Natural Language Processing for Detecting Medication-Related Notes in Heart Failure Telehealth Patients.

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.

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.

Experimenting with Generative Adversarial Networks to Expand Sparse Physiological Time-Series Data.

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.

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.

Is Regular Re-Training of a Predictive Delirium Model Necessary After Deployment in Routine Care?

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.

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.

Predictive Modelling and Its Visualization for Telehealth Data - Concept and Implementation of an Interactive Viewer.

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.

Utilising Information of the Case Fee Catalogue to Enhance 30-Day Readmission Prediction in the German DRG System.

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.

Prediction of Readmissions in the German DRG System Based on §21 Datasets.

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.

On the Representation of Machine Learning Results for Delirium Prediction in a Hospital Information System in Routine Care.

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.

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.