A dilated inception CNN-LSTM network for fetal heart rate estimation.

Objective. Fetal heart rate (HR) monitoring is routinely used during pregnancy and labor to assess fetal well-being. The noninvasive fetal electrocardiogram (ECG), obtained by electrodes on the maternal abdomen, is a promising alternative to standard fetal monitoring. Subtraction of the maternal ECG from the abdominal measurements results in fetal ECG signals, in which the fetal HR can be determined typically through R-peak detection. However, the low signal-to-noise ratio and the nonstationary nature of the fetal ECG make R-peak detection a challenging task.Approach. We propose an alternative approach that instead of performing R-peak detection employs deep learning to directly determine the fetal HR from the extracted fetal ECG signals. We introduce a combination of dilated inception convolutional neural networks (CNN) with long short-term memory networks to capture both short-term and long-term temporal dynamics of the fetal HR. The robustness of the method is reinforced by a separate CNN-based classifier that estimates the reliability of the outcome.Main results. Our method achieved a positive percent agreement (within 10% of the actual fetal HR value) of 97.3% on a dataset recorded during labor and 99.6% on set-A of the 2013 Physionet/Computing in Cardiology Challenge exceeding top-performing state-of-the-art algorithms from the literature.Significance. The proposed method can potentially improve the accuracy and robustness of fetal HR extraction in clinical practice.

Deep Convolutional Long Short-Term Memory Network for Fetal Heart Rate Extraction.

Fetal electrocardiography is a valuable alternative to standard fetal monitoring. Suppression of the maternal electrocardiogram (ECG) in the abdominal measurements, results in fetal ECG signals, from which the fetal heart rate (HR) can be determined. This HR detection typically requires fetal R-peak detection, which is challenging, especially during low signal-to-noise ratio periods, caused for example by uterine activity. In this paper, we propose the combination of a convolutional neural network and a long short-term memory network that directly predicts the fetal HR from multichannel fetal ECG. The network is trained on a dataset, recorded during labor, while the performance of the method is evaluated both on a test dataset and on set-A of the 2013 Physionet /Computing in Cardiology Challenge. The algorithm achieved a positive percent agreement of 92.1% and 98.1% for the two datasets respectively, outperforming a top-performing state-of-the-art signal processing algorithm.

Enhancement of low-quality fetal electrocardiogram based on time-sequenced adaptive filtering.

Extraction of a clean fetal electrocardiogram (ECG) from non-invasive abdominal recordings is one of the biggest challenges in fetal monitoring. An ECG allows for the interpretation of the electrical heart activity beyond the heart rate and heart rate variability. However, the low signal quality of the fetal ECG hinders the morphological analysis of its waveform in clinical practice. The time-sequenced adaptive filter has been proposed for performing optimal time-varying filtering of non-stationary signals having a recurring statistical character. In our study, the time-sequenced adaptive filter is applied to enhance the quality of multichannel fetal ECG after the maternal ECG is removed. To improve the performance of the filter in cases of low signal-to-noise ratio (SNR), we enhance the ECG reference signals by averaging consecutive ECG complexes. The performance of the proposed augmented time-sequenced adaptive filter is evaluated in both synthetic and real data from PhysioNet. This evaluation shows that the suggested algorithm clearly outperforms other ECG enhancement methods, in terms of uncovering the ECG waveform, even in cases with very low SNR. With the presented method, quality of the fetal ECG morphology can be enhanced to the extent that the ECG might be fit for use in clinical diagnostics. Graphical abstract The extracted fetal ECG signals from non-invasive abdominal recordings still contain a substantial amount of noise. The time-sequenced adaptive filter provides a relatively accurate estimate of the underlying fetal ECG signal when the quality of the reference channels is enhanced prior to filtering.

[Exercised-induced asthma in soccer players ages from 8 to 13 years]. / Anstrengungsinduziertes Asthma bei Fussballspielern im Alter von 8 bis 13 Jahren.

The purpose of this study was the detection of exercise induced asthma in soccer players aged 8-13 years. Thirty boys, 8-13 years old participated in the study. They were coming from an athletic team of north of Thessaloniki. The study included clinical examination, administration of a respiratory health questionnaire and the exercise -- free running -- test with spirometric measurements. Spirometric measurements were performed by using a microspirometer, before exercise and 2, 5, 10, 15 and 30 min after a 6 min free running exercise (80 - 90 % max heart rate). The highest forced expiratory volume in one second (FEV (1)) value before exercise was compared with the lowest of post exercise values. The results showed a decline in FEV (1) > 15 % in 12 out of 30 children. Particularly, decline in FEV (1) was present in 1 (11 %) out of 9 children with free personal medical history but positive family history for asthma, in 3 (25 %) out of 12 children with allergies, and in 8 (89 %) out of 9 children with asthma. Symptoms were reported by 9 of 12 children with fall in FEV (1) > 15 %, during the 6 min exercise test, who had no symptoms during the soccer games. Identification of EIA by exercise challenge test in young athletes is a useful component for the diagnosis of bronchial hyperresponsiveness. Similar studies should be performed on older and younger athletes who participate in different sports and games.

Standardization of the motor scales of the Griffiths Test II on children aged 3 to 6 years in Greece.

AIMS: The present study aimed at the standardization of the motor scales (A-locomotor and D-eye-hand co-ordination) of the Griffiths Test II on Greek preschool-aged children. PARTICIPANTS: Nine hundred and thirty children living in Northern Greece were assessed (455 boys and 475 girls), aged from 37 to 72 months (3-6 years old). RESULTS: Percentile ranks were determined depending on the developmental quotient and the chronological age of the child. Through the present application of the Griffiths Test to the children in our country, we showed that the average developmental quotients of the two scales were higher than the relevant published quotients of the Griffiths Test II. DISCUSSION: Some of the factors that may have contributed to faster motor development are passage of time and the environmental and cultural differences between countries. The findings reinforce the need for standardization of a test before it is applied to the population of a country, and its re-standardization on the population of the country where it was first applied.

Gross and fine motor skills of left-handed preschool children.

From a population of 765 preschool children 4-6 years old, 31 children (4.1%) were identified as left-handers. Using the two motor subscales A (gross motor) and D (fine motor) of the Griffiths Test No. II, these children were compared with 31 right-handers, matched for age, sex, and preschool attended. Right-handed children received higher quotients than left-handed on both Griffiths' subscales, with a significant difference only on Scale D. However, the differences between right- and left-handed children arose from the poorer performance of left-handed boys on fine motor tasks (Scale D). These differences could be responsible for learning difficulties that left-handed children face later at school. Such difficulties should be identified as early as possible to facilitate psychoeducational intervention in preschool programs.

Dietary intakes and food habits of adolescents in northern Greece.

The purpose of this study was to assess the dietary intakes and food habits of 582 adolescents in Northern Greece. Anthropometric data have been collected for all the participating adolescents. The prevalence of obesity as determined by both body mass index (BMI) and triceps skinfold thickness (TST) was higher for boys than for girls. Furthermore, boys had higher energy and macronutrient intakes compared to girls. Of total energy intake, 41% for boys and 43% for girls was derived from fat. Energy intake was found adequate whereas fat intake was much higher than recommended. A percentage of adolescents also had lower than recommended iron, vitamin A, folate and zinc intakes, showing an unbalanced diet.