Gerard Cybulski

Reliable detection of event-related potentials (ERPs) at the single-trial level remains a challenge due to low signal-to-noise ratio and high variability in electroencephalography (EEG) recordings. This work investigates the use of the Deep-Match framework (Deep-MF) for ERP detection. We examine whether incorporating prior knowledge of an ERP template into deep learning models improves detection performance. As a proof-of-concept study, the framework was evaluated on a single dataset with multi-channel EEG recordings during laser stimulation. The model was trained in two stages. First, an encoder–decoder architecture was trained to reconstruct input EEG signals in order to learn compact signal representations. In the second stage, the decoder was replaced with a detection module and the network was fine-tuned for ERP identification. Two model variants were evaluated: a standard model with randomly initialized filters and a Deep-MF model in which input kernels were initialized using ERP templates. Models performance was assessed on a single-trial ERP detection task during leave-one-out validation, and then compared with matched filter detector. The neural network models outperformed the matched filter detector and proposed that the Deep-MF model slightly outperformed the detector with standard kernel initialization for the majority of held-out subjects. Although both approaches exhibited substantial inter-subject variability, Deep-MF achieved a higher average F1-score (0.37) compared to the standard network (0.34), indicating improved robustness to cross-subject differences. Performance varied considerably across participants. The best performance obtained by Deep-MF reached an F1-score of 0.71, exceeding the maximum score achieved by the standard model (0.59). These results showed that ERP-informed kernel initialization provides improvements in single-trial ERP detection under subject-independent evaluation. These findings demonstrate that integrating domain knowledge with deep learning architectures can improve single-trial ERP detection. The proposed approach provides a step towards practical wearable EEG and passive brain–computer interface applications, as well as towards real-time monitoring of cognitive processes.

Background: Bioimpedance measurement is a noninvasive diagnostic method that enables the assessment of the condition of internal organs and their activity by recording changes in impedance of the examined body area. One of the bioimpedance techniques that allows the evaluation of cardiac mechanical activity, including the estimation of stroke volume, is impedance cardiography (ICG). Purpose: The aim of this project was to create a computer program written in widespread Java, a versatile language, valued for its reliability, scalability, and built-in features that optimize application performance. The application dedicated to mobile devices, written using the Android Studio environment, enables visualization of ICG signals simultaneously with one channel of electrocardiographic signal (ECG) and allows the preliminary analysis of basic hemodynamic parameters. Methods: The signal analysis included determination of heart rate (HR), stroke volume (SV), cardiac output (CO), and left ventricular ejection time (LVET). Discussion and Conclusions: The program allows the user the quick visual check of the recorded signal quality, browse the traces and manually select the characteristic points on the ECG and ICG waveforms, which are then used to calculate the ICG-derived cardiac parameters. It may be used to visualize ECG and ICG signals by anyone, who could enter ICG data formatted in three text columns where each row reflects a sample of ECG, first derivative of ICG signal (dz/dt) and basic impedance (Z0).

Impedance cardiography is a non-invasive method for assessing the activity of the cardiovascular system. Despite some simplifications of the physical model used in the determination of several hemodynamic parameters, it is a constantly evolving non-invasive method with potential ambulatory and/or clinical applications in cardiac diagnostics and treatment support. Besides its applications in cardiology, this method might be used as an auxiliary tool in assisting the diagnosis of psychiatric disorders or hormonal imbalances. This highlights the potential importance of impedance cardiography as an area of research worth further development in terms of metrological and qualitative approaches, leading to the acceptance of this method in clinical/ambulatory practice. The review was created to present information on the results of studies conducted in recent years, which describe the current state of knowledge regarding cardiac and new areas of application for the impedance cardiography method.

Photoplethysmography is a non-invasive physical method used for monitoring arterial blood flow in the subject's body by measuring the amount of light absorbed or reflected by the pulsatile blood flow within the vessels. It is commonly used in wearable devices, primarily for pulse measurement. In ambulatory and clinical practice, it is implemented in pulse oximetry for the estimation of pulse and blood oxygen saturation levels. However, this method has the potential for a much broader range of measurements, such as detecting atrial fibrillation episodes. Innovative applications of this field continue to emerge in the analysis of the cardiovascular system, along with the implementation of new technological solutions aimed at analyzing and improving signal quality. Thus, we have decided to collect information on the current advancements in the field of photoplethysmography. Also, the aim of this mini-review was to bring closer non-obvious applications of photoplethysmography and its development prospects.

Photoplethysmography is a non-invasive physical method used for measurement and monitoring of arterial blood flow in the subject's body with application of light. Pulse oximetry is the modification of photoplethysmography enriched with monitoring blood oxygen saturation. Acquisition of pulse oximetry data can be achieved using two types of pulse oximeters: transmission or reflectance. Both methods require the use of physical light sources and a receiver, set in specific positions. This results in different construction of devices and may lead to diverse ways of calculating the blood saturation values. One of these ways uses second-degree polynomial made from three constants and a variable calculated with ratio of red- to infrared-based variables. We used this method to develop the wireless pulse oximeter paired with the dedicated mobile application. The device acquired 400 samples per second and calculated oxygen saturation level and heart rate, as well as provided data for photoplethysmography curve. In this system data are transferred in real time to the application, which displays the saturation values and presents photoplethysmography curve for last several heartbeats. Calculation of the values was checked with a commercial pulse oximeter and the results were mostly similar, with the difference in SpO2 not greater than one percentage point and the difference in heart rate not greater than five beats per minute. The design of the pulse oximeter allows further miniaturization. Mobile application is intuitive for user and does not need any training.

Assessment of autonomic nervous system (ANS) functioning may be performed non-invasively using autonomic tests which are based on evaluation of response of cardiovascular system to the applied stimuli, such as increased air pressure during Valsalva maneuver, skeletal muscle contraction during static handgrip or deep slow breathing. The cardiovascular response depends, besides ANS reaction and test protocol, also on the way stimulus is self-applied by the test subject. We present a versatile device for controlling stimulus self-application during three ANS tests: Valsalva maneuver, static handgrip, and deep breathing. It integrates two different gauges and a pace setter for breathing into one device. The core of the device is a linear LED display which, using green, yellow, and red diodes, informs the subject about the correctness of self-application of respective stimulus. The settings of the device can be adjusted to the needs of the protocol chosen. The device can record the duration of mouth air pressure or the force produced by the subject during ANS tests, which assures correctness of the tests, thus allowing to track individual variability changes in the response to the test. The device was verified during ANS tests and its use was intuitive for patients, reducing the time needed for training before tests and decreasing the effort of the physician.