Martin Schmidt

• Doctor of Engineering
• Group Leader at TU Dresden

Introduction Artificial intelligence (AI), particularly deep learning (DL), has demonstrated high performance in various diagnostic problems, including the detection of paroxysmal atrial fibrillation (AF) from electrocardiograms (ECGs). In mobile applications, these approaches can help to detect AF at an early stage and thus prevent possible second...

This preprint describes the TIMELY RCT

Atrial fibrillation (AF) is a prevalent diagnosis in Western countries and is associated with significant morbidity and mortality if untreated. Due to its initial paroxys-mal nature, long-term or regular short-term electrocardio-grams (ECGs) are required for diagnosis of AF. Wearables with reduced leads can be used for this purpose, although they p...

Aiming to apply automatic arousal detection to support sleep laboratories, we evaluated an optimized, state-of-the-art approach using data from daily work in our university hospital sleep laboratory. Therefore, a machine learning algorithm was trained and evaluated on 3423 polysomnograms of people with various sleep disorders. The model architectur...

Deep learning (DL) has demonstrated high accuracy in ECG analysis but lacks in explainability. Although explanations can be estimated using explainable artificial intelligence, their causality has not yet been sufficiently investigated. We present a generalizable method for extensively validating the DL explanations’ causality by relating them to c...

Deep learning-based methods have demonstrated high classification performance in the detection of cardiovascular diseases from electrocardiograms (ECGs). However, their blackbox character and the associated lack of interpretability limit their clinical applicability. To overcome existing limitations, we present a novel deep learning architecture fo...

Beat-to-beat (B2B) variability in biomedical signals has been shown to have high diagnostic power in the treatment of various cardiovascular and autonomic disorders. In recent years, new techniques and devices have been developed to enable non-invasive blood pressure (BP) measurements. In this work, we aim to establish the concept of two-dimensiona...

Deep learning-based methods have demonstrated high classification performance in the detection of cardiovascular diseases from electrocardiograms (ECGs). However, their blackbox character and the associated lack of interpretability limit their clinical applicability. To overcome existing limitations, we present a novel deep learning architecture fo...

Aiming to apply automatic arousal detection to support sleep laboratories, we evaluated an optimized, state-of-the-art approach using data from daily work in our university hospital sleep laboratory. Therefore, a machine learning algorithm was trained and evaluated on 3423 polysomnograms of people suffering from various sleep disorders. The model a...

Postanoxic coma is caused by global anoxia of the brain, most often due to cardiac arrest. Electroencephalography (EEG) has been shown to provide prognostic information, where synchronous EEG activity is linked to cortico-cortical connectivity and arousals are linked to cortico-subcortical connectivity. Previous studies indicated changes in both co...

Sympathovagal imbalance is known to precede the onset of atrial fibrillation (AF) and has been analyzed extensively based on heart rate variability (HRV). However, the relationship between sympathetic and vagal effects before AF onset and their influence on various HRV features have not been fully elucidated. QT interval variability (QTV) reflects...

Numerous vital signs are reported in association with stress response assessment, but their application varies widely. This work provides an overview over methods for stress induction and strain assessment, and presents a multimodal experimental study to identify the most important vital signs for effective assessment of the response to acute menta...

The rowing technique is a key factor in the overall rowing performance. Nowadays the athletes’ performance is so advanced that even small differences in technique can have an impact on sport competitions. To further improve the athletes’ performance, individualized rowing is necessary. This can be achieved by intelligent measurement technology that...

Atrial fibrillation (AF) is our society’s most common cardiac arrhythmic disease, leading to increased morbidity and mortality. Predicting AF episodes during sinus rhythm based on electrocardiograms (ECGs) allows timely interventions. It is known, that changes in selected ECG morphology features are a predictor for the onset of AF, but no systemati...

The rowing technique is a key factor in the overall rowing performance. Nowadays the athletes’ performance is so advanced that even small differences in technique can have an impact on sport competitions. To further improve the athletes’ performance, individualized rowing is necessary. This can be achieved by intelligent measurement technology that...

In this work, four different algorithms (fast Fourier transform FFT, short-time Fourier transform STFT, continuous wavelet transform CWT, and instantaneous frequency IF) for calculating median frequency (MDF) from surface EMG signals were investigated for studying muscle fatigue during a on-water rowing training. The study protocol included 5 conse...

Objective Current eHealth enable integration of artificial intelligence (AI) and the Internet of Things (IoT)-devices to optimize health behaviors for prevention of incident and recurrent cardiovascular disease, including coronary artery disease (CAD). These novel eHealth interventions can be used to augment the availability and effectiveness of ca...

Background: Cardiac rehabilitation (CR) is an evidence-based therapy to limit the physiological and psychological effects of CAD, manage symptoms, and reduce the risk of future events. CR is far from general implementation and the potential of CR components over the continuum of CAD is not fully exhausted. Current eHealth innovations allow the inte...

Objective. After skin flap transplants, perfusion strength monitoring is essential for the early detection of tissue perfusion disorders and thus to ensure the survival of skin flaps. Camera-based photoplethysmography (cbPPG) is a non-contact measurement method, using video cameras and ambient light, which provides spatially resolved information ab...

Mental stress triggers positive inotropic and chronotropic effects as well as peripheral vasoconstriction. This alters the pulse arrival time (PAT), the duration between electrical excitation of the ventricles and arrival of the pulse wave in the periphery. We conducted a study to examine PAT during five rest blocks and under mental stress utilizin...

Imaging photoplethysmography (iPPG) is a camera-based approach for the remote measurement of superficial tissue perfusion most commonly applied to facial video recordings. Since only tissue contains information about perfusion, skin detection is a necessary processing step. Several approaches for the detection of skin pixels in video recordings hav...

Mental stress causes a physiological response and is often assessed by heart rate variability. In this work, we investigated cardiovascular parameters other than heart rate variability. We performed a stress test with 44 healthy volunteers and evaluated 17 cardiovascular parameters measured with a CNSystems Task Force® Monitor, several self-report...

Cardiovascular diseases are the global leading cause of death. Automated electrocardiogram (ECG) analysis can support clinicians to identify abnormal excitation of the heart and prevent premature cardiovascular death. An explainable classification is particularly important for support systems. Our contribution to the PhysioNet/CinC Challenge 2021 (...

Cardiovascular diseases are the global leading cause of death. Automated electrocardiogram (ECG) analysis can support clinicians to identify abnormal excitation of the heart and prevent premature cardiovascular death. An explainable classification is particularly important for support systems. Our contribution to the PhysioNet/CinC Challenge 2021 (...

Objective: The heart rate is an essential vital sign that can be measured remotely with camera-based photoplethysmography (cbPPG). Systems for cbPPG typically use cameras that deliver red, green, and blue (RGB) channels. The combination of these channels has been proven to increase signal-to-noise ratio (SNR) and heart rate measurement accuracy (AC...

Due to the ageing of society, health insurers and care sectors in many western countries are facing major challenges. Technical Assistance Systems (TAS) could have the potential to ease the situation, while at the same time promoting the independence and self-determination of care-dependent people. However, TAS have not yet been fully established i...

Spontaneous baroreflex sensitivity (BRS) is a widely used tool for the quantification of the cardiovascular regulation. Numerous groups use the xBRS method, which calculates the cross-correlation between the systolic beat-to-beat blood pressure and the R-R interval (resampled at 1 Hz) in a 10 s sliding window, with 0–5 s delays for the interval. Th...

Spontaneous baroreflex sensitivity (BRS) is a widely used tool for the quantification of the cardiovascular regulation. Numerous groups use the xBRS method, which calculates the cross-correlation between the systolic beat-to-beat blood pressure and the R-R interval (resampled at 1 Hz) in a 10 s sliding window, with 0–5 s delays for the interval. Th...

Camera-based heart rate (HR) estimation is used with different color spaces and regions of interest (ROIs). In this work, seven commonly used ROIs were determined via facial landmarks focusing on forehead, cheeks and glabella, and one ROI was derived by level set segmentation. For each ROI, 25 signals of eight color spaces were derived and HR estim...

In this work we developed a simple distance metric which uses only one channel to detect fQRS morphology changes introduced by fetal movement.

Increased beat-to-beat QT interval variability in electrocardiograms is a robust descriptor of ventricular depolarization and repolarization lability. Variability analysis of the depolarization and repolarization intervals in vectorcardiogram has indicated potential diagnostic abilities. Here, we describe an inhomogeneous signal adaptation techniqu...

The objective of the present study was to quantify repolarization lability and its association with sex, sleep stage, and cardiovascular mortality. We analyzed polysomnographic recordings of 2,263 participants enrolled in the Sleep Heart Health Study (SHHS-2). Beat-to-beat QT interval variability (QTV) was quantified for consecutive epochs of 5 min...

Purpose: Camera-based photoplethysmography (cbPPG) remotely detects the volume pulse of cardiac ejection in the peripheral circulation. The cbPPG signal is sourced from the cutaneous microcirculation, yields a two-dimensional intensity map and is therefore an interesting monitoring technique. In this study we investigated, whether cbPPG is in gene...

The assessment of subtle morphological changes in noisy signals is a common challenge in the field of biomedical signal processing. Concerning the electrocardiogram (ECG), it may yield novel risk factors for cardiac mortality. Here, we describe an iterative two-dimensional signal warping algorithm (i2DSW), which morphological analyses even in case...

Background: Camera-based photoplethysmography (cbPPG) is a measurement technique which enables remote vital sign monitoring by using cameras. To obtain valid plethysmograms, proper regions of interest (ROIs) have to be selected in the video data. Most automated selection methods rely on specific spatial or temporal features limiting a broader appl...

Telemedicine focuses on improving the quality of health care, particularly in out-of-hospital settings. One of the most important applications is the continuous remote monitoring of vital parameters. Long-term monitoring of biopotentials requires skin-electrodes. State-of-the-art electrodes such as Ag/AgCl wet electrodes lead, especially during lon...

Camera-Based Photoplethysmography is a measuring technique that permits the remote assessment of vital signs by using cameras. The face is the preferred area of measurement (region of interest: ROI) that has to be selected automatically for convenient application. Most works use common face detection algorithm for this purpose. However, these appro...

Objectives: The inverse relationship between QT interval variability (QTV) and T wave amplitude potentially confounds QT variability assessment. We quantified the influence of the T wave amplitude on QTV in a comprehensive dataset and devised a correction formula. Methods: Three ECG datasets of healthy subjects were analyzed to model the relationsh...

Beat-to-beat variability of the QT interval (QTV) has been used as a marker of repolarization lability and sympathetic activation. The aim of this study was to establish ECG sampling rate requirements for reliable QT interval variability measurement. We measured QTV in high resolution simulated (1000 Hz) and real ECG (1600 Hz; in the supine positio...

Background: Camera-based photoplethysmography (cbPPG) is an optical measurement technique that reveals pulsatile blood flow in cutaneous microcirculation from a distance. cbPPG has been shown to reflect pivotal haemodynamic events like cardiac ejection in healthy subjects. In addition, it provides valuable insight into intrinsic microcirculatory r...

The QT interval in an electrocardiogram (ECG) reflects complex processes affecting the repolarization of ventricular myocardium. Increased QT interval variability (QTV) is thought to be caused by ventricular repolarization lability and has been associated with cardiac mortality. Recent publications have shown that template-based methods are more ro...

Autonomic activity affects beat-to-beat variability of heart rate and QT interval. The aim of this study was to explore whether entropy measures are suitable to detect changes in neural outflow to the heart elicited by two different stress paradigms. We recorded short-term ECG in 11 normal subjects during an experimental protocol that involved head...

We propose a novel method for evaluating the similarity between two 1d patterns. Our method, referred to as two-dimensional signal warping (2DSW), extends the basic ideas of known warping techniques such as dynamic time warping and correlation optimized warping. By employing twodimensional piecewise stretching 2DSW is able to take into account inho...

We propose a novel two-dimensional warping technique to match two one-dimensional patterns. Our approach, referred to as two-dimensional signal warping (2DSW), extends the basic ideas of known warping techniques such as dynamic time warping and correlation optimized warping. By employing two-dimensional piecewise stretching 2DSW is able to capture...

This contribution presents a novel warping method, two-dimensional signal warping (2DSW), for tracking beat-to-beat changes in time intervals from electrocardiograms. To evaluate the efficiency of 2DSW to capture subtle changes in the QT interval we apply 2DSW to the Physionet QT database. It is shown that 2DSW allows highly accurate tracking of QR...