AIM:This study investigated central autonomic network maturation deviations using a previously defined machine learning model set to estimate a functional maturation age (FMA) from heart rate variability (HRV) analysis. We investigated whether these deviations were associated with maternal, fetal, perinatal, or postnatal complications and with neurodevelopment at 2 years of age. METHODS:Differences (ΔHRV) between post-menstrual age (PMA) and FMA were measured in a multicenter prospective cohort of 132 preterm infants born < 30 weeks gestational age (GA). The relationship between ΔHRV and clinical factors, occurrence of complications or alterations in neurodevelopment assessed by Ages and Stages Questionnaire (ASQ) at 2 years of age was studied. RESULTS:ΔHRV expressed in weeks delay at 34 weeks of PMA was greater when GA was lower (3 IQR 2.3-3.9) at 24-26 versus 1.3 (IQR 0.8-2.4) at 28-30 weeks GA (p < 0.0001), in cases of bronchopulmonary dysplasia (p < 0.0001) or patent ductus arteriosus (p < 0.0001). ΔHRV was also associated with altered social skills at 2 years of age (OR 2.05, 95% CI 1.02; 4.14 for each week, p < 0.05) but not with ASQ total score (p = 0.06). CONCLUSION:ΔHRV, early and non-invasively estimated, depends on GA, perinatal and postnatal complications. Its assessment could contribute to evaluation of neurodevelopmental risk.

Late-onset sepsis affects between 10 to 25% of very premature babies, standing as a primary contributor to neonatal mortality. In this paper, we present an innovative approach that relies solely on the analysis of newborns’ motion, derived from the processing of videos acquired in neonatal intensive care units, for several consecutive days. Among a group of 16 very premature newborns, consisting of 8 sepsis and 8 control subjects, we initially extract 14 distinct motion features, in a total of 2636 hours of video recordings. These features are processed through a fusion of fuzzy spatio-temporal coding and smoothed principal component analysis. It leads to 16 trajectories, one per newborn, positioned differently in a 2D plane. They are then compared across parameters such as position, speed, and acceleration. Our findings underscore significant differences in 8 trajectory parameters between sepsis and control newborns. Finally, unsupervised classification was used to separate infected and healthy newborns using these parameters, achieving an accuracy of 81.3%.Clinical relevance— This approach offers a non invasive video-based motion method for early sepsis detection in premature newborns, enabling timely interventions and potentially improving neonatal outcomes.

Monitoring sleep of premature infants is a vital aspect of clinical care, as it can reveal potential future pathologies and health issues. This study presents a novel approach to automatically estimate and track Quiet Sleep (QS) in 33 newborns using ECG, respiration, and video motion features. Using an annotated dataset from 15 neonates (10 preterm, 5 full-term) encompassing 127.2 hours, a comprehensive feature extraction and selection process was employed. Three classifiers (Random Forest, Logistic Regression, K-Nearest Neighbors) were evaluated to develop a QS estimation model. A compact and interpretable model was selected, achieving a balanced accuracy of 84.6 $\pm$ 7.5% . The robustness of the model was further enhanced by incorporating a switching mechanism between models using only ECG and respiration when video data was unavailable. The study further explored the evolution of QS during hospitalization using a large dataset with 18 newborns (16 preterm and 2 term) and 1396.6 hours of data. It highlighted an increase in QS duration and mean interval duration with post-menstrual age. The results offer valuable insights into the developmental progress of healthy preterm infants and underscore the potential of continuous, non-invasive monitoring in neonatal intensive care units.

BACKGROUND:There is a growing concern about the potential role of environmental exposure in congenital male anomalies. OBJECTIVE:We aimed to assess the association between the domestic use of products containing solvents or pesticides during pregnancy and the risk of hypospadias in the offspring. METHODS:We included newborns from the PENEW case-control study, which took place in Brittany, France, from October 2012 to December 2018. Newborns affected with hypospadias (n = 100) were matched with one to four controls (n = 283) according to the biological sex assigned at birth, center of birth, year, and season of birth. We assessed self-reported domestic exposure to solvents (cosmetics, house cleaning, and home renovation products) and pesticides (used indoors and outdoors) through a maternal questionnaire at birth. We performed multivariable conditional logistic regression, adjusting for potential confounders. RESULTS:The self-reported use of indoor pesticides during pregnancy was associated with an increased risk of hypospadias in offspring (adjusted odds ratio [aOR] = 2.68, 95% CI = 1.5, 4.81), especially those against wood insects (aOR = 13.19, 95% CI = 1.11, 59.57), rodents (aOR = 4.61, 95% CI = 1.03, 20.7), and flying and crawling insects (aOR = 2.77, 95% CI = 1.46, 5.28). Other studies have shown that domestic exposure was not statistically significantly associated with a risk of hypospadias. CONCLUSION:The use of indoor pesticides during pregnancy may be associated with a higher risk of hypospadias in offspring, especially those against flying and crawling insects. Further studies might be needed to identify specific molecules to target and confirm our results on a larger sample.

In this paper, we present a new non-contact strategy to estimate the respiratory rate (RR) in a neonatal intensive care unit (NICU) based on the Eulerian motion video magnification technique and a 3D Convolutional Neural Network (3D CNN). The magnification procedure was carried out using the Hermite decomposition. The RR is estimated using a 3D CNN and a region of interest (ROI) detected manually. We have tested the method on 8 infants in NICU during quiet sleep. A contact respiratory signal is acquired synchronously to the videos to compute the RR as reference for training the CNN. To compare the performance of the method, we compute the Mean Absolute Error, the Root Mean Squared Error and metrics from the Bland and Altman analysis to investigate the agreement of the method with respect to the respiratory signal reference. The proposed solution shows an agreement with respect to the reference of 95% and root mean squared error of 2.88.

Background: Hypospadias is a male genital tract defect for which an increase in prevalence has been documented over the last few decades. A role for environmental risk factors is suspected, including prenatal exposure to pesticides. Objectives: To study the risk of hypospadias in association with multiple pesticide measurements in meconium samples. Methods: The Brittany Registry of Congenital Anomalies (France) conducted a case–control study between 2012 and 2018. Cases were hypospadias, ascertained by a pediatrician and a pediatric surgeon, excluding genetic conditions, following European Surveillance of Congenital Anomalies guidelines (N = 69). Controls (N = 135) were two male infants without congenital anomaly born after each case in the same maternity unit. Mothers in the maternity units completed a self-administered questionnaire, we collected medical data from hospital records, and medical staff collected meconium samples. We performed chemical analysis of 38 pesticides (parent compound and/or metabolite) by UHPLC/MS/MS following strict quality assurance/quality control criteria and blind to case–control status. We carried out logistic regression accounting for frequency-matching variables and major risk factors. Results: Among the 38 pesticides measured, 16 (42%) were never detected in the meconium samples, 18 (47%) were in <5% of samples, and 4 (11%) in ≥5% of the samples. We observed an association between the detection of fenitrothion in meconium and the risk of hypospadias (OR = 2.6 [1.0–6.3] with n cases = 13, n controls = 21), but not the other pesticides. Conclusions: Our small study provides a robust assessment of fetal exposure. Fenitrothion’s established antiandrogenic activities provide biologic plausibility for our observations. Further studies are needed to confirm this hypothesis.

BACKGROUND:Neonatal sepsis is responsible for significant morbidity and mortality worldwide. Its accurate and timely diagnosis is hindered by vague symptoms and the urgent necessity for early antibiotic intervention. The gold standard for diagnosing the condition is the identification of a pathogenic organism from normally sterile sites via laboratory testing. However, this method is resource-intensive and cannot be conducted continuously. OBJECTIVE:This study aimed to predict the onset of late-onset sepsis (LOS) with good diagnostic value as early as possible using non-invasive biosignal measurements from neonatal intensive care unit (NICU) monitors. METHODS:In this prospective multicenter study, we developed a multimodal machine learning algorithm based on a convolutional neural network (CNN) structure that uses the power spectral density (PSD) of recorded biosignals to predict the onset of LOS. This approach aimed to discern LOS-related pathogenic spectral signatures without labor-intensive manual artifact removal. RESULTS:The model achieved an area under the receiver operating characteristic score of 0.810 (95 % CI 0.698-0.922) on the validation dataset. With an optimal operating point, LOS detection had 83 % sensitivity and 73 % specificity. The median early detection was 44 h before clinical suspicion. The results highlighted the additive importance of electrocardiogram and respiratory impedance (RESP) signals in improving predictive accuracy. According to a more detailed analysis, the predictive power arose from the morphology of the electrocardiogram's R-wave and sudden changes in the RESP signal. CONCLUSION:Raw biosignals from NICU monitors, in conjunction with PSD transformation, as input to the CNN, can provide state-of-the-art prediction performance for LOS without the need for artifact removal. To the knowledge of the authors, this is the first study to highlight the independent and additive predictive potential of electrocardiogram R-wave morphology and concurrent, sudden changes in the RESP waveform in predicting the onset of LOS using non-invasive biosignals.

Background: Prematurity is one of the risk factors for sudden unexpected infant death (SUID), a phenomenon that remains poorly explained. Materials and methods: The analysis of speci fic factors associated with SUID among very premature infants (VPI) was performed through a retrospective review of data collected in the French SUID registry from May 2015 to December 2018. The factors associated with SUID among VPI were compared with those observed among full -term infants (FTI). Results are expressed as means (standard deviation [SD]) or medians (interquartile range [IQR)]. Results: During the study period, 719 cases of SUID were included in the registry, 36 (incidence: 0.60 %) of which involved VPI (gestational age: 29.2 [2] weeks, 1157 [364]) g] and 313 (0.18 %) involved FTI (gestational age: 40 [0.8] weeks, 3298 [452] g). The infants ' postnatal age at the time of death was similar in the two groups: 15.5 (12.2 -21.8) vs. 14.5 (7.1 -23.4) weeks. We observed low breastfeeding rates and a high proportion of fathers with no occupation or unemployment status among the VPI compared to the FTI group (31% vs. 55 %, p = 0.01 and 32% vs. 13 %, p = 0.05, respectively). Among the VPI, only 52 % were in supine position, and 29 % were lying prone at the time of the SUID (compared to 63 % and 17 %, respectively, in the FTI group). Conclusion: This study con firms prematurity as a risk factor for SUID with no difference in the SUID-speci fic risk factors studied except for breastfeeding and socioeconomic status of the fathers. VPI and FTI died at similar chronological ages with a high proportion of infants dying in prone position. These results argue for reinforcement of prevention strategies in cases of prematurity. f (c) 2024 Published by Elsevier Masson SAS on behalf of French Society of Pediatrics.

Training novice ophthalmology residents on the EyeSi® simulator increases cataract surgery safety. However, there is no consensus regarding how much training residents should perform before their first time on patients. We evaluated the French national training program through the analysis of the learning curves of novice residents. This prospective multicentric pedagogic study was conducted with French novice residents. Each resident completed the recommended four two-hour training sessions and performed a standardized assessment simulating standard cataract surgery before the first session (A0), at the end of the first (A1), second (A2), third (A3) and fourth (A4) sessions. For each surgical step of each attempt, the following data were collected: score, odometer, completion time, posterior capsular rupture and cumulative energy delivered (ultrasounds) during phacoemulsification. A performance threshold was set at a score of 80/100 for each surgical step, 400/500 for the overall procedure. Only descriptive statistics were employed. Sixteen newly nominated ophthalmology residents were included. Median score progressively increased from 95 [IQR 53; 147]) at A0 to 425 [IQR 411; 451] at A4. Despite a significant progression, the “emulsification” step had the lowest A4 scores 86 [IQR 60; 94] without reduction in completion time, odometer or ultrasounds delivered. The rate of posterior capsular rupture decreased linearly from 75

Abstract Background Preterm birth is a major health issue due to its potential outcomes and socioeconomic impact. Prenatal counseling is of major importance for parents because it is believed that the risk of preterm birth is associated with a higher parental mental burden. Nowadays in France, the content and delivery of antenatal counseling is based on personal experience since there is a lack of official guidelines. The goal of the study was to evaluate maternal perception of antenatal information delivered in the setting of preterm births. Methods A qualitative study was performed using semi-structured individual interviews of 15 mothers with a child born > 26–34 GW. Data analysis was based on a constant comparative method. Results Concerning prenatal counseling content, parents wanted to be informed of their role in the care of their preterm child more so than statistics that were not always considered relevant. Parents’ reactions to the announcement of the risk of a preterm birth was dominated by stupefaction, uncertainty and anxiety. When it comes to the setting of prenatal counseling, patients’ room was deemed an appropriate setting by parents and ideally the presence of a coparent was appreciated as it increased patients’ understanding. The physicians’ attitude during the counseling was considered appropriate and described as empathic and optimistic. The importance of support throughout the hospitalization in the form of other parents’ experiences, healthcare professionals and the possibility to preemptively visit the NICU was emphasized by participants. Delivery experience was dominated by a sense of uncertainty, and urgency. Some leads for improvement included additional support of information such as virtual NICU visit; participants also insisted on continuity of care and the multidisciplinary aspect of counseling (obstetrician, neonatologist, midwife, nurse, lactation consultant and psychologist). Conclusion Highlighting parents’ expectations about prenatal counseling could lead to the establishment of overall general guidelines. However, some topics like the use of statistics and mentioning the risk of death underline the importance of a personalized information.

BACKGROUND:The cardiotoxicity of prenatal exposure to mercury has been suggested in populations having regular contaminated seafood intake, though replications in the literature are inconsistent. METHODS:The Timoun Mother-Child Cohort Study was set up in Guadeloupe, an island in the Caribbean Sea where seafood consumption is regular. At seven years of age, 592 children underwent a medical examination, including cardiac function assessment. Blood pressure (BP) was taken using an automated blood pressure monitor, heart rate variability (HRV, 9 parameters) and electrocardiogram (ECG) characteristics (QT, T-wave parameters) were measured using Holter cardiac monitoring during the examination. Total mercury concentrations were measured in cord blood at birth (median = 6.6 μg/L, N = 399) and in the children's blood at age 7 (median = 1.7 μg/L, N = 310). Adjusted linear and non-linear modelling was used to study the association of each cardiac parameter with prenatal and childhood exposures. Sensitivity analyses included co-exposures to lead and cadmium, adjustment for maternal seafood consumption, selenium and polyunsaturated fatty acids (n3-PUFAs), and for sporting activity. RESULTS:Higher prenatal mercury was associated with higher systolic BP at 7 years of age (βlog2 = 1.02; 95% Confidence Interval (CI) = 0.10, 1.19). In boys, intermediate prenatal exposure was associated with reduced overall HRV and parasympathetic activity, and longer QT was observed with increasing prenatal mercury (βlog2 = 4.02; CI = 0.48, 7.56). In girls, HRV tended to increase linearly with prenatal exposure, and no association was observed with QT-wave related parameters. Mercury exposure at 7 years was associated with decreased BP in girls (βlog2 = -1.13; CI = -2.22, -0.004 for diastolic BP). In boys, the low/high-frequency (LF/HF) ratio increased for intermediate levels of exposure. CONCLUSION:Our study suggests sex-specific and non-monotonic modifications in some cardiac health parameters following prenatal exposure to mercury in pre-pubertal children from an insular fish-consuming population.

Cataract surgery is the most common surgical procedure performed in France. While the incidence of intraoperative complications affecting visual prognosis is extremely low, given the large number of patients operated on, the absolute number of patients affected by complications is quite high. Complication rates are significantly higher when ophthalmology residents (ORs) perform the surgery. Although lack of experience remains the main risk factor, sleep deprivation may adversely affect ORs’ successful surgery rate. The value of the EyeSi® surgical simulator in initial training has been demonstrated to increase cataract surgery safety through the transfer of surgical skills from the simulator to the operating room. However, there is no consensus regarding how much training is needed before the first-time ORs are allowed to operate. There is also no scientific evidence that sleep deprivation is associated with a decrease in surgical performance. Establishing a validated protocol for cataract surgery training using the EyeSi surgical simulator (referred to further as the EyeSi) and identifying risk factors for intraoperative complications related to sleep deprivation will improve cataract surgery safety and lead to the reorganization of our healthcare systems. This multi-centre educational cohort study will include two distinct axes which will both aim to reduce the risks of cataract surgery. Enrollment will include 16 first-year ORs for Axis 1 and 25 experienced residents for Axis 2, all from the University Hospitals of Nantes, Tours, Angers and Rennes. Axis 1 will focus on investigating the learning curve of first-year ORs using the EyeSi, following the training program recommended by the “College des Ophtalmologistes Universitaires de France” in order to set up a future “licence to operate.” Axis 2 will evaluate the impact of sleep deprivation on the surgical performance of experienced ORs using the EyeSi. ClinicalTrial.gov identifier: NCT05722080.

Monitoring sleep states of newborns, especially those born prematurely, before 37 weeks of gestation, is essential for tracking their development. This study presents an automated method for estimating the state of Quiet Sleep (QS). Given that QS is characterized by regular cardiorespiratory rhythm and non-movement, this approach combines machine learning algorithms trained on cardiorespiratory features with body motion segmentation. It was evaluated on manually annotated recordings from 10 preterm and 5 full-term newborns. Each newborn was recorded for eight hours during their first week of life, and preterm newborns were recorded again at 37 weeks Post-Menstrual Age (PMA). The results achieved an average balanced accuracy of 78% and a Cohen's kappa of 0.51 across all recordings. For neonates with a PMA greater than 33 weeks, these values increased to 82% and 0.58, respectively. This approach proves effective and holds promise for continuously monitoring QS in newborns with a PMA greater than 33 weeks using non-invasive signals.

The follow-up of the development of the premature baby is a major component of its clinical care since it has been shown that it can reveal a pathology. However, no method allowing an automated and continuous monitoring of this development has been proposed. Within the framework of the Digi-NewB European project, our team wishes to offer new clinical indices qualifying the maturation of newborns. In this study, we propose a new method to characterize motor activity from video recordings. For this purpose, we have chosen to characterize the motion temporal organization by drawing inspiration from sleep organization. Thus, we propose a fully automatic process allowing to extract motion features and to combine them to estimate a functional age. By investigating two datasets, one of 28.5 hours (manually annotated) from 33 newborns and one of 4,920 hours from 46 newborns, we show that the proposed approach is relevant for monitoring in clinical routine and that the extracted features reflect the maturation of preterm newborns. Indeed, a compact and interpretable model using gestational age and three motion features (mean duration of intervals with motion, total percentage of time spent in motion and number of intervals without motion) was designed to predict post-menstrual age of newborns and showed an admissible mean absolute error of 1.3 weeks. While the temporal organization of motion was not studied clinically due to a lack of technological means, these results open the door to new developments, new investigations and new knowledge on the evolution of motion in newborns.

Abstract Background : Prematurity is a major health issue due to its potential outcomes and socioeconomic impact. Prenatal counseling is of major importance for parents because it is believed that the risk of preterm birth is associated with a higher parental mental burden. Nowadays in France, the content and delivery of antenatal counseling is based on personal experience since there is a lack of official guidelines. The goal of the study was to evaluate maternal perception of antenatal information delivered in the setting of premature births. Methods : A qualitative study was performed using semi-structured individual interviews of 15 mothers with a child born >26-34 GW. Data analysis was based on a constant comparative method. Results : We found that concerning prenatal counselling content, parents wanted to be informed of their role in the care of their premature child more so than statistics that were not always considered relevant. Parents’ reactions to the announcement of the risk of a premature birth was dominated by stupefaction, uncertainty and anxiety. When it comes to the setting of prenatal counselling, patients’ room was deemed an appropriate setting by parents and ideally the presence of a coparent was appreciated as it increased patients’ understanding. The physicians’ behavior during the counselling was considered appropriate and described as empathic and optimistic. The importance of support throughout the hospitalization in the form of other parents’ experiences, healthcare professionals and the possibility to preemptively visit the NICU was emphasized by participants. Delivery experience was dominated by a sense of uncertainty, and urgency. Some leads for improvement included additional support of information such as virtual NICU visit; participants also insisted on continuity of care and the multidisciplinary aspect of counselling (obstetrician, pediatrician, midwive, nurse, lactation consultant and psychologist). Conclusion : Overall general guidelines on prenatal counseling seem necessary, however personalization remains fundamental.

BACKGROUND:Training clinicians on the use of hospital-based patient monitoring systems (PMS) is vital to mitigate the risk of use errors and of frustration using these devices, especially when used in ICU settings. PMS training is typically delivered through face-to-face training sessions in the hospital. However, it is not always feasible to deliver training in this format to all clinical staff given some constraints (e.g., availability of staff and trainers to attend in-person training sessions and the costs associated with face-to-face training).OBJECTIVE:The literature indicates that E-learning has the potential to mitigate barriers associated with time restrictions for trainers and trainees and evidence shows it to be more flexible, and convenient for learners in healthcare settings. This study aimed to develop and carry out a preliminary evaluation via a case study of an e-learning training platform designed for a novel neonatal sepsis risk monitor system (Digi-NewB).METHODS:A multi-modal qualitative research case study approach was used, including the analysis of three qualitative data sources: (i) audio/video recordings of simulation sessions in which participants were asked to operate the system as intended (e.g., update the clinical observations and monitor the sepsis risk), (ii) interviews with the simulation participants and an attending key opinion leader (KOL), who observed all simulation sessions, and (iii) post-simulation survey.RESULTS:After receiving ethical approval for the study, nine neonatal intensive care unit (NICU) nurses completed the online training and participated in the simulation and follow-up interview sessions. The KOL was also interviewed, and seven out of the nine NICU nurses answered the post-simulation survey. The video/audio analysis of the simulations revealed that participants were able to use and interpret the Digi-NewB interface. Interviews with simulation participants and the KOL, and feedback extracted from the survey, revealed that participants were overall satisfied with the training platform and perceived it as an efficient and effective method to deliver medical device training.CONCLUSIONS:This study developed an online training platform to train clinicians in the use of a critical care medical device and carried out a preliminary evaluation of the platform via a case study. The e-learning platform was designed to supplement and enhance other training approaches. Further research is required to evaluate the effectiveness of this approach.

Background Respiratory viruses can be responsible for severe apneas and bradycardias in newborn infants. The link between systemic inflammation with viral sepsis and cardiorespiratory alterations remains poorly understood. We aimed to characterize these alterations by setting up a full-term newborn lamb model of systemic inflammation using polyinosinic:polycytidylic acid (Poly I:C). Methods Two 6-h polysomnographic recordings were carried out in eight lambs on two consecutive days, first after an IV saline injection, then after an IV injection of 300 μg/kg Poly I:C. Results Poly I:C injection decreased locomotor activity and increased NREM sleep. It also led to a biphasic increase in rectal temperature and heart rate. The latter was associated with an overall decrease in heart-rate variability, with no change in respiratory-rate variability. Lastly, brainstem inflammation was found in the areas of the cardiorespiratory control centers 6 h after Poly I:C injection. Conclusions The alterations in heart-rate variability induced by Poly I:C injection may be, at least partly, of central origin. Meanwhile, the absence of alterations in respiratory-rate variability is intriguing and noteworthy. Although further studies are obviously needed, this might be a way to differentiate bacterial from viral sepsis in the neonatal period. Impact Provides unique observations on the cardiorespiratory consequences of injecting Poly I:C in a full-term newborn lamb to mimic a systemic inflammation secondary to a viral sepsis. Poly I:C injection led to a biphasic increase in rectal temperature and heart rate associated with an overall decrease in heart-rate variability, with no change in respiratory-rate variability. Brainstem inflammation was found in the areas of the cardiorespiratory control centers.

This study was designed to test if heart rate variability (HRV) data from preterm and full-term infants could be used to estimate their functional maturational age (FMA), using a machine learning model. We propose that the FMA, and its deviation from the postmenstrual age (PMA) of the infants could inform physicians about the progress of the maturation of the infants. The HRV data was acquired from 50 healthy infants, born between 25 and 41 weeks of gestational age, who did not present any signs of abnormal maturation relative to their age group during the period of observation. The HRV features were used as input for a machine learning model that uses filtering and genetic algorithms for feature selection, and an ensemble machine learning (EML) algorithm, which combines linear and random forest regressions, to produce as output a FMA. Using HRV data, the FMA had a mean absolute error of 0.93 weeks, 95% CI [0.78, 1.08], compared to the PMA. These results demonstrate that HRV features of newborn infants can be used by an EML model to estimate their FMA. This method was also generalized using respiration rate variability (RRV) and bradycardia data, obtaining similar results. The FMA, predicted either by HRV, RRV or bradycardia, and its deviation from the true PMA of the infants, could be used as a surrogate measure of the maturational age of the infants, which could potentially be monitored non-invasively and in real-time in the setting of neonatal intensive care units.

Despite advances in prenatal health care, neonatal sepsis remains a major cause of neonatal mortality. Early diagnosis and adequate treatment are essential to reduce morbidity and mortality related to this disease. In this paper, we propose a new method to detect neonatal sepsis based on heart rate (HR) complexity measures (entropy and compression indices) that takes into consideration neonatal gestational age. First, the percentile curves were computed for all the complexity indices using data from 118 control neonates. Eight indices were computed: the sample entropy (SampEn) and three indices to quantify the multiscale entropy (MSE) curve - the sum, the slope, and the product of the previous two - and the compression ratio (CR), using the bzip2 compressor, as well as the same three indices but related to the multiscale compression (MSC) curve. Then, the corresponding percentile was estimated for 23 sepsis neonates. Results show a significant decrease in the entropy indices SampEn and MSEsum and in the MSCslope a day before the detection of sepsis by the clinicians. The indices CR and MSCsum increased before the antibiotic take. These results imply that sepsis causes a random, uncorrelated pattern on the HR signal. Future studies should include a bigger data set to calculate a compound index comprising information of other physiological signals. Clinical Relevance - Prompt and accurate diagnosis of neona-tal sepsis is essential for the successful clinical management of neonates and significantly reduce morbidity and mortality. Complexity measures applied to the HR time series appear to detect sepsis in neonates starting one day before the clinical detection