Ebook: MEDINFO 2017: Precision Healthcare through Informatics

Welcome to MedInfo2017

On behalf of the Editorial Committee (EC) for MedInfo2017, please accept our warm welcome to Hangzhou to celebrate the art and science of informatics in a truly breath-taking venue and with colleagues from around the world.

Learning from the experience of prior chairs

Learning from prior work and the experience of those who walked the path before is invaluable when embarking on a new venture. The first emails and calls after receiving word of my nomination to be EC chair were to prior chairs Christoph U. Lehmann (MedInfo2013) and Indra Neil Sarkar (MedInfo2015). While assuring me that this was a task that could be done (as they had so wonderfully demonstrated!), they did tell me that it was a huge effort that would take time, resources, and patience. It would be worth all the effort, they added. I am grateful to them for their guidance and gracious sharing of their experiences and lessons learned.

The journey

Starting with assisting the Scientific Program Committee (SPC) to bring out the call for papers, to witnessing the submissions start to come in as a trickle and end with an avalanche, to planning and executing the copy editing and formatting of the accepted papers and posters, the journey has been an interesting one to say the least.

First, let me start by saying what a great opportunity it has been to serve the international informatics community through MedInfo2017. It is an extraordinary honor to be able to chair the EC and I am grateful to the leadership of MedInfo2017 and the International Medical Informatics Association (IMIA) for their trust in me.

Second, I must acknowledge that it has truly been a great experience, as my predecessors had indicated it would be. Conceptualizing and executing the process of copy editing and formatting of nearly 400 five-page papers and one-page posters is a daunting task. I was ably assisted by two senior associate editors who are two amazing informatics students and rising stars in the field: Shauna Overgaard (University of Minnesota) and Kate Fultz Hollis (Oregon Health & Science University). Brainstorming, planning, and finally executing the work of the EC became a pleasure and I looked forward to our weekly conference calls to assess progress and resolve issues.

Third, working with Shauna and Kate, we recruited 41 outstanding associate editors (AEs) who then set out to copy edit and check the formatting of the accepted submissions. We set-up a multi-phase, cross-over plan wherein one AE would perform the editing and formatting and later another AE would review the work and revise as needed. The third phase involved the senior AEs reviewing the submissions and finally, I personally reviewed each and every submission and then finalized the documents for the proceedings.

The editorial task is not trivial; the authors represent all continents (except Antarctica), and hail from varied backgrounds and professions, stages of training and career, and thereby epitomize a wide-range of experience in our field. Imagine a multifaceted channel in which technical research findings are communicated, by diverse researchers, often through a language barrier, to a diverse audience, who have been instructed to write academically in the official language of MedInfo (English). Now, add to that the requirement to adhere to a strict template (that is of paramount importance for uniformity and layout for the publishers). Indeed, this sets the stage for our work. But, be certain that it is undeniably humbling to experience the breadth, depth, and quality of the work presented by authors at MedInfo2017 and the proficiency with which their findings are communicated to an international audience.

The credit for preparing the submissions for the official conference proceedings goes to the the AE team, the senior AEs, and the Editorial Committee. Even through a process where at least four individuals have reviewed a submission, it is possible that we may have missed a word here or formatting there. We offer our apologies for any inadvertent errors in the final proceedings.

The final stretch

It truly takes a village to complete such a large task. We acknowledge and thank the publishers, IOS Press, for their work on the proceedings. Paul Weij has been a great ally in this venture: offering advice and guidance on the technical aspects and being patient with us while we asked many questions and ultimately delivered the final files. Our thanks to the entire IOS Press team for their professional work and service with a smile. The VP of MedInfo2017, Kaija Saranto, has been an ardent supporter from the beginning. The SPC co-chairs, Elizabeth Borycki and Niels Peek, have been invaluable in their support and gracious with their advice in helping the EC complete its work. A special thanks and shout-out to Elaine Huesing, CEO, IMIA for her help in counseling and patiently guiding me through the work of the EC. Our thanks to Yongqin Huang (Chair), Emmett Huang (Vice-Chair), and the entire local organizing committee for their guidance in finalizing the proceedings. Our thanks to the two EC members, Dongsheng Zhao (China) and Marie-Christine Jaulent (France) for their involvement and culturally appropriate advice. And finally, listed in Table 1 are the AEs that spent countless hours reviewing, formatting, and copy-editing the nearly 400 papers and posters that make up the official MedInfo2017 conference proceedings.

Table 1 – Our dynamic and enthusiastic Assistant Editors for MedInfo2017

Assistant Editor (AE) / Institution

Abu Saleh Mohammad Mosa / University of Missouri School of Medicine, USA

Bryan Steitz / Vanderbilt University, USA

Celena B. Peters / VA Salt Lake City Health Care System and University of Utah School of Medicine, USA

Chen Liang / Louisiana Tech University, USA

Danny T. Y. Wu / University of Cincinnati, USA

David Chartash / Indiana University School of Medicine, USA

Doug Redd / George Washington University, USA

Andreas Triantafyllidis / Centre for Research and Technology Hellas (CERTH), Greece

Florence Femi Odekunle / Rutgers, The State University of New Jersey, USA

Elizabeth A. Lindemann / University of Minnesota, USA

Feichen Shen / Mayo Clinic, USA

Grace Gao / University of Minnesota and Robert Wood Johnson Foundation Future of Nursing Scholar Program, USA

Gregory W Hruby / Mount Sinai Medical Center, USA

Hyunggu Jung / University of Washington, USA

Jacob P. VanHouten / Vanderbilt University Medical Center, USA

Jenna Levenson Brager / Johns Hopkins University, USA

Jennifer Staley / Kent State University, USA

Kate Fultz Hollis (Senior AE) / Oregon Health & Science University, USA

Lacey Lewis / Veterans Health Administration, USA

Lisiane Pruinelli / University of Minnesota, USA

Lucy Lu Wang / University of Washington, USA

Marjorie E. Carter / University of Utah School of Medicine, USA

Mattias Georgsson / Blekinge Institute of Technology, Sweden

Maurine Tong / University Medical Center, USA

Preethi Srinivas / Regenstrief Institute Inc., USA

Rafeek Adeyemi Yusuf / University of Texas Health Science Center at Houston, USA

Ranyah Aldekhyyel / University of Minnesota, USA and King Saud University, Saudi Arabia

Rashmi Mishra / National Institute of Dental and Craniofacial Research, USA

Ryan A. McInerney / Queens University, Canada

Satish M. Mahajan / Veterans Health Administration, USA

Scott McGrath / University of Nebraska at Omaha, USA

Shauna M. Overgaard (Senior AE) / University of Minnesota, USA

Sripriya Rajamani / University of Minnesota, USA

Stacey Slager / VA Salt Lake City Health Care System and University of Utah School of Medicine, USA

Taya Irizarry / University of Pittsburgh, USA

Tiffany I. Leung / Maastricht University, The Netherlands

Tiffany J. Callahan / University of Colorado Denver, USA

Todd Lingren / University of Cincinnati, USA

Vignesh Subbian / University of Arizona, USA

Warren B P Pettey / VA Salt Lake City Health Care System and University of Utah School of Medicine, USA

Yanshan Wang / Mayo Clinic, USA

Yiye Zhang / Weill Cornell Medical College, Cornell University, USA

Zhe He / Florida State University, USA

As this editing experience carries prestige, is an enjoyable challenge, and is highly valuable for the CV, several members of the team have served as AEs for two and even three years. They have our gratitude and the satisfaction of having contributed to a worthy academic venture that will be read and cited for years to come. We have learned a few more lessons to add to the playbook created many years ago by our predecessors.

To the next MedInfo team, we wish you good luck and you know where to find us.

With warm regards and best wishes for a productive and successful MedInfo2017,

Adi V. Gundlapalli, MD, PhD, MS

Chair, Editorial Committee

Smoking is the largest avoidable cause of preventable morbidity worldwide. It causes most of the cases of lung cancer and chronic obstructive pulmonary disease (COPD) and contributes to the development of other lung diseases. SmokeFreeBrain aims to address the effectiveness of a multi-level variety of interventions aiming at smoking cessation in high risk target groups within High Middle Income Countries (HMIC) such as unemployed young adults, COPD and asthma patients, and within the general population in Low-Middle Income Countries (LMIC). The project addresses existing approaches aimed to prevent lung diseases caused by tobacco while developing new treatments and evaluating: (i) Public Service Announcement (PSA) against smoking, (ii) the use of electronic cigarettes, (iii) neurofeedback protocols against smoking addiction, (iv) a specifically developed intervention protocol based on behavioral therapy, social media/mobile apps and short text messages (sms) and (v) pharmacologic interventions. Emphasis in this paper, however, is placed on the e-heath, m-health, open (big) data, mobile game and neuroscientific challenges and developments upon facilitating the aforementioned interventions.

Smartphones that collect user geolocation provid opportunities for mobile Health (mHealth). Although granularity of geolocation data may be high, data completeness depends on the device's operating system, application developer decisions, and user actions. We investigate completeness of geolocation data collected via smartphones of 5601 people that self-reported daily chronic pain symptoms on 349,293 days. On 17% of these days, hourly geolocation data is reported, but days with 0 (16%), 1 (14%) and 2 (13%) geolocations are common. Android phones collect geolocation more often than iPhones (median 17 versus 2 times a day). Factors on operating system level and individual user level influence completeness of geolocation data collected with smartphones. mHealth researchers should be aware of these factors when designing their studies. The mHealth research community should devise standards for reporting geolocation data quality, analysing systematic differences in data quality between participant groups, and methods for data imputation.

In this paper, the authors outline a vision for the future of mobile usability, workflow and safety testing. The authors argue for the use of glasses that can audio and video record usability, workflow and safety data. Here, citizens, patients and health professionals would become collectors of study data as they use mobile devices and software to support healthcare in the real world. This has become quite feasible with the introduction of low-cost glasses and software applications that allow for the uploading of data for additional analysis by researchers and evaluators of mobile technologies.

Previous studies showed that a stronger focus on integrated care models is required, targeting at a seamless coordinated care reaching patients even at home and thus establish patient centered and patient driven innovation activities. Such integrated care model is important among others for ensuring traceability that is necessary when problems during treatment occur or in cases of product counterfeiting for ensuring patient safety. The objective of our work is to realize an efficient, continuous care process, considering an optimal, end-to-end treatment path. In this paper, we describe the process how to pave the way for developing technologies for realizing a cross-sector treatment pathway. Following a multi-stakeholder principle and by applying requirement analysis and world café methodology we designed first concepts and strategies.

This study aims to design a transcutaneous electrical nerve stimulation Application (TENS App) according to the suggestions from potential users. To the best of our knowledge, this is the first App including meridian and acupoints for TENS. After its development, there are eight participants recruited for evaluating the usability. Despite two out of eight users reporting that the typical TENS system requires lower cost and has better functionality than TENS App, the results show that almost seventy percent of participants have a better perception of TENS App on price, functionality, convenience, operational ability, and quality. However, participants still reported concerns about the safety issue of adopting TENS App. Therefore, for people who are the first time or unfamiliar with TENS App, instructions from occupational or physical therapists are recommended. We conclude that by using TENS App, users can not only use the portable electrotherapy devices at anyplace, but also reduce their outpatient visits.

Healthcare systems increasingly rely on digital technologies to sustain costs and improve access to quality care. Data drive a wave of automation aspiring to improve productivity by forging connections between health and wellness, medical research, and clinical decision support. Mobile apps and patient-generated data combined with provider recordings pave the way towards personalized care pathways and just-in time access to health services. Navigating the health ecosystem becomes challenging as roles and relationships change. This paper reflects on the digital health compass to navigate the health system using one's own data. Health information technology standards are at the core of the compass, to tap the potential of shared aggregate data and sustain trust. The notion of the patient summary as a window to one's health is used as an example to drive our call for action for health informatics to develop methods to calibrate the digital health compass and feed on ‘my data’, respecting ‘my decision’, to fuel ‘our ePower’.

In South Africa, the recording of health data is done manually in a paper-based file, while attempts to digitize healthcare records have had limited success. In many countries, Electronic Health Records (EHRs) has developed in silos, with little or no integration between different operational systems. Literature has provided evidence that the cloud can be used to ‘leapfrog’ some of these implementation issues, but the adoption of this technology in the public health care sector has been very limited. This paper aims to identify the major reasons why the cloud has not been used to implement EHRs for the South African public health care system, and to provide recommendations of how to overcome these challenges. From the literature, it is clear that there are technology, environmental and organisational challenges affecting the implementation of EHRs in the cloud. Four recommendations are provided that can be used by the National Department of Health to implement EHRs making use of the cloud.

Pneumococcal Conjugate Vaccine (PCV) has the potential to save lives in low-income countries. We have developed a computational model and web-based decision support software for comparing cost-benefit tradeoffs from alternative PCV program designs, considering their direct and indirect effects on early childhood populations in resource-poor settings. This supports policy-makers in estimating potential health outcomes and cost-effectiveness of different vaccination program strategies for a wide range of population coverage and vaccine effectiveness assumptions.

The rise of distributed ledger technology, initiated and exemplified by the Bitcoin blockchain, is having an increasing impact on information technology environments in which there is an emphasis on trust and security. Management of electronic health records, where both conformation to legislative regulations and maintenance of public trust are paramount, is an area where the impact of these new technologies may be particularly beneficial. We present a system that enables fine-grained personalized control of third-party access to patients' electronic health records, allowing individuals to specify when and how their records are accessed for research purposes. The use of the smart contract based Ethereum blockchain technology to implement this system allows it to operate in a verifiably secure, trustless, and openly auditable environment, features crucial to health information systems moving forward.

When newborns remain hospitalized in a neonatal intensive care unit, they are often unable to feed themselves and receive human milk through enteral nutrition devices such as orogastric or nasogastric probes. Therefore, the Nursing staff is responsible for the fractionation, storage and administration of human milk. Breast milk has a great biological complexity being the optimal food for the baby to provide all the nutrients needed. At the same time, it is a bodily fluid that carries the risk of disease transmission if not administered properly. Patient safety should be a priority in healthcare, and health information technologies could be used to avoid preventable adverse events. Barcoding technology has the ability to accurately verify patient identity and prescription accuracy before milk administration. This paper describes the steps followed to implement breast milk barcoding technology in an academic tertiary hospital.

Receptive music therapy is active hearing of music that is specifically selected to cause a certain effect on a person, such as pain reduction, mental opening, confrontation etc. This active, guided hearing could be helpful as a supporting ritual for patients at home and could extend traditional therapy. However, patients are often unable to select the music pieces that might be helpful for them in a current situation. We are suggesting a self-learning decision support system that allows a patient to answer questions on music anamnesis, is ready for inclusion into an electronic health record, and which enables a therapist to compile a therapeutic music program for the patient at home. Beyond this, the system also suggests appropriate music and duration of listening based on the patient's reported current mental state. In this paper, a concept for such a mobile system for receptive music therapy will be proposed.

For healthcare professionals to use mobile applications we need someone who knows software development, provide them. In healthcare institutions, health professionals use clinical protocols to govern care, and sometimes these documents are computerized through mobile applications to assist them. This work aims to present a proposal of an application of flow as a way of describing clinical protocols for automatic generation of mobile applications to assist health professionals. The purpose of this research is to enable health professionals to develop applications from the description of their own clinical protocols. As a result, we developed a web system that automates clinical protocols for an Android platform, and we validated with two clinical protocols used in a Brazilian hospital. Preliminary results of the developed architecture demonstrate the feasibility of this study.

In the United Arab Emirates (UAE), health services have developed greatly in the past 40 years. To ensure they continue to meet the needs of the population, innovation and change are required including investment in a strong e-Health infrastructure with a single transferrable electronic patient record. In this paper, using the Emirate of Dubai as a case study, we report on the Middle East Electronic Medical Record Adoption Model (EMRAM). Between 2011–2016, the number of participating hospitals has increased from 23 to 33. Currently, while 20/33 of hospitals are at Stage 2 or less, 10/33 have reached Stage 5. Also Dubai's median EMRAM score in 2016 (2.5) was higher than the scores reported from Australia (2.2), New Zealand (2.3), Malaysia (0.06), the Philippines (0.06) and Thailand (0.5). EMRAM has allowed the tracking of the progress being made by healthcare facilities in Dubai towards upgrading their information technology infrastructure and the introduction of electronic medical records.

A large number of biometric connected devices are currently available with a variety of designs. Healthcare users cannot easily choose the reliable ones that correspond the best to their healthcare problems. The existing evaluation methods do not consider at the same time aspects of connectivity and healthcare usage. In this study, a collaborative evaluation framework for biometric connected devices in healthcare usage is proposed. This framework contains six dimensions: medical validity, technical reliability, usability, ergonomy, legal compliance, and accuracy of measurements. In a first step, these dimensions were assessed by designing a self administered questionnaire answered by the stakeholders (patients, health professionals, payers, and manufacturers). A case study was then carried out in a second step to test this framework in a project of telemonitoring for heart failure patients. The results are in favor of the efficiency of the proposed framework as a decision making tool in healthcare usage.

Parkinson's Disease rehabilitation can be long and boring being difficult to maintain patient engagement on therapy programs. Novel technologies are allowing computer games to be played throught natural interfaces. This paper presents the development and assessment of a system of serious games for fine motor skills rehabilitation using natural interfaces. The games were assessed throught a questionnaire that evaluated the game experience through seven components: immersion, flow, competence, tension, challenge and positive and negative affect. In addition, a conceptual framework for development of serious games for fine motor skills rehabilitation was proposed. The results from the quantitative questionnaire suggested that the player experience was positive on all components assessed. Also, player experience between the three games was statistically the same, implying that the games can be used with consistency in a physical therapy rehabilitation program.

Despite the increasing availability of online patient portals that provide access to electronic health records, little is known about their adoption by patients. We systematically reviewed the literature to investigate adoption of patient portals across studies. We searched MEDLINE and Scopus to identify relevant papers. We included 40 studies: 24 were controlled experiments, with prospective data collection in an actively recruited population; 16 were real-world experiments, with adoption being evaluated retrospectively after system deployment in clinical practice. Our meta-analysis showed an overall mean adoption rate of 52% (95% Confidence Interval [CI], 42 to 62%). Rates differed markedly between study types: controlled experiments yielded a mean adoption rate of 71% (95% CI 64 to 79%), compared to 23% (95% CI, 13 to 33%) in real-world experiments. This difference was confirmed in a meta-regression analysis of the influence of study characteristics on adoption rates. Our findings suggest that adoption rates reported in controlled studies do not reflect those in everyday clinical practice. Until we understand how to effectively increase adoption, patient portals are unlikely to consistently lead to improvements in care processes and health outcomes.

In this paper, we describe the development of a unified framework and a digital workbench for the strategic, tactical and operational hospital management plan driven by information technology and analytics. The workbench can be used not only by multiple stakeholders in the healthcare delivery setting, but also for pedagogical purposes on topics such as healthcare analytics, services management, and information systems. This tool combines the three classical hierarchical decision-making levels in one integrated environment. At each level, several decision problems can be chosen. Extensions of mathematical models from the literature are presented and incorporated into the digital platform. In a case study using real-world data, we demonstrate how we used the workbench to inform strategic capacity planning decisions in a multi-hospital, multi-stakeholder setting in the United Kingdom.

This paper uses consumer health informatics as a framework to explore whether and how direct-to-consumer personal genomic testing can be regarded as a form of information which assists consumers to manage their health. It presents findings from qualitative content analysis of web sites that offer testing services, and of transcripts from focus groups conducted as part a study of the Australian public's expectations of personal genomics. Content analysis showed that service offerings have some features of consumer health information but lack consistency. Focus group participants were mostly unfamiliar with the specifics of test reports and related information services. Some of their ideas about aids to knowledge were in line with the benefits described on provider web sites, but some expectations were inflated. People were ambivalent about whether these services would address consumers' health needs, interests and contexts and whether they would support consumers' health self-management decisions and outcomes. There is scope for consumer health informatics approaches to refine the usage and the utility of direct-to-consumer personal genomic testing. Further research may focus on how uptake is affected by consumers' health literacy or by services' engagement with consumers about what they really want.

The design of an early mobile health application (app) prototype to manage interstitial cystitis/painful bladder syndrome, a chronic condition characterized by recurrent pain/discomfort in the bladder and pelvic floor, is described. The purpose of this app prototype is to help people who have IC/PBS manage and learn what triggers their symptoms. Another aim of this research was to provide an example of how sex and gender could be included into the design of a health information system. Based on a literature search of common symptoms and challenges faced by people living with IC/PBS, the researcher created an app prototype design including many features: resources for relaxation, mental health, intimacy, pregnancy, and daily life; reminders for appointments, and medication; logs for diet, activity, sleep, pain, menstruation; and a link to a public washroom locator. This prototype will later undergo usability and content evaluation.

Knowing the dynamics of one's daily stress is essential to effective stress management in the context of smart and connected health. However, there lacks a practical and unobtrusive means to obtain real-time and longitudinal stress information. In this paper, we attempt to derive a convenient HRV-based (heart rate variability) biomarker named cHRV, which can be used to reliably reflect stress dynamics. cHRV's key advantage lies in its low maintenance and high practicality. It can be efficiently calculated only using data from photoplethysmography (PPG) sensors, the mainstream heart rate sensor embedded in most of the consumer wearables like Apple Watch. Benefiting from the proliferation of wearables, cHRV is ideal for day-to-day stress monitoring. To evaluate its feasibility and performance, we have conducted 14 in-lab controlled experiments. The result shows that the proposed cHRV has strong correlation with the stress dynamics (r > 0.95), therefore exhibits great potential for continuous stress assessment.

Significant efforts have been made to improve physician-to-physician communication and care coordination during transition of care in order to reduce adverse events and readmissions. As electronic health records (EHRs) become widely available, many hospitals have implemented physician collaboration and hand-off tools to automatically send admission notifications, discharge summaries, and pending laboratory results to a patient's primary care physician (PCP). However, the effectiveness of such tools depends on a fundamental question that remains unstudied: who is the patient's PCP? Missing or outdated PCP information may become the bottleneck to effective patient-centered care coordination regardless of existing efforts on promoting interoperability among healthcare providers. In this paper, we characterized patient-reported PCPs and experimented with an imputation algorithm that automatically infers a patient's primary provider based on patient-provider encounter data. We compared the imputation results with patient-reported PCPs and suggested practical uses of our findings.

Large population studies are important sources for medical research. These studies are well planned, well organized, and costly. However, people record health data themselves using different sensors, which are mostly unplanned, unorganized and inexpensive. Nevertheless, self-recorded data might be an important supplement to population studies. The question is how to access and use this data. In the seventh survey of the Tromsøcohort study, questionnaires and accelerometers were used to collect data on physical activity (PA). We now plan to collect historical PA data from these participants, using mobile sensor data already stored in the cloud. We will examine the feasibility of this approach and the quality of this data. Objectively measured historical data will provide valuable insights in the potential and limitations of mobile sensors as new data collection tools in medical research.