Expanded Criteria Donor (ECD) organs are being used more often in clinical setting. The regenerative ability of the organs might be able to restore the organ to full functionality ex vivo. For long term kidney stabilization, optimization and monitoring an organ incubator is preferable. However, it is unclear which available parts would work best in synergy. A Normothermic Machine Perfusion (NMP) setup and a Mathematical Windkessel Model were created as a first step in a larger project of prolonged preservation of ECD organs. While the current NMP setup was found adequate for academic research, it can only be used for simple studies using water. Several fundamental improvements need to be made before the setup can be used as a fully functioning NMP setup for kidneys. Key improvements would be the addition of a Windkessel and a different cardiac pump.

In the realm of healthcare, the effective management of alarm systems within the Neonatal Intensive Care Unit (NICU) is of paramount importance to ensure patient safety and reduce alarm fatigue among nurses. This study presents a comprehensive exploration of designing interfaces tailored to nurses' needs for adjusting alarm limits, aimed at enhancing their decision-making and patient care. Leveraging a multidisciplinary approach, this project amalgamates insights from nursing practices, user-centered design, and data visualization. Drawing on meticulous literature review, direct observations, interviews, and user surveys, the project meticulously dissected the intricacies of nurses' interactions with alarm systems. This investigation highlighted the necessity for a dashboard that not only reduces the cognitive load on nurses but also empowers them to make informed decisions based on alarm data. The resulting system interfaces offer data customization and visualization capabilities, facilitating rapid and accurate alarm limit adjustments. Therefore, this project has generated interfaces that involves tracking, analyzing, and visualizing the data logged by the nurses in response to alarms and their evaluations, thus supports nurses in adjusting alarm limits for an individual patient. The evaluation of the designed interfaces through two kinds of questionnaires reflects a promising usability score, with nuanced insights about nurses' varying levels of comfort and trust with the interface. Future recommendations include personalized information delivery based on experience levels, Leverage machine learning algorithms and so on.

In the Netherlands the preterm birth rate is around 7%. The problematic part is that these preterm infants make up for 72% of all deaths during or shortly after birth. To provide a way to aid these infants the following question was stated by the doctor: "turn on a light in the Neonatal Intensive Care Unit when the preterm infant’s development is not as expected". This question was interpreted as following: first of all, find an informative signal present for preterm infants which can provide knowledge on the state of development. Secondly, find a way to quantify this signal through measurement and provide a way to automate the detection. Based on literature the delta brush was selected as a promising waveform in the neonatal EEG, which can be used to follow the maturation of the brain. The spectral behavior of the EEG is used to identify the specific waveforms, but this analysis of the EEG is still mainly based on visual analysis, which is a subjective and time-consuming task. A way to quantify and automate this process was found in the Continuous Wavelet Transform (CWT). Using the Morlet mother wavelet, a time-frequency distribution of the EEG was calculated. The CWT’s redundant behavior was found to provide a finer sampling which could be used to reinforce specific waveform behavior. A third goal was to investigate the troubles that new innovations face in being accepted by the medical field. This was found to be related to the building of trust. The key elements for building trust in this work were identified as: interpretability of the results, transparency of the process, and ease of operation. These elements will be taken into account in the proposed solution. A set of high-density EEG measurements of preterm infants was acquired through collaboration with the the Academic Hospital Antwerp and the Erasmus Medical Center. This high-density consists of 19 electrode channels instead of the more commonly used 11 electrode channels. The measurement was done at 30 weeks postmenstrual age (PMA). These measurements were accompanied with annotation for the waveform of interest. An interactive application for visualization of the EEG data and wavelet coefficients was designed in MATLAB. This application can run standalone and can be used to visualize the detector’s results for the end user. Based on the inherent characteristics of the target waveform two detection features were chosen. The first feature is a measure of the ratio between peak in the high-frequency region (3.3-40 Hz) and the low-frequency region (0.1-3.3 Hz). The second feature is an energy calculation based on a windowed Squared Energy Operator (SEO). A triple-threshold multi-channel detector, based on these features, was initialized and performance was tested over the full threshold range. A Precision-Recall (PRC) curve was provided showing the total solution space for both feature thresholds. Based on the point closest to (100,100) in the training set PRC, a single threshold was selected for validation with the validation datasets. This has resulted in a detector with a sensitivity of 73.66% and a precision of 21.71%. This performance is expected to increase with cross-validation, due to lower quality EEG datasets in the validation set. The differences in performance can be explained by the uncertainties in the exact delta brush behavior and the incomplete annotation set, which causes possible detected delta brush activity to be labeled as false positives. In the end an informative waveform was found and a suitable quantification method has been proposed. A delta brush detector has been designed based on the inherent characteristics of the waveform. A standalone interactive application has been developed to visualize the EEG signal in combination with its time-frequency behavior. The application can also be used in combination with the detector to provide insight into the decision-making process and to visualize the detector’s output.

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.

Neonates are among the most fragile in the human population. Even more so when born prematurely. Their loss of development time in the womb disrupts their growth, and the neonatal intensive care unit environment can add multiple stresses that hinder their development. This can partly be attributed to the intrusive environment of a neonatal intensive care unit incubator. Neonatal development cannot be monitored without multiple wires and sensors, such as pulse oximetry and electrocardiogram (ECG). The strong adhesives of these sensors can hurt the delicate skin of the neonates and the sensors make bonding with parents difficult. The issue of the intrusive nature of current neonatal healthcare has led this thesis towards something not normally associated with healthcare: radar. Millimeter wave radar with frequency modulation of the continuous wave transmission has been shown to measure adult’s heart and respiration rate without contact with the patient. Using the small wavelength and high configurability of frequency modulated millimeter wave radar, the goal will be to scale down this technology from adults to neonates that can be as small as 500 grams. This thesis provides a look into the application investigation of frequency modulated millimeter wave radar in monitoring neonates. It dives into the environment of the neonatal intensive care unit incubator and the radar monitoring system operation. The environment is modelled with a thermal focus to avoid high temperature increases caused by the radar module. The system operation is described and the most influential component simulated and characterized. Lastly, the thermal model of the neonatal intensive care unit incubator is validated to understand how the system operation influences the environment. And the radar system operation will be characterized for measuring the smallest amplitude changes of a chest to understand how the environment influences the system performance. The conclusion of this thesis will provide reasoning for why or why not the application of frequency modulated millimeter wave radar has the capability to be safely implemented in the neonatal intensive care unit.

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.

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.

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.