Predicting CPAP failure after less invasive surfactant administration (LISA) in preterm infants by machine learning model on vital parameter data: a pilot study.

Objective. Less invasive surfactant administration (LISA) has been introduced to preterm infants with respiratory distress syndrome on continuous positive airway pressure (CPAP) support in order to avoid intubation and mechanical ventilation. However, after this LISA procedure, a significant part of infants fails CPAP treatment (CPAP-F) and requires intubation in the first 72 h of life, which is associated with worse complication free survival chances. The aim of this study was to predict CPAP-F after LISA, based on machine learning (ML) analysis of high resolution vital parameter monitoring data surrounding the LISA procedure.Approach. Patients with a gestational age (GA) <32 weeks receiving LISA were included. Vital parameter data was obtained from a data warehouse. Physiological features (HR, RR, peripheral oxygen saturation (SpO2) and body temperature) were calculated in eight 0.5 h windows throughout a period 1.5 h before to 2.5 h after LISA. First, physiological data was analyzed to investigate differences between the CPAP-F and CPAP-Success (CPAP-S) groups. Next, the performance of two types of ML models (logistic regression: LR, support vector machine: SVM) for the prediction of CPAP-F were evaluated.Main results. Of 51 included patients, 18 (35%) had CPAP-F. Univariate analysis showed lower SpO2, temperature and heart rate variability (HRV) before and after the LISA procedure. The best performing ML model showed an area under the curve of 0.90 and 0.93 for LR and SVM respectively in the 0.5 h window directly after LISA, with GA, HRV, respiration rate and SpO2as most important features. Excluding GA decreased performance in both models.Significance. In this pilot study we were able to predict CPAP-F with a ML model of patient monitor signals, with best performance in the first 0.5 h after LISA. Using ML to predict CPAP-F based on vital signals gains insight in (possibly modifiable) factors that are associated with LISA failure and can help to guide personalized clinical decisions in early respiratory management.

The eye lens dose of the interventionalist: Measurement in practice.

OBJECTIVE: Early 2018, the new eye lens dose limit of 20 mSv per year for occupational exposure to ionising radiation was implemented in the European Union. Dutch guidelines state that monitoring is compulsory above an expected eye lens dose of 15 mSv/year. In this study we propose a method to investigate whether the eye lens dose of interventionalists would exceed 15 mSv/year and to determine if the eye lens dose can be derived from the regular personal dosimeter measurements. METHODS: The eye lens dose, Hp(3), of interventional radiologists (n = 2), cardiologists (n = 2) and vascular surgeons (n = 3) in the Máxima Medical Centre, The Netherlands, was measured during six months, using thermoluminescence dosimeters on the forehead. Simultaneously, the surface dose, Hp(0,07), and whole body dose, Hp(10), were measured using regular dosimeters outside the lead skirt at chest level. The dosimeters were simultaneously refreshed every four weeks. The eye lens dose was compared to both the body-worn dosimeter values. Measurements were performed in the angiography suite, Cath lab and hybrid OR. RESULTS: A clear relation was observed between the two dosimeters: Hp(3) ≈ 0,25 Hp(0,07). The extrapolated year dose for the eye lens did not exceed 15 mSv for any of the interventionalists (average 3 to 10 studies/month). CONCLUSIONS: The eye lens dose can be monitored indirectly through the regular dosimeter at chest level. Additionally, based on the measurements we conclude that all monitored interventionalists remain below the dose limit and compulsory monitoring limit for the eye lens dose.

DOSE EVALUATION FOR DIGITAL X-RAY IMAGING OF PREMATURE NEONATES.

X-ray radiography is a commonly used diagnostic method for premature neonates. However, because of higher radiosensitivity and young age, premature neonates are more sensitive to the detrimental effects of ionising radiation. Therefore, it is important to monitor and optimise radiation doses at the neonatal intensive care unit (NICU). The number of x-ray examinations, dose-area product (DAP) and effective doses are evaluated for three Dutch NICUs using digital flat panel detectors. Thorax, thorax-abdomen and abdomen protocols are included in this study. Median number of examinations is equal to 1 for all three hospitals. Median DAP ranges between 0.05 and 1.02 µGy m2 for different examination types and different weight categories. These examinations result in mean effective doses between 4 ± 4 and 30 ± 10 µSv per examination. Substantial differences in protocols and doses can be observed between hospitals. This emphasises the need for up-to-date reference levels formulated specifically for premature neonates.

Interhemispheric connectivity estimated from EEG time-correlation analysis in preterm infants with normal follow-up at age of five.

Brain connectivity is associated with axonal connections between brain structures. Our goal was to quantify the interhemispheric neuronal connectivity in healthy preterm infants by automated quantitative EEG time-correlation analysis. As with advancing postmenstrual age (PMA, gestational age + postnatal age) the neuronal connectivity between left and right hemisphere increases, we expect to observe changes in EEG time-correlation with age. Thirty-six appropriate-for-gestational age preterm infants (PMA between 27-37 weeks) and normal neurodevelopmental follow-up at 5 years of age were included. Of these, 22 infants underwent 3-8 repeated EEG recordings at weekly intervals. The reduced 10-20 EEG electrode system for newborns was used with five sets of bipolar channels: central-temporal, frontal polar-temporal, frontal polar-central, temporal-occipital and central-occipital. We performed EEG time-correlation analysis between homologous channels of the brain hemispheres to identify interhemispheric similarity in EEG signal shape. For each 8 s epoch of the EEG the time-correlation values and the corresponding lag times were calculated for homologous channels on both hemispheres. In all channels, the median correlation value decreased significantly (between -40% and -60% decrease) from 27 to 37 weeks PMA, for gestational maturation. For the postnatal maturation only the central-temporal channel showed a significantly decreasing trend. In contrast, the median lag time showed no uniform change with PMA. The decreasing median correlation values in all homologous channels indicate a decrease in similarity in signal shape with advancing PMA. This finding may reflect greater functional differentiation of cortical areas in the developing preterm brain and may be explained by the increase of complex neural networks with excitatory and inhibitory circuitries.

Safe patient monitoring is challenging but still feasible in a neonatal intensive care unit with single family rooms.

AIM: Patient monitoring generates a large number of alarms. The aim of this study was to evaluate the rate, type and management of alarms and to determine the risks of a distributed alarm system in a neonatal intensive care unit (NICU) with single family rooms. METHODS: A risk analysis was performed before implementation. Alarms from patient monitors recorded for a year were identified, classified and counted. The first alarms, which went to the nurse responsible for the patient, were distinguished from the repeat alarms that were generated if the nurse failed to respond within 45 sec. RESULTS: The alarm handling protocol was changed as staff felt they needed a greater overview of the NICU alarms to avoid risks. In 1 year, 222 751 critical alarms including 12 309 repeat alarms were generated by patient monitors, equivalent to two alarms per patient per hour. Most of the alarms were oxygen desaturation alarms, followed by bradycardia alarms. About 3% of the desaturation alarms and 0.2% of the bradycardia alarms were repeated. CONCLUSION: Safe patient monitoring was challenging in a NICU with single family rooms, but possible by employing a distributed alarm system. The low number of repeat alarms indicated quick response times.

The development of an obstetric tele-monitoring system.

Fetal growth restriction and preterm uterine contractions can turn a normal pregnancy into a problematic one. In previous work, we have developed a system for electrophysiological measurement of fetal heart rate (fHR), fetal electrocardiogram (fECG) and (premature) uterine contractions to enable early detection of foetal problems. In this work we have expanded this system into a tele-monitoring system for measurement at home. In order to permit home monitoring, the communication chain of the data has to be designed such that home-measured signals (fHR, fECG, uterine activities) are available in the hospital in real-time. Furthermore, the data must be transferred wirelessly to any location (worldwide) for interpretation by gynaecologists. A web application helps the gynaecologist or midwife to access the signals everywhere, provided that internet access is available. We developed a webserver as the heart of the entire system; it manages the patient database, transforms the signals in a graphical representation similar to that of the cardiotocography and manages the data communication with the proper data security policy. This tele-monitoring system can be used also during home deliveries enabling prompt transfer and proper intervention in the hospital when complications occur.

Functional connectivity in preterm infants derived from EEG coherence analysis.

OBJECTIVE: To quantify the neuronal connectivity in preterm infants between homologous channels of both hemispheres. METHODS: EEG coherence analysis was performed on serial EEG recordings collected from preterm infants with normal neurological follow-up. The coherence spectrum was divided in frequency bands: δnewborn(0-2 Hz), θnewborn(2-6 Hz), αnewborn(6-13 Hz), ßnewborn(13-30 Hz). Coherence values were evaluated as a function of gestational age (GA) and postnatal maturation. RESULTS: All spectra show two clear peaks in the δnewborn and θnewborn-band, corresponding to the delta and theta EEG waves observed in preterm infants. In the δnewborn-band the peak magnitude coherence decreases with GA and postnatal maturation for all channels. In the θnewborn-band, the peak magnitude coherence decreases with GA for all channels, but increases with postnatal maturation for the frontal polar channels. In the ßnewborn-band a modest magnitude coherence peak was observed in the occipital channels, which decreases with GA. CONCLUSIONS: Interhemispherical connectivity develops analogously with electrocortical maturation: signal intensities at low frequencies decrease with GA and postnatal maturation, but increase at high frequencies with postnatal maturation. In addition, peak magnitude coherence is a clear trend indicator for brain maturation. SIGNIFICANCE: Coherence analysis can aid in the clinical assessment of the functional connectivity of the infant brain with maturation.

QRS classification and spatial combination for robust heart rate detection in low-quality fetal ECG recordings.

Non-invasive fetal electrocardiography (ECG) can be used for prolonged monitoring of the fetal heart rate (FHR). However, the signal-to-noise-ratio (SNR) of non-invasive ECG recordings is often insufficient for reliable detection of the FHR. To overcome this problem, source separation techniques can be used to enhance the fetal ECG. This study uses a physiology-based source separation (PBSS) technique that has already been demonstrated to outperform widely used blind source separation techniques. Despite the relatively good performance of PBSS in enhancing the fetal ECG, PBSS is still susceptible to artifacts. In this study an augmented PBSS technique is developed to reduce the influence of artifacts. The performance of the developed method is compared to PBSS on multi-channel non-invasive fetal ECG recordings. Based on this comparison, the developed method is shown to outperform PBSS for the enhancement of the fetal ECG.

Quantitative fiber tracking in the corpus callosum and internal capsule reveals microstructural abnormalities in preterm infants at term-equivalent age.

BACKGROUND AND PURPOSE: Signal-intensity abnormalities in the PLIC and thinning of the CC are often seen in preterm infants and associated with poor outcome. DTI is able to detect subtle abnormalities. We used FT to select bundles of interest (CC and PLIC) to acquire additional information on the WMI. MATERIALS AND METHODS: One hundred twenty preterm infants born at <31 weeks' gestation with 3T DTI at TEA entered this prospective study. Quantitative information (ie, volume, length, anisotropy, and MD) was obtained from fiber bundles passing through the PLIC and CC. A general linear model was used to assess the effects of factor (sex) and variables (GA, BW, HC, PMA, and WMI) on FT-segmented parameters. RESULTS: Seventy-two CC and 85 PLIC fiber bundles were assessed. For the CC, increasing WMI and decreasing FA (P = .038), bundle volume (P < .001), and length (P = .001) were observed, whereas MD increased (P = .001). For PLIC, MD increased with increasing WMI (P = .002). Higher anisotropy and larger bundle length were observed in the left PLIC compared with the right (P = .003, P = .018). CONCLUSIONS: We have shown that in the CC bundle, anisotropy was decreased and diffusivity was increased in infants with high WMI scores. A relation of PLIC with WMI was also shown but was less pronounced. Brain maturation is affected more if birth was more premature.

31P MR spectroscopy and in vitro markers of oxidative capacity in type 2 diabetes patients.

BACKGROUND: Skeletal muscle mitochondrial function in type 2 diabetes (T2D) is currently being studied intensively. In vivo (31)P magnetic resonance spectroscopy ((31)P MRS) is a noninvasive tool used to measure mitochondrial respiratory function (MIFU) in skeletal muscle tissue. However, microvascular co-morbidity in long-standing T2D can interfere with the (31)P MRS methodology. AIM: To compare (31)P MRS-derived parameters describing in vivo MIFU with an in vitro assessment of muscle respiratory capacity and muscle fiber-type composition in T2D patients. METHODS: (31)P MRS was applied in long-standing, insulin-treated T2D patients. (31)P MRS markers of MIFU were measured in the M. vastus lateralis. Muscle biopsy samples were collected from the same muscle and analyzed for succinate dehydrogenase activity (SDH) and fiber-type distribution. RESULTS: Several (31)P MRS parameters of MIFU showed moderate to good correlations with the percentage of type I fibers and type I fiber-specific SDH activity (Pearson's R between 0.70 and 0.75). In vivo and in vitro parameters of local mitochondrial respiration also correlated well with whole-body fitness levels (VO (2peak)) in these patients (Pearson's R between 0.62 and 0.90). CONCLUSION: Good correlations exist between in vivo and in vitro measurements of MIFU in long-standing insulin-treated T2D subjects, which are qualitatively and quantitatively consistent with previous results measured in healthy subjects. This justifies the use of (31)P MRS to measure MIFU in relation to T2D.

Ischemia-induced ADC changes are larger than osmotically-induced ADC changes in a neonatal rat hippocampus model.

Diffusion-weighted imaging (DWI) is frequently used to diagnose stroke. However, the origin of the observed reduction in the apparent diffusion coefficient (ADC) in the acute phase following ischemia is not well understood. Although cell swelling is considered to play an important role, it is unclear whether this can completely explain the large ADC decrease. We developed a method to induce in neonatal rat hippocampal slices both osmotic perturbations, which lead to cell swelling, and oxygen/glucose deprivation (OGD), which simulates ischemia. A perfusion system was used to provide the hippocampal slices with nutrients and oxygen to maintain slice viability, which was verified with the use of fluorescent dyes (live/dead staining). Upon induction of OGD, the ADC decreased to approximately 57% of the initial value within 2 hr. The ADC reduction cannot fully be explained by changes due to cell swelling, since these led only to a maximum decrease of approximately 83%. Therefore, in addition to cell swelling, other changes must contribute significantly to the ADC reduction.

MRI for diagnosing aortic valve stenosis: a comparison study of MRI and ultrasound.

BACKGROUND: In cases when Doppler ultrasound examinations are not reliable for determining the severity of aortic valve stenosis, patients undergo a catheterisation. Cardiac magnetic resonance imaging (MRI) is a promising tool for the determination of this disease. AIM: We investigated the value of MRI as a substitute for catheterisation in such circumstances, by comparing MRI measurements with Doppler ultrasound measurements. METHODS: Five volunteers and ten patients entered this study, which was approved by the Institutional Ethics Committee. A 1.0T MRI scanner was used for cardiac MRI. On the same day, a Doppler ultrasound examination was performed. The maximum velocity and the orifice area of the aortic valve (called orifice) were compared. RESULTS: A good correlation was observed between the maximum velocity measured with MRI and that measured with ultrasound (r2=0.95) and between the orifice determined by MRI and by ultrasound (r2=0.94); however, the orifice determined by MRI is consistently larger than the orifice determined by ultrasound. CONCLUSION: MRI measurements of velocity and orifice of the aortic valve correlate well with Doppler ultrasound measurement. MRI is a useful diagnostic tool and can be a good substitute for catheterisation, in particular because it allows simultaneous acquisition of anatomical and functional information.