Search

The early detection of neurodevelopmental disorders in newborns is of utmost importance in clinical practice. Recently, to predict the neurodevelopment scores in preterms, Artificial Intelligence (AI) methods have been proposed mainly based on Electroencephalographic (EEG) or heart rate variability (HRV) analysis. In this work, HRV measures of preterm newborns with and without Sepsis are computed and used as input features of AI regression models. The study assesses the reliability of such features in predicting BAYLEY-III scores obtained during the clinical follow-up at 6- and 12-months. Forty-eight preterms (gestational age $27.8{\pm }1.8$ weeks) were involved, 27 of which were diagnosed with Sepsis. HRV analysis was performed on ECG signals recorded at the corrected term age. BAYLEY-III score prediction was implemented, considering HRV features as input predictors of ensemble regression models. Models were validated using the Leave-One-Subject-Out (LOSO) framework. Encouraging results were achieved, with a Mean Absolute Error (MAE) < 5 points for the Sepsis group in the BAYLEY-III cognitive and language scales at 6- and 12-months. Preliminary results suggested that the autonomic nervous system development may be linked to central nervous system maturation. HRV features, and AI regression models could predict alterations that affect the correct neurodevelopment of newborns.

Background and aim: First, to compare somatosensory evoked potentials (SEPs) in preterm newborns without major brain injury studied at term equivalent age (TEA) with a term historical control group. Second, to investigate the impact of pain exposure during the first 28 days after birth on SEPs. Third, to evaluate the association between SEPs and Bayley-III at 2 years corrected age (CA). Methods: Infants born at p < 0.005), adjusting for clinical risk factors. Younger GA and postmenstrual age (PMA) at SEP recording were associated with longer N1 latency and lower N1-P1 amplitude (all p < 0.005). A normal SEP at TEA positively predicted cognitive outcome at 2 years CA (p < 0.005). Conclusion: Pain exposure and prematurity were risk factors for altered SEP parameters at TEA. SEPs predicted cognitive outcome.

During Integrated Multiparametric Neurophysiological Monitoring (IMNA), a newborn with suspected hypoxia at birth and microhaemorrhagic and ischaemic lesions presented some clonic-tonic episodes with specific EEG patterns characterized by rolandic and temporal spikes and the appearance of a unilateral enhanced Somatosensory Evoked Potential (SEP) (10.45 µv). Since the literature does not seem to describe cases of giant SEP in newborns, in this case report, we will discuss the hypotheses underlying this potential. It could be assumed that the ischaemic and haemorrhagic lesions presented by the newborn may have developed as a result of neurotransmitter balance failure. This may be the origin of the EEG picture, which, consequently, could have triggered a potential with high amplitude.

Abstract Objective Prefeed gastric residuals (GRs) monitoring has been correlated with an increased time to reach full feeds and longer parenteral nutrition without beneficial effect on necrotizing enterocolitis (NEC) occurrence. We aimed to assess effects of a new local protocol to provide for the selective evaluation of GRs excluding their routine monitoring. Methods We carried out a retrospective study based on a “before and after” design in a cohort of infants born at 23+0–31+6 weeks of gestation. The primary outcome was the age at full enteral feeding (150 mL/kg/d). Secondary outcomes included age at regaining of birth weight, and evaluation of Z-scores of weight, length, and head circumference at discharge. Results We studied 49 infants in the selective GR group and 59 in the routine GR group. Age at full (150 mL/kg) enteral feeding (17.8 ± 10.1 vs. 22.9 ± 10.5 days, P = 0.017) and regaining of birth weight (11.1 ± 3.0 vs. 12.5 ± 3.5 days, P = 0.039) were lower while the Z-scores of weight at discharge (-1.10 ± 0.83 vs. -1.60 ± 1.45, P = 0.040) were higher in infants in the selective GR group in comparison with infants in the routine GR group. Conclusions Selective monitoring of GRs decreased age at full enteral feeding and at regaining of birth weight and induced better Z-scores of weight at discharge in comparison with routine GR monitoring in a cohort of extremely preterm infants without increasing the incidence of NEC. Omitting prefeed GRs monitoring in clinical practice seems reasonable.

Data in the literature report that latency and morphology in the cutaneous sympathetic skin response (SSR) do not change according to the type of stimulus delivered, unlike the amplitude which shows greater values in relation to the intensity of the physical impact caused in patient. Since the acoustic stimulus represents a method better tolerated by the pediatric patient, the aim of this study is to evaluate the presence or absence of significant differences in SSR between electrical and acoustic stimuli. The SSR was performed for each child of 18 recruited in this study, deriving from the palm of the hand and the sole of the foot and initially delivering an electrical stimulus at the level of the median nerve at the wrist. Two acoustic stimuli were subsequently delivered with the aid of audiometric headphones. Our results show no significant differences for the amplitude values obtained (p values > 0.05). For the latency there was a statistically significant difference (p-value = 0.001) for the left hand, subsequently not confirmed by the comparison performed between the two sides (p-values = 0.28 and 0.56). If these preliminary data are confirmed by a larger sample, the acoustic stimulus could be introduced in a standardized protocol for performing SSR in pediatric patients.

In Neonatal Intensive Care Units (NICUs), the early detection of neonatal seizures is of utmost importance for a timely clinical intervention. Over the years, several neonatal seizure detection systems were proposed to detect neonatal seizures automatically and speed up seizure diagnosis, most based on the EEG signal analysis. Recently, research has focused on other possible seizure markers, such as electrocardiography (ECG). This work proposes an ECG-based NSD system to investigate the usefulness of heart rate variability (HRV) analysis to detect neonatal seizures in the NICUs. HRV analysis is performed considering time-domain, frequency-domain, entropy and multiscale entropy features. The performance is evaluated on a dataset of ECG signals from 51 full-term babies, 29 seizure-free. The proposed system gives results comparable to those reported in the literature: Area Under the Receiver Operating Characteristic Curve = 62%, Sensitivity = 47%, Specificity = 67%. Moreover, the system’s performance is evaluated in a real clinical environment, inevitably affected by several artefacts. To the best of our knowledge, our study proposes for the first time a multi-feature ECG-based NSD system that also offers a comparative analysis between babies suffering from seizures and seizure-free ones.

Abstract Background We studied late preterm and term infants who were admitted to our neonatal care unit in a tertiary hospital for unexpected episodes of cyanosis that occurred during rooming-in for evaluation of their frequency, most frequent associated diseases, and documentation of the diagnostic clinical approach. Methods We carried out a retrospective study of infants with a gestational age ≥35 weeks who were admitted from the nursery with the diagnosis of cyanosis from January 2009 to December 2016. Exclusion criteria were the occurrence of acrocyanosis and the diagnosis of sudden unexpected postnatal collapse (SUPC). Results We studied 49 infants with a mean gestational age of 38 ± 2 weeks. The frequency of admission for cyanosis was 1.8/1000 live births and was similar (p = 0.167) in late preterm and term infants. The majority of episodes occurred during the first 24 h of life (57%). Only 16 infants (33%) were discharged with a diagnosis, that was mostly (n = 5;10%) gastro-esophageal reflux. Conclusions Unexpected episodes of cyanosis caused admission of 1.8/1000 live births to the neonatal care unit without differences between late preterm and term infants. These episodes occurred mainly during the first day of life and infants were mostly discharged without a known diagnosis.