distributed and reactive. Thus, the health care arena requires real time data management in areas such as patient monitoring, detection of adverse events and adaptive responses to operational failures. This research presents a new architecture that enables real time patient data management through the use of intelligent data sources.

Many clinical research databases are built for specific purposes and their design is often guided by the requirements of their particular setting. Not only does this lead to issues of interoperability and reusability between research groups in the wider community but, within the project itself, changes and additions to the system could be implemented using an ad hoc approach, which may make the system difficult to maintain and even more difficult to share. In this paper, we outline a hybrid Entity-Attribute-Value and relational model approach for modelling data, in light of frequently changing requirements, which enables the back-end database schema to remain static, improving the extensibility and scalability of an application. The model also facilitates data reuse. The methods used build on the modular architecture previously introduced in the CURe project.

Cloud computing, Internet of things (IOT) and NoSQL database technologies can support a new generation of cloud-based PHR services that contain heterogeneous (unstructured, semi-structured and structured) patient data (health, social and lifestyle) from various sources, including automatically transmitted data from Internet connected devices of patient living space (e.g. medical devices connected to patients at home care). The patient data stored in such PHR systems constitute big data whose analysis with the use of appropriate machine learning algorithms is expected to improve diagnosis and treatment accuracy, to cut healthcare costs and, hence, to improve the overall quality and efficiency of healthcare provided. This paper describes a health data analytics engine which uses machine learning algorithms for analyzing cloud based PHR big health data towards knowledge extraction to support better healthcare delivery as regards disease diagnosis and prognosis. This engine comprises of the data preparation, the model generation and the data analysis modules and runs on the cloud taking advantage from the map/reduce paradigm provided by Apache Hadoop.

In Healthcare Decision Support System, the development and evaluation of effective “Quality of Care” (QOC) indicators, in simulation-based training, are key feature to develop resilient and antifragile organization scenarios. Is it possible to conceive of QOC not only as a result of a voluntary and rational decision, imposed or even not, but also as an overall system “emergent phenomenon” out of a small-world network of relational synthetic actors, endowed with their own personality profiles to simulate human behaviour (for short, called “subjects”)? In order to answer this question and to observe the phenomena of real emergence we should use computational models of high complexity, with heavy computational load and extensive computational time. Nevertheless, De Giacomo's Elementary Pragmatic Model (EPM) intrinsic self-reflexive functional logical closure enables to run simulation examples to classify the outcomes grown out of a small-world network of relational subjects fast and effectively. Therefore, it is possible to take note and to learn of how much strategic systemic interventions can induce context conditions of QOC facilitation, which can improve the effectiveness of specific actions, which otherwise might be paradoxically counterproductive also. Early results are so encouraging to use EPM as basic block to start designing more powerful Evolutive Elementary Pragmatic Model (E2PM) for real emergence computational model, to cope with ontological uncertainty at system level.

Public health information systems are often implemented considering the functionalities and requirements established by administrative staff or researchers, but sometimes ignoring the particular needs of decision makers. This paper describes a proposal to support the design of a Decision Support System for Public Health Surveillance in Colombia, by conducting a qualitative study to identify the real needs of people involved in decision making processes. Based on the study results, an intelligent computational component that supports Data Analysis Automation, Prediction of future scenarios and the identification of new Behavioral Patterns is proposed. The component will be implemented using the Case Based Reasoning methodology, which will be integrated as a new component of the Open Source DHIS2 Platform, enabling public health decision-making.

More and more people search for health information regarding diseases, diagnoses and treatments over the Web. However, lay people often have difficulties in assessing the understandability of related articles. Therefore, they could benefit from a system, which computes the medical expert degree of a corresponding piece of text in advance. In this paper we present an approach to automatically compute this expert degree using a machine learning approach. For evaluation purposes we constructed a large text corpus and tested our trained text classifier, which is based on Support Vector Machines.

Conventional case-based reasoning (CBR) does not perform efficiently for high volume dataset because of case-retrieval time. Some previous researches overcome this problem by clustering a case-base into several small groups, and retrieve neighbors within a corresponding group to a target case. However, this approach generally produces less accurate predictive performances than the conventional CBR. This paper suggests a new case-based reasoning method called the Clustering-Merging CBR (CM-CBR) which produces similar level of predictive performances than the conventional CBR with spending significantly less computational cost.

The education in First Aid through health education programs can help in promoting the health of the population. Meanwhile, the development of alternative forms of education with emphasis on distance learning implemented with e-learning creates an innovative system of knowledge and skills in different population groups. The main purpose of this research proposal is to investigate the effectiveness of the educational program to candidates educators about knowledge and emergency preparedness at school. The study used the Solomon four group design (2 intervention groups and 2 control groups). Statistical analysis showed significant difference within the four groups. Intervention groups had improved significantly their knowledge showing that the program was effective and that they would eventually deal with a threatening situation with right handlings. There were no statistical significant findings regarding other independent variables (p>0,05).The health education program with the implementation of synchronous distance learning succeeded to enhance the knowledge of candidates educators.

The aim of the present study is to analyze the popularity of information sources of medical educational sites <webmedinfo.ru>, medical information portal <meduniver.com>, medical portal for students <6years.net>, electronic library of medical literature <booksmed.com>, <medliter.ru> and <medbook.net.ru>. Three sites (<www.webmedinfo.ru>, <meduniver.com> and <6years.net>) provide sources of medical literature, educational videos, medical histories, medical papers and medical popular literature. And three other sites (<www.booksmed.com>, <www.medliter.ru> and <www.medbook.net.ru>) provide sources for electronic medical books on various subjects. Using on-line programs Alexa and Cy-pr we have analyzed the website's rating and identified the main data and time-varying data of the sites. Calculated Alexa Rank rating was determined for each site. Our study has shown that the most popular information sources of medical education among the six studied sites for Russian users is <meduniver.com>; the site <booksmed.com> is at the second place referring to the Alexa Rank rating and the site <webmedinfo.ru> is at the second place referring to the citation index in Yandex. The most popular medical site of electronic medical books is <booksmed.com>.

The purpose of this exploratory study is to provide an overview of a web-based health educational site created by the King Faisal Specialist Hospital and Research Center (KFSH&RC) in the Kingdom of Saudi Arabia (KSA). Sources of data included two interviews with Saudi IT personnel, three health educators, and two medical consultants working at KFSH&RC. The interviews ranged between 45 minutes and 120 minutes. The KFSH&RC website was also searched for the type of health information content posted. Results show that the KFSH&RC web-based health educational site provides health information through a medical encyclopedia, a social networking platform, health educational links, and targeted health information for children, which includes tools such as games and coloring books. Further research is needed on the effectiveness of the KFSH&RC web-based health education site in terms of improving knowledge and changing behavior of Saudi patients. The study recommends that targeted web-based health education strategies should be developed to reach large rural populations which have inadequate computer skills and limited access to the internet.

The Health Information Technology can improve public health, quality of health care etc. Thus, it is important for professionals to be well educated by training programs. The aim of this paper is to record all the educational programs with specializations in Health Informatics, Medical Informatics, Bioinformatics, Biomedical Informatics and Biomedical Engineering in European Universities and Institutions. An on-line research was conducted on Scopus, PubMed, Scholar Google, and Google. More than 150 universities and colleges in Europe conduct educational programs for these domains. The majority them, expertise in Biomedical Engineering (31%), 22% of the educational programs correspond to Bioinformatics, while Health Informatics studies have 18%. On the last few years, a growth of Health informatics professionals has been observed in Europe.

Laboratory turnaround time is considered one of the most important indicators of work efficiency in hospitals, physicians always need timely results to take effective clinical decisions especially in the emergency department where these results can guide physicians whether to admit patients to the hospital, discharge them home or do further investigations. A retrospective data analysis study was performed to identify the effects of ER and Lab staff training on new routines for sample collection and transportation on the pre-analytical phase of turnaround time. Renal profile tests requested by the ER and performed in 2013 has been selected as a sample, and data about 7,519 tests were retrieved and analyzed to compare turnaround time intervals before and after implementing new routines. Results showed significant time reduction on “Request to Sample Collection” and “Collection to In Lab Delivery” time intervals with less significant improvement on the analytical phase of the turnaround time.

Current research in health informatics should provide the techniques and tools that will enable the development of an efficient hospital information ecosystem. The different information systems (IS) will be able to efficiently communicate with each other and provide a patient oriented environment. It is thus important to provide a clear understanding of this ecosystem during the analysis phase. The solution is to develop a hospital information systems ontology that will provide the infrastructure for a clear understanding of this ecosystem and thus lead to the development of systems that will be able to work efficiently with each other. This ontology is developed here and its value is demonstrated through a case study.

Self-monitoring experiments are becoming increasingly common as it is the case in other complex environments their interpretation and reproducibility relies heavily in the amount of associated meta-data available. In this work we propose a standardised reporting guideline to annotate these experiments and facilitate their interpretation. The existence of such reporting guideline may lead the development of future standards that would facilitate platform interoperability, data sharing and the improvement in the interpretation of such experiments as well as their reproducibility.

Purpose: The present study aims to develop a simple, reliable and easy tool enabling clinicians to codify the major part of individualized medical details (patient history and findings of physical examination) quickly and easily in routine medical practice, by entering data to a purpose-built software application, using structure data elements and detailed medical illustrations.

Materials and Methods: We studied medical records of 9,320 patients and we extracted individualized medical details. We recorded the majority of symptoms and the majority of findings of physical examination into the system, which was named IMPACT® (Intelligent Medical Patient Record and Coding Tool). Subsequently the system was evaluated by clinicians, based on the examination of 1206 patients.

Results: The evaluation results showed that IMPACT® is an efficient tool, easy to use even under time-pressing conditions.

Conclusion: IMPACT® seems to be a promising tool for illustration-guided, structured data entry of medical narrative, in electronic patient records.

The use of Health Information Technology (HIT) to improve healthcare service delivery is constantly increasing due to research advances in medical science and information systems. Having a fully automated process solution for a Healthcare Organization (HCO) requires a combination of organizational strategies along with a selection of technologies that facilitate the goal of improving clinical outcomes. HCOs, requires dynamic management of care capability to realize the full potential of HIT. Business Process Management (BPM) is being increasingly adopted to streamline the healthcare service delivery and management processes. Emergency Departments (EDs) provide a case in point, which require multidisciplinary resources and services to deliver effective clinical outcomes. Managed care involves the coordination of a range of services in an ED. Although fully automated processes in emergency care provide a cutting edge example of service delivery, there are many situations that require human interactions with the computerized systems; e.g. Medication Approvals, care transfer, acute patient care. This requires a coordination mechanism for all the resources, computer and human, to work side by side to provide the best care. To ensure evidence-based medical practice in ED, we have designed a Human Task Management service to model the process of coordination of ED resources based on the UK's NICE Clinical guideline for managing the care of acutely ill patients. This functionality is implemented using Java Business process Management (jBPM).

The paper describes safety analysis and justification of a clinical service (accidents and emergencies), using a deviation based approaches