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.

Cardiovascular diseases (CVD) are the leading cause of death in the Western world.Several modifiable risk factors contribute to the pathogenesis of CVD which are all addressed during cardiac rehabilitation (CR).CR is conducted in three phases: I: acute care hospital, II: subsequent in-or outpatient CR, and III: out-patient CR with focus on lifelong prevention.Despite its proven merits, the adherence to healthy lifestyle changes following completion of CR phase II is challenging.This gap is addressed in recent recommendations, suggesting that clinicians should help patients to set personal goals to i) achieve and maintain the benefits of physical activity, ii) include physical activity into their daily routine and iii) overcome barriers to exercise, to achieve behavior change more effectively and more sustainably.We have developed tele-rehabilitation services to support patients during home-based exercise training in CR phase III.Our services provide a link between CR experts and patients by means of individualized exercise prescription supported by different kinds of wearables for measuring e.g.physical activity volume.The effectiveness of such services and other supportive measures regarding adherence to home training plans and changes in exercise capacity during CR phase III CR is currently evaluated in a study.

Advances in artificial intelligence and computer science have allowed for powerful assistive tools in a wide range of fields.Decision support systems could help health professionals to provide patients with quick and cost-efficient diagnostic analysis.The 2020 CinC Challenge challenges participants to develop such a tool for 12-lead ECG recordings.In this paper, an approach for a multi-stream neural network is presented.Two parallel models were trained with different input data to combine the two relevant paradigms in modern machine learning.A simple multilayer perceptron and a deep convolutional neural network were concatenated for the final classification.Since the data originated from different sources, an ensemble of models was trained.Due to technical difficulties, we (easyG) submitted a trimmed version and achieved a test score of -0.290, which ranked as the 39 th entry.Validation score was 0.403.Although these results were mixed, offline 5-fold cross validation showed the potency of the full version.Our results indicate that deep learning methods could in fact benefit from the addition of features derived via classical signal processing.

Machine Learning research and its application have gained enormous relevance in recent years. Their usage in medical settings could support patients, increase patient safety and assist health professionals in various tasks. However, medical data is often sparse, which renders big data analytics methods like deep learning ineffective. Data synthesis helps to augment small data sets and potentially improves patient data integrity. The presented work illustrates how Generative Adversarial Networks can be applied specifically to small data sets for enlarging sparse data. Following a state-of-the-art analysis is conducted, experimental methods with such networks are documented, which have been applied to three different data sets. Results from all three sets are presented and take-away messages are summarized. Concluding, the results' quality and limitations of the work are discussed.

Heart Failure is a severe chronic disease of the heart. Telehealth networks implement closed-loop healthcare paradigms for optimal treatment of the patients. For comprehensive documentation of medication treatment, health professionals create free text collaboration notes in addition to structured information. To make this valuable source of information available for adherence analyses, we developed classifiers for automated categorization of notes based on natural language processing, which allows filtering of relevant entries to spare data analysts from tedious manual screening. Furthermore, we identified potential improvements of the queries for structured treatment documentation. For 3,952 notes, the majority of the manually annotated category tags was medication-related. The highest F1-measure of our developed classifiers was 0.90. We conclude that our approach is a valuable tool to support adherence research based on datasets containing free-text entries.

Heart failure (HF) is one of the biggest concerns for health care systems in developed countries. To support the long-term treatment of HF patients, the Austrian Institute of Technology implemented a HF telehealth network called "HerzMobil". While most data within this network are stored in a structured format, health care professionals can also communicate via clinical notes in free text format. These notes are hardly ever analyzed automatically, even though a large number contains valuable information for the patient's treatment process. With currently more than 20,000 notes stored in the system, an automatic approach is beneficial to spare manual screening time. One important step in this process concerns the extraction of time references from the notes. This information could, for example, be used to match the time references with events from the same note. Therefore, two Python scripts were developed to: extract time references from the notes (Script A) and subsequently calculate the corresponding dates (Script B). Script A was compared to an already existing Python library and achieved superior results for all calculated key figures. The time calculation algorithm of Script B achieved an accuracy of 75.34%. These scripts could be implemented in the HerzMobil network to provide additional information for the treatment process and further improve the telehealth system.

BACKGROUND:Predictive modelling is becoming increasingly important in the healthcare sector. A comprehensive understanding of obtained models and their predictions is indispensable for the development and later acceptance of such systems.OBJECTIVES:A general concept of a toolset that supports data scientists in the development of predictive models in the telehealth context had to be developed and subsequently implemented.METHODS:Based on surveys the user requirements were determined. The concept development was based on the data model of the 'HerzMobil Tirol' telehealth program. The implementation was conducted in MATLAB.RESULTS:A list of requirements was identified, based on which a viewer was implemented.CONCLUSION:The developed viewer concept and its implementation facilitate a deeper insight and a better understanding of the development process of predictive models in the telehealth context.

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.

BACKGROUNDHuge 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.RESEARCHIn scenarios, where several data sources are obtained without universal identifiers, record linkage methods need to be applied to obtain a comprehensive dataset.OBJECTIVESIn 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.METHODSWe 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.RESULTSThe 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%.CONCLUSIONFor 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.

Adoption of electronic medical records in hospitals generates a large amount of data. Health care professionals can easily lose their sight on the important insights of the patients' clinical and medical history. Although machine learning algorithms have already proved their significance in healthcare research, remains a challenge translation and dissemination of fully automated prediction algorithms from research to decision support at the point of care. In this paper, we address the effect of changes in the characteristics of data over time on the performance of deployed models for the use case of predicting delirium in hospitalised patients. We have analysed the stability of models trained with subsets of data from one single year (2012, 2013...2016, respectively), and tested the models with data from 2017. Our results show that in the case of delirium prediction, the models were stable over time, indicating that re-training the models is not necessary e.g. once per year might be more than sufficient.

Hospital readmissions receive increasing interest, since they are burdensome for patients and costly for healthcare providers. For the calculation of reimbursement fees, in Germany there is the German-Diagnosis Related Groups (G-DRG) system. For every hospital stay, data are collected as a so-called "case", as the basis for the subsequent reimbursement calculations ("§21 dataset"). Merging rules lead to a loss of information in §21 datasets. We applied machine learning to §21 datasets and evaluated the influence of case merging for the resulting accuracy of readmission risk prediction. Data from 478,966 cases were analysed by applying a random forest. Many cases with readmissions within 30 days had been merged and thus their prediction required additional data. Using 10-fold cross validation, the prediction for readmissions within 31-60 days showed no notable difference in the area under the ROC curves comparing unedited §21 datasets with §21 datasets with restored original cases. The achieved AUC values of 0.69 lie in a similar range as the values of comparable state-of-the-art models. We conclude that dealing with merged cases, i.e. adding data, is required for 30-day-readmission prediction, whereas un-merging brings no improvement for the readmission prediction of period beyond 30 days.

Digitalisation of health care for the purpose of medical documentation lead to huge amounts of data, hence having an opportunity to derive knowledge and associations of different attributes recorded. Many health care events can be prevented when identified. Machine learning algorithms could identify such events but there is ambiguity in understanding the suggestions especially in clinical setup. In this paper we are presenting how we explain the decision based on random forest to health care professionals in the course of the project predicting delirium during hospitalisation on the day of admission.

Unplanned hospital readmissions are a burden to the healthcare system and to the patients. To lower the readmission rates, machine learning approaches can be used to create predictive models, with the intention to provide actionable information for caregivers. According to the German Diagnosis Related Groups (G-DRG) system, for every stay in a German hospital, data are collected for the subsequent reimbursement calculations. After statistical evaluation, these data are summarised in the yearly updated Case Fee Catalogue, which not only contains the weights for the reimbursement calculations, but also the expected length of stay values. The aim of the present paper was to evaluate potential enhancements of the prediction accuracy of our 30-day readmission prediction model by utilising additional information from the Case Fee Catalogue. A bagged ensemble of 25 regression trees was applied to §21 datasets from five independent German hospitals from 2013 to 2017, resulting in 422,597 cases. The overall model showed an area under the receiver operating characteristics curve of 0.812. Three of the top five features ranked by out of bag feature importance emerged from the Case Fee Catalogue. We conclude, that additional information from the Case Fee Catalogue can enhance the accuracy of 30-day readmission prediction.

Due to an ever-increasing amount of data generated in healthcare each day, healthcare professionals are more and more challenged with information. Predictive models based on machine learning algorithms can help to quickly identify patterns in clinical data. Requirements for data driven decision support systems for health and care (DS4H) are similar in many ways to applications in other domains. However, there are also various challenges which are specific to health and care settings. The present paper describes a) healthcare specific requirements for DS4H and b) how they were addressed in our Predictive Analytics Toolset for Health and care (PATH). PATH supports the following process: objective definition, data cleaning and pre-processing, feature engineering, evaluation, result visualization, interpretation and validation and deployment. The current state of the toolset already allows the user to switch between the various involved levels, i.e. raw data (ECG), pre-processed data (averaged heartbeat), extracted features (QT time), built models (to classify the ECG into a certain rhythm abnormality class) and outcome evaluation (e.g. a false positive case) and to assess the relevance of a given feature in the currently evaluated model as a whole and for the individual decision. This allows us to gain insights as a basis for improvements in the various steps from raw data to decisions.

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.