Relating Factors for Acceptance of Health Care Technology: Focus on Mental Workload

Medical information systems and care robots are two typical examples of human computer interaction in health care. Although used in a stressful environment, effects on mental workload and acceptance are hardly evaluated. We conducted an experimental design including collaborative robotics and eye tracking in a nursing situation to test the practicability and plausibility of eye tracking as a measuring method for workload. Results showed that eye tracking is feasible if context factors are adjusted. Data reduction and classification of tasks are necessary.

Preliminary Assessment of the Interoperability Maturity of Healthcare Digital Services vs Public Services of Other Sectors

The development of electronic services for healthcare presents challenges related to the effective cooperation of systems and stakeholders in a highly regulated environment. Assessing the interoperability maturity of the provided services helps to identify interoperability issues in public administration. This paper presents a typical healthcare digital service: the inpatient admission in a public hospital in Greece. The Interoperability Maturity Model (IMM) is applied to assess its maturity, identify improvement priorities, and compare it with digital services of the healthcare sector. An analysis is also performed to compare a group of fourteen healthcare digital public services with sixty-seven public services of other sectors in the country. The IMM is a useful tool to facilitate awareness raising and priority setting concerning interoperability in public administration. What is discovered, through this preliminary assessment, is that healthcare digital services seem to have higher overall interoperability maturity than those of other sectors in Greece.

Semantic Provenance Graph for Reproducibility of Biomedical Research Studies: Generating and Analyzing Graph Structures from Published Literature

OBJECTIVE

To characterize the scientific reproducibility of biomedical research studies by query and analysis of semantic provenance graphs generated from provenance metadata terms extracted from PubMed articles.

METHODS

We develop a new semantic provenance graph generation algorithm that uses a provenance ontology developed as part of the Provenance for Clinical and Health Research (ProvCaRe) project. The ProvCaRe project has processed and extracted provenance metadata from more than 1.6 million full text articles from the PubMed database.

RESULTS

The semantic provenance graph generation algorithm is evaluated using provenance terms extracted from 75 selected articles describing sleep medicine research studies. In addition, we use eight provenance queries to evaluate the quality of semantic provenance graphs generated by the new algorithm.

CONCLUSION

The ProvCaRe project has created a unique resource to characterize the reproducibility of biomedical research studies and the semantic provenance graph generation algorithm enables users to effectively query and analyze the provenance metadata in the ProvCaRe knowledge repository.

Designed Strategies and Adaptation of a Master Patient Index for Transgender Patients in a Tertiary Care Hospital

Transgender people experience their gender identity as different from the sex assigned to them at birth and/or those listed on their legal identification. A Master Patient Index (MPI) is a centralized index of all patients in a health care system. The objective of this work was to describe the designed strategies and adapting of a MPI that contemplates transgender patient registration needs as regards as health and legal context.

Expectations in the Development of Computer Technology in Primary Care: A Multidisciplinary Delphi Study Among 23 French Experts

The goal of this study was to determine a consensual proposition for the development of computer tools in primary care. A Delphi study using colored abaci was conducted among 23 French experts, some of whom were patients. The tools expected by the experts were: a customizable knowledge database integrated into an efficient clinical support system, a follow-up calendar designed as a collaborative patient-focused tool, and an information exchange data system.

Enterprise Architecture in Hospitals: Resolving Incongruence Issues

Enterprise Architecture allows addressing technologies and processes in a holistic way and mirrors choices related to process standardization and data integration. It has the potential to address long-standing problems in health information systems related to fragmented IT portfolios, immature IT infrastructures, and silo-structured organizing. Nevertheless, uptake of Enterprise Architecture in hospitals has been slow. To understand the issues related to this slow uptake we have undertaken an interview study with architects and managers. The issues identified reveal a level of incongruence between healthcare as a domain and the practice of EA. Specifically, by analyzing the experiences of architects and managers we identified four different areas of such incongruence that create the need to reconcile a) Bottom-up vs. Top-down Planning b) Clinical vs. Systems' Knowledge, c) Local vs. Global Arrangements and d) Patient Safety vs. Patient Privacy. Building on prior related research we propose ways for resolving the incongruence issues identified.

'Hybrid Doctors' Can Fast Track the Evolution of a Sustainable e-Health Ecosystem in Low Resource Contexts: The Sri Lankan Experience

Although e-health is an area recognized as essential in the rapid development of healthcare systems in low resource contexts, many challenges prevent the emergence of an effective e-health ecosystem. Lack in capacity around health informatics is one of the main challenges. Based on a longitudinal case study gathering data pertaining to a master's program in biomedical informatics in Sri Lanka designed for doctors, in this paper we demonstrate that creating 'hybrid doctors' may be the way forward. We illustrate how hybrid doctors conversant in healthcare and information and communication technology (ICT) are able to facilitate the creation of an e-health ecosystem in a way that it would contribute significantly to the ICT driven healthcare reforms. Through this case study we highlight the importance of multidisciplinarity, participatory design, strategic investments, learning that aligns with developmental needs, networking, gaining legitimacy and re-packaging perspectives on 'health informatics capacity development'.

Open and Linkable Knowledge About Management of Health Information Systems

Given a care delivery organization, its health information system can be defined as the part of the organization that processes and stores data, information, and knowledge. There is an enormous number of frameworks, textbooks and articles that describe the scope of health information system management from the perspective of medical informatics. Transforming this knowledge to Linked Open Data results in a structured data representation that is accessible for both humans and machines, the Semantic Network of Information Management in Hospitals (SNIK). We present interfaces that are useful for researchers, practitioners and students, depending on their objectives and their Semantic Web skills.

Measuring the effect of different types of unsupervised word representations on Medical Named Entity Recognition

BACKGROUND

This work deals with Natural Language Processing applied to the clinical domain. Specifically, the work deals with a Medical Entity Recognition (MER) on Electronic Health Records (EHRs). Developing a MER system entailed heavy data preprocessing and feature engineering until Deep Neural Networks (DNNs) emerged. However, the quality of the word representations in terms of embedded layers is still an important issue for the inference of the DNNs.

GOAL

The main goal of this work is to develop a robust MER system adapting general-purpose DNNs to cope with the high lexical variability shown in EHRs. In addition, given that EHRs tend to be scarce when there are out-domain corpora available, the aim is to assess the impact of the word representations on the performance of the MER as we move to other domains. In this line, exhaustive experimentation varying information generation methods and network parameters are crucial.

METHODS

We adapted a general purpose sequential tagger based on Bidirectional Long-Short Term Memory cells and Conditional Random Fields (CRFs) in order to make it tolerant to high lexical variability and a limited amount of corpora. To this end, we incorporated part of speech (POS) and semantic-tag embedding layers to the word representations.

RESULTS

One of the strengths of this work is the exhaustive evaluation of dense word representations obtained varying not only the domain and genre but also the learning algorithms and their parameter settings. With the proposed method, we attained an error reduction of 1.71 (5.7%) compared to the state-of-the-art even that no preprocessing or feature engineering was used.

CONCLUSIONS

Our results indicate that dense representations built taking word order into account leverage the entity extraction system. Besides, we found that using a medical corpus (not necessarily EHRs) to infer the representations improves the performance, even if it does not correspond to the same genre.

Classification of Skin Disease using Ensemble Data Mining Techniques

Objective: Skin diseases are a major global health problem associated with high number of people. With the rapid development of technologies and the application of various data mining techniques in recent years, the progress of dermatological predictive classification has become more and more predictive and accurate. Therefore, development of machine learning techniques, which can effectively differentiate skin disease classification, is of vast importance. The machine learning techniques applied to skin disease prediction so far, no techniques outperforms over all the others. Methods: In this research paper, we present a new method, which applies five different data mining techniques and then developed an ensemble approach that consists all the five different data mining techniques as a single unit. We use informative Dermatology data to analysis different data mining techniques to classify the skin disease and then, an ensemble machine learning method is applied. Results: The proposed ensemble method, which is based on machine learning was tested on Dermatology datasets and classify the type of skin disease in six different classes like include C1: psoriasis, C2: seborrheic dermatitis, C3: lichen planus, C4: pityriasis rosea, C5: chronic dermatitis, C6: pityriasis rubra. The results show that the dermatological prediction accuracy of the test data set is increased compared to a single classifier. Conclusion: The ensemble method used on Dermatology datasets give better performance as compared to different classifier algorithms. Ensemble method gives more accurate and effective skin disease prediction.

Major Adverse Kidney Events in Pediatric Sepsis

BACKGROUND AND OBJECTIVES

Major adverse kidney events, a composite of death, new kidney replacement therapy, or persistent kidney dysfunction, is a potential patient-centered outcome for clinical trials in sepsis-associated kidney injury. We sought to determine the incidence of major adverse kidney events within 30 days and validate this end point in pediatric sepsis.

DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS

We conducted a retrospective observational study using the Pediatric Health Information Systems Plus database of patients >6 months to <18 years old with a diagnosis of severe sepsis/septic shock; orders for bacterial blood culture, antibiotics, and at least one fluid bolus on hospital day 0/1; and known hospital disposition between January 2007 and December 2011. The primary outcome was incidence of major adverse kidney events within 30 days. Major adverse kidney events within 30 days were validated against all-cause mortality at hospital discharge, hospital length of stay, total hospital costs, hospital readmission within 30 days and 1 year, and lowest eGFR between 3 months and 1 year after discharge. We reported incidence of major adverse kidney events within 30 days with 95% confidence intervals using robust SEM and used multivariable logistic regression to test the association of major adverse kidney events within 30 days with hospital costs and mortality.

RESULTS

Of 1685 admissions, incidence of major adverse kidney events within 30 days was 9.6% (95% confidence interval, 8.1% to 11.0%), including 4.5% (95% confidence interval, 3.5% to 5.4%) death, 1.7% (95% confidence interval, 1.1% to 2.3%) kidney replacement therapy, and 5.8% (95% confidence interval, 4.7% to 6.9%) persistent kidney dysfunction. Patients with versus without major adverse kidney events within 30 days had higher all-cause mortality at hospital discharge (28% versus 1%; P<0.001), higher total hospital costs ($61,188; interquartile range, $21,272-140,356 versus $28,107; interquartile range, $13,056-72,697; P<0.001), and higher proportion with eGFR<60 ml/min per 1.73 m² between 3 months and 1 year after discharge (19% versus 4%; P=0.001). Major adverse kidney events within 30 days was not associated with length of stay or readmissions.

CONCLUSIONS

In children with sepsis, major adverse kidney events within 30 days are common, feasible to measure, and a promising end point for future clinical trials.

Hidden deaths: corrected estimates of homicides in Bahia, Brazil, 1996- 2015

The objective of this study was to correct and estimate five-year homicide rates in Bahia, Brazil, for the 1996-2015 period. An ecological study of the homicides was carried out using official data from the Mortality Information System of the Ministry of Health. Deaths due to assault are classified in the codes X85-Y09 of the International Classification of Disease 10th Revision (ICD-10). A proportional redistribution of deaths classified as events of undetermined intent (Y10-Y34) was carried out and mortality correction factors were applied. In the analyzed period, 67,599 homicides were registered in the Mortality Information System; after the second correction, 88,429 homicide deaths were estimated. Comparing the official and adjusted figures, there was an underreporting of 30.8%. The highest corrected homicide rates were observed in the eastern region, in Pojuca (129.8 homicides per 100,000 inhabitants), Lauro de Freitas (117.7) and Simões Filho (114.3); in the southern region, in Santa Luzia (121.4), Valença (87.6) and Itabuna (86.5); and in the far south, Santa Cruz Cabrália (128.2), Itabela (113.3) and Porto Seguro (106.8). After correction, there was an increase in homicides in all of the five-year periods in the municipalities analyzed, which resulted in an even higher mortality rate.

Health Referral Enterprise Architecture Design in Indonesia

Objectives

In this study an enterprise architecture (EA) was developed for a health referral information system (HRIS) for individual healthcare in Indonesia with reference to the Open Group Architecture Framework (TOGAF) 9.1. The HRIS includes patient referrals for vertical and horizontal references (internal and external), specimen referrals, and health personnel referrals.

Methods

This research was a qualitative study that used the interview and observation method of the Primary Health Care Information System (SIMPUS) application developed by the Agency for Assessment and Application of Technology (BPPT). The interviews were conducted at South Tangerang City Government Health Office with five resource persons who were responsible for conducting health referral processes.

Results

The EA of the HRIS includes the principles of architecture, business, application, data, and technology architecture. Twelve principles, four referral processes, and three application reference modules and centralized applications comprise the architecture of the HRIS. The HRIS is a centralized integrated application that uses application program interface (API) to integrate with SIMPUS.

Conclusions

The proposed architecture was developed in an integrated and comprehensive manner for the individual healthcare referral process, which can be implemented by regulators and healthcare facilities. This architecture can also help regulators and healthcare facilities to standardize and integrate health referral data and related processes.

Interoperability Improvement of Mobile Patient Survey (MoPat) Implementing Fast Health Interoperability Resources (FHIR)

Despite the advances in health information technology and the increasing usage of electronic systems, syntactic and semantic interoperability between different health information systems remains challenging. An emerging standard to tackle interoperability issues is HL7 FHIR, which uses modern web technologies for communication like Representational State Transfer. The electronic patient reported outcome system Mobile Patient Survey (MoPat) was adapted to support metadata import and clinical data export using HL7 FHIR. Thereby, the data models of HL7 FHIR and MoPat were compared and the existing import and export functions of MoPat were extended to support HL7 FHIR. A test protocol including eight test datasets to proof functioning of the new features was successfully conducted. In the near future, a real time searching toolbar of FHIR metadata resources will be integrated within MoPat. MoPat FHIR import and export functions are ready to be used in a clinical setting in combination with a FHIR compliant clinical data server.

Next Generation EHRs - What Problems Are These Systems Aiming to Solve?

EHRs elicit an array of different aspirations all underpinned by the widely held conviction that they can deliver benefits for patients, clinicians, researchers, IT vendors, policy-makers and society as a whole. While techno-centric visions abound, reflection on their history, the challenges evident in their design, implementation and evaluation and the limited evidence of their beneficial impacts over time is instructive. From a socio-technical perspective EHRs appear to be a set of 'wicked problems' unlikely to be resolved in favor of one position or another, but rather requiring judgement, nuance and negotiation around the kinds of problems we want these systems to solve. This paper presents some perspectives on important potential features for next generation EHRs and on the types of problems that these systems could aspire to solve. The focus is not on prediction but rather on actively shaping the kind of future that we desire and how EHRs will support its achievement.

Leveraging hospital big data to monitor flu epidemics

BACKGROUND AND OBJECTIVE

Influenza epidemics are a major public health concern and require a costly and time-consuming surveillance system at different geographical scales. The main challenge is being able to predict epidemics. Besides traditional surveillance systems, such as the French Sentinel network, several studies proposed prediction models based on internet-user activity. Here, we assessed the potential of hospital big data to monitor influenza epidemics.

METHODS

We used the clinical data warehouse of the Academic Hospital of Rennes (France) and then built different queries to retrieve relevant information from electronic health records to gather weekly influenza-like illness activity.

RESULTS

We found that the query most highly correlated with Sentinel network estimates was based on emergency reports concerning discharged patients with a final diagnosis of influenza (Pearson's correlation coefficient (PCC) of 0.931). The other tested queries were based on structured data (ICD-10 codes of influenza in Diagnosis-related Groups, and influenza PCR tests) and performed best (PCC of 0.981 and 0.953, respectively) during the flu season 2014-15. This suggests that both ICD-10 codes and PCR results are associated with severe epidemics. Finally, our approach allowed us to obtain additional patients' characteristics, such as the sex ratio or age groups, comparable with those from the Sentinel network.

CONCLUSIONS

Conclusions: Hospital big data seem to have a great potential for monitoring influenza epidemics in near real-time. Such a method could constitute a complementary tool to standard surveillance systems by providing additional characteristics on the concerned population or by providing information earlier. This system could also be easily extended to other diseases with possible activity changes. Additional work is needed to assess the real efficacy of predictive models based on hospital big data to predict flu epidemics.

Development of an Evaluation Framework for Health Information Systems (DIPSA)

Introduction:

Use of Integrated Health Information Systems (IHIS) for the provision of healthcare services benefits both healthcare professionals and patients, while requiring continuous evaluation and upgrading to fully support its role.

Aim:

The main purpose of the study was to develop an evaluation framework for hospitals utilizing IHIS, within the three main areas identified as Human factor, Technology and Organization.

Material and methods:

The questionnaire consisted of 43 questions, with 17 questions (related to categories procedures, system quality and satisfaction), 25 questions (related to categories, safety and collaboration) and 1 question related to accessibility to the system (within the category system quality). Three open questions were added to evaluate users’ perception on what was needed for the improvement of health services in their respective hospitals for all 3 variables being evaluated. The open questions were included to allow participants to express their opinion in a more detailed setting. A database was developed, and the data were processed and analyzed.

Results:

Factor analysis formed 5 categories for the evaluation framework. Cronbach’s alpha coefficient was found in all categories to be above > 0.85.

Conclusion:

Evaluation frameworks can be designed, developed and implemented by using different methodologies. For an evaluation framework to be effective it should be designed and implemented based on the aims and purpose of the research and the specific needs of the particular healthcare setting or hospital. Considering the categories satisfaction, collaboration, safety, system quality, procedures, and by using Likert scale and open questions in the current study, DIPSA can provide a holistic image of IHIS by evaluating any hospital system.

Strategies for Effectively Documenting Sexual Orientation and Gender Identity in Electronic Health Record

In this communication we identify strategies for effectively documenting Sexual Orientation and Gender Identity in Electronic Health Records. For this review a multidisciplinary group composed by three physicians, a nurse, an engineer and a lawyer analyzed the evidence in bibliography related to the topic and summarized the results. After analyzing the information, we summarized and classified them into three major topics: To request, to store and to display and access to the information. How to standardize those data and where data specifically will be populated in EHRs have not been answered yet. The target of all of these efforts should be: to be sensitive with the needs of the patient and to ensure high quality of care.

Improving Patient Safety by Reusing Clinical Routine Data - An Expert Survey on Patient Safety Indicators

BACKGROUND

Patient safety is an important issue and receiving increasing attention. Information technology (IT) and IT-based strategies as the secondary use of already existing data within hospital information systems can help to improve patient safety.

OBJECTIVE

To investigate experts' knowledge and opinions regarding relevant patient safety problems, their measurability in existing clinical routine data and potential challenges in the field. We also wanted to get an overview of already deployed indicators for patient safety.

METHODS

Semi structured interviews with 20 experts from different healthcare domains were conducted and analyzed using a qualitative content analysis methodology.

RESULTS

The expert interviews offered a deeper insight into patient safety and quarried relevant patient safety problems including possibilities to measure them. The most often mentioned indicators were infection, complication and pressure ulcer.

CONCLUSION

From an experts' perspective there are several challenges but equally a high potential for improving patient safety by the use of health IT.

Comparison of Three Internship Training Sites for an Undergraduate Health Information Management Program in Saudi Arabia

Objectives

While internship training is well established for medical records and for healthcare quality improvement, it is not quite so for training related to IT/health informatics. A comparison was made on the hospital-based IT/health informatics internship training received by students completing their training at the Imam AbdulRahman Bin Faisal University (IAU) in the Eastern province of Saudi Arabia.

Methods

The three hospitals studied all have the Joint Commission International accreditation and advanced Electronic Health Record (EHR) systems. Over the period from 2011 to 2015, interns from the IAU prepared 120 reports based on their training at these three hospitals. Data abstraction was done on the internship reports, and the results were summarized and interpreted.

Results

The study found wide differences in the training received at these hospitals. The main reason for the differences is whether or not the EHR system used in the hospital was a commercial one or developed in-house.

Conclusions

The hospital that had developed its own EHR system made more use of health information management interns during their IT rotation in comparison to hospitals which had adopted commercial EHR systems. Recommendations are made of both local relevance and of international relevance.

Validation of the DeLone and McLean Information Systems Success Model

Objectives

This study is an adaptation of the widely used DeLone and McLean information system success model in the context of hospital information systems in a developing country.

Methods

A survey research design was adopted in the study. A structured questionnaire was used to collect data from 442 health information management personnel in five Nigerian teaching hospitals. A structural equation modeling technique was used to validate the model's constructs.

Results

It was revealed that system quality significantly influenced use (β = 0.53, p < 0.001) and user satisfaction (β = 0.17, p < 0.001). Information quality significantly influenced use (β = 0.24, p < 0.001) and user satisfaction (β = 0.17, p < 0.001). Also, service quality significantly influenced use (β = 0.22, p < 0.001) and user satisfaction (β = 0.51, p < 0.001). However, use did not significantly influence user satisfaction (β = 0.00, p > 0.05), but it significantly influenced perceived net benefits (β = 0.21, p < 0.001). Furthermore, user satisfaction did not significantly influence perceived net benefits (β = 0.00, p > 0.05).

Conclusions

The study validates the DeLone and McLean information system success model in the context of a hospital information system in a developing country. Importantly, system quality and use were found to be important measures of hospital information system success. It is, therefore, imperative that hospital information systems are designed in such ways that are easy to use, flexible, and functional to serve their purpose.

Use of an Off-the-Shelf Corporate Information Tool to Track a High-Level-Disinfection Process

High-Level Disinfection (HLD) of endoscopic equipment is a critical process to ensure patient safety. Although commercial tracking software is available, here we demonstrate the successful design and implementation of a HLD tracking system using pre-existing corporate information tools. After a brief development and implementation stage, the HLD unit is successfully tracking the process and are able to create simple visualizations to monitor and improve the existing procedures.

Automatic Conversion of Metadata from the Study of Health in Pomerania to ODM

BACKGROUND

Electronic collection and high quality analysis of medical data is expected to have a big potential to improve patient care and medical research. However, the integration of data from different stake holders is posing a crucial problem. The exchange and reuse of medical data models as well as annotations with unique semantic identifiers were proposed as a solution.

OBJECTIVES

Convert metadata from the Study of Health in Pomerania to the standardized CDISC ODM format.

METHODS

The structure of the two data formats is analyzed and a mapping is suggested and implemented.

RESULTS

The metadata from the Study of Health in Pomerania was successfully converted to ODM. All relevant information was included in the resulting forms. Three sample forms were evaluated in-depth, which demonstrates the feasibility of this conversion.

CONCLUSION

Hundreds of data entry forms with more than 15.000 items can be converted into a standardized format with some limitations, e.g. regarding logical constraints. This enables the integration of the Study of Health in Pomerania metadata into various systems, facilitating the implementation and reuse in different study sites.

Enabling Patient Control of Personal Electronic Health Records Through Distributed Ledger Technology

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.

Operational Data Model Conversion to ResearchKit

The increasing use of electronic health information systems brings up an unresolved issue: the lack of interoperability between these systems. The Clinical Data Interchange Standards Consortium's Operational Data Model (ODM) is an xml based standard for the exchange of clinical data and metadata. The University of Münster has been using ODM to store medical forms in a web based metadata registry called Portal of Medical Data Models, which includes a complete set of tools to transform ODM forms into other formats. One kind of medical form is the Patient Reported Outcome, a trending type due to its easy integration with mobile data capture systems. ResearchKit is a development framework that allows the easy creation of these for iOS devices; unfortunately its current interoperability is limited. This research proposes a mapping between ODM and ResearchKit and presents the successful implementation of a converter for ODM into JSON based ResearchKit readable files.