Stefan Gradl

Comparison of real-time classification systems for arrhythmia detection on Android-based mobile devices

The electrocardiogram (ECG) is a key diagnostic tool in heart disease and may serve to detect ischemia, arrhythmias, and other conditions. Automatic, low cost monitoring of the ECG signal could be used to provide instantaneous analysis in case of symptoms and may trigger the presentation to the emergency department. Currently, since mobile devices (smartphones, tablets) are an integral part of daily life, they could form an ideal basis for automatic and low cost monitoring solution of the ECG signal. In this work, we aim for a realtime classification system for arrhythmia detection that is able to run on Android-based mobile devices. Our analysis is based on 70% of the MIT-BIH Arrhythmia and on 70% of the MIT-BIH Supraventricular Arrhythmia databases. The remaining 30% are reserved for the final evaluation. We detected the R-peaks with a QRS detection algorithm and based on the detected R-peaks, we calculated 16 features (statistical, heartbeat, and template-based). With these features and four different feature subsets we trained 8 classifiers using the Embedded Classification Software Toolbox (ECST) and compared the computational costs for each classification decision and the memory demand for each classifier. We conclude that the C4.5 classifier is best for our two-class classification problem (distinction of normal and abnormal heartbeats) with an accuracy of 91.6%. This classifier still needs a detailed feature selection evaluation. Our next steps are implementing the C4.5 classifier for Android-based mobile devices and evaluating the final system using the remaining 30% of the two used databases.

Temporal correction of detected R-peaks in ECG signals: A crucial step to improve QRS detection algorithms

In the last decade the interest for heart rate variability analysis has increased tremendously. Related algorithms depend on accurate temporal localization of the heartbeat, e.g. the R-peak in electrocardiogram signals, especially in the presence of arrhythmia. This localization can be delivered by numerous solutions found in the literature which all lack an exact specification of their temporal precision. We implemented three different state-of-the-art algorithms and evaluated the precision of their R-peak localization. We suggest a method to estimate the overall R-peak temporal inaccuracy-dubbed beat slackness-of QRS detectors with respect to normal and abnormal beats. We also propose a simple algorithm that can complement existing detectors to reduce this slackness. Furthermore we define improvements to one of the three detectors allowing it to be used in real-time on mobile devices or embedded hardware. Across the entire MIT-BIH Arrhythmia Database, the average slackness of all the tested algorithms was 9ms for normal beats and 13ms for abnormal beats. Using our complementing algorithm this could be reduced to 4ms for normal beats and to 7ms for abnormal beats. The presented methods can be used to significantly improve the precision of R-peak detection and provide an additional measurement for QRS detector performance.

Somnography using unobtrusive motion sensors and Android-based mobile phones

Sleep plays a fundamental role in the life of every human. The prevalence of sleep disorders has increased significantly, now affecting up to 50% of the general population. Sleep is usually analyzed by extracting a hypnogram containing sleep stages. The gold standard method polysomnography (PSG) requires subjects to stay overnight in a sleep laboratory and to wear a series of obtrusive devices. This work presents an easy to use method to perform somnography at home using unobtrusive motion sensors. Ten healthy male subjects were recorded during two consecutive nights. Sensors from the Shimmer platform were placed in the bed to record accelerometer data, while reference hypnograms were collected using a SOMNOwatch system. A series of filters were used to extract a motion feature in 30 second epochs from the accelerometer signals. The feature was used together with the ground truth information to train a Naive Bayes classifiers that distinguished wakefulness, REM and non-REM sleep. Additionally the algorithm was implemented on an Android mobile phone. Averaged over all subjects, the classifier had a mean accuracy of 79.0 % (SD 9.2%) for the three classes. The mobile phone implementation was able to run in realtime during all experiments. In future this will lead to a method for simple and unobtrusive somnography using mobile phones.

Arrhythmia classification using RR intervals: Improvement with sinusoidal regression feature

Far too many people are dying from stroke or other heart related diseases each year. Early detection of abnormal heart rhythm could trigger the timely presentation to the emergency department or outpatient unit. Smartphones are an integral part of everyone;s life and they form the ideal basis for mobile monitoring and real-time analysis of signals related to the human heart. In this work, we investigated the performance of arrhythmia classification systems using only features calculated from the time instances of individual heart beats. We built a sinusoidal model using N (N = 10, 15, 20) consecutive RR intervals to predict the (N+1)th RR interval. The integration of the innovative sinusoidal regression feature, together with the amplitude and phase of the proposed sinusoidal model, led to an increase in the mean class-dependent classification accuracies. Best mean class-dependent classification accuracies of 90% were achieved using a Naïve Bayes classifier. Well-performing realtime analysis arrhythmia classification algorithms using only the time instances of individual heart beats could have a tremendous impact in reducing healthcare costs and reducing the high number of deaths related to cardiovascular diseases.

Instantaneous P- and T-wave detection: Assessment of three ECG fiducial points detection algorithms

Arrhythmia detection algorithms require the exact and instantaneous detection of fiducial points in the ECG signal. These fiducial points (QRS-complex, P- and T-wave) correspond to distinct cardiac contraction phases. The performance evaluation of different fiducial points detection algorithms require the existence of large databases (DBs) encompassing reference annotations. Up to last year, P- and T-wave annotations were only available for the QT DB. This was addressed by Elgendi et al. who provided P- and T-wave annotations to the MIT-BIH arrhythmia DB. A variety of ECG fiducial points detection algorithms exists in literature, whereas, to the best knowledge of the authors, we could not identify any single-lead algorithm ready for instantaneous P- and T-wave detection. In this work, we present three P- and T-wave detection algorithms: a revised version for QRS detection using line fitting capable to detect P- and T-wave, an expeditious version of a wavelet based ECG delineation algorithm, and a fast naive fiducial points detection algorithm. The fast naive fiducial points detection algorithm performed best on both DBs with sensitivities ranging from 73.0% (P-wave detection, error interval of ± 40 ms) to 89.4% (T-wave detection, error interval of ± 80 ms). As this algorithm detects a wave event in every search window, it has to be investigated how this affects arrhythmia detection algorithms. The reference Matlab implementations are available for download to encourage the development of high-accurate and automated ECG processing algorithms for the integration in daily life using mobile computers.

Filter and processing method to improve R-peak detection for ECG data with motion artefacts from wearable systems

The electrocardiogram (ECG) is one of the most reliable information sources for assessing cardiovascular health and training success. Since the early 1990s, the heart rate variability (HRV), namely the variation from beat to beat, has become the focus of investigations as it provides insight into the complex interplay of body circulation and the influence of the autonomic nervous system on heartbeats. However, HRV parameters during physical activity are poorly understood, mostly due to the challenging signal processing in the presence of motion artefacts. To derive HRV parameters in time (heart rate (HR)) and frequency domains (high frequency (HF), low frequency (LF)), it is crucial to reliably detect the exact position of the R-peaks. We introduce a full algorithm chain where a sophisticated filtering technique is combined with an enhanced R-peak detection that can cope with motion artefacts in ECG data originating from physical activity.

“MigraineMonitor” – Towards a System for the Prediction of Migraine Attacks using Electrostimulation

Abstract Migraine attacks can be accompanied by many different symptoms, some of them appearing within 24 hours before the onset of the headache. In previous work, reduced habituation to an electrical pain stimulus at the head was observed in the pre-ictal phase within 24 hours before the headache attack. Based on these results, this work presents an application to track influence factors on migraine attacks and an Arduino-based control unit which replaces the traditional approach of manual electrical stimulation. The usability of both components of the project was evaluated in separate user studies. Results of the usability study show a good acceptance of the systems with a mean SUS score of 92.4. Additionally, they indicate that the developed control unit may substitute the current manual electrical stimulation. Overall, the designed system allows standardized repeatable measurements and is a first step towards the home-use of a device for establishing a new method for migraine prediction.

Textile Integrated Wearable Technologies for Sports and Medical Applications

Innovative and pervasive monitoring possibilities are given using textile integration of wearable computing components. We present the FitnessSHIRT (Fraunhofer IIS, Erlangen, Germany) as one example of a textile integrated wearable computing device. Using the FitnessSHIRT, the electric activity of the human heart and breathing characteristics can be determined. Within this chapter, we give an overview of the market situation, current application scenarios, and related work. We describe the technology and algorithms behind the wearable FitnessSHIRT as well as current application areas in sports and medicine. Challenges using textile integrated wearable devices are stated and addressed in experiments or in explicit recommendations. The applicability of the FitnessSHIRT is shown in user studies in sports and medicine. This chapter is concluded with perspectives for textile integrated wearable devices.

Virtual and augmented reality in sports: an overview and acceptance study

The interest in virtual and augmented reality exploded during the last two years. We propose the use of these systems in the field of sports by combining this technology with a local area radio-based localization technology. This allows for novel application scenarios using virtual environments in team-based sports, which are outlined in this work. We conducted an online survey among 227 athletes about the acceptance of virtual reality headsets for training in different kind of sport disciplines.

Detection of fetal kicks using body-worn accelerometers during pregnancy: Trade-offs between sensors number and positioning

Monitoring fetal wellbeing is key in modern obstetrics. While fetal movement is routinely used as a proxy to fetal wellbeing, accurate, noninvasive, long-term monitoring of fetal movement is challenging. A few accelerometer-based systems have been developed in the past few years, to tackle common issues in ultrasound measurement and enable remote, self-administrated monitoring of fetal movement during pregnancy. However, many questions remain unanswered to date on the optimal setup in terms of body-worn accelerometers as well as signal processing and machine learning techniques used to detect fetal movement. In this paper, we systematically analyze the trade-offs between sensor number and positioning, the presence of reference accelerometers outside of the abdominal area and provide guidelines on dealing with class imbalance. Using a dataset of 15 measurements collected employing 6 three-axial accelerometers we show that including a reference accelerometer on the back of the participant consistently improves fetal movement detection performance regardless of the number of sensors utilized. We also show that two accelerometers plus a reference accelerometer are sufficient for optimal results.Monitoring fetal wellbeing is key in modern obstetrics. While fetal movement is routinely used as a proxy to fetal wellbeing, accurate, noninvasive, long-term monitoring of fetal movement is challenging. A few accelerometer-based systems have been developed in the past few years, to tackle common issues in ultrasound measurement and enable remote, self-administrated monitoring of fetal movement during pregnancy. However, many questions remain unanswered to date on the optimal setup in terms of body-worn accelerometers as well as signal processing and machine learning techniques used to detect fetal movement. In this paper, we systematically analyze the trade-offs between sensor number and positioning, the presence of reference accelerometers outside of the abdominal area and provide guidelines on dealing with class imbalance. Using a dataset of 15 measurements collected employing 6 three-axial accelerometers we show that including a reference accelerometer on the back of the participant consistently improves fetal movement detection performance regardless of the number of sensors utilized. We also show that two accelerometers plus a reference accelerometer are sufficient for optimal results.