Ebook: MEDINFO 2015: eHealth-enabled Health

MEDINFO is the premier international Health and Biomedical Informatics event. MEDINFO 2015 is hosted by SBIS (Brazilian Health Informatics Society) on behalf of the International Medical Informatics Association (IMIA) and will take place in the city of São Paulo from the 19^th to 23^rd August 2015. MEDINFO 2015 continues a 41-year tradition of bringing together world leaders, policy makers, researchers, practitioners, educators, and students to exchange ideas and contribute to the latest developments, innovations, and global trends in this rapidly advancing, multidisciplinary field of Health and Biomedical Informatics. This is the first MEDINFO that has been organized to reflect the new two-yearly cycle approved by IMIA. We were thus very happy when we reached the submission and registration deadlines with numbers very similar to previous MEDINFOs that had been organized in three-yearly cycles.

Under the theme: “eHealth-enabled Health”, the world leaders in this field will gather in Brazil to share knowledge and analyze how Health and Biomedical Informatics is contributing to address some of the most challenging problems in health care, public health, consumer health and biomedical research. Researchers, clinicians, technologists and managers will attend and share experiences on the use of information methods, systems and technologies to promote patient-centered care, improve patient safety, enhance care outcomes, facilitate translational research, enable precision medicine and improve education and skills in health informatics.

This is an historical event as MEDINFO is hosted in Latin America for the first time. Inclusiveness has been a main goal in MEDINFO 2015 with affordable registration fees for the regional audience and use of Spanish and Portuguese language in tutorials and simultaneous translation in sessions held in the main auditorium. MEDINFO 2015 features a precongress offering of an extensive tutorial program by leading experts and a student paper competition that draws the best young talent from all over the world. The main program includes keynote talks, papers, posters, panels, workshops, and scientific demonstrations that span a broad range of topics from emerging methodologies that contribute to the conceptual and scientific foundations of Health and Biomedical Informatics, to successful implementations of innovative application, integration, and evaluation of eHealth systems and solutions.

The conference program features five keynote presentations, 178 paper presentations, 248 poster abstract presentations, 27 panels, 30 workshops and 17 scientific demonstrations.

The contributions and presentations included in the program were carefully selected through a rigorous review process involving almost 400 reviewers for a large number of submissions (793) sent by 2500 authors from 59 countries all over the world. The Scientific Program Committee Co-Chairs are grateful to the four Track Chairs, the members of the Scientific Program Committee and all the reviewers who have contributed to the process, and thank the Editorial Committee, the Local Organizing Committee and the IMIA officers (in particular CEOs and VP Medinfo) for assisting us in putting this program together.

The conference participants come to São Paulo from all continents and 60 different countries. We hope that you will enjoy the published proceedings and the overall program!

Sincerely,

Fernando Martin-Sanchez, PhD, FACHI, FACMI &

Kaija Saranto, PhD, FACMI, FAAN

Co-Chairs, MEDINFO 2015 Scientific Program Committee

Electronic Health Records (EHRs) have made patient information widely available, allowing health professionals to provide better care. However, information confidentiality is an issue that continually needs to be taken into account. The objective of this study is to describe the implementation of rule-based access permissions to an EHR system. The rules that were implemented were based on a qualitative study. Every time users did not meet the specified requirements, they had to justify access through a pop up window with predetermined options, including a free text option (“other justification”).

A secondary analysis of a deidentified database was performed. From a total of 20,540,708 hits on the electronic medical record database, 85% of accesses to the EHR system did not require justification. Content analysis of the “Other Justification” option allowed the identification of new types of access. At the time to justify, however, users may choose the faster or less clicks option to access to EHR, associating the justification of access to the EHR as a barrier.

Definition and configuration of clinical content in an enterprise-wide electronic health record (EHR) implementation is highly complex. Sharing of data definitions across applications within an EHR implementation project may be constrained by practical limitations, including time, tools, and expertise. However, maintaining rigor in an approach to data governance is important for sustainability and consistency. With this understanding, we have defined a practical approach for governance of structured data elements to optimize data definitions given limited resources. This approach includes a 10 step process: 1) identification of clinical topics, 2) creation of draft reference models for clinical topics, 3) scoring of downstream data needs for clinical topics, 4) prioritization of clinical topics, 5) validation of reference models for clinical topics, and 6) calculation of gap analyses of EHR compared against reference model, 7) communication of validated reference models across project members, 8) requested revisions to EHR based on gap analysis, 9) evaluation of usage of reference models across project, and 10) Monitoring for new evidence requiring revisions to reference model.

From a national level to give Internet technology support, the Nationwide Integrated Healthcare System in Uruguay requires a model of Information Systems Architecture. This system has multiple healthcare providers (public and private), and a strong component of supplementary services. Thus, the data processing system should have an architecture that considers this fact, while integrating the central services provided by the Ministry of Public Health. The national electronic health record, as well as other related data processing systems, should be based on this architecture. The architecture model described here conceptualizes a federated framework of electronic health record systems, according to the IHE affinity model, HL7 standards, local standards on interoperability and security, as well as technical advice provided by AGESIC. It is the outcome of the research done by AGESIC and Systems Integration Laboratory (LINS) on the development and use of the e-Government Platform since 2008, as well as the research done by the team Salud.uy since 2013.

The use of Electronic Dental Records (EDRs) and management software has become more frequent, following the increase in prevelance of new technologies and computers in dental offices. The purpose of this study is to identify and evaluate the use of EDRs by the dental community in the São Paulo city area. A quantitative case study was performed using a survey on the phone. A total of 54 offices were contacted and only one declinedparticipation in this study. Only one office did not have a computer. EDRs were used in 28 offices and only four were paperless. The lack of studies in this area suggests the need for more usability and implementation studies on EDRs so that we can improve EDR adoption by the dental community.

As the field of medicine grows more complicated and doctors become more specialized in a particular field, the number of healthcare providers involved in healing an individual patient increases. This is particularly true of patients with multiple chronic conditions. Establishing effective communications among the care providers becomes critical to facilitate care coordination and more efficient resource use, which will ultimately result in health outcome improvement. The first step for care coordination is to understand who have been involved in a patient's care and their relationships with the patient. The widespread adoption of Electronic Health Records provides us an opportunity to explore solutions to well-coordinated care. This paper presents the concept of a patient's care team and demonstrates the feasibility of identifying relevant healthcare providers for an individual patient by leveraging electronic patient encounter data. Combined with network analysis techniques, we further visualize the care team structure with quantified strength of patient-provider relationships. Our work is foundational to the larger goal of patient-centered, coordinated care in the digital age of healthcare.

The use of EHRs and the benefits from them are significant for healthcare and health informatics. Data form the basis for any EHR and its potential to realize these benefits. This paper considers the housing of information and knowledge management in an EHR system. Are we experiencing a revolution in healthcare? Findings from an investigation of alternative approaches, followed by an evaluation of the importance of the adoption of a standard information model relative to benefit realization, is presented. We conclude that an EHR in any environment is not limited to sharing or information exchange. A paradigm shift in thinking, based on the requirement for standardized concept representation, is required. This is an essential prerequisite for a new vision of healthcare supported by digital technologies.

Digital patient modeling targets the integration of distributed patient data into one overarching model. For this integration process, both a theoretical standard-based model and information structures combined with concrete instructions in form of a lightweight development process of single standardized Electronic Health Records (EHRs) are needed. In this paper, we introduce such a process along side a standard-based architecture. It allows the modeling and implementation of EHRs in a lightweight Electronic Health Record System (EHRS) core. The approach is demonstrated and tested by a prototype implementation. The results show that the suggested approach is useful and facilitates the development of standardized EHRSs.

Medical information extraction is the automatic extraction of structured information from electronic medical records, where such information can be used for improving healthcare processes and medical decision making. In this paper, we study one important medical information extraction task called section classification. The objective of section classification is to automatically identify sections in a medical document and classify them into one of the pre-defined section types. Training section classification models typically requires large amounts of human labeled training data to achieve high accuracy. Annotating institution-specific data, however, can be both expensive and time-consuming; which poses a big hurdle for adapting a section classification model to new medical institutions. In this paper, we apply two advanced machine learning techniques, active learning and distant supervision, to reduce annotation cost and achieve fast model adaptation for automated section classification in electronic medical records. Our experiment results show that active learning reduces the annotation cost and time by more than 50%, and distant supervision can achieve good model accuracy using weakly labeled training data only.

“Heart failure (HF) is a frequent health problem with high morbidity and mortality, increasing prevalence and escalating healthcare costs” [1]. By calculating a HF survival risk score based on patient-specific characteristics from Electronic Health Records (EHRs), we can identify high-risk patients and apply individualized treatment and healthy living choices to potentially reduce their mortality risk. The Seattle Heart Failure Model (SHFM) is one of the most popular models to calculate HF survival risk that uses multiple clinical variables to predict HF prognosis and also incorporates impact of HF therapy on patient outcomes. Although the SHFM has been validated across multiple cohorts [1-5], these studies were primarily done using clinical trials databases that do not reflect routine clinical care in the community. Further, the impact of contemporary therapeutic interventions, such as beta-blockers or defibrillators, was incorporated in SHFM by extrapolation from external trials. In this study, we assess the performance of SHFM using EHRs at Mayo Clinic, and sought to develop a risk prediction model using machine learning techiniques that applies routine clinical care data. Our results shows the models which were built using EHR data are more accurate (11% improvement in AUC) with the convenience of being more readily applicable in routine clinical care. Furthermore, we demonstrate that new predictive markers (such as co-morbidities) when incorporated into our models improve prognostic performance significantly (8% improvement in AUC).

Healthcare Information Systems are a big business. Currently there is an explosion of EHR/EMR products available on the market, and the best tools are really expensive. Many developing countries and healthcare providers cannot access such tools, and for those who can, there is not a clear strategy for the evolution, scaling, and cost of these electronic health products. The lack of standard-based implementations conduct to the creation of isolated information silos that cannot be exploited (i.e. shared between providers to promote a holistic view of each patient's medical history). This paper exposes the main elements behind a Standard-based Open Source EHR Platform that is future-proof and allows to evolve and scale with minimal cost. The proposed EHR Architecture is based on openEHR specifications, adding elements emerged from research and development experiences, leading to a design that can be implemented in any modern technology. Different implementations will be interoperable by design. This Platform will leverage contexts of scarce resources, reusing clinical knowledge, a common set of software components and services.

The language and communication constitute the development mainstays of several intellectual and cognitive skills in humans. However, there are millions of people around the world who suffer from several disabilities and disorders related with language and communication, while most of the countries present a lack of corresponding services related with health care and rehabilitation. On these grounds, we are working to develop an ecosystem of intelligent ICT tools to support speech and language pathologists, doctors, students, patients and their relatives. This ecosystem has several layers and components, integrating Electronic Health Records management, standardized vocabularies, a knowledge database, an ontology of concepts from the speech-language domain, and an expert system. We discuss the advantages of such an approach through experiments carried out in several institutions assisting children with a wide spectrum of disabilities.

Although Electronic Health Records (EHR) can offer benefits to the health care process, there is a growing body of evidence that these systems can also incur risks to patient safety when developed or used improperly. This work is a literature review to identify these risks from a software quality perspective. Therefore, the risks were classified based on the ISO/IEC 25010 software quality model. The risks identified were related mainly to the characteristics of “functional suitability” (i.e., software bugs) and “usability” (i.e., interface prone to user error). This work elucidates the fact that EHR quality problems can adversely affect patient safety, resulting in errors such as incorrect patient identification, incorrect calculation of medication dosages, and lack of access to patient data. Therefore, the risks presented here provide the basis for developers and EHR regulating bodies to pay attention to the quality aspects of these systems that can result in patient harm.

Using real-world clinical data from the Indiana Network for Patient Care, we analyzed the associations between non-adherence to oral antihyperglycemic agents (OHA) and subsequent diabetes-related hospitalization and all-cause mortality for patients with type 2 diabetes. OHA adherence was measured by the annual proportion of days covered (PDC) for 2008 and 2009. Among 24,067 eligible patients, 35,507 annual PDCs were formed. Over 90% (n=21,798) of the patients had a PDC less than 80%. In generalized linear mixed model analyses, OHA non-adherence is significantly associated with diabetes related hospitalizations (OR: 1.2; 95% CI [1.1,1.3]; p<0.0001). Older patients, white patients, or patients who had ischemic heart disease, stroke, or renal disease had higher odds of hospitalization. Similarly, OHA non-adherence increased subsequent mortality (OR: 1.3; 95% CI [1.02, 1.61]; p<0.0001). Patient age, male gender, income and presence of ischemic heart diseases, stroke, and renal disease were also significantly associated with subsequent all-cause death.

Studies on the validation of minimum data sets from international information standards have drawn the attention of the academic community to the identification of necessary requirements for the development of Electronic Health Records (EHRs). The primary motivation of such studies is the development of systems using archetypes. The aim of this study was to validate the minimum data set that should be used when constructing an archetyped EHR for prenatal care applications in telehealth. In order to achieve this, a data validation tool was built and used by nine expert obstetricians. The statistical analysis employed was the percentage of agreement and the content validity index. The study was conducted in three steps: 1) Literature review, 2)Instrument development, and 3) Validation of the minimum data set. Of the 179 evaluated pieces of data, 157 of them were validated to be included in the archetyped record of the first prenatal consultation, while 56 of them were allocated for the subsequent consultation record. The benefit of this research is the standardization (data validation for an archetyped system) of prenatal care, with the perspective of employing, both nationally and internationally, an archtyped telehealth system.

In 722 cities of Minas Gerais (Brazil), primary care patients can have their ECGs remotely interpreted by cardiologists of the Telehealth Network of Minas Gerais (TNMG), a public telehealth service. As of December 2014, more than 1.9 million ECGs were interpreted. This study analyzed the database of all ECGs performed by the TNMG on primary care patients from 2009 to 2013 (n=1,101,993). Structured patient data and the results of automated ECG interpretation by the Glasgow Program are described. Mean patient age is 51 years old, 59% of them are women. The average body mass index is 25.9 kg/m², with an average increase of 0.15 kg/m² per civil year. Those patients notably have hypertension (33.2%), family history of coronary artery disease (14.5%), smoking (6.9%), diabetes (5.8%), obesity (5.8%) or Chagas Disease (3.0%). Seventy percent of ECGs are normal. This percentage is higher in women (72.3%) and decreases in average by 7.4 every 10 years of life. There are notably 12% of possible myocardial infarction, 10% of possible left ventricular hypertrophy and 8% of possible supraventricular extra systole.

In North Norway, no telemonitoring services for chronic heart failure (CHF) have yet been established, hence no investigations in the area have been published. However, large distances and a sparse population are causes for extra expenditure on hospital visits. In this paper, we describe the ePoint.telemed platform for home telemonitoring of CHF patients. We have reviewed the literature on home monitoring techniques, and developed two prototype platforms for remote collection of physiological data. We have refined one of the prototypes and subjected it to user testing among health professionals and their clients. Fifty patients will be involved in a randomized controlled trial aiming to establish if the home telemonitoring of CHF is clinically feasible and cost-effective. The ePoint.telemed platform is a fully automated internet based system meant for early warnings in a CHF rehabilitation program. The core of the platform is a dashboard connected to a blood pressure meter, a weight scale, and a web-based patient questionnaire. Unlike traditional systems built on dedicated medical equipment, we are applying easy-to-use components geared towards the sports market.

Portable Healthcare Clinic (PHC) is a mobile healthcare system comprising of medical sensors and health assessment criteria. It has been applied in Bangladesh for the last two years as a pilot program to identify non-communicable diseases. In this study, we adapted PHC to fit post-disaster conditions. The PHC health assessment criteria are redesigned to deal with emergency cases and healthcare worker insufficiency. A new algorithm makes an initial assessment of age, symptoms, and whether the person is seeing a doctor. These changes will make the turn-around time shorter and will enable reaching the most affected patients better. We tested the operability and turn-around time of the adapted system at the debris flow disaster shelters in Hiroshima, Japan. Changing the PHC health assessment criteria and other solutions such as a list of medicine preparation makes the PHC system switch into an emergency mode more smoothly following a natural disaster.

The Online Diabetes Exercise System was developed to motivate people with Type 2 diabetes to do a 25 minutes low-volume high-intensity interval training program. In a previous multi-method evaluation of the system, several usability issues were identified and corrected. Despite the thorough testing, it was unclear whether all usability problems had been identified using the multi-method evaluation. Our hypothesis was that adding the eye-tracking triangulation to the multi-method evaluation would increase the accuracy and completeness when testing the usability of the system. The study design was an Eye-tracking Triangulation; conventional eye-tracking with predefined tasks followed by The Post-Experience Eye-Tracked Protocol (PEEP). Six Areas of Interests were the basis for the PEEP-session. The eye-tracking triangulation gave objective and subjective results, which are believed to be highly relevant for designing, implementing, evaluating and optimizing systems in the field of health informatics. Future work should include testing the method on a larger and more representative group of users and apply the method on different system types.

Recent studies demonstrated that the duration of inactivity (sedentary state) is independently associated with increased risk of cardiovascular disease. Our goal was to develop the technology that can measure the amount of inactivity in real time, remind a person that a preprogrammed period of inactivity has occurred and encourage a period of activity, and provide web-based feedback with tailored information to the participant and investigators. Once it was developed, we carried out a pilot study in a group of sedentary overweight women. The objective of the study was to assess potential of the mobile app to reduce inactivity in our target population. A randomized crossover design was employed with study subjects randomly assigned to a 4-week each “message-on” and “message-off” periods. Out of 30 enrolled subjects, 27 completed the study. The average age of particpants was 52±12; BMI: 37±6; 47% were white and 47% were African American. Overall, inactivity was significantly lower (p<0.02) during “message-on” periods (24.6%) as compared to the “message-off” periods (30.4%). We conluded that mobile app monitoring inactivity and providing a real-time notification when inactivity period exceeds healthy limits was able to significantly reduce inactivity periods in overweight sedentary women.

Diabetes is a complex disease affecting 29.1 million (9.3%) US citizens [1]. It is a chronic illness that needs continual medical care and ongoing patient self-management, education, and support [2]. There is no cure for diabetes, requiring patients to conduct frequent self-monitoring of blood glucose and dosing of insulin in many cases. Evidence has shown that patients are more adherent to their diabetes management plan when they incorporate personal lifestyle choices [3]. To address the challenge of empowering patients to better manage their diabetes, we have developed a novel mobile application prototype, iDECIDE, that refines rapid-acting insulin dose calculations by incorporating two important patient variables in addition to carbohydrates consumed that are not a part of standard insulin dose calculation algorithms: exercise and alcohol intake [4, 5]. A retrospective analysis for the calibration and evaluation of iDECIDE is underway by comparing recommendations made by the application against dosing recommendations made by insulin pumps.

Smartphones include features that offers the chance to develop mobile systems in medical field, resulting in an area called mobile-health. One of the most common medical examinations is the electrocardiogram (ECG), which allows the diagnosis of various heart diseases, leading to preventative measures and preventing more serious problems. The objective of this study was to develop a wireless reconfigurable embedded system using a FPAA (Field Programmable Analog Array), for the acquisition of ECG signals, and an application showing and storing these signals on Android smartphones. The application also performs the partial FPAA reconfiguration in real time (adjustable gain). Previous studies using FPAA usually use the development boards provided by the manufacturer (high cost), do not allow the reconfiguration in real time, use no smartphone and communicate via cables. The parameters tested in the acquisition circuit and the quality of ECGs registered in an individual were satisfactory.

The recent development of mobile technologies allows nurses to receive different types of requests anywhere. However, the interruptions generated by these devices often presents a challenge for nurses in their daily work in a hospital department. In previous inquires we have investigated nurses' strategies to managing technology-mediated interruptions in the form of nurse calls. This study reports on an effort to co-design a system that supports an important strategy employed by nurses. Through the involvement of domain experts, the study elicits requirements for an awareness system to support nurses' collaborative effort in handling nurse calls.

The Tailored Lifestyle Change Decision Aid (TLC DA) system was designed to provide support for a person to make an informed choice about which behavior change to work on when multiple unhealthy behaviors are present. TLC DA can be delivered via web, smartphones and tablets. The system collects a significant amount of information that is used to generate tailored messages to consumers to persuade them in certain healthy lifestyles. One limitation is the necessity to collect vast amounts of information from users who manually enter. By identifying an optimal set of self-reported parameters we will be able to minimize the data entry burden of the app users. The study was to identify primary determinants of health behavior choices made by patients after using the system. Using discriminant analysis an optimal set of predictors was identified. The resulting set included smoking status, smoking cessation success estimate, self-efficacy, body mass index and diet status. Predicting smoking cessation choice was the most accurate, followed by weight management. Physical activity and diet choices were better identified in a combined cluster.