Health data space nodes for privacy-preserving linkage of medical data to support collaborative secondary analyses.

Introduction: The potential for secondary use of health data to improve healthcare is currently not fully exploited. Health data is largely kept in isolated data silos and key infrastructure to aggregate these silos into standardized bodies of knowledge is underdeveloped. We describe the development, implementation, and evaluation of a federated infrastructure to facilitate versatile secondary use of health data based on Health Data Space nodes. Materials and methods: Our proposed nodes are self-contained units that digest data through an extract-transform-load framework that pseudonymizes and links data with privacy-preserving record linkage and harmonizes into a common data model (OMOP CDM). To support collaborative analyses a multi-level feature store is also implemented. A feasibility experiment was conducted to test the infrastructures potential for machine learning operations and deployment of other apps (e.g., visualization). Nodes can be operated in a network at different levels of sharing according to the level of trust within the network. Results: In a proof-of-concept study, a privacy-preserving registry for heart failure patients has been implemented as a real-world showcase for Health Data Space nodes at the highest trust level, linking multiple data sources including (a) electronical medical records from hospitals, (b) patient data from a telemonitoring system, and (c) data from Austria's national register of deaths. The registry is deployed at the tirol kliniken, a hospital carrier in the Austrian state of Tyrol, and currently includes 5,004 patients, with over 2.9 million measurements, over 574,000 observations, more than 63,000 clinical free text notes, and in total over 5.2 million data points. Data curation and harmonization processes are executed semi-automatically at each individual node according to data sharing policies to ensure data sovereignty, scalability, and privacy. As a feasibility test, a natural language processing model for classification of clinical notes was deployed and tested. Discussion: The presented Health Data Space node infrastructure has proven to be practicable in a real-world implementation in a live and productive registry for heart failure. The present work was inspired by the European Health Data Space initiative and its spirit to interconnect health data silos for versatile secondary use of health data.

Towards an Electronic Health Prevention Record Based on HL7 FHIR and the OMOP Common Data Model.

BACKGROUND: Approximately 40% of all recorded deaths in Austria are due to behavioral risks. These risks could be avoided with appropriate measures. OBJECTIVES: Extension of the concept of EHR and EMR to an electronic prevention record, focusing on primary and secondary prevention. METHODS: The concept of a structured prevention pathway, based on the principles of P4 Medicine, was developed for a multidisciplinary prevention network. An IT infrastructure based on HL7 FHIR and the OHDSI OMOP common data model was designed. RESULTS: An IT solution supporting a structured and modular prevention pathway was conceptualized. It contained a personalized management of prevention, risk assessment, diagnostic and preventive measures supported by a modular, interoperable IT infrastructure including a health app, prevention record web-service, decision support modules and a smart prevention registry, separating primary and secondary use of data. CONCLUSION: A concept was created on how an electronic health prevention record based on HL7 FHIR and the OMOP common data model can be implemented.

Towards a Verification Approach of a Smart Registry for Chronic Heart Failure Patients.

BACKGROUND: The daily increasing amount of health data from different sources like electronic medical records and telehealth systems go hand in hand with the ongoing development of novel digital and data-driven analytics. Unifying this in a privacy-preserving data aggregation infrastructure can enable services for clinical decision support in personalized patient therapy. OBJECTIVES: The goal of this work was to consider such an infrastructure, implemented in a smart registry for heart failure, as a comparative method for the analysis of health data. METHODS: We analyzed to what extent the dataset of a study on the telehealth program HerzMobil Tirol (HMT) can be reproduced with the data from the smart registry. RESULTS: A table with 96 variables for 251 patients of the HMT publication could theoretically be replicated from the smart registry for 248 patients with 80 variables. The smart registry contained the tables to reproduce a large part of the information, especially the core statements of the HMT publication. CONCLUSION: Our results show how such an infrastructure can enable efficient analysis of health data, and thus take a further step towards personalized health care.

Concept for Visualisation of Guideline Adherence of Medication Prescriptions in a Heart Failure Telehealth System.

BACKGROUND: Heart failure is a chronic disease that affects around 26 million people worldwide. Projections assume a substantial increase in prevalence over the next years. To improve the survival rate and quality of life in patients suffering from heart failure, the European Society of Cardiology published guidelines for diagnosis and treatment. Adherence of healthcare professionals' medication prescriptions with regard to these guidelines is critical for optimal outcomes. METHODS: Data from the conceptional phase of the existing disease management network 'HerzMobil Tirol' were analysed. Prescriptions and patient- reported intake data of the four major substances of recommended heart failure medication were used to calculate the relative prescribed doses as a percentage of the recommended target doses. A concept for visualisation of the prescription status was developed in cooperation with health professionals. RESULTS: The documented prescriptions were analysed and used to develop a mock-up in order to visualise the prescription status for the individual patient. CONCLUSION: Analysis and visualisation can be managed by displaying the calculated daily relative dose per substance group in a traffic light system.

A Computer Model for Patient Individual Parametrizing of Ventricular Tachycardia Termination Algorithms.

BACKGROUND: Antitachycardial pacing (ATP) is a painless method for terminating ventricular tachycardias (VT) which would otherwise be treated using a painful high energy shock. However, it is well known that not each VT can be successfully terminated by ATP. Furthermore, ATP can be parametrized in several ways using scan, ramp or scan ramp approaches and can be applied in the right ventricle or in both ventricles (biventricular). In this work, we investigate the therapeutically most convenient ATP protocol based on a computer simulation using a patient individual model. METHODS: A patient individual model generated from a 3D/4D data set and a hybrid automaton was used for modeling and simulation of different VT scenarios. On the different VTs (from cycle length 288 ms up to 408 ms) different ATP approaches derived from the ADVANCE-CRT trial were applied in order to determine the effectiveness of these approaches. RESULTS: In this computer simulation study we were able to verify and validate the results from the ADVANCE-CRT trial. Biventricular ATP does not prove to be more effective than RV ATP but has a slight advantage in terminating fast VTs. CONCLUSIONS: The availability of a patient individual model and knowledge about the ischemic area and the underlying mechanism of the VTs will allow the use of these models to optimize ATP management.

Heart Rate Performance Curve Is Dependent on Age, Sex, and Performance.

Introduction: The Heart Rate Performance Curve (HRPC) is neither linear nor uniform and related to ß1-adrenoceptor sensitivity. As aging and exercise influence ß1-adrenoceptors we suggested age, sex and performance effects on the HRPC. Aim of the study was to examine the effects of aging on the deflection of the HRPC in maximal incremental cycle ergometer exercise (CE) in a large cohort of healthy subjects. Methods: Heart rate (HR) data of 2,980 men (51 ± 15 years) and 1,944 women (52 ± 14 years) were classified into age groups (≤20 up to >80 years). We analyzed age and performance (Plow 25%-quartile and Phigh 75%-quartile of age predicted power) effects on HRmax and on the degree (k) and the type (regular downward deflection k > 0.1, linear -0.1 ≤ k ≤ 0.1 and atypical upward deflection k < -0.1) of the HRPC. Results:k-values decreased significantly with age in men and women and were significantly higher in women. Atypical HRPC's increased by a linear trend from ≤20 to 70 years (m) respectively 80 years (w) from 10 to 43% (m) and 9 to 30% (w). HRmax of all age groups was lower in Plow and overall number of atypical HRPC's was 21% (m) and 16% (w) higher compared to Phigh. Conclusion: Aging increased the number of atypical HRPC's with upward deflection in CE tests, which influences exercise intensity prescription especially when using fixed percentages of HRmax. Changes in HRPC's were affected by sex and performance, where women generally and subjects with higher performance presented less atypical HRPC's even at older age.

Telemonitoring readiness among Austrian diabetic patients: A cross-sectional validation study.

Digitalized healthcare services offer remote and cost-effective treatment of diabetes patients. Thus, the present online study analyzed the readiness to use telemonitoring among Austrian diabetes patients. We developed and validated a German version of the patient telehealth readiness assessment tool and performed quantitative context analysis of free-text comments on perceived barriers and benefits of telemonitoring. Participants (n = 41, 42.6% females) achieved a medium average readiness level for telemonitoring. The three top benefits were intensified care, shorter travel and waiting times, and better therapy adjustment. The top three barriers were data privacy issues, loss of personal communication and focus on blood sugar, and teledoctor competence. Diabetes patients represent a suitable target group for remote treatment opportunities. However, a shift from traditional face-to-face medical care to exclusive telemonitoring treatment from diagnosis to consultation and treatment requires fundamental new legal framework conditions.

Patient Record Linkage for Data Quality Assessment Based on Time Series Matching.

BACKGROUND: Huge amounts of data are collected by healthcare providers and other institutions. However, there are data protection regulations, which limit their utilisation for secondary use, e.g. RESEARCH: In scenarios, where several data sources are obtained without universal identifiers, record linkage methods need to be applied to obtain a comprehensive dataset. OBJECTIVES: In this study, we had the objective to link two datasets comprising data from ergometric performance tests in order to have reference values to free text annotations for assessing their data quality. METHODS: We applied an iterative, distance-based time series record linkage algorithm to find corresponding entries in the two given datasets. Subsequently, we assessed the resulting matching rate. The implementation was done in Matlab. RESULTS: The matching rate of our record linkage algorithm was 74.5% for matching patients' records with their ergometry records. The highest rate of appropriate free text annotations was 87.9%. CONCLUSION: For the given scenario, our algorithm matched 74.5% of the patients. However, we had no gold standard for validating our results. Most of the free text annotations contained the expected values.

Readiness to use telemonitoring in diabetes care: a cross-sectional study among Austrian practitioners.

BACKGROUND: Telemonitoring services could dramatically improve the care of diabetes patients by enhancing their quality of life while decreasing healthcare expenditures. However, the potential for implementing innovative treatment options in the Austrian public and private health system is not known yet. Thus, we analyzed the readiness to use telemonitoring in diabetes care among Austrian practitioners. METHODS: We conducted an online survey among a purposive sample of Austrian practitioners (n = 41) using an adapted German version of the practitioner telehealth readiness assessment tool. We assessed three readiness domains for telemonitoring in the context of diabetes care, i.e. core readiness, engagement readiness, and structural readiness, and validated the German tool using principal components analysis. RESULTS: Study subjects perceived themselves as open to innovations and also expressed optimistic attitudes towards telemonitoring in general and offering telemonitoring-based services for their patients. Participants achieved a medium average readiness level for telemonitoring (58.2, 95% CI 53.9-62.5) and were thus in a good position to use telemonitoring, although some arguments may adversely affected its use. The top three perceived benefits of telemonitoring were enhanced quality of treatment, better therapy adjustment, and reduced travel and waiting times for patients. The top three barriers were reduced personal communication, practitioner time expenditure and equally placed poor financial compensation as well as data security and privacy issues. CONCLUSION: Our data revealed that Austrian practitioners showed a quite moderate readiness to use telemonitoring in diabetes care. To further advance telemonitoring readiness among all pillars of diabetes care in Austria, joint efforts among healthcare stakeholders are required to overcome existing financial, organizational, and technical obstacles.

Automated Measurement and Subtask Analysis of the Timed Up-and-Go Test in the Field of Geriatrics.

Multimorbidity and age-physiological functional restrictions can lead to frailty and a loss of a self-determined life in elderly patients. The Timed Up-and-Go test (TUG) is a sensitive and specific measure of frailty and has also many other areas of application, for example in chronic diseases. Besides the measurement of the complete TUG time, the analysis of subtasks may also reveal important information about particular aspects of the health status of test subjects. We developed an ultrasonic-based device for performing the TUG automatically, which can be attached to the backrest of a chair. This device provides the total TUG time as well as the displacement-time data for all included subtasks. To prepare for its use in clinical studies, we performed a field test at a geriatric center. The goal was to confirm feasibility, i.e., to assess its application in real patients. Despite some improvement potential revealed by the field test, the concept turned out to be an appropriate method for monitoring the TUG time and its subtasks.

HEALTHeBIKES - Smart E-Bike Prototype for Controlled Exercise in Telerehabilitation Programs.

E-Bikes in telerehabilitation programs could be a new intervention for more sustainable rehabilitation results. The aim is to design and build a prototype of an E-Bike usable for rehabilitation - a HEALTHeBIKE. It should avoid over-exercising, work independently of the environment and it should enable cycling in a group despite different reference exercise intensities. To achieve these goals, requirements for this system architecture have been identified. A system architecture including an Arduino microcontroller, an Android smartphone and a telemonitoring platform was presented. A power output regulated proportional-integral controller to adjust the motor assistance has been implemented. A feasibility study with two subjects cycling in a group was performed. Seven test rides on varying terrain (flat, hilly, mountainous and uphill) with the same and different exercise intensities were completed. The mean power output was close to or below the target power output of the cyclist for all test rides with a maximal error of 6.7% above and 27.6% below the target. Although the exercise intensities of the two subjects were clearly different, cycling in a group was possible without over-exercising.

Is Austria Ready for Telemonitoring? A Readiness Assessment Among Doctors and Patients in the Field of Diabetes.

BACKGROUND: Telemonitoring offers new opportunities in the treatment of chronically ill patients and could help to improve their quality of life while reducing healthcare costs. OBJECTIVES: The willingness to use telemonitoring is examined for both physicians and patients. From the perspective of the most important stakeholders, advantages and disadvantages as well as barriers for telemonitoring are analysed. METHODS: A Telehealth Readiness Assessment was carried out with physicians (n = 41) and patients (n = 47) in a cross-sectional study. A stakeholder survey was conducted by use of interviews (n = 28). RESULTS: Average readiness for telemonitoring is 58% for physicians, and 65% for patients. Both are thus in a position where there are several arguments which adversely affect the success of telemonitoring. The most important advantage is the intensified care, while the biggest concerns are data protection as well as the loss of personal communication. The greatest barriers are the lack of funding, the weak clinical and economic evidence and the organisation of the Austrian healthcare system. CONCLUSION: There are still some barriers to overcome, especially financial, political and organisational.

Challenges of a HL7 CDA Guideline for Telehealth Based DMP Systems.

BACKGROUND: Disease management programs (DMP) are a modern way of treating health conditions and are becoming a part of standard care. One telehealth DMP service has been in regular operation since 2017, named "HerzMobil Tirol". OBJECTIVES: This paper investigates, if the electronic health record standard HL7 CDA, which is widely accepted in the health care industry, could be used for telehealth DMP services as well. It is already in use in a legally required integrated element of healthcare in Austria called ELGA. An official guideline from the Austrian Ministry of Health sets the standard for telemonitoring with data logging. METHODS: After the background knowledge was built up, requirements have been gathered through existing official guidelines and interviews and existing documentation by "HerzMobil Tirol". RESULTS: Twenty-five requirements were collected, categorized and analyzed to determine if the existing CDA guidelines are suitable or a new standard must be designed. CONCLUSION: Based on the requirements, it was established that seven specific sections and two different CDA documents are needed.

HerzMobil, an Integrated and Collaborative Telemonitoring-Based Disease Management Program for Patients With Heart Failure: A Feasibility Study Paving the Way to Routine Care.

BACKGROUND: Heart failure is a major health problem associated with frequent hospital admissions. HerzMobil Tirol is a multidisciplinary postdischarge disease management program for heart failure patients to improve quality of life, prevent readmission, and reduce mortality and health care costs. It uses a telemonitoring system that is incorporated into a network of specialized heart failure nurses, physicians, and hospitals. Patients are equipped with a mobile phone, a weighing scale, and a blood pressure and heart rate monitor for daily acquisition and transmission of data on blood pressure, heart rate, weight, well-being, and drug intake. These data are transmitted daily and regularly reviewed by the network team. In addition, patients are scheduled for 3 visits with the network physician and 2 visits with the heart failure nurse within 3 months after hospitalization for acute heart failure. OBJECTIVE: The objectives of this study were to evaluate the feasibility of HerzMobil Tirol by analyzing changes in health status as well as patients' self-care behavior and satisfaction and to derive recommendations for implementing a telemonitoring-based interdisciplinary disease management program for heart failure in everyday clinical practice. METHODS: In this prospective, pilot, single-arm study including 35 elderly patients, the feasibility of HerzMobil Tirol was assessed by analyzing changes in health status (via Kansas City Cardiomyopathy Questionnaire, KCCQ), patients' self-care behavior (via European Heart Failure Self-Care Behavior Scale, revised into a 9-item scale, EHFScB-9), and user satisfaction (via Delone and McLean System Success Model). RESULTS: A total of 43 patients joined the HerzMobil Tirol program, and of these, 35 patients completed it. The mean age of participants was 67 years (range: 43-86 years). Health status (KCCQ, range: 0-100) improved from 46.2 to 69.8 after 3 months. Self-care behavior (EHFScB-9, possible range: 9-22) after 3 months was 13.2. Patient satisfaction in all dimensions was 86% or higher. Lessons learned for the rollout of HerzMobil Tirol comprise a definite time schedule for interventions, solid network structures with clear process definition, a network coordinator, and specially trained heart failure nurses. CONCLUSIONS: On the basis of the positive evaluation results, HerzMobil Tirol has been officially introduced in the province of Tyrol in July 2017. It is, therefore, the first regular financed telehealth care program in Austria.

Identification of Cost Indicators with Significant Economic Impact on the Total Treatment Costs of Chronic Heart Failure Patients - A Meta-Analysis.

Increasing treatment costs of HF patients affect the initiation of appropriate treatment method. Divergent approaches to measure the costs of treatment and the lack of common cost indicators impede the comparison of therapy settings. OBJECTIVES: In the context of the present meta-analysis, key cost indicators from the perspective of healthcare providers are to be identified, described, analyzed and quantified. This review helps narrowing down the cost indicators, which have the most significant economic impact on the total treatment costs of HF patients. Telemedical services are to be compared to standard therapy methods. METHODS: The identification process was based on several steps. For the quantitative synthesis, we used the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement. An additional set of criteria was defined for the following qualitative analysis. RESULTS: 5 key cost indicators were identified with significant economic impact on the treatment costs of HF patients. CONCLUSION: 95% of the reported treatment costs could be captured based on the identified cost indicators.

Comparison of Body Weight Trend Algorithms for Prediction of Heart Failure Related Events in Home Care Setting.

BACKGROUND: Automatic event detection is used in telemedicine based heart failure disease management programs supporting physicians and nurses in monitoring of patients' health data. OBJECTIVES: Analysis of the performance of automatic event detection algorithms for prediction of HF related hospitalisations or diuretic dose increases. METHODS: Rule-Of-Thumb and Moving Average Convergence Divergence (MACD) algorithm were applied to body weight data from 106 heart failure patients of the HerzMobil-Tirol disease management program. The evaluation criteria were based on Youden index and ROC curves. RESULTS: Analysis of data from 1460 monitoring weeks with 54 events showed a maximum Youden index of 0.19 for MACD and RoT with a specificity > 0.90. CONCLUSION: Comparison of the two algorithms for real-world monitoring data showed similar results regarding total and limited AUC. An improvement of the sensitivity might be possible by including additional health data (e.g. vital signs and self-reported well-being) because body weight variations obviously are not the only cause of HF related hospitalisations or diuretic dose increases.

Timed Up-and-Go Device for Unsupervised Functional Assessment of Elderly Patients.

Functional evaluation of elderly patients is one key component in a comprehensive Geriatric Assessment. The increased workload and high costs associated to close and continuous monitoring in clinical settings may be counterbalanced by the application of ICT-supported remote follow-up. Although clinical parameters and questionnaires can be supported with smartphones and smart gadgets, physical performance trials pose a challenge for community-based approaches with difficulties arising from setting up trials, the lack of guidance and supervision. We developed an ultrasonic-based device to overcome all of these barriers and enable elderly people to perform the Timed Up-and-Go test in an autonomous and unsupervised setting. Moreover, we introduce an algorithm to verify the successful performance of the test in order to increase the reliability of the information provided.

Continual Screening of Patients Using mHealth: The Rolling Score Concept Applied to Sleep Medicine.

Continual monitoring of patients utilizing mHealth-based telemonitoring applications are more and more used for individual management of patients. A new approach in risk assessment called Rolling Score Concept uses standardized questionnaires for continual scoring of individuals' health state through electronic patient reported outcome (ePRO). Using self-rated questionnaires and adding a specific Time Schedule to each question result in a movement of the questionnaires' scores over time, the Rolling Score. A text-processing pipeline was implemented with KNIME analytics platform to extract a Score Mapping Rule Set for three standardized screening questionnaires in the field of sleep medicine. A feasibility study was performed in 10 healthy volunteers equipped with a mHealth application on a smartphone and a sleep tracker. Results show that the proposed Rolling Score Concept is feasible and deviations of scores are in a reasonable range (< 7%), sustaining the new approach. However, further studies are required for verification. In addition, parameter quantification could avoid incorrect subjective evaluation by substitution of questions with sensor data.

Development of text mining based classification of written communication within a telemedical collaborative network.

Chronic diseases like Heart Failure are widespread in the ageing population. Affected patients can be treated with the aid of a disease management program, including a telemedical collaborative network. Evaluation of a currently used system has shown that the information of the textual communication is of pivotal importance for the collaboration in the network. Thus, the challenge is to make this unstructured information useable, potentially leading to a better understanding of the collaboration so as to optimize the processes. This paper presents the setup of an analysis pipeline for processing textual information automatically, and, how this pipeline can be utilized to train a model that is able to automatically classify the written messages into a set of meaningful task and status categories.