LMLucie Maršánová

Lucie Maršánová

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Lucie Maršánová has a total of 26 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Brno University of Technology ECG Signal Database with Annotations of P Wave (BUT PDB)

    by Lucie Maršánová, Radovan Smíšek, Andrea Němcová, Lukáš Smital, Martin Vítek

    Background: Brno University of Technology ECG Signal Database with Annotations of P Wave (BUT PDB) is an ECG signal database with marked peaks of P waves created by the cardiology team at the Department of Biomedical Engineering, Brno University of Technology. Results: The database consists of 50 2-minute 2-lead ECG signal records with various types of pathologies. The ECGs were selected from 3 existing databases of ECG signal - MIT-BIH Arrhythmia Database, MIT-BIH Supraventricular Arrhythmia Database and Long Term AF Database. The P waves positions were manually annotated by two ECG experts in all 50 records. Each record contains also dominant diagnosis (pathology) present in the record and annotated positions and types of QRS complexes (from the original database). Conclusion: The database is created for the development, evaluation and objective comparison of P wave detection algorithms.


  • Open Access

    Brno University of Technology Smartphone PPG Database (BUT PPG): Annotated Dataset for PPG Quality Assessment and Heart Rate Estimation

    by Andrea Nemcova, Enikö Vargova, Radovan Smisek, Lucie Marsanova, Lukas Smital, Martin Vitek

    To the best of our knowledge, there is no annotated database of PPG signals recorded by smartphone publicly available. This article introduces Brno University of Technology Smartphone PPG Database (BUT PPG) which is an original database created by the cardiology team at the Department of Biomedical Engineering, Brno University of Technology, for the purpose of evaluating photoplethysmographic (PPG) signal quality and estimation of heart rate (HR). The data comprises 48 10‐second recordings of PPGs and associated electrocardiographic (ECG) signals used for determination of reference HR. The data were collected from 12 subjects (6 female, 6 male) aged between 21 and 61. PPG data were collected by smartphone Xiaomi Mi9 with sampling frequency of 30 Hz. Reference ECG signals were recorded using a mobile ECG recorder (Bittium Faros 360) with a sampling frequency of 1,000 Hz. Each PPG signal includes annotation of quality created manually by biomedical experts and reference HR. PPG signal quality is indicated binary: 1 indicates good quality for HR estimation, 0 indicates signals where HR cannot be detected reliably, and thus, these signals are unsuitable for further analysis. As the only available database containing PPG signals recorded by smartphone, BUT PPG is a unique tool for the development of smart, user‐friendly, cheap, on‐the‐spot, self‐home‐monitoring of heart rate with the potential of widespread using.


  • Real-Time Quality Assessment of Long-Term ECG Signals Recorded by Wearables in Free-Living Conditions

    by Lukas Smital, Clifton R. Haider, Martin Vitek, Pavel Leinveber, Pavel Jurak, Andrea Nemcova, Radovan Smisek, Lucie Marsanova, Ivo Provaznik, Christopher L. Felton, et al.

    Nowadays, methods for ECG quality assessment are mostly designed to binary distinguish between good/bad quality of the whole signal. Such classification is not suitable to long-term data collected by wearable devices. In this paper, a novel approach to estimate long-term ECG signal quality is proposed. The real-time quality estimation is performed in a local time window by calculation of continuous signal-to-noise ratio (SNR) curve. The layout of the data quality segments is determined by analysis of SNR waveform. It is distinguished between three levels of ECG signal quality: signal suitable for full wave ECG analysis, signal suitable only for QRS detection, and signal unsuitable for further processing. The SNR limits for reliable QRS detection and full ECG waveform analysis are 5 and 18 dB respectively. The method was developed and tested using synthetic data and validated on real data from wearable device. The proposed solution is a robust, accurate and computationally efficient algorithm for annotation of ECG signal quality that will facilitate the subsequent tailored analysis of ECG signals recorded in free-living conditions. The field of long-term ECG signals self-monitoring by wearable devices is swiftly developing. The analysis of massive amount of collected data is time consuming. It is advantageous to characterize data quality in advance and thereby limit consequent analysis to useable signals.


  • Open Access

    Advanced P Wave Detection in Ecg Signals During Pathology: Evaluation in Different Arrhythmia Contexts

    by Lucie Maršánová, Andrea Němcová, Radovan Smíšek, Martin Vítek, Lukáš Smital

    Reliable P wave detection is necessary for accurate and automatic electrocardiogram (ECG) analysis. Currently, methods for P wave detection in physiological conditions are well-described and efficient. However, methods for P wave detection during pathology are not generally found in the literature, or their performance is insufficient. This work introduces a novel method, based on a phasor transform, as well as innovative rules that improve P wave detection during pathology. These rules are based on the extraction of a heartbeats’ morphological features and knowledge of heart manifestation during both physiological and pathological conditions. To properly evaluate the performance of the proposed algorithm in pathological conditions, a standard database with a sufficient number of reference P wave positions is needed. However, such a database did not exist. Thus, ECG experts annotated 12 chosen pathological records from the MIT-BIH Arrhythmia Database. These annotations are publicly available via Physionet. The algorithm performance was also validated using physiological records from the MIT-BIH Arrhythmia and QT databases. The results for physiological signals were Se = 98.42% and PP = 99.98%, which is comparable to other methods. For pathological signals, the proposed method reached Se = 96.40% and PP = 85.84%, which greatly outperforms other methods. This improvement represents a huge step towards fully automated analysis systems being respected by ECG experts. These systems are necessary, particularly in the area of long-term monitoring.


  • Multi-stage SVM approach for cardiac arrhythmias detection in short single-lead ECG recorded by a wearable device

    by Radovan Smisek, Jakub Hejc, Marina Ronzhina, Andrea Nemcova, Lucie Marsanova, Jana Kolarova, Lukas Smital, Martin Vitek

    Objective : Use of wearable ECG devices for arrhythmia screening is limited due to poor signal quality, small number of leads and short records, leading to incorrect recognition of pathological events. This paper introduces a novel approach to classification (normal/‘N’, atrial fibrillation/‘A’, other/‘O’, and noisy/‘P’) of short single-lead ECGs recorded by wearable devices. Approach : Various rhythm and morphology features are derived from the separate beats (‘local’ features) as well as the entire ECGs (‘global’ features) to represent short-term events and general trends respectively. Various types of atrial and ventricular activity, heart beats and, finally, ECG records are then recognised by a multi-level approach combining a support vector machine (SVM), decision tree and threshold-based rules. Main results : The proposed features are suitable for the recognition of ‘A’. The method is robust due to the noise estimation involved. A combination of radial and linear SVMs ensures both high predictive performance and effective generalisation. Cost-sensitive learning, genetic algorithm feature selection and thresholding improve overall performance. The generalisation ability and reliability of this approach are high, as verified by cross-validation on a training set and by blind testing, with only a slight decrease of overall F1-measure, from 0.84 on training to 0.81 on the tested dataset. ‘O’ recognition seems to be the most difficult (test F1-measures: 0.90/‘N’, 0.81/‘A’ and 0.72/‘O’) due to high inter-patient variability and similarity with ‘N’. Significance : These study results contribute to multidisciplinary areas, focusing on creation of robust and reliable cardiac monitoring systems in order to improve diagnosis, reduce unnecessary time-consuming expert ECG scoring and, consequently, ensure timely and effective treatment.


  • Assessment of ECG Signal Quality After Compression

    by Andrea Němcová, Martin Vítek, Lucie Maršánová, Radovan Smíšek, Lukáš Smital

  • Automatic Detection of P Wave in ECG During Ventricular Extrasystoles

    by Lucie Maršánová, Andrea Němcová, Radovan Smíšek, Tomáš Goldmann, Martin Vítek, Lukáš Smital


  • Open Access

    ECG features and methods for automatic classification of ventricular premature and ischemic heartbeats: A comprehensive experimental study

    by Lucie Maršánová, Marina Ronzhina, Radovan Smíšek, Martin Vítek, Andrea Němcová, Lukas Smital, Marie Nováková

    Accurate detection of cardiac pathological events is an important part of electrocardiogram (ECG) evaluation and subsequent correct treatment of the patient. The paper introduces the results of a complex study, where various aspects of automatic classification of various heartbeat types have been addressed. Particularly, non-ischemic, ischemic (of two different grades) and subsequent ventricular premature beats were classified in this combination for the first time. ECGs recorded in rabbit isolated hearts under non-ischemic and ischemic conditions were used for analysis. Various morphological and spectral features (both commonly used and newly proposed) as well as classification models were tested on the same data set. It was found that: a) morphological features are generally more suitable than spectral ones; b) successful results (accuracy up to 98.3% and 96.2% for morphological and spectral features, respectively) can be achieved using features calculated without time-consuming delineation of QRS-T segment; c) use of reduced number of features (3 to 14 features) for model training allows achieving similar or even better performance as compared to the whole feature sets (10 to 29 features); d) k-nearest neighbours and support vector machine seem to be the most appropriate models (accuracy up to 98.6% and 93.5%, respectively).


  • CSE database: extended annotations and new recommendations for ECG software testing

    by Radovan Smíšek, Lucie Maršánová, Andrea Němcová, Martin Vítek, Jiří Kozumplík, Marie Nováková

    Nowadays, cardiovascular diseases represent the most common cause of death in western countries. Among various examination techniques, electrocardiography (ECG) is still a highly valuable tool used for the diagnosis of many cardiovascular disorders. In order to diagnose a person based on ECG, cardiologists can use automatic diagnostic algorithms. Research in this area is still necessary. In order to compare various algorithms correctly, it is necessary to test them on standard annotated databases, such as the Common Standards for Quantitative Electrocardiography (CSE) database. According to Scopus, the CSE database is the second most cited standard database. There were two main objectives in this work. First, new diagnoses were added to the CSE database, which extended its original annotations. Second, new recommendations for diagnostic software quality estimation were established. The ECG recordings were diagnosed by five new cardiologists independently, and in total, 59 different diagnoses were found. Such a large number of diagnoses is unique, even in terms of standard databases. Based on the cardiologists’ diagnoses, a four-round consensus (4R consensus) was established. Such a 4R consensus means a correct final diagnosis, which should ideally be the output of any tested classification software. The accuracy of the cardiologists’ diagnoses compared with the 4R consensus was the basis for the establishment of accuracy recommendations. The accuracy was determined in terms of sensitivity = 79.20–86.81%, positive predictive value = 79.10–87.11%, and the Jaccard coefficient = 72.21–81.14%, respectively. Within these ranges, the accuracy of the software is comparable with the accuracy of cardiologists. The accuracy quantification of the correct classification is unique. Diagnostic software developers can objectively evaluate the success of their algorithm and promote its further development. The annotations and recommendations proposed in this work will allow for faster development and testing of classification software. As a result, this might facilitate cardiologists’ work and lead to faster diagnoses and earlier treatment.


  • Classification of ventricular premature and ischemic beats in animal electrograms

    by Marina Ronzhina, Lucie Marsanova, Radovan Smisek, Veronika Olejnickova, Oto Janousek, Petr Vesely, Jana Kolarova, Marie Novakova, Ivo Provaznik

    Many approaches have been proposed for automatic classification of different pathological events in ECG signals. Present study is focused on analysis and classification of non-ischemic, moderate and severe ischemic, and VPB segments in data obtained in rabbit isolated hearts. It is shown, that use of low number of morphological parameters calculated from electrograms combined with even simple classification method allows achieving of accurate results (with overall accuracy up to 0.99) for four types of the segments.