Dataset Information

Non-contact physiological monitoring of preterm infants in the Neonatal Intensive Care Unit.

ABSTRACT: The implementation of video-based non-contact technologies to monitor the vital signs of preterm infants in the hospital presents several challenges, such as the detection of the presence or the absence of a patient in the video frame, robustness to changes in lighting conditions, automated identification of suitable time periods and regions of interest from which vital signs can be estimated. We carried out a clinical study to evaluate the accuracy and the proportion of time that heart rate and respiratory rate can be estimated from preterm infants using only a video camera in a clinical environment, without interfering with regular patient care. A total of 426.6?h of video and reference vital signs were recorded for 90 sessions from 30 preterm infants in the Neonatal Intensive Care Unit (NICU) of the John Radcliffe Hospital in Oxford. Each preterm infant was recorded under regular ambient light during daytime for up to four consecutive days. We developed multi-task deep learning algorithms to automatically segment skin areas and to estimate vital signs only when the infant was present in the field of view of the video camera and no clinical interventions were undertaken. We propose signal quality assessment algorithms for both heart rate and respiratory rate to discriminate between clinically acceptable and noisy signals. The mean absolute error between the reference and camera-derived heart rates was 2.3 beats/min for over 76% of the time for which the reference and camera data were valid. The mean absolute error between the reference and camera-derived respiratory rate was 3.5 breaths/min for over 82% of the time. Accurate estimates of heart rate and respiratory rate could be derived for at least 90% of the time, if gaps of up to 30 seconds with no estimates were allowed.

SUBMITTER: Villarroel M

PROVIDER: S-EPMC6908711 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Non-contact physiological monitoring of preterm infants in the Neonatal Intensive Care Unit.

Villarroel Mauricio M Chaichulee Sitthichok S Jorge João J Davis Sara S Green Gabrielle G Arteta Carlos C Zisserman Andrew A McCormick Kenny K Watkinson Peter P Tarassenko Lionel L

NPJ digital medicine 20191212

The implementation of video-based non-contact technologies to monitor the vital signs of preterm infants in the hospital presents several challenges, such as the detection of the presence or the absence of a patient in the video frame, robustness to changes in lighting conditions, automated identification of suitable time periods and regions of interest from which vital signs can be estimated. We carried out a clinical study to evaluate the accuracy and the proportion of time that heart rate and ...[more]

PMID: 31872068

Similar Datasets

Project description:ImportanceA higher level of care improves outcomes in extremely and very preterm infants, yet the impact of neonatal intensive care unit (NICU) level on moderate and late preterm (MLP) care quality is unknown.ObjectiveTo examine the association between NICU type and care quality in MLP (30-36 weeks' gestation) and extremely and very preterm (25-29 weeks' gestation) infants.Design, setting, and participantsThis cohort study was a prospective analysis of 433 814 premature infants born in 465 US hospitals between January 1, 2016, and December 31, 2020, without anomalies and who survived more than 12 hours and were transferred no more than once. Data were from the Vermont Oxford Network all NICU admissions database.ExposuresNICU types were defined as units with ventilation restrictions without surgery (type A with restrictions, similar to American Academy of Pediatrics [AAP] level 2 NICUs), without surgery (type A) and with surgery not requiring cardiac bypass (type B, similar to AAP level 3 NICUs), and with all surgery (type C, similar to AAP level 4 NICUs).Main outcomes and measuresThe primary outcome was gestational age (GA)-specific composite quality measures using Baby-Measure of Neonatal Intensive Care Outcomes Research (Baby-MONITOR) for extremely and very preterm infants and an adapted MLP quality measure for MLP infants. Secondary outcomes were individual component measures of each scale. Composite scores were standardized observed minus expected scores, adjusted for patient characteristics, averaged, and expressed with a mean of 0 and SD of 1. Between May 2021 and October 2022, Kruskal-Wallis tests were used to compare scores by NICU type.ResultsAmong the 376 219 MLP (204 181 [54.3%] male, 172 038 [45.7%] female; mean [SD] GA, 34.2 [1.7] weeks) and 57 595 extremely and very preterm (30 173 [52.4%] male, 27 422 [47.6%] female; mean [SD] GA, 27.7 [1.4] weeks) infants included, 6.6% received care in type A NICUs with restrictions, 29.3% in type A NICUs without restrictions, 39.7% in type B NICUs, and 24.4% in type C NICUs. The MLP infants had lower MLP-QM scores in type C NICUs (median [IQR]: type A with restrictions, 0.4 [-0.1 to 0.8]; type A, 0.4 [-0.4 to 0.9]; type B, 0.1 [-0.7 to 0.7]; type C, -0.7 [-1.6 to 0.4]; P < .001). No significant differences were found in extremely and very preterm Baby-MONITOR scores by NICU type. In type C NICUs, MLP infants had lower scores in no extreme length of stay and change-in-weight z score.Conclusions and relevanceIn this cohort study, composite quality scores were lower for MLP infants in type C NICUs, whereas extremely and very preterm composite quality scores were similar across NICU types. Policies facilitating care for MLP infants at NICUs with less complex subspecialty services may improve care quality delivered to this prevalent, at-risk population.

Project description:ImportanceThe Chinese Neonatal Network was established in 2018 and maintains a standardized national clinical database of very preterm or very low-birth-weight infants in tertiary neonatal intensive care units (NICUs) throughout China. National-level data on outcomes and care practices of very preterm infants (VPIs) in China are lacking.ObjectiveTo assess the care practices in NICUs and outcomes among VPIs in China.Design, setting, and participantsA cohort study was conducted comprising 57 tertiary hospitals from 25 provinces throughout China. All infants with gestational age (GA) less than 32 weeks who were admitted to the 57 NICUs between January 1 and December 31, 2019, were included.Main outcomes and measuresCare practices, morbidities, and survival were the primary outcomes of the study. Major morbidities included bronchopulmonary dysplasia, severe intraventricular hemorrhage (grade ≥3) and/or periventricular leukomalacia, necrotizing enterocolitis (stage ≥2), sepsis, and severe retinopathy of prematurity (stage ≥3).ResultsA total of 9552 VPIs were included, with mean (SD) GA of 29.5 (1.7) weeks and mean (SD) birth weight of 1321 (321) g; 5404 infants (56.6%) were male. Antenatal corticosteroids were used in 75.6% (6505 of 8601) of VPIs, and 54.8% (5211 of 9503)were born through cesarean delivery. In the delivery room, 12.1% of VPIs received continuous positive airway pressure and 26.7% (2378 or 8923) were intubated. Surfactant was prescribed for 52.7% of the infants, and postnatal dexamethasone was prescribed to 9.5% (636 of 6675) of the infants. A total of 85.5% (8171) of the infants received complete care, and 14.5% (1381) were discharged against medical advice. The incidences of the major morbidities were bronchopulmonary dysplasia, 29.2% (2379 of 8148); severe intraventricular hemorrhage and/or periventricular leukomalacia, 10.4% (745 of 7189); necrotizing enterocolitis, 4.9% (403 of 8171 ); sepsis, 9.4% (764 of 8171); and severe retinopathy of prematurity, 4.3% (296 of 6851) among infants who received complete care. Among VPIs with complete care, 95.4% (7792 of 8171) survived: 65.6% (155 of 236) at 25 weeks' or less GA, 89.0% (880 of 988) at 26 to 27 weeks' GA, 94.9% (2635 of 2755)at 28 to 29 weeks' GA, and 98.3% (4122 of 4192) at 30 to 31 weeks' GA. Only 57.2% (4677 of 8171) of infants survived without major morbidity: 10.5% (25 of 236) at 25 weeks' or less GA, 26.8% (48 of 179) at 26 to 27 weeks' GA, 51.1% (1409 of 2755) at 28 to 29 weeks' GA, and 69.3% (2904 of 4192) at 30 to 31 weeks' GA. Among all infants admitted, the survival rate was 87.6% (8370 of 9552)and survival without major morbidities was 51.8% (4947 of 9552).Conclusions and relevanceThe findings of this study suggest that survival and survival without major morbidity of VPIs in Chinese NICUs have improved but remain lower than in high-income countries. Comprehensive and targeted quality improvement efforts are needed to provide complete care for all VPIs, optimize obstetrical and neonatal care practices, and improve outcomes.

Project description:Every year in the United States, more than 300,000 infants are admitted to neonatal intensive care units (NICU) where they are exposed to a chemical-intensive hospital environment during a developmentally vulnerable period. The neurodevelopmental impact of environmental exposure to phthalates during the NICU stay is unknown. As phthalate exposure during the third trimester developmental window has been implicated in neurobehavioral deficits in term-born children that are strikingly similar to a phenotype of neurobehavioral morbidity common among children born premature, the role of early-life phthalate exposure on the neurodevelopmental trajectory of premature infants may be clinically important. In this study, premature newborns with birth weight <1500g were recruited to participate in a prospective environmental health cohort study, NICU-HEALTH (Hospital Exposures and Long-Term Health), part of the DINE (Developmental Impact of NICU Exposures) cohort of the ECHO (Environmental influences on Child Health Outcomes) program. Seventy-six percent of eligible infants enrolled in the study. Sixty-four of 81 infants survived and are included in this analysis. 164 urine specimens were analyzed for phthalate metabolites using high-performance liquid chromatography/tandem mass spectrometry. The NICU Network Neurobehavioral Scale (NNNS) was performed prior to NICU discharge. Linear and weighted quantile sum regression quantified associations between phthalate biomarkers and NNNS performance, and between phthalate biomarkers and intensity of medical intervention. The sum of di(2-ethylhexyl) phthalate metabolites (?DEHP) was associated with improved performance on the Attention and Regulation scales. Specific mixtures of phthalate biomarkers were also associated with improved NNNS performance. More intense medical intervention was associated with higher ?DEHP exposure. NICU-based exposure to phthalates mixtures was associated with improved attention and social response. This suggests that the impact of phthalate exposure on neurodevelopment may follow a non-linear trajectory, perhaps accelerating the development of certain neural networks. The long-term neurodevelopmental impact of NICU-based phthalate exposure needs to be evaluated.

Dataset Information

Non-contact physiological monitoring of preterm infants in the Neonatal Intensive Care Unit.

Publications

Non-contact physiological monitoring of preterm infants in the Neonatal Intensive Care Unit.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets