Marcel Młyńczak

Dr. Marcel Młyńczak

Warsaw University of Technology, Faculty of Mechatronics, Institute of Metrology and Biomedical Engineering
orcid

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 January 2022 in Computer Methods and Programs in Biomedicine
Verified
Journal Article
Open access
MRMaciej Rosoł
Maciej Rosoł
MMMarcel Młyńczak
Marcel Młyńczak
GCGerard Cybulski
Gerard Cybulski
Causality defined by Granger in 1969 is a widely used concept, particularly in neuroscience and economics. As there is an increasing interest in nonlinear causality research, a Python package with a neural-network-based causality analysis approach was created. It allows performing causality tests using neural networks based on Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), or Multilayer Perceptron (MLP). The aim of this paper is to present the nonlinear method for causality analysis and the created Python package. The created functions with the autoregressive (AR) and Generalized Radial Basis Functions (GRBF) neural network models were tested on simulated signals in two cases: with nonlinear dependency and with absence of causality from Y to X signal. The train-test split (70/30) was used. Errors obtained on the test set were compared using the Wilcoxon signed-rank test to determine the presence of the causality. For the chosen model, the proposed method of study the change of causality over time was presented. In the case when X was a polynomial of Y, nonlinear methods were able to detect the causality, while the AR model did not manage to indicate it. The best results (in terms of the prediction accuracy) were obtained for the MLP for the lag of 150 (MSE equal to 0.011, compared to 0.041 and 0.036 for AR and GRBF, respectively). When there was no causality between the signals, none of the proposed and AR models did indicate false causality, while it was detected by GRBF models in one case. Only the proposed models gave the expected results in each of the tested scenarios. The proposed method appeared to be superior to the compared methods. They were able to detect non-linear causality, make accurate forecasting and not indicate false causality. The created package enables easy usage of neural networks to study the causal relationship between signals. The neural-networks-based approach is a suitable method that allows the detection of a nonlinear causal relationship, which cannot be detected by the classical Granger method. Unlike other similar tools, the package allows for the study of changes in causality over time.

12 October 2016 in PLOS ONE
Verified
Journal Article
Open access
PDF file
JKJaroslaw Krzywanski
Jaroslaw Krzywanski
TMTomasz Mikulski
Tomasz Mikulski
HKHubert Krysztofiak
Hubert Krysztofiak
MMMarcel Młyńczak
Marcel Młyńczak
EGEwa Gaczynska
Ewa Gaczynska
AZAndrzej Ziemba
Andrzej Ziemba
Vitamin D does not only influence the musculoskeletal health and mineral homeostasis but it also affects cardiovascular, endocrine, nervous, immune and mental functions, thus it is of considerable importance for both physically active people and elite athletes. However, vitamin D deficiency is common worldwide and results from inadequate endogenous skin synthesis (insufficient ultraviolet B exposure) and diet. To improve the vitamin D status elite athletes often travel to lower latitude during winter. The aim of the study was to evaluate the seasonal vitamin D status in Polish elite athletes according to the sun exposure and oral supplementation. Serum concentration of 25-hydroxyvitamin D (25(OH)D) was measured in the years 2010–2014 in 409 elite athletes, who were divided into the following groups: OUTD—outdoor sports, represented by track and field athletes, who trained in Poland; IND—weightlifters, handball and volleyball players who trained indoors in Poland; SUN—track and field athletes who trained during Polish winter in lower latitude with high sunshine exposure; SUPL—track and field athletes who trained in Poland, had an inadequate vitamin D status (25(OH)D < 30 ng/ml) and were supplemented orally. Inadequate Vitamin D status was observed in 80% of OUTD and 84% of IND athletes in winter, whereas in summer the values amounted to 42% and 83%, respectively. The athletes exposed to sun in winter had significantly higher vitamin D concentration than OUTD group. Oral supplementation improved vitamin D concentration by 45%, whereas winter sun exposure caused its increase by 85%. Except for a few summer months an inadequate status of vitamin D was found in the majority of Polish elite athletes, with the deficiency level being similar to the one observed in non-athletic population. The most serious deficiency was observed in indoor disciplines. Adequate vitamin D status can be achieved by both increased sun exposure, especially in winter, and oral supplementation. Athletes should therefore routinely assess their vitamin D status and be educated how to approach their sunlight exposure, diet and supplementation.

16 October 2020 in Diagnostics
Verified
Journal Article
Open access
PDF file
Bartosz HoffmannBartosz Hoffmann
Bartosz Hoffmann
AFAndrew Flatt
Andrew Flatt
LSLuiz Eduardo Silva
Luiz Eduardo Silva
MMMarcel Młyńczak
Marcel Młyńczak
RBRafał Baranowski
Rafał Baranowski
Jakub S. GąsiorJakub S. Gąsior
Jakub S. Gąsior
Research on reliability of heart rate variability (HRV) parameters in athletes has received increasing attention. The aims of this study were to examine the inter-day reliability of short-term (5 min) and ultra-short-term (1 min) heart rate (HR), respiratory rate (RespRate) and HRV parameters, agreement between short-term and ultra-short-term parameters, and association between differences in HR, RespRate and HRV parameters in elite modern pentathletes. Electrocardiographic recordings were performed in stable measurement conditions with a week interval between tests. Relative reliability was evaluated by intra-class correlation coefficients, absolute reliability was evaluated by within-subject coefficient of variation, and agreement was evaluated using Bland–Altman (BA) plot with limits of agreement and defined a priori maximum acceptable difference. Short-term HR, RespRate, log transformed (ln) root mean square of successive normal-to-normal interval differences (lnRMSSD), ln high frequency (lnHF) and SD2/SD1 HRV indices and ultra-short-term HR, RespRate and lnRMSSD presented acceptable, satisfactory inter-day reliability. Although there were no significant differences between short-term and ultra-short-term HR, RespRate and lnRMSSD, no parameter showed acceptable differences with BA plots. Differences in time-domain and non-linear HRV parameters were more correlated with differences in HR than with differences in RespRate. Inverse results were observed for frequency-domain parameters. Short-term HR, RespRate, lnRMSSD, lnHF, and SD2/SD1 and ultra-short-term HR, RespRate and lnRMSSD could be used as reliable parameters in endurance athletes. However, practitioners should interpret changes in HRV parameters with regard to concomitant differences in HR and RespRate and caution should be taken before considering 5 min and 1 min parameters as interchangeable.

1 January 2022 in Journal of Science and Medicine in Sport
Verified
Journal Article
Open access
JKJarosław Krzywański
Jarosław Krzywański
TMTomasz Mikulski
Tomasz Mikulski
HKHubert Krysztofiak
Hubert Krysztofiak
APAndrzej Pokrywka
Andrzej Pokrywka
MMMarcel Młyńczak
Marcel Młyńczak
EKErnest Kuchar
Ernest Kuchar
The aim of the study was to identify predictors determining the course of COVID-19 and antibody response in elite athletes. Observational study. Routine medical screening with physical examination, resting ECG, and laboratory tests including antibody response was performed 12-68 days after the diagnosis of COVID-19 in 111 athletes of different sports. Clinical symptoms were observed in 84% of subjects. The severity of COVID-19 was mild in 82% of athletes and moderate in 2% of cases. Athletes aged above 26 and male were more likely to develop symptomatic COVID-19. Asymptomatic subjects were younger and predominantly female. In 18% of subjects, symptoms were still present 20 (12-68) days (median and range) since positive diagnosis. Antibody response was observed in 88% of athletes, and its magnitude correlated with time since diagnosis of COVID-19 (RT-PCR), fatigue, fever, and conjunctivitis. There were no differences in antibody response between groups distinguished by sports discipline (p=0.50), and sex (p=0.59), and antibody response did not correlate with BMI (p=0.12), age (p=0.13), the number of symptoms (p=0.43) or their duration (p=0.19). The severity of COVID-19 in elite athletes is predominantly mild and without complications. Athletes can return to sport after two symptom-free weeks and additional heart screening is usually not required. Determination of antibodies has been shown to be a useful indicator of a previous COVID-19 disease, and some symptoms can be used as predictors of antibody response.

9 April 2020 in Nutrients
Verified
Journal Article
Open access
PDF file
JKJaroslaw Krzywanski
Jaroslaw Krzywanski
TMTomasz Mikulski
Tomasz Mikulski
APAndrzej Pokrywka
Andrzej Pokrywka
MMMarcel Młyńczak
Marcel Młyńczak
HKHubert Krysztofiak
Hubert Krysztofiak
AZAndrzej Ziemba
Andrzej Ziemba
Background: Athletes and coaches believe in the ergogenic effect of vitamin B12 (which results from enhanced erythropoiesis) and they often insist on its unjustified supplementation. Therefore, our study aimed to assess the vitamin B12 status in Polish elite athletes and its influence on red blood cell parameters. Methods: In total, 1131 blood samples were collected during six years from 243 track and field athletes divided into strength and endurance groups, as well as according to the declared use of vitamin B12 injections. Results: An average vitamin B12 concentration in all subjects was 739 ± 13 pg/mL, with no cases of deficiency. A weak but significant relationship was found between vitamin B12 and hemoglobin concentrations. A significant increase in hemoglobin appeared from very low vitamin B12 concentration and up to approx. 400 pg/mL, while hemoglobin did not significantly change from 700 pg/mL and onwards. Vitamin B12 injections were used by 34% of athletes, significantly more often by endurance than by strength athletes. In athletes who declared no use of injections, a higher concentration of vitamin B12 was observed in the endurance group. Conclusion: The main finding of the present study is the determination of the range of vitamin B12 concentration which may favor better hemoglobin synthesis in athletes. They should regularly monitor vitamin B12 concentration and maintain the range of 400–700 pg/mL as it may improve red blood cell parameters. We might suggest application of a supplementation if necessary. Special attention is required in athletes with a vitamin B12 concentration below 400 pg/mL.

30 October 2018 in Frontiers in Physiology
Verified
Journal Article
Open access
PDF file
MMMarcel Młyńczak
Marcel Młyńczak
HKHubert Krysztofiak
Hubert Krysztofiak
Training of elite athletes requires regular physiological and medical monitoring to plan the schedule, intensity and volume of training, and subsequent recovery. In sports medicine, ECG-based analyses are well-established. However, they rarely consider the correspondence of respiratory and cardiac activity. Given such mutual influence, we hypothesize that athlete monitoring might be developed with causal inference and that detailed, time-related techniques should be preceded by a more general, time-independent approach that considers the whole group of participants and parameters describing whole signals. The aim of this study was to discover general causal paths among cardiac and respiratory variables in elite athletes in two body positions (supine and standing), at rest. ECG and impedance pneumography signals were obtained from 100 elite athletes. The mean heart rate, the root-mean-square difference of successive RR intervals (RMSSD), its natural logarithm (lnRMSSD), the mean respiratory rate (RR), the breathing activity coefficients, and the resulting breathing regularity (BR) were estimated. Several causal discovery frameworks were applied, comprising Generalized Correlations (GC), Causal Additive Modeling (CAM), Fast Greedy Equivalence Search (FGES), Greedy Fast Causal Inference (GFCI), and two score-based Bayesian network learning algorithms: Hill-Climbing (HC) and Tabu Search. The discovery of cardiorespiratory paths appears ambiguous. The main, still mild, rules best supported by data are: for supine - tidal volume causes heart activity variation, which causes average heart activity, which causes respiratory timing; and for standing - normalized respiratory activity variation causes average heart activity. The presented approach allows data-driven and time-independent analysis of elite athletes as a particular population, without considering prior knowledge. However, the results seem to be consistent with the medical background. Causality inference is an interesting mathematical approach to the analysis of biological responses, which are complex. One can use it to profile athletes and plan appropriate training. In the next step, we plan to expand the study using time-related causality analyses.