IT-Related Barriers and Facilitators to the Implementation of a New European eHealth Solution, the Digital Survivorship Passport (SurPass Version 2.0): Semistructured Digital Survey.

BACKGROUND: To overcome knowledge gaps and optimize long-term follow-up (LTFU) care for childhood cancer survivors, the concept of the Survivorship Passport (SurPass) has been invented. Within the European PanCareSurPass project, the semiautomated and interoperable SurPass (version 2.0) will be optimized, implemented, and evaluated at 6 LTFU care centers representing 6 European countries and 3 distinct health system scenarios: (1) national electronic health information systems (EHISs) in Austria and Lithuania, (2) regional or local EHISs in Italy and Spain, and (3) cancer registries or hospital-based EHISs in Belgium and Germany. OBJECTIVE: We aimed to identify and describe barriers and facilitators for SurPass (version 2.0) implementation concerning semiautomation of data input, interoperability, data protection, privacy, and cybersecurity. METHODS: IT specialists from the 6 LTFU care centers participated in a semistructured digital survey focusing on IT-related barriers and facilitators to SurPass (version 2.0) implementation. We used the fit-viability model to assess the compatibility and feasibility of integrating SurPass into existing EHISs. RESULTS: In total, 13/20 (65%) invited IT specialists participated. The main barriers and facilitators in all 3 health system scenarios related to semiautomated data input and interoperability included unaligned EHIS infrastructure and the use of interoperability frameworks and international coding systems. The main barriers and facilitators related to data protection or privacy and cybersecurity included pseudonymization of personal health data and data retention. According to the fit-viability model, the first health system scenario provides the best fit for SurPass implementation, followed by the second and third scenarios. CONCLUSIONS: This study provides essential insights into the information and IT-related influencing factors that need to be considered when implementing the SurPass (version 2.0) in clinical practice. We recommend the adoption of Health Level Seven Fast Healthcare Interoperability Resources and data security measures such as encryption, pseudonymization, and multifactor authentication to protect personal health data where applicable. In sum, this study offers practical insights into integrating digital health solutions into existing EHISs.

Usability of a telehealth-nurse supported home-based walking training for peripheral arterial disease - The Keep Pace! pilot study.

Background: Guidelines recommend walking trainings for peripheral arterial disease (PAD) management. Supervised walking training is superior to walking advise to improve the walking distance. Telehealth service with nurse support may close this gap. Patients and methods: This study introduces a telehealth service, "Keep pace!", which has been developed for patients with symptomatic PAD (Fontaine stage IIa and IIb), enabling a structured home-based walking training while monitoring progress via an app collecting unblinded account of steps and walking distance in self-paced 6-minute-walking-tests by geolocation tracking to enhance intrinsic motivation. Supervision by nurses via telephone calls was provided for 8 weeks, followed by 4 weeks of independent walking training. Patient satisfaction, walking distance and health-related quality of life were assessed. Results: 19 patients completed the study. The analysis revealed an overall high satisfaction with the telehealth service (95.4%), including system quality (95.1%), information quality (94.4%), service quality (95.6%), intention to use (92.8%), general satisfaction with the program (98.4%) and health benefits (95.8%). 78.9% asserted that the telehealth service lacking nurse calls would be less efficacious. Pain-free walking distance (76.3±36.8m to 188.4±81.2m, +112.2%, p<0.001) as well as total distance in 6-minute-walking test (308.8±82.6m to 425.9±107.1m, +117.2%, p<0.001) improved significantly. The telehealth service significantly reduced discomfort by better pain control (+15.5%, p=0.015) and social participation (+10.5%, p=0.042). Conclusions: In conclusion, patients were highly satisfied with the telehealth service. The physical well-being of the PAD patients improved significantly post vs. prior the telehealth program.

Medication management needs information and communications technology-based approaches, including telehealth and artificial intelligence.

Life expectancy is rising in most parts of the world as is the prevalence of chronic diseases. Suboptimal adherence to long-term medications is still rather the norm than the exception, although it is well known that suboptimal adherence compromises the therapeutic effectiveness. Information and communications technology provides new concepts for improving adherence to medications. These so-called telehealth concepts or services help to implement closed-loop healthcare paradigms and to establish collaborative care networks involving all stakeholders relevant to optimising the overall medication therapy. Together with data from Electronic Health Records and Electronic Medical Records, these networks pave the way to data-driven decision support systems. Recent advances in machine learning, predictive analytics, and artificial intelligence allow further steps towards fully autonomous telehealth systems. This might bring advances in the future: disburden healthcare professionals from repetitive tasks, enable them to timely react to critical situations, and offer a comprehensive overview of the patients' medication status. Advanced analytics can help to assess whether patients have taken their medications as prescribed, to improve adherence via automatic reminders. Ultimately, all relevant data sources need to be collated into a basis for data-driven methods, with the goal to assist healthcare professionals in guiding patients to obtain the best possible health status, with a reasonable resource utilisation and a risk-adjusted safety and privacy approach. This paper summarises the state-of-the-art of telehealth and artificial intelligence applications in medication management. It focuses on 3 major aspects: latest technologies, current applications, and patient related issues.

Busulfan and melphalan versus carboplatin, etoposide, and melphalan as high-dose chemotherapy for high-risk neuroblastoma (HR-NBL1/SIOPEN): an international, randomised, multi-arm, open-label, phase 3 trial.

BACKGROUND: High-dose chemotherapy with haemopoietic stem-cell rescue improves event-free survival in patients with high-risk neuroblastoma; however, which regimen has the greatest patient benefit has not been established. We aimed to assess event-free survival after high-dose chemotherapy with busulfan and melphalan compared with carboplatin, etoposide, and melphalan. METHODS: We did an international, randomised, multi-arm, open-label, phase 3 cooperative group clinical trial of patients with high-risk neuroblastoma at 128 institutions in 18 countries that included an open-label randomised arm in which high-dose chemotherapy regimens were compared. Patients (age 1-20 years) with neuroblastoma were eligible to be randomly assigned if they had completed a multidrug induction regimen (cisplatin, carboplatin, cyclophosphamide, vincristine, and etoposide with or without topotecan, vincristine, and doxorubicin) and achieved an adequate disease response. Patients were randomly assigned (1:1) to busulfan and melphalan or to carboplatin, etoposide, and melphalan by minimisation, balancing age at diagnosis, stage, MYCN amplification, and national cooperative clinical group between groups. The busulfan and melphalan regimen comprised oral busulfan (150 mg/m2 given on 4 days consecutively in four equal doses); after Nov 8, 2007, intravenous busulfan was given (0·8-1·2 mg/kg per dose for 16 doses according to patient weight). After 24 h, an intravenous melphalan dose (140 mg/m2) was given. Doses of busulfan and melphalan were modified according to bodyweight. The carboplatin, etoposide, and melphalan regimen consisted of carboplatin continuous infusion of area under the plasma concentration-time curve 4·1 mg/mL per min per day for 4 days, etoposide continuous infusion of 338 mg/m2 per day for 4 days, and melphalan 70 mg/m2 per day for 3 days, with doses for all three drugs modified according to bodyweight and glomerular filtration rate. Stem-cell rescue was given after the last dose of high-dose chemotherapy, at least 24 h after melphalan in patients who received busulfan and melphalan and at least 72 h after carboplatin etoposide, and melphalan. All patients received subsequent local radiotherapy to the primary tumour site followed by maintenance therapy. The primary endpoint was 3-year event-free survival, analysed by intention to treat. This trial is registered with ClinicalTrials.gov, number NCT01704716, and EudraCT, number 2006-001489-17. FINDINGS: Between June 24, 2002, and Oct 8, 2010, 1347 patients were enrolled and 676 were eligible for random allocation, 598 (88%) of whom were randomly assigned: 296 to busulfan and melphalan and 302 to carboplatin, etoposide, and melphalan. Median follow-up was 7·2 years (IQR 5·3-9·2). At 3 years, 146 of 296 patients in the busulfan and melphalan group and 188 of 302 in the carboplatin, etoposide, and melphalan group had an event; 3-year event-free survival was 50% (95% CI 45-56) versus 38% (32-43; p=0·0005). Nine patients in the busulfan and melphalan group and 11 in the carboplatin, etoposide, and melphalan group had died without relapse by 5 years. Severe life-threatening toxicities occurred in 13 (4%) patients who received busulfan and melphalan and 29 (10%) who received carboplatin, etoposide, and melphalan. The most frequent grade 3-4 adverse events were general condition (74 [26%] of 281 in the busulfan and melphalan group vs 103 [38%] of 270 in the carboplatin, etoposide, and melphalan group), infection (55 [19%] of 283 vs 74 [27%] of 271), and stomatitis (138 [49%] of 284 vs 162 [59%] of 273); 60 (22%) of 267 patients in the busulfan and melphalan group had Bearman grades 1-3 veno-occlusive disease versus 21 (9%) of 239 in the carboplatin, etoposide, and melphalan group. INTERPRETATION: Busulfan and melphalan improved event-free survival in children with high-risk neuroblastoma with an adequate response to induction treatment and caused fewer severe adverse events than did carboplatin, etoposide, and melphalan. Busulfan and melphalan should thus be considered standard high-dose chemotherapy and ongoing randomised studies will continue to aim to optimise treatment for high-risk neuroblastoma. FUNDING: European Commission 5th Framework Grant and the St Anna Kinderkrebsforschung.

Analyzing health insurance claims on different timescales to predict days in hospital.

Health insurers maintain large databases containing information on medical services utilized by claimants, often spanning several healthcare services and providers. Proper use of these databases could facilitate better clinical and administrative decisions. In these data sets, there exists many unequally spaced events, such as hospital visits. However, data mining of temporal data and point processes is still a developing research area and extracting useful information from such data series is a challenging task. In this paper, we developed a time series data mining approach to predict the number of days in hospital in the coming year for individuals from a general insured population based on their insurance claim data. In the proposed method, the data were windowed at four different timescales (bi-monthly, quarterly, half-yearly and yearly) to construct regularly spaced time series features extracted from such events, resulting in four associated prediction models. A comparison of these models indicates models using a half-yearly windowing scheme delivers the best performance on all three populations (the whole population, a senior sub-population and a non-senior sub-population). The superiority of the half-yearly model was found to be particularly pronounced in the senior sub-population. A bagged decision tree approach was able to predict 'no hospitalization' versus 'at least one day in hospital' with a Matthews correlation coefficient (MCC) of 0.426. This was significantly better than the corresponding yearly model, which achieved 0.375 for this group of customers. Further reducing the length of the analysis windows to three or two months did not produce further improvements.

The Evolution of Telehealth in Heart Failure Management: The Role of Large Language Models and HerzMobil as a Potential Use Case.

The burgeoning domain of telehealth has witnessed substantial transformation through the advent of advanced technologies such as Large Language Models (LLMs). This study examines the integration of LLMs in heart failure management, with a focus on HerzMobil as a pioneering telehealth program. The technical underpinnings of LLMs, their current applications in the medical field, and their potential to enhance telehealth services, have been explored. The paper highlights the benefits of LLMs in patient interaction, clinical documentation, and decision-making processes. Through the HerzMobil case study, improvements in patient self-management and reductions in hospital readmission rates have been observed, showcasing the successful application of telehealth in chronic disease management. The paper also delves into the challenges and ethical considerations of LLM integration, such as data privacy, potential biases, and regulatory compliance, underscoring the need for a balanced approach that prioritizes patient safety and ethical standards.

Instance Selection Algorithms for Predictive Modelling in Telehealth Applications.

Telehealth services are becoming more and more popular, leading to an increasing amount of data to be monitored by health professionals. Machine learning can support them in managing these data. Therefore, the right machine learning algorithms need to be applied to the right data. We have implemented and validated different algorithms for selecting optimal time instances from time series data derived from a diabetes telehealth service. Intrinsic, supervised, and unsupervised instance selection algorithms were analysed. Instance selection had a huge impact on the accuracy of our random forest model for dropout prediction. The best results were achieved with a One Class Support Vector Machine, which improved the area under the receiver operating curve of the original algorithm from 69.91 to 75.88 %. We conclude that, although hardly mentioned in telehealth literature so far, instance selection has the potential to significantly improve the accuracy of machine learning algorithms.

A Novel Deep Ensemble Method for Selective Classification of Electrocardiograms.

OBJECTIVE: Telehealth paradigms are essential for remotely managing patients with chronic conditions. To assist clinicians in handling the large volumes of data collected through these systems, clinical decision support systems (CDSSs) have been developed. However, the effectiveness of CDSSs depends on the quality of remotely recorded physiological data and the reliability of the algorithms used for processing this data. This study aims to reliably detect atrial fibrillation (AF) from short-term single-lead (STSL) electrocardiogram (ECG) recordings obtained in unsupervised telehealth environments. METHODS: A novel deep ensemble-based method was developed for detecting AF from STSL ECG recordings. Following this, a postprocessing algorithm was created to assess uncertainty in classified STSL ECGs and to refrain from interpretation when confidence is low. The proposed method was validated through a 5-fold cross-validation on the Cardiology Challenge 2017 (CinC2017) dataset. RESULTS: The deep ensemble method achieved 83.5 ± 1.5% sensitivity, 98.4 ± 0.2% specificity, and an F 1-score of 0.847 ± 0.016in AF detection. Implementing the selective classification algorithm resulted in significant improvements, with sensitivity increasing to 92.8 ± 2.2%, specificity to 99.7 ± 0.0%, and an F 1-score of 0.919 ± 0.016. CONCLUSION: The proposed method demonstrates the feasibility of accurately detecting AF from STSL ECG recordings. The selective classification approach offers a substantial enhancement to automated ECG interpretation algorithms in telehealth solutions. SIGNIFICANCE: These findings highlight the potential for improving the utility of telehealth systems by integrating advanced CDSSs capable of managing uncertainty and ensuring higher accuracy, thereby improving patient outcomes in remote healthcare settings.

A Standardized Treatment Pathway for Telehealth-Based Care of Chronic Wounds in Austria.

Chronic wounds present a significant healthcare challenge in Austria as well as in other countries. The interdisciplinary approach to wound treatment involving various caregivers, doctors, and relatives, poses challenges in documentation and information exchange. To overcome these barriers and promote patient-centered care, a new telehealth-supported treatment pathway for chronic wounds has been developed. The primary focus was to regularly update the status of the chronic wound by responding to predefined questions and transmitted images of the chronic wound. This was achieved by an interdisciplinary team of experts in chronic wound care, providing a new perspective for digital implementation in the healthcare system.

Telemedicine for Ketogenic Dietary Treatment in Refractory Epilepsy and Inherited Metabolic Disease: State of Play and Future Perspectives.

Ketogenic dietary therapies (KDT) are diets that induce a metabolic condition comparable to fasting. All types of KDT comprise a reduction in carbohydrates whilst dietary fat is increased up to 90% of daily energy expenditure. The amount of protein is normal or slightly increased. KDT are effective, well studied and established as non-pharmacological treatments for pediatric patients with refractory epilepsy and specific inherited metabolic diseases such as Glucose Transporter Type 1 Deficiency Syndrome. Patients and caregivers have to contribute actively to their day-to-day care especially in terms of (self-) calculation and (self-) provision of dietary treatment as well as (self-) measurement of blood glucose and ketones for therapy monitoring. In addition, patients often have to deal with ever-changing drug treatment plans and need to document occurring seizures on a regular basis. With this review, we aim to identify existing tools and features of telemedicine used in the KDT context and further aim to derive implications for further research and development.

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.

Neural Network-Based Prediction of Perceived Sleep Quality Through Wearable Device Data.

BACKGROUND: This study focuses on the development of a neural network model to predict perceived sleep quality using data from wearable devices. We collected various physiological metrics from 18 participants over four weeks, including heart rate, physical activity, and both device-measured and self-reported sleep quality. OBJECTIVES: The primary objective was to correlate wearable device data with subjective sleep quality perceptions. METHODS: Our approach used data processing, feature engineering, and optimizing a Multi-Layer Perceptron classifier. RESULTS: Despite comprehensive data analysis and model experimentation, the predictive accuracy for perceived sleep quality was moderate (59%), highlighting the complexities in accurately quantifying subjective sleep experiences through wearable data. Applying a tolerance of 1 grade (on a scale from 1-5), increased accuracy to 92%. DISCUSSION: More in-depth analysis is required to fully comprehend how wearables and artificial intelligence might assist in understanding sleep behavior.

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.

Smart FOX - Enabling Citizen-Based Donation of EHR-Standardised Data for Clinical Research in Austria.

Access to healthcare data for secondary use in clinical research is often restricted due to privacy concerns or business interests, hindering comprehensive analysis across patient pathways. The Smart FOX project seeks to address this challenge by developing concepts, methods, and tools to facilitate citizen/patient-driven donations of health data for clinical research. Leveraging the groundwork, laid by the national Electronic Health Record implementation in Austria (called ELGA), Smart FOX aims to harness structured datasets from ELGA for research purposes through an opt-in approach. With funding secured from the Austrian Research Promotion Agency, the project embarks on innovative solutions encompassing governance frameworks, community engagement, and technical infrastructure. The Smart FOX consortium, comprising key stakeholders across various healthcare-associated domains, will evaluate these efforts through demonstrators focusing on clinical registries, patient-generated data, and recruitment services. The project targets to accompany the development of future data donation infrastructure while ultimately advancing clinical research efficiency and bolstering Austria's preparedness for the European Health Data Space. This paper presents the first systematic evaluation of the technical concept and proposal for the federated system architecture of the Austrian Health Data Donation Space, which is the socio-technical goal of Smart FOX.

Childhood Cancer Survivorship Passport Challenges in the European Health Data Space.

Innovation in cancer therapy has increased childhood cancer survival rates. However, survivors are still at risk of developing late effects. In the digital transformation of the health sector, the Survivorship Passport (SurPass) can support long-term follow-up care plans. Gaps in seamless connectivity among hospital departments, primary care, combined with the time of health professionals required to collect and fill-in health data in SurPass, are barriers to its adoption in daily clinical practice. The PanCareSurPass (PCSP) project was motivated to address these gaps by a new version of SurPass (v2.0) that supports semi-automatic assembly from organizational Electronic Health Record (EHR) systems of the treatment summary data using HL7 FHIR, to create SurPass, and to link it to regional or national digital health infrastructures in six European countries. In this paper we present the methodology used to develop the SurPass technical implementation strategy with special focus on the European Health Data Space (EHDS). The recently provisionally approved EHDS regulation instruments a digital health data ecosystem with opportunities for cost-effective SurPass implementation across Europe. Moving forward, a European HL7 FHIR SurPass Implementation Guide along with synthetic data sets, and validation tools can enrich the European Electronic Health Record Exchange Format (EEHRxF) with use cases on health & wellness of childhood cancer survivors.

Scaling up and implementing the digital Survivorship Passport tool in routine clinical care - The European multidisciplinary PanCareSurPass project.

BACKGROUND: Childhood cancer survivors (CCS), of whom there are about 500,000 living in Europe, are at an increased risk of developing health problems [1-6] and require lifelong Survivorship Care. There are information and knowledge gaps among CCS and healthcare providers (HCPs) about requirements for Survivorship Care [7-9] that can be addressed by the Survivorship Passport (SurPass), a digital tool providing CCS and HCPs with a comprehensive summary of past treatment and tailored recommendations for Survivorship Care. The potential of the SurPass to improve person-centred Survivorship Care has been demonstrated previously [10,11]. METHODS: The EU-funded PanCareSurPass project will develop an updated version (v2.0) of the SurPass allowing for semi-automated data entry and implement it in six European countries (Austria, Belgium, Germany, Italy, Lithuania and Spain), representative of three infrastructure healthcare scenarios typically found in Europe. The implementation study will investigate the impact on person-centred care, as well as costs and processes of scaling up the SurPass. Interoperability between electronic health record systems and SurPass v2.0 will be addressed using the Health Level Seven (HL7) International interoperability standards. RESULTS: PanCareSurPass will deliver an interoperable digital SurPass with comprehensive evidence on person-centred outcomes, technical feasibility and health economics impacts. An Implementation Toolkit will be developed and freely shared to promote and support the future implementation of SurPass across Europe. CONCLUSIONS: PanCareSurPass is a novel European collaboration that will improve person-centred Survivorship Care for CCS across Europe through a robust assessment of the implementation of SurPass v2.0 in different healthcare settings.

Assessment of HL7 FHIR Interoperability Between EHR Systems and the Survivorship Passport v2.0 Platform to Generate Treatment Summaries for Childhood Cancer Survivors in Six Clinics: Preliminary Testing Results.

The Survivorship Passport (SurPass) for childhood cancer survivors provides a personalized treatment summary together with a care plan for long-term screening of possible late effects. HL7 FHIR connectivity of Electronic Health Record (EHR) systems with the SurPass has been proposed to reduce the burden of collecting and organizing the relevant information. We present the results of testing and validation efforts conducted across six clinics in Austria, Belgium, Germany, Italy, Lithuania, and Spain. We also discuss ways in which this experience can be used to reduce efforts for the SurPass integration in other clinics across Europe.

Mobile health (mHealth) based medication adherence measurement - a pilot trial using electronic blisters in diabetes patients.

AIMS: The aim of the present study was to evaluate a mobile health (mHealth) based remote medication adherence measurement system (mAMS) in elderly patients with increased cardiovascular risk treated for diabetes, high cholesterol and hypertension. Cardiovascular risk was defined as the presence of at least two out of the three risk factors: type 2 diabetes, hypercholesterolaemia and hypertension. METHODS: For treatment of diabetes, hypercholesterolaemia and hypertension, four predefined routinely used drugs were selected. Drug adherence was investigated in a controlled randomized doctor blinded study with crossover design. The mAMS was used to measure and improve objectively the adherence by means of closed-loop interactions. RESULTS: The mean age of the 53 patients (30 female) was 69.4 ± 4.8 years. A total of 1654 electronic blisters were handed out. A statistically significant difference (P = 0.04) between the monitoring and the control phase was observed for the diabetes medication only. In a post-study questionnaire twenty-nine patients appreciated that their physician knew if and when they had taken their medications and 13 asked for more or automated communication with their physicians. Only one subject withdrew from the study because of technical complexity. CONCLUSIONS: The results indicate that mHealth based adherence management is feasible and well accepted by patients with increased cardiovascular risk. It may help to increase adherence, even in patients with high baseline adherence and, subsequently, lead to improved control of indicators including blood pressure and cholesterol concentrations. Electronic blisters can be used in a multi-medication regimen but need to be carefully designed for day-to-day application.

Leg edema quantification for heart failure patients via 3D imaging.

Heart failure is a common cardiac disease in elderly patients. After discharge, approximately 50% of all patients are readmitted to a hospital within six months. Recent studies show that home monitoring of heart failure patients can reduce the number of readmissions. Still, a large number of false positive alarms as well as underdiagnoses in other cases require more accurate alarm generation algorithms. New low-cost sensors for leg edema detection could be the missing link to help home monitoring to its breakthrough. We evaluated a 3D camera-based measurement setup in order to geometrically detect and quantify leg edemas. 3D images of legs were taken and geometric parameters were extracted semi-automatically from the images. Intra-subject variability for five healthy subjects was evaluated. Thereafter, correlation of 3D parameters with body weight and leg circumference was assessed during a clinical study at the Medical University of Graz. Strong correlation was found in between both reference values and instep height, while correlation in between curvature of the lower leg and references was very low. We conclude that 3D imaging might be a useful and cost-effective extension of home monitoring for heart failure patients, though further (prospective) studies are needed.

Introduction and Comparison of Novel Decentral Learning Schemes with Multiple Data Pools for Privacy-Preserving ECG Classification.

Artificial intelligence and machine learning have led to prominent and spectacular innovations in various scenarios. Application in medicine, however, can be challenging due to privacy concerns and strict legal regulations. Methods that centralize knowledge instead of data could address this issue. In this work, 6 different decentralized machine learning algorithms are applied to 12-lead ECG classification and compared to conventional, centralized machine learning. The results show that state-of-the-art federated learning leads to reasonable losses of classification performance compared to a standard, central model (-0.054 AUROC) while providing a significantly higher level of privacy. A proposed weighted variant of federated learning (-0.049 AUROC) and an ensemble (-0.035 AUROC) outperformed the standard federated learning algorithm. Overall, considering multiple metrics, the novel batch-wise sequential learning scheme performed best (-0.036 AUROC to baseline). Although, the technical aspects of implementing them in a real-world application are to be carefully considered, the described algorithms constitute a way forward towards preserving-preserving AI in medicine.