Models for oxygen transport in preterm infants can aid the development and evaluation of automated oxygen controllers by providing insight into the FiO2-SpO2 response and enabling virtual trials. A computer simulation model of oxygen transport in preterm infants is developed and FiO2-SpO2 responses in preterm infants are investigated. The model consists of a respiration and circulation submodule, interconnected by a pulmonary gas exchange submodule. Literature-based parameter ranges are provided. The model's ability to reproduce a patient's FiO2-SpO2 response, be generalised to different FiO2-SpO2 responses, and replicate physiological shunting and apnea scenarios is investigated. FiO2-SpO2 responses in preterm infants exhibit high variability and few responses are found stable. The model could be calibrated to specific FiO2-SpO2 responses using literature-based parameter ranges and could replicate physiologically expected shunting and apnea scenarios. The calibrated model could not be generalised to another FiO2-SpO2 response. The developed model for oxygen transport in preterm infants is a useful, modular, well-documented framework that can be used to develop and evaluate automated oxygen controllers.

This graduation thesis is on the topic of Critical audible alarm-sound design for handheld monitoring devices in Neonatal ICUs. Hand-held mobile devices are being tested in the field for effective alarm perception and response in the NICU at Erasmus MC Sophia's Hospital, Rotterdam. Based on the context analysis, the major stakeholder, and the focus of the design is the nurses and possibly neonatologist at the NICU, with the former being the main scope of this project.

The goal of this project is to The new critical audible alarms on the device must be able to distinguish the individual alarms, identify them for each patient per nurse, and respond to them by reaching the ideal destination of the patient room in a NICU. These responses should be achieved without the assistance of a visual cue.

A grammar for the new design is established via semantic network association methods (analogy) and in this case, it is the use of ‘Baby Toys’ as the building block for the sound design, The newly designed audible alarm library consists of 6 sounds namely Chimes, Lullaby, Shakers, Dial Tone, Piano A, and Piano S, which are then equalized under masked conditions for effective use in the NICU environment. Their functionality (response time & identification), urgency, and perceived pleasantness are tested for the context.

A soundscape is the acoustic environment that is constantly surrounding us. Soundscapes in the neonatal intensive care unit (NICU) might adversely affect neonates, their families, and healthcare providers. In this unit, the number of alarms and nuisance is very high, and studies show that it negatively affects both the well-being of patients and the performance of healthcare professionals (Bliefnick, Ryherd, Jackson, & 2019). Additionally, elevated sound levels in the NICU may contribute to undesirable physiologic and behavioral effects in infants. Hearing impairment, heart rate, blood pressure, oxygen saturation, respiratory rate, and sleep were all deteriously affected (Zimmerman & Lahav, 2013).Sound studies within NICUs have only focused on short-term outcomes such as monitoring sound levels in decibels (dB) and reporting the results, with no further implication. Current market solutions give only feedback on high dB levels, limiting medical professionals’ complete understanding of the cacophonous environment. Additionally, they rely on counting sound in dB, discarding the effect of tone and frequency. Therefore, the problem with the dB measure is that it represents only one part of the complex sound taxonomy. Still, interpreting sound beyond dB is challenging to understand for people who are unfamiliar with the physics of sound.SOUNDscapes is a digital platform that maps and localizes sound events occurring at the NICU. It displays sound trends in real time and assesses the quality of the environment by having two main visualization pages: sound level trends and constellation map.The goal of providing real-time feedback is to make nurses aware of specific (sound) behaviours and their consequences. Additionally, they can assess and observe their collective impact on the unit. This dashboard motivates them to change their attitudes towards harmful sound events by ultimately triggering a behaviour change. The dashboard is a tool that will help nurses understand, assess and change their sound behaviour and patterns of harmful sound sources, ultimately having valuable feedback for reducing high sound levels at the unit.First, the proposed solution provides the first step for permanent sound monitoring, mapping, and visualising real-time sound-producing events. Additionally, supporting nurses and giving them the confidence to act upon harmful sound sources occurring at the NICU. Secondly, the suggested design, apart from advocating for a nurse’s sound quality, is also a tool that can go beyond their caring role. For the Neonatology department at ErasmusMC, this platform means a new source of data streams that healthcare developers can use for measuring and evaluating the care quality they are delivering. The new system provided opens new research possibilities in the future that will allow researchers to link the quality of the physical sound environment to physiological and psychological effects on listeners.

Abstract—Background: cardiotocography (CTG) has long been used in clinical decision making to help assess the fetus’ condition during pregnancy. However it’s usefulness in the detection of fetal acidosis is debated due to high inter and intraobserver variability and general difficulty in interpreting the signals. The introduction of automatic analysis methods aims to decrease these issues originating from human limitations, but additional questions still remain. There is no clear concession when is it most useful to perform CTG measurements and which time periods posses the highest predictive capabilities. Method: a database of 1932 patients was analyzed after baseline and feature extraction. Several machine learning methods (SVM,logistic regression, random forest, KNN) were compared based on accuracy, F1 score, recall, precision, sensitivity and specificity.Furthermore the database was divided, based on when the measurement was taken (relative to time of birth), and the accuracy of the methods was compared again at intervals of 1 to 24 hours.
Results: from the machine learning methods the support vector machine using polynomial kernel achieved the highest scores(sensitivity of 55% and specificity of 56%). The inclusion of older measurements caused a decrease (≈20%) in the predictive performance of the models.
Conclusion: the results show that in clinical decision making the most crucial fetal heart rate measurements are the ones that are taken the closest to birth.

The placenta is very important during the start of life, providing the fetus with oxygen and nutrients from the maternal blood. Impaired growth of the placenta and additional placental ischaemia endangers the exchange of gasses, exchange of nutrients, and optimal growth of the fetus. This thesis investigates the feasibility of intrauterine ECMO to improve oxygen levels in fetal blood during placental ischaemia. Fetal blood would be retrieved from the umbilical artery, oxygenated in the ECMO system and fed back into the umbilical artery. The objective of this thesis is to design a cardiovascular model to simulate the cardiovascular response to an ECMO support system. A lumped parameter model is created to approximate the fetal cardiovascular system. By performing a parameter search, haemodynamic parameters were gathered for the fetal model. Data from 30 week fetuses was used as initial input, because of parameter accessibility. Parameters for the gestational age of 20 to 29 weeks were obtained by extrapolating the parameters from the fetus of 30 weeks with scaling factors. A sensitivity analysis was performed to analyse the flow and pressure distribution through the fetal cardiovascular system and the cardiovascular response to different parameters. Implementation of a cannula into one of the umbilical arteries increases the resistance of that artery. Simulating the cardiovascular response to the addition of the cannula showed promising results for the feasibility of intrauterine ECMO. The fetal heart is able to maintain blood flow through the cannula despite the fact that the resistance of the artery is increased. The placental resistance increases during placental ischaemia. Because of this higher resistance, blood flow through the placenta will decrease. However, even at a lower flow rate, oxygenation of blood flow via the umbilical artery is mostly sufficient. The reason is the high percentage of fetal cardiac output flowing through the placental circulation. The designed model is able to simulate the fetal cardiovascular system and provides a simulation tool to further develop an intrauterine ECMO support system.

The problem of premature births is widespread throughout the world affecting 41000 newborns daily; the issues that follow, often related to breathing, require the use of mechanical ventilation to compensate for the poor compliance of the respiratory muscles of newborns. However, side effects associated with artificial ventilation, including atrophy, require a cyclic interruption of automatic ventilation so that infants can develop and train their respiratory muscles (the so-called weaning from ventilation).
However, the criteria for judging the readiness and progression of the detachment from ventilation are unsatisfactory since they rely on the subjective judgments of the clinicians.
As a consequence, a research project in collaboration between TU Delft, the DEMCON BV (a Dutch mechatronics engineering company) and the Erasmus Medical Center of Rotterdam was carried out to look for an objective measure, provided with visual feedback, to give indications of the respiratory fatigue of newborns to the clinicians, also referred as work of breathing (WOB). This research revealed that the analysis of the diaphragmatic electromyography (dEMG) is a non-invasive tool that can be used to measure the WOB. As a result, three WOB detection algorithms named peak-to-peak (P2P), differential-peak-to-peak (DP2P) and area-under-the-curve (AUC) were developed. The relevance of these algorithms consists in extracting the WOB information from the dEMG and giving direct visual feedback to the clinicians.
Moreover, since often weaning from ventilation is impaired by the advent of adverse events such as apnea and brachicardia, two algorithms were implemented to detect such complications as well. \newline\newline
Before starting the actual research, some background work was carried out for the DEMCON BV. DEMCON BV deals with the acquisition and processing of dEMG utilizing a Software called Polybench. The first part of the background work was to write a Simulink program which has the same functionality as Polybench. The relevance of this work consists in allowing better communication between DEMCON and any other professional who wants to collaborate with them since Simulink is a popular software while Polybench is not. The second part of the background work was to create a Simulink block-chain that given a raw dEMG signal can extract the breathing envelope from it.

Data analysis for electrical impedance tomography (EIT) research requires manual selection of sequences with a normal breathing pattern. This procedure is lengthy and the lack of a standardised approach results in different practices among EIT studies, limiting the potential and comparability of the research.
This article presents a new approach to solving this problem, using automatic detection of EIT sequences with normal breathing pattern. An algorithm was developed to differentiate between normal and disturbed breathing patterns. To facilitate data analysis, it was implemented in an application that allows for EIT parameter calculation of selected sequences. EIT recordings of three patients recruited in an observational study were used to develop the algorithm. A reference standard was defined as the majority vote of five biomechanical engineering students performing manual classification. Frequency and time domain properties were compared between the signals that these graders classified as reliable and unreliable, and were used to define classification rules for the algorithm. Matlab was used to create the classification algorithm and implement it in an application. The developed algorithm was validated with a new data set containing EIT recordings of an additional three patients, classified by the same volunteers. Qualitative analysis was performed to investigate the causes of conflict between manual and automated data selection.
The resulting algorithm achieved a sensitivity of 92.8% (95% CI, 92.6%-92.9%) and a specificity of 85.5% (95% CI, 85.1%-85.8%) on the EIT files used for development. On the validation set the algorithm accomplished a sensitivity of 86.5% (95% CI, 86.3%-86.7%), and specificity of 79.7% (95% CI, 79.4%-80.0%).
Most differences between manual and automatic data selection were found to be around the edges of the selected sequences. Other discrepancies can be explained by difference in data selection behaviour for varying recording qualities during manual selection. The presented algorithm proves its potential for quick and reliable data classification of EIT recordings. It not only provides a new standard for data selection in EIT research, but also reduces the time investment of researchers. The freely available data analysis application enables easy implementation of the algorithm. The presented study therefore provides a first step towards a uniform approach in EIT research, improving comparability of studies and increasing the scientific value of their findings.

An estimated 9 million infants are born prematurely each year in south Asia and sub-Saharan Africa, and the leading cause of death in preterms is respiratory distress syndrome (RDS). Continuous positive airway pressure (CPAP) is a popular treatment for RDS and has been proven to be safe, feasible, and effective for use in low- and middle-income countries (LMICs). The well-documented success of supportive CPAP in LMICs and prophylactic CPAP in developed countries indicates that delivery room CPAP has the potential to be implemented successfully in LMICs. The aim of this thesis is to explore the feasibility of a simple, low-cost, portable neonatal CPAP device for use in the delivery room in LMICs. A portable CPAP device was modelled in Simulink to predict the pressure and flowrate at any point in the CPAP circuit. A prototype composed of a centrifugal fan, silicone tubing, nasal cannula, and a PEEP valve was constructed. The prototype was tested using a Dräger Infant Test Lung to simulate a breathing neonate. The model predicted that neonates with higher peak inspiratory flows risked rebreathing exhaled gas. When compared to the experimental data, it was determined that the model underestimated resistance in the circuit and overestimated the mean pressure delivered to the patient. The prototype effectively delivered a positive pressure to the simulated patient; however, the pressure was not consistent across all experimental conditions. Cannula type, amount of leak, and breathing pattern all impacted the treatment delivered. The Simulink model can be used as a tool to aid in design decisions, but is not highly accurate, and thus does not eliminate the need for practical experimentation. The prototype was a good proof-of-concept and should be investigated further in consultation with clinicians.