Ebook: Enabling Health Informatics Applications

The current volume presents the accepted 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 2015 Conference, which is being held from 9 to 11 July, 2015 in Athens, Greece.

The ICIMTH 2015 Conference is the 13th 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 as a major focus the enabling of Biomedical Informatics applications in the whole spectrum from Clinical Informatics, Health Informatics to Public Health Informatics as applied 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 legal and social issues and setting research priorities in Health Informatics.

However, in this volume we have incorporated only full papers accepted for oral 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 in this series of the Conference as an e-book with e-access 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 the series of Studies in Health Technology and Informatics (SHTI) of IOS Press provides.

At the end of the deadline we had 95 submissions, from which after reviewing we have accepted 65 as full papers to be included in the volume proceedings.

The compilation of the proceedings is an enormous task and this effort could not have been done without the dedication, accuracy, persistence, and tiresome contribution of our Assistant Editors, mainly performed by Miss Katia Kolokathi and Mr. Parisis Gallos both members of the research staff of the Health Informatics Laboratory of the University of Athens.

The Editors would like to thank the Members of the Scientific Programme Committee, the Organising Committee, and all Reviewers, who have done a thorough and objective refereeing of the scientific work to produce a high quality publishing achievement and a successful scientific event.

Athens, 26.05.2015

The Editors,

John Mantas, Arie Hasman and Mowafa S. Househ

In this contribution the principles behind Structural Equation Modeling (SEM) are presented. SEM is used for assessing the quality of models that are proposed on the basis of theory and experience. This contribution has an introductory level.

The aim of this work was to evaluate conjunctival redness as an objective allergy symptom during the conjunctival provocation test (CPT). The CPT is an instillation of ophthalmic solution containing an allergen into the ocular mucosa. Allergic severity using the CPT was evaluated in the multicenter, randomized, controlled, double-blind, dose-finding study of 159 patients with birch pollen allergy where the mucosal sensitivity of the eye was assessed based on subjective and objective symptoms such as itching and redness, respectively. High-resolution digital photos were taken, arranged in image matrices, and analyzed by an external central observer to assess conjunctival redness. The photodocumentation method described here was successfully applied in a dose-finding study using the CPT. The evaluations of allergic severity carried out by an external observer agreed with the investigators' assessments.

Conjunctival redness is an objective allergy symptom which can be analyzed using objective computer imaging methods. To evaluate allergic inflammation of the eyes, a robust and precise image-based method was developed and applied to analyze allergic hyperemia under the conjunctival provocation test (CPT). High-resolution digital photos were taken and analyzed via digital analysis software to obtain and document conjunctival redness. The evaluations made using this newly developed image-based method concurred with the study investigators' assessments: the therapeutic effects of the highest doses were superior to the lowest dose.

Brain tumours are the most frequently occuring solid tumours affecting childhood, representing 27% of all cancers. The most common posterior fossa tumours are medulloblastoma, pilocytic astrocytoma and ependymoma. Texture Analysis (TA) of Magnetic Resonance Imaging (MRI) aims to represent pixel distributions, intensities and dependencies using mathematically defined features. Such features could potentially provide quantifiable information that is beyond the human vision capabilities, and hence be used to supplement qualitative assessments conducted by radiologists. The primary aim of this study was to carry out a multicentre investigation on the efficacy of 3D TA for diagnostic classification of childhood brain tumours, using conventional MRI images. The data used had been acquired at three different hospitals and consisted of pre-contrast T1 and T2-weighted MRI series, obtained from 121 children diagnosed with medulloblastoma, pilocytic astrocytoma and ependymoma. Using 3D textural features, based on first, second and higher order statistical methods, a support vector machine (SVM) classifier was trained and tested using the leave-one-out cross-validation (LOOCV) approach. An essential outcome of this study is that 3D TA demonstrated a good overall performance, when used on data acquired from a number of centres and using scanners made by different manufacturers and at different magnetic field strengths.

Medical device evaluation presents several unique challenges due to the great diversity and complexity of medical devices and their rapid technological evolution. There has been a variety of work conducted on the development of disease based registries and health surveillance systems in Saudi Arabia. However, the progress of medical device registry systems and post-market medical device surveillance systems remains in its infancy in Saudi Arabia and within the region. In 2007, a royal decree assigned the responsibility for regulating medical devices to the Saudi Food and Drug Authority (SFDA). Soon afterwards, the SFDA established the Medical Devices National Registry (MDNR) to house medical device information relating to manufacturers, agents, suppliers and end-users. The aim of this paper is to provide an overview on the Medical Device National Registry (MDNR) in Saudi Arabia and describe the current experience and future work of establishing a comprehensive medical device registry and post-market surveillance system in Saudi Arabia.

The objective of this paper is to investigate the experiences in implementing a smart capsule system for a Saudi endoscopy department. The study was conducted at a leading Saudi healthcare institution located in Riyadh, Saudi Arabia. A case study approach was used in the study. Endoscopy Information System (EIS) system data documentation, key informant interviews, and meeting documents were the data collection sources used in the study. A thematic analysis of the data was conducted. Preliminary data showed improvements in hospital clinical workflow as a result of implementing the new EIS. Although the findings of this study are preliminary, more work is needed to evaluate the overall impact of the new EIS on clinical workflow, patient wait times, usability, and data accuracy.

The objective of this paper is to report the implementation experiences of a remote patient monitoring system at a cardiac care center in Saudi Arabia. Key informant interviews, meeting documents, and experience of the researcher were part of the data collection sources used in the study. A thematic analysis of the data was conducted. Our preliminary work shows improvements in patient monitoring within the cardiac care center as a result of the new patient monitoring system. Lessons learned are also reported as well as study limitations. Future work will further investigate the impacts of the patient monitoring system on physician and patient satisfaction and health outcomes.

The objective of this paper is to report on the implementation of a Vagal Nerve Stimulation (VNS) Therapy System at a neurology department in Saudi Arabia. Key informant interviews, meeting documents, and experience of the researcher were part of the data collection sources used in the study. A thematic analysis of the data was conducted. The preliminary work shows improvements in epilepsy treatment within the neurology department as a result of the new Vagal Nerve Stimulation (VNS) therapy system. We discuss the lessons learned and identify the limitations of the study. Future work will further investigate the impacts of the VNS system on physician and patient satisfaction and health outcomes.

Improving the performance of Emergency Room (ER) has become a major concern for both healthcare professionals and researchers. ER patients' length of stay is one of the most important indicators for performance monitoring as well as improvement. The main objective of this study is to evaluate the effects of enhancing ER information accessibility of nurses, through a special ER nurses training program, on reducing patients' length of stay. Data on 5,769 ER encounters were retrospectively retrieved and analyzed to compare ER length of stay and related intervals of the first quarter of 2015, after implementing the training program, to the first quarter of 2014, before implementing the program. There was a 25.5% improvement on “Arrival to Triage” interval, 17.7% improvement on “Triage to ER Bed”, 16.1% improvement on “ER Bed Assigned to Doctor Examination” and 13.2% improvement on “Doctor Examination to Discharge” interval. The total ER length of stay was improved by 13.7%.

This paper proposes a first approach for the automation of the Fugl-Meyer assessment scale used in physical neurorehabilitation. The main goal of this research is to automatically estimate an objective measurement for five Fugl-Meyer scale items related to the assessment of the upper limb motion. An objective score has been calculated for 7 patients. Obtained results indicate that the automation of the scale can be a useful tool for the objective assessment of upper limb motion of stroke survivors.

Novel imaging techniques are playing an increasing role in tumour characterisation, assessment and management. However, incorporating imaging data into clinical trials presents a number of challenges in terms of quality control, standardisation in data collection, interoperability of widely used archiving systems and extensibility of imaging software architectures. Additionally, currently available monolithic applications cannot fulfil the diverse and rapidly changing needs of the clinical imaging research community. This paper discusses the limitations of the current CCLG Remote Data Entry (RDE) system and introduces the prototype of an alternative modular system based on the Extensible Neuroimaging Archive Toolkit (XNAT). The modular nature of the presented prototype promotes incremental software evolution and allows for flexible system customisation to suit the needs of individual imaging centres.

Computerized order sets for medication management were recently shown to be associated with increased patient safety risks in primary care setting. This study was aimed at demonstrating similar phenomenon in a hospital setting. After introduction of computerized order set targeting hypoglycemia, the frequency of hypoglycemia significantly decreased from 1/1/07 to 12/31/08. However, the frequency of hyperglycemia also increased at the same time from 1/1/07 to 12/31/07. Only after subsequent introduction of a hospital-wide standardized insulin order set including hyperglycemia policies, the frequency of hyperglycemic episodes declined. Hypo/hyperglycemia is associated with adverse clinical outcomes in the inpatient setting. Retroactive analysis showed that if hypoglycemic and hyperglycemic policies were introduced simultaneously, unexpected increase in frequency of hyperglycemic episodes could have been avoided. These data are informative in identifying unanticipated consequences of an insulin management order sets focused entirely on hypoglycemia. A balanced approach in implementing insulin management EMR order sets that concurrently addresses both hypoglycemia and hyperglycemia policies is warranted.

Due to the increasing amount of health information being gathered and the potential benefit of data reuse, it is now becoming a necessity for tools, which collect and analyse this data, to support integration of heterogeneous datasets, as well as provide intuitive user interfaces, which allow clinicians and researchers to query the data without needing to form complex SQL queries. The West Midlands Query Tool consists of an easy-to-use graph-based GUI, which interacts with a flexible middleware application. It has the main objective of querying heterogeneous data sources for exploring patient cohorts through a query builder and criteria set.

An interactive resistance chair (RC) exercise system has been designed to support patients at home in following their individualized strengthening exercise plan. The aim of this study was (1) to introduce a computer-assisted home-based resistance exercise for older adults and (2) to demonstrate feasibility of the proposed system in older adults with diabetes. The RC exercise system was well accepted by older adults with diabetes regardless of education level, race or gender. The post-task questionnaires demonstrated ease of system use and satisfaction with the system. The attitudinal survey results showed positive seniors' attitudes towards the RC exercise system. The system usability (SUS) scale score was 94.0±5.76 demonstrating high acceptance of the RC exercise system. From the qualitative interviews, individualized feedback yielded important system upgrade solutions that can be useful in tailoring patient needs, values and preferences specific for seniors with diabetes. Further research is warranted to assess impact of RC exercise system in home setting with a larger sample size in a randomized trial.

Clinical Decision Support Systems have been shown to increase quality of care, patient safety, improve adherence to guidelines for prevention and treatment, and avoid medication errors. Such systems depend mainly on two types of content; the clinical information related to patients and the medical knowledge related to the specialty that informs the system rules and alerts. At King Faisal Specialist Hospital and Research Center, Saudi Arabia, the Health Information Technology Affairs worked on identifying best strategies and recommendations for successful CDSS knowledge management. A review of literature was conducted to identify main areas of challenges and factors of success. A qualitative survey was used over six months' duration to collect opinions, experiences and suggestions from both IT and healthcare professionals. Recommendations were categorized into ten main topics that should be addressed during the development and implementation of CDSS knowledge management tools in the hospital.

The aim of the present study was to assess the effectiveness and validity of prognostic scale CRASH which is calculated using on-line resources and which may serve as a decision support for physicians in treating severe traumatic brain injury (TBI) in children. This retrospective study was conducted using clinical and physiological data of 168 hospitalized pediatric patients with severe traumatic brain injury (GCS score less than or equal to 8). CRASH scale was used for calculating the severity of patients' state and for prognosing death outcomes at 14 days and at 6 months using the on-line resource. Our research has shown that the prognostic scale CRASH has an excellent discrimination ability (AUROC=0.816) in each version. The study has also shown that the scale has a satisfactory calibration ability in the option of 14 days with CT (χ2 equal 8.7 and p-value equal to 0.368). Calibration ability for other options was unsatisfactory. Thus, CRASH scale with CT scan has turned to be useful for assessing death outcomes at 14 days in children with severe TBI.

Survival time prediction at the time of diagnosis is of great importance to make decisions about treatment and long-term follow-up care. However, predicting the outcome of cancer on the basis of clinical information is a challenging task. We now examined the ability of ten different data mining algorithms (Perceptron, Rule Induction, Support Vector Machine, Linear Regression, Naïve Bayes, Decision Tree, k-nearest Neighbor, Logistic Regression, Neural Network, Random Forest) to predict the dichotomous attribute “5-year-survival” based on seven attributes (sex, UICC-stage, etc.) which are available at the time of diagnosis. For this study we made use of the nationwide German research data set on colon cancer provided by the Robert Koch Institute. To assess the results a comparison between data mining algorithms and physicians' opinions was performed. Therefore, physicians guessed the survival time by leveraging the same seven attributes. The average accuracy of the physicians' opinion was 59%, the average accuracy of the machine learning algorithms was 67.7%.

Complicated dosage regimens often reduce adherence to drug treatments. The ease-of-administration must thus be taken into account when prescribing. Given one drug, there exists often several dosage regimens. Hence, comparison to similar drugs is difficult. Simplifying and summarizing them appears to be a required task for supporting General Practitioners to find the drug with the simplest regimen for the patient. We propose a summarization in two steps: first prunes out all low-importance information, and second proceed to fusion of remaining information. Rules for pruning and fusion strategies were designed by an expert in drug models. Evaluation was conducted on a dataset of 169 drugs. The agreement rate was 27.2%. We demonstrate that applying rules leads to a result that is correct by a computational point of view, but the result is often meaningless for the GP. We conclude with recommendations for further work.

There are several types of Diagnostic Decision Support Systems (DDSS) but all move towards a common direction: provide assistance to the doctors/clinicians to make the right diagnosis for a specific patient, minimizing as much as possible the needed time for this. In doing so, some DDSS systems exploit existing crisp medical databases while others take an advantage of human knowledge and experience, by building fuzzy medical databases from scratch. It would be of interest though, as well as time saving, to combine these two together and examine how one can actually use an existing crisp medical dataset to transform it into a new fuzzy medical database with parameters being expressed and defined based on the clinicians' way of thinking. A methodology implementing this task is proposed in this paper accompanied by the results of its application on a real crisp medical database.