Search

We present a combined method of classical signal analysis and machine learning algorithms for the automated classification of 1-lead ECG recordings, which was developed in the course of the Computing in Cardiology Challenge 2017. To classify ECG recordings into the four classes as defined for the Challenge (normal, suspicious to AF, suspicious to other arrhythmia, noise) we used MATLAB- and a set of algorithms for detection of beats, wave point detection on detected beats, quality evaluation of the detection, averaging of beats, beat classification, rhythm classification and many more. We extracted a variety of features from both time and frequency domain etc. as input features for the classifier. A total of 380 features were used to train a Random Forest-based classifier (bagged decision trees). Since classes for the Challenge were severely unbalanced, weights based on the class distribution were applied. To train the classifier and for our internal evaluation we used cross-validation on all available ECGS from the training-set. 10-fold cross-validated F1 score on the training set is 0.83. Final F1 score from the official challenge evaluation on the enhanced dataset is 0.81, which is quite close to the other top performing algorithms.

Automatic event detection is used in telemedicine based heart failure disease management programs supporting physicians and nurses in monitoring of patients' health data.Analysis of the performance of automatic event detection algorithms for prediction of HF related hospitalisations or diuretic dose increases.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.Analysis of data from 1460 monitoring weeks with 54 events showed a maximum Youden index of 0.19 for MACD and RoT with a specificitygt; 0.90.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.

Delirium is an acute confusion condition, which is common in elderly and often misdiagnosed in hospitalized patients. Early identification and prevention of delirium could reduce morbidity and mortality rates in those affected and reduce hospitalization costs. We have developed and validated a multivariate prediction model that predicts delirium and gives an early warning to physicians. A large set of patient electronic medical records have been used in developing the models. Classical learning algorithms have been used to develop the models and compared the results. Excellent results were obtained with the feature set and parameter settings attaining accuracy of 84%.

Machine learning algorithms are a promising approach to help physicians to deal with the ever increasing amount of data collected in healthcare each day. However, interpretation of suggestions derived from predictive models can be difficult.The aim of this work was to quantify the influence of a specific feature on an individual decision proposed by a random forest (RF).For each decision tree within the RF, the influence of each feature on a specific decision (FID) was quantified. For each feature, changes in outcome value due to the feature were summarized along the path. Results from all the trees in the RF were statistically merged. The ratio of FID to the respective feature's global importance was calculated (FIDrel).Global feature importance, FID and FIDrel significantly differed, depending on the individual input data. Therefore, we suggest to present the most important features as determined for FID and for FIDrel, whenever results of a RF are visualized.Feature influence on a specific decision can be quantified in RFs. Further studies will be necessary to evaluate our approach in a real world scenario.

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.

SummaryBackground: Blood transfusion is a highly prevalent procedure in hospitalized patients and in some clinical scenarios it has lifesaving potential. However, in most cases transfusion is administered to hemodynamically stable patients with no benefit, but increased odds of adverse patient outcomes and substantial direct and indirect cost. Therefore, the concept of Patient Blood Management has increasingly gained importance to pre-empt and reduce transfusion and to identify the optimal transfusion volume for an individual patient when transfusion is indicated.Objectives: It was our aim to describe, how predictive modeling and machine learning tools applied on pre-operative data can be used to predict the amount of red blood cells to be transfused during surgery and to prospectively optimize blood ordering schedules. In addition, the data derived from the predictive models should be used to benchmark different hospitals concerning their blood transfusion patterns.Methods: 6,530 case records obtained for elective surgeries from 16 centers taking part in two studies conducted in 2004–2005 and 2009–2010 were analyzed. Transfused red blood cell volume was predicted using random forests. Separate models were trained for overall data, for each center and for each of the two studies. Important characteristics of different models were compared with one another.Results: Our results indicate that predictive modeling applied prior surgery can predict the transfused volume of red blood cells more accurately (correlation coefficient cc = 0.61) than state of the art algorithms (cc = 0.39). We found significantly different patterns of feature importance a) in different hospitals and b) between study 1 and study 2.Conclusion: We conclude that predictive modeling can be used to benchmark the importance of different features on the models derived with data from different hospitals. This might help to optimize crucial processes in a specific hospital, even in other scenarios beyond Patient Blood Management.Citation: Hayn D, Kreiner K, Ebner H, Kastner P, Breznik N, Rzepka A, Hofmann A, Gombotz H, Schreier G. Development of multivariable models to predict and benchmark transfusion in elective surgery supporting patient blood management. Appl Clin Inform 2017; 8: 617–631 https://doi.org/10.4338/ACI-2016-11-RA-0195

Opsoclonus Myoclonus Syndrome (OMS) is a rare disease in children which is often associated with neuroblastoma and, therefore, requires treatment by pediatric neurologists and oncologists. The ongoing OMS trial investigates questions related to OMS and potentially underlying neuroblastomas. To support this trial with an adequate IT infrastructure, linkage of neuroblastoma research databases with the OMS electronic data capture (EDC) system was required. Therefore, an EDC system for the OMS trial was developed and integrated into the research infrastructure of the European Network for Cancer Research in Children and Adolescents (ENCCA) project. Application of ENNCA's pseudonymization concept enabled linkage of the OMS trial with neuroblastoma trials from two different scientific societies, while being compliant with current data protection regulations. Linkage of the neurological and the oncological domain could successfully be demonstrated and a promising concept for secondary use of the data of both domains has been developed, proofing the broad potential of the concepts for cross-domain research as promoted in the ENCCA project.

Electronic Patient Reported Outcomes (ePRO) gathered using telemonitoring solutions might be a valuable source of information in rare cancer research.The objective of this paper was to develop a concept and implement a prototype for introducing ePRO into the existing neuroblastoma research network by applying Near Field Communication and mobile technology.For physicians, an application was developed for registering patients within the research network and providing patients with an ID card and a PIN for authentication when transmitting telemonitoring data to the Electronic Data Capture system OpenClinica. For patients, a previously developed telemonitoring system was extended by a Simple Object Access Protocol (SOAP) interface for transmitting nine different health parameters and toxicities.The concept was fully implemented on the front-end side. The developed application for physicians was prototypically implemented and the mobile application of the telemonitoring system was successfully connected to OpenClinica. Future work will focus on the implementation of the back-end features.

Research in blood transfusions mainly focuses on Donor Blood Management, including donation, screening, storage and transport. However, the last years saw an increasing interest in recipient related optimizations, i.e. Patient Blood Management (PBM). Although PBM already aims at reducing transfusion rates by pre- and intra-surgical optimization, there is still a high potential of improvement on an individual level. The present paper investigates the feasibility of predicting blood transfusions needs based on datasets from various treatment phases, using data which have been collected in two previous studies. Results indicate that prediction of blood transfusions can be further improved by predictive modelling including individual pre-surgical parameters. This also allows to identify the main predictors influencing transfusion practice. If confirmed in a prospective dataset, these or similar predictive methods could be a valuable tool to support PBM with the ultimate goal to reduce costs and improve patient outcomes.

Data from two contexts, i.e. the European Unresectable Neuroblastoma (EUNB) clinical trial and results from comparative genomic hybridisation (CGH) analyses from corresponding tumour samples shall be provided to existing repositories for secondary use. Utilizing the European Unified Patient IDentity Management (EUPID) as developed in the course of the ENCCA project, the following processes were applied to the data: standardization (providing interoperability), pseudonymization (generating distinct but linkable pseudonyms for both contexts), and linking both data sources. The applied procedures resulted in a joined dataset that did not contain any identifiers that would allow to backtrack the records to either data sources. This provided a high degree of privacy to the involved patients as required by data protection regulations, without preventing proper analysis.

Patients with diabetes were enrolled into a telemonitoring programme. They were offered the choice of collecting their health data either by using Near Field Communication (NFC) enabled mobile phones equipped with a dedicated application (App), or by means of a web-browser based user interface (Web). At the end of the study, each patient was categorized as belonging to either the App or Web group, based on the proportion of data they had transmitted using each method. Of the 403 patients, there were 291 in the App group and 112 in the Web group. The two groups were similar in their demographics, except for gender distribution where 68% of men preferred using the App method in contrast to 95% for women ( P < 0.001). Kaplan-Meier analysis showed a steady decline of the compliance rate for both groups, at a similar rate during the first year. It also showed a more rapid decline of the compliance rate thereafter for the Web group, which resulted in a significantly higher rate for the App group over the whole observation period ( P = 0.03). We conclude that different types of data acquisition technologies may have an important effect on patients’ willingness to participate in telehealth programmes in the long-term.

Although immediate feedback concerning ECG signal quality during recording is useful, up to now not much literature describing quality measures is available. We have implemented and evaluated four ECG quality measures. Empty lead criterion (A), spike detection criterion (B) and lead crossing point criterion (C) were calculated from basic signal properties. Measure D quantified the robustness of QRS detection when applied to the signal. An advanced Matlab-based algorithm combining all four measures and a simplified algorithm for Android platforms, excluding measure D, were developed. Both algorithms were evaluated by taking part in the Computing in Cardiology Challenge 2011. Each measure's accuracy and computing time was evaluated separately. During the challenge, the advanced algorithm correctly classified 93.3% of the ECGs in the training-set and 91.6 % in the test-set. Scores for the simplified algorithm were 0.834 in event 2 and 0.873 in event 3. Computing time for measure D was almost five times higher than for other measures. Required accuracy levels depend on the application and are related to computing time. While our simplified algorithm may be accurate for real-time feedback during ECG self-recordings, QRS detection based measures can further increase the performance if sufficient computing power is available.

This paper investigates the application of the enterprise information system (EIS) paradigm to standardized cardiovascular condition monitoring. There are many specifications in cardiology, particularly in the ECG standardization arena. The existence of ECG formats, however, does not guarantee the implementation of homogeneous, standardized solutions for ECG management. In fact, hospital management services need to cope with various ECG formats and, moreover, several different visualization applications. This heterogeneity hampers the normalization of integrated, standardized healthcare information systems, hence the need for finding an appropriate combination of ECG formats and a suitable EIS-based software architecture that enables standardized exchange and homogeneous management of ECG formats. Determining such a combination is one objective of this paper. The second aim is to design and develop the integrated healthcare information system that satisfies the requirements posed by the previous determination. The ECG formats selected include ISO/IEEE11073, Standard Communications Protocol for Computer-Assisted Electrocardiography, and an ECG ontology. The EIS-enabling techniques and technologies selected include web services, simple object access protocol, extensible markup language, or business process execution language. Such a selection ensures the standardized exchange of ECGs within, or across, healthcare information systems while providing modularity and accessibility.

Patients with psoriasis who are being treated with biologics require intensive monitoring. However, the monitoring tool teledermatology is not commonly used. We investigated the applicability of a mobile phone based teledermatological system for monitoring psoriasis patients on biologic therapy. Nineteen patients were given mobile phones with built-in cameras, in order to transmit health status data and images (mobile visits) weekly for a 6-month period. Face-to-face visits were carried out at weeks 0, 4, 12 and 24. Image quality, the Psoriasis Area and Severity Index (PASI), the handling of adverse events, and patients' feedback questionnaires were evaluated. Ninety-five percent of the images were of sufficient quality to enable accurate assessment of the PASI. The distance between the interpolated face-to-face PASIs and the corresponding mobile visit PASIs was 0.46 ± 2.15 (median ± interquartile range). All 155 adverse events were handled correctly by the system. This teledermatological system represents a reliable tool for management of psoriasis patients who are on systemic treatment.

SummaryObjective: Telemonitoring of vital signs is an established option in treatment of patients with chronic heart failure (CHF). In order to allow for early detection of atrial fibrillation (AF) which is highly prevalent in the CHF population telemonitoring programs should include electrocardiogram (ECG) signals. It was therefore the aim to extend our current home monitoring system based on mobile phones and Near Field Communication technology (NFC) to enable patients acquiring their ECG signals autonomously in an easy-to-use way.Methods: We prototypically developed a sensing device for the concurrent acquisition of blood pressure and ECG signals. The design of the device equipped with NFC technology and Bluetooth allowed for intuitive interaction with a mobile phone based patient terminal. This ECG monitoring system was evaluated in the course of a clinical pilot trial to assess the system’s technical feasibility, usability and patient’s adherence to twice daily usage.Results: 21 patients (4f, 54 ± 14 years) suffering from CHF were included in the study and were asked to transmit two ECG recordings per day via the telemonitoring system autonomously over a monitoring period of seven days. One patient dropped out from the study. 211 data sets were transmitted over a cumulative monitoring period of 140 days (overall adherence rate 82.2%). 55% and 8% of the transmitted ECG signals were sufficient for ventricular and atrial rhythm assessment, respectively.Conclusion: Although ECG signal quality has to be improved for better AF detection the developed communication design of joining Bluetooth and NFC technology in our telemonitoring system allows for ambulatory ECG acquisition with high adherence rates and system usability in heart failure patients.

Data that has been collected in the course of clinical trials are potentially valuable for additional scientific research questions in so called secondary use scenarios. This is of particular importance in rare disease areas like paediatric oncology. If data from several research projects need to be connected, so called Core Datasets can be used to define which information needs to be extracted from every involved source system. In this work, the utility of the Clinical Data Interchange Standards Consortium (CDISC) Operational Data Model (ODM) as a format for Core Datasets was evaluated and a web tool was developed which received Source ODM XML files and--via Extensible Stylesheet Language Transformation (XSLT)--generated standardized Core Dataset ODM XML files. Using this tool, data from different source systems were extracted and pooled for joined analysis in a proof-of-concept study, facilitating both, basic syntactic and semantic interoperability.

The European Society of Cardiology guidelines for heart failure management are based on strong evidence that adherence to optimal medication is beneficial for heart failure patients. Telemonitoring with integrated clinical decision support enables physicians to adapt medication dose based on up to date vital parameters and reduces the number of hospital visits needed solely for up-titration of heart failure medication. Although keeping track of weight and blood pressure changes is recommended during unstable phases, e.g. post-discharge and during up-titration of medication, guidelines are rather vague regarding telehealth aspects. In this paper, we focus on the evaluation of a clinical decision support system for adaption of heart failure medication and for detecting early deteriorations through monitoring of blood pressure, heart rate and weight changes. This clinical decision support system is currently used in INTENSE-HF, a large scale telemonitoring trial with heart failure patients. The aim of this paper was to apply the decision support algorithm to an existing telemonitoring dataset, to assess the ability of the decision support concept to adhere to the guidelines and to discuss its limitations and potential improvements.

Pressure ulcers are a common skin disease which is associated with pain, reduced autonomy, social isolation, and reduced quality of life. There are several systems for monitoring of pressure ulcer-related risk factors on the market, but up to now no satisfactory solution is available, especially for people with medium pressure ulcer risk. We present a novel pressure ulcer risk assessment and prevention system, which combines the advantages of accelerometer and pressure sensors for monitoring pressure ulcer risk factors. Sensors are used for detection of repositionings of the person lying on the mattress. Sensor data are sent to a tablet where they are analysed and presented graphically. The system was evaluated in a long-term test at the homes of people of the target group. Results indicate that the system is able to detect movements of persons while lying in bed. Weak correlation in between mobility and Braden pressure ulcer risk was found (correlation factor = 0.31). From our data, long-term trends could be visualized as well as 24 h mobility profiles. Such graphical illustrations might be helpful for caregivers in order to optimize care of people with medium to high pressure ulcer risk.

The aim of this study was to quantify the effect of cardiac anisotropy in the activation-based inverse problem of electrocardiography. Differences of the patterns of simulated body surface potential maps for isotropic and anisotropic conditions were investigated with regard to activation time (AT) imaging of ventricular depolarization. AT maps were estimated by solving the nonlinear inverse ill-posed problem employing spatio-temporal regularization. Four different reference AT maps (sinus rhythm, right-ventricular and septal pacing, accessory pathway) were calculated with a bidomain theory based anisotropic finite-element heart model in combination with a cellular automaton. In this heart model a realistic fiber architecture and conduction system was implemented. Although the anisotropy has some effects on forward solutions, effects on inverse solutions are small indicating that cardiac anisotropy might be negligible for some clinical applications (e.g., imaging of focal events) of our AT imaging approach. The main characteristic events of the AT maps were estimated despite neglected electrical anisotropy in the inverse formulation. The worst correlation coefficient of the estimated AT maps was 0.810 in case of sinus rhythm. However, all characteristic events of the activation pattern were found. The results of this study confirm our clinical validation studies of noninvasive AT imaging in which cardiac anisotropy was neglected.

This paper presents and compares mobile phone-based solutions for assisting chronically ill patients in the self managing process by establishing an active cooperation and connection between patients and physicians. The article focuses on the patient terminal, i.e. how to provide the patient with a method to enter the measured data into the system, which is still one of the most challenging tasks.

We assessed a two-stage follow-up procedure for cardiac pacemakers, where in-clinic follow-ups were partly replaced by telemedical follow-ups. This was compared with the standard follow-up regime (in-clinic follow-up only). The new procedure required an electronic patient record, a telemedical follow-up unit for recording ECGs while the pacemaker was temporarily set to magnet mode, an ECG processing unit, and a reviewing and reporting unit. A total of 177 (86 female) patients were randomized to the control group and 182 (98 female) patients to the telemedicine group. In the telemedicine group, 234 telemedical follow-ups were performed. Out of these, 68 required an additional in-clinic follow-up, while 166 were sufficient for assessing the pacemakers' working status. During the study, there were 19 deaths in the telemedicine group and 20 in the control group. There was no significant difference between the two groups( P = 0.40). The probability that an individual patient’s pacemaker would not to be replaced over time was analysed in a similar way to the Kaplan-Meier survival function. Fewer pacemakers were replaced in the telemedicine group (14) than in the control group (18), but the difference was not significant ( P = 0.26). We conclude that alternating telemedical and in-clinic follow-ups brings no additional risks for patients. The follow-up procedure is feasible and interpretation of the pacemakers’ magnet effect provides an easy-to-use, manufacturer-independent method of assessing the pacemakers’ working status. This should reduce the patient load on pacemaker centres and decrease the overall costs of pacemaker therapy.

State-of-the-art decubitus prevention focuses mainly on special decubitus mattresses, which are indicated for extremely high risk only, while other risk factors such as nutrition or physical activity are hardly considered. Therefore, a monitoring system for decubitus prevention for persons with medium risk has been developed. The system consisted of an unobtrusive sensor system and a tablet for manual input of decubitus-relevant data concerning nutrition, drinking behavior and physical activity. The system was tested in a feasibility study. Results indicate that the system is usable and can provide useful information for decubitus prevention. Future work will include a field study, evaluating the system in a long-term study.

Poor patients' adherence to intake of prescribed medication has been identified as a serious problem in the treatment of chronically ill patients. Technical solutions are needed to measure and - if necessary - to increase the patients' adherence. A telemonitoring solution was developed to record a patient's medication intake based on smart blisters and mobile phones with NFC functionality. The components allowed recording of drug type, timestamp, and dosage of pills taken. The system's usability and technical feasibility was evaluated in the course of an application study. Over a period of 13 months 59 patients suffering from diabetes were monitored. 1,760 blisters were handed out to these patients and 14,843 takeout events were recorded and transmitted via mobile phone. Results indicate the feasibility of this concept to monitor adherence. Although the system still needs to be optimized for routine use it shows the potential for targeting the problem of poor patient adherence by NFC enabled devices.

Utilization of information and communication technologies such as mobile phones and wireless sensor networks becomes more and more common in the field of telemonitoring for chronic diseases. Providing elderly people with a mobile-phone-based patient terminal requires a barrier-free design of the overall user interface including the setup of wireless communication links to sensor devices. To easily manage the connection between a mobile phone and wireless sensor devices, a concept based on the combination of Bluetooth and near-field communication technology has been developed. It allows us initiating communication between two devices just by bringing them close together for a few seconds without manually configuring the communication link. This concept has been piloted with a sensor device and evaluated in terms of usability and feasibility. Results indicate that this solution has the potential to simplify the handling of wireless sensor networks for people with limited technical skills.

Since several decades pacemakers and implantable cardioverter defibrillators (ICDs) are a common therapy for patients with cardiac rhythm abnormalities. More recently developed devices like implantable cardiac resynchronization therapy devices (CRTs) (Anand et al. 2009) or implantable loop recorders (ILRs) (Boersma et al. 2003) are implanted with increasing frequency and provide promising results. Selection and implantation of devices are only first steps in cardiac rhythm disease management. Continuous adaptation of device settings to patient’s needs, monitoring of device’s battery status, revision of devices and several other issues need to be considered. Additionally, the functionality of devices is closely related to other therapeutic aspects, such as medication or the patient’s health parameters – assessed either by general practitioners or by the patient him/ herself (e.g. blood pressure). In many cases a given patient needs more than one therapy: e.g. pacemaker therapy is closely related to medication monitoring; or an increasing number of remotely monitored congestive heart failure patients also have an implanted CRT device. Therefore, a system is needed which is able to handle data from various sources (from implanted devices, from patient’s home, from general practitioners, from hospitals, etc.) and provide the physician with all information necessary for an optimal therapy. While from the patient’s view it is primarily essential that all data from various sources are combined in one single system, from the physician’s view it is also important to have one single system for all the patients she/ he is responsible for. There are several manufacturers for each of the therapeutic tools used in cardiac rhythm disease management. Each of those provides the physician with its own proprietary data interface. And, of course, one physician’s patients are not all equipped with devices of one and the same manufacturer. Therefore, it is not only necessary to combine devices supporting different therapies (pacemakers, remote monitoring, etc.), but also to combine systems from different manufacturers within one single platform. Additionally, eHealth infrastructures with electronic health records are currently envisaged, conceived or already established in many environments (single healthcare institutions, health management organisations, whole healthcare systems, or even nation-wide) (Pfeiffer

Congestive Heart Failure (CHF) is a common chronic heart disease with high socioeconomic impact. Conventional treatment of CHF is often ineffective and inefficient, since self-management is complex and patients are insufficiently involved in therapy management. With telemedical concepts, continuous monitoring of the health status can be ensured, and consequently therapy management can be adapted to the individual requirements of every individual patient. Therefore, a mobile phone based patient terminal for the concurrent acquisition of biosignals (e.g. ECG) and bioparameters (e.g. blood pressure) for patients with CHF has been developed and prototypically implemented. Usability and interoperability aspects were especially considered by using Bluetooth and Near Field Communication (NFC) technology for data acquisition and standardized data formats for transmission of the data to a central monitoring centre. Results indicated that even complicated measurements like the acquisition of ECG signals could be accomplished autonomously by the patients in an intuitive and easy-to-use way. Through the usage of IHE conform HL7 messages, self-measured data could easily be integrated into a higher-ranking eHealth infrastructure.

The Internet of Things (IoT) is the logical further development of today’s Internet. Technological advancements lead to smart objects being capable of identifying, locating, sensing and connecting and thus leading to new forms of communication between people and things and things themselves. Ambient Assisted Living (AAL) encompasses technical systems to support elderly people in their daily routine to allow an independent and safe lifestyle as long as possible. Keep In Touch (KIT) uses smart objects and technologies (Near Field Communication and Radio Frequency Identification) to facilitate telemonitoring processes. Closed Loop Healthcare Services take use of KIT technology and are capable of processing relevant data and establishing communication channels between elderly people and their environment and different groups of care-givers (physicians, relatives, mobile care providers). The combination of KIT technology (smart objects) and Closed Loop Healthcare Services results in an applied IoT infrastructure for AAL scenarios. Already applied IoT and AAL applications in telemonitoring and medication intake compliance projects show that these applications are useful and accepted by the elderly and that the developed infrastructure enables a new form of communication between people and people, people-to-people (P2P) communication. The personal communication between elderly people, their environment and relevant groups of care givers is an important aspect in AAL. Through the combination of KIT and Closed Loop Healthcare, a central AAL paradigm can be realized through the IoT, where the elderly live in their homes with smart objects, thus smart homes, communicating to the outside world in an intelligent and goal-orientated manner.

A mobile phone-based telemonitoring system for long-term psoriasis therapy is described, intended to increase patients' compliance by optimizing the patient-physician communication. Patients themselves can acquire health parameters and take photos of their psoriasis lesions. The data are sent to a monitoring centre, where they are provided to the patients' physician who returns a feed-back message. The system is currently tested in a study with 20 patients. Preliminary results prove the feasibility and usabililty of such a system and indicate that it is useful for optimizing psoriasis-therapy.

Electronic data capture systems are utilized to collect, document, and process research data for clinical trials. Ideally, the workflow of collecting the data could be simplified by using mobile clients that enable for data acquisition at the point-of-care. Mobile phones provide a range of features to act as data acquisition unit for clinical trials. A novel approach towards an automated solution is the combination of mobile phones with Near Field Communication (NFC) technology. This technology enables for easy-to-use data acquisition just by touching items. The aim of this work has been to design and develop an additional path for clinical data acquisition based on mobile phones and NFC technology. The system was utilized in a pilot trial and evaluated regarding usability and feasibility for clinical application.

Optimizing the treatment of chronic diseases requires continuous monitoring of the health status. With standard information and communication technology this challenge can be solved, with respect to special needs of patients, stated as marginal effort and simple handling. We present a therapy-management-system where patients acquired their health data using a Java-application running on mobile phones. The data were transferred to the health centre, which provided data visualization, individual feedback, reminders and surveillance of critical events. The system was evaluated in the course of two clinical trials with patients suffering from diabetes mellitus. Seven out of ten patients of the first trial returned questionnaires and reported feasibility of the concept for regular daily use. Patients of the second trial reported problems to a telephone-hotline, most were related to faulty data insertion. Based on their high user acceptance and ubiquitous availability mobile phones show the potential to be the patient-terminal of choice.

We propose a telemedicine framework for remote and manufacturer independent pacemaker (PM) follow-up. The main goal is to provide the caregiver at the point-of-care with an efficient screening method to identify possible malfunction of the pacing system in collaboration with the specialist at the PM clinic. The concept was evaluated in a clinical trial on 44 patients (mean age 76 years). A total of 62 electrocardiogram (ECG) recordings were transmitted using a mobile PM follow-up unit. Using the automatic classification algorithm, 32 PMs were classified as 'OK' and eight PMs were classified as 'not OK'. In four cases a prediction regarding the working status of the PM was not possible. The signal processing classification was confirmed by expert classification (manual review of the ECG). The results indicate that the proposed PM follow-up concept has the potential to work as an efficient screening method and may spare a significant number of patients the burden of having to travel to specialized PM clinics.

The contribution of the epi-and endocardial as well as the myocardial electrical activity to the body surface potential was investigated in this study. A volume conductor including a realistic anisotropic ventricular model was built up and the forward problem of electrocardiography was solved for four different rhythms, in order to quantitatively describe the cardiac electrical contribution of each compartment of the heart. The results show, that the body surface potentials depend to a high degree on the epi-and endocardial electrical spread of excitation during the depolarization phase, whereas the influence of myocardial activity is more pronounced during repolarization. These findings indicate that the depolarization phase can be approximated by cardiac isotropic electrical.

Atrial fibrillation is the most common cardiac arrhythmia, affecting more than two million people in the US. Several therapies for patients with atrial fibrillation are available, but methods to help physicians select the optimal therapy for an individual patient are still required. Knowledge of whether a patient with a normal ECG will exhibit atrial fibrillation in the future, as well as whether atrial fibrillation will terminate spontaneously, would be very useful in clinical routine. The paper presents a software system for predicting the initiation and termination of atrial fibrillation from the ECG. The algorithms have been validated on ECGs from several signal databases. Prediction of the initiation of atrial fibrillation was achieved by detecting premature heart beats and analyzing the morphology of their P waves. Prediction of the termination of atrial fibrillation was based on calculation of the major atrial frequency. This frequency has been shown to decrease significantly prior to the termination of atrial fibrillation. Nevertheless, the effect is much less distinct in the large data set used for this study compared to previous studies. The initiation of atrial fibrillation, however, could be correctly predicted in approximately 75% of the data analyzed.

According to international guidelines implanted cardiac pacemakers (PM) have to be checked periodically to ensure that they are working correctly. To spare a significant number of patients the burden of traveling to specialized PM clinics a telemedicine framework has been developed prototypically. A mobile, personal digital assistant (PDA) based PM follow-up unit provides the caregiver at the point-of-care with the necessary infrastructure to perform a basic PM follow-up examination remotely. In case of detected malfunction of the PM the patient is ordered to the hospital for further examination. The system has been evaluated in a clinical pilot trial on 44 patients with a total of 23 different PM models from 8 different manufacturers. The initial results indicate the potential of the concept to work as an efficient, manufacturer independent screening method with the ultimate goal to increase the safety, quality and efficiency of PM therapy.

An algorithm for differentiating ECGs with atrial fibrillation (AF) that will spontaneously terminate within 60 seconds from signals, where it won't, has been developed using the AF termination challenge database from physionet. The algorithm was based on the calculation of the major AF frequency by canceling out the QRS complexes and T waves from the original ECGs and then applying short time Fourier transform techniques to the remaining signals. The major AF frequency and the mean RR interval were considered for classification. Validation of the algorithm was done by sending the algorithm's results for test-set-a of the AF termination challenge database to physionet. We found, that for ECGs with a low AF frequency it was more likely, that AF would terminate spontaneously than for ECGs with higher frequencies. Our algorithm was able to correctly classify 93.3% (28/30) of the signals of the test-set-a.

Due to international standards each implantable cardiac pacemaker reacts to the application of a permanent magnet by changing the pacing rate in a predefined way depending on the depletion level of its battery. The purpose of this study has been to use a routine ECG recording to verify in a telemedicine framework whether the pacemaker works correctly or if further examination is indicated. The system has been implemented prototypically and has been evaluated in a clinical pilot trial on 24 consecutive patients with a total of 17 different pacemaker models from 6 different manufacturers. The promising results indicate that the presented follow-up concept, which can be handled by general practitioners, has the potential to work as an efficient screening method and may spare a significant number of patients the burden of having to travel to specialized hospitals which are often far away from patients' homes

An algorithm for automated QT interval assessments has been developed and evaluated using the PhysioNet QT database and the electrocardiogram multilead database (2 collections of electrocardiograms with different characteristics, eg, numbers of leads and expert annotations). QRS onset and coarse T offset detection was based on the definition of a short time window, within which the range of signal amplitudes was calculated and compared to given threshold values. The final position of T offset was based on a combination of 3 methods: decreasing thresholds, multiple tangents, and a model based approach. The evaluation was based on the comparison of a waveform marker as computed automatically, and those of the human experts. Mean and standard deviation of those differences compared well to other algorithms and to inter-expert variations. Waveform marker detection was successful in at least 98% of the annotated beats in both databases, thus, indicating the robustness of the proposed method.

Health informatics develops methods and tools that should, when applied to health care, contribute to a high-quality, efficient care of individuals and populations [1]. The translation of health informatics research into practice can be seen as a “continuum” from IT development to healthcare problem solving [2], starting with developing and validating early solutions (tools, algorithms, technologies ...) that are then integrated and tested in clinical practice, first in small pilot projects, later in larger evaluation studies. Scientific publication of the outcome of these projects and studies is an important step to increase awareness on new solutions, to allow sharing of experiences, and to decide on continuation or stop of the developments as part of evidence-based health informatics [3]. Health informatics has been developing solutions for intra-organizational information systems for many decades now. Recently, with the emergence of inter-organi zational (or trans-institutional) information systems [1, 4], the term “eHealth” has been shaped to describe “an emerging field in the intersection of medical informatics, public health and business, referring to health services and information delivered or enhanced through the Internet and related technologies” [5]. Generally speaking, the term eHealth encompasses more traditional concepts such as telemedicine and tele monitoring [6] as well as newer concepts such as shared electronic health records [7] or pervasive health care systems [8]. eHealth applications offer the potential for large benefits for health care, such as improved quality of care, patient empowerment, health promotion, and cost savings [9 –11]. However, a lot of challenges need to be overcome to exploit these potential benefits, such as semantic and technical integration and human-computer interaction [12], but also social, cultural, eco nomical and organizational challenges [10, 13], as eHealth will have an impact on the way health care is delivered in the future. This special issue presents the best three contributions from the eHealth2009 conference in Vienna, highlighting recent challenges and achievements in the area of eHealth. The eHealth-conference series is an annual series of scientific events dealing with health informatics methods and their applications to eHealth [14]. The paper by Christoph Rinner and coauthors [15] tackles the problem of semantic interoperability. At the moment, XML-based document standards such as Clinical Document Architecture (CDA) or ISO/EN 13606 are being developed to support semantic interoperability within inter-organizational information systems. The authors present an approach to automatically validate EHR documents, to assess whether they are conformant to the described standards. Their approach allows EHR documents to be validated for conformance with the underlying reference models and archetypes of the mentioned standards by means of XML schema, without requiring an additional validation language. This will allow simplifying the overall validation process in the future. The paper by Tuncay Namli and Asuman Dogac [16] addresses the technical interoperability of EHR systems. There are many standards and initiatives (such as HL7 v3 or IHE) that support the exchange of data. To allow interoperability based on these standards, application systems need to prove that they are conformant to these standards. The authors present an automated, modular and scenario-based testing framework that allows testing conformMethods Inf Med 2010; 49: 269–270

According to international standards, cardiac pacemakers have to indicate the status of their batteries upon magnet application by specific stimulation patterns. The purpose of this study has been to assess whether this concept can be used as a basis for automated and manufacturer independent examination of the depletion level of pacemakers in the framework of a collaborative telemedical pacemaker follow-up system. A prototype of such a system was developed and tested in a real clinical environment. Electrocardiograms (ECGs) were recorded during magnet application and automatically processed to extract the specific stimulation patterns. The results were used to assign each signal a corresponding pacemaker status: "ok," "replace" or "undefined," based on the expected behavior of the devices as specified by the manufacturer. The outcome of this procedure was compared to the result of an expert examination, resulting in a positive predictive value of 100% for the detection of ECGs indicating pacemaker status "ok." The method can, therefore, be utilized to quickly, safely and manufacturer neutrally classify cases into the categories "ok" and "needs further checking," which - in a telemedical setting - may be used to increase the efficiency of pacemaker follow-up procedures in the future.