Background: Pendelluft results from differences in time constants, airway opening pressures and heterogenous pressure distributions. It has been associated with increased lung strain, and worse clinical outcomes (4). Although scientific interest in pendelluft has grown, no consensus exists on the optimal method for its detection and quantification. This thesis aimed to compare five EIT-based pendelluft quantification methods regarding pendelluft prevalence across different datasets of mechanically ventilated ICU patients.

Methods: The five methods (5-9) were implemented as described in their original publications and applied to three patient groups: those with healthy lungs, those with hypoxemic failure, and those on non-invasive ventilation. To compare prevalence results, thresholds were derived from measurements in patients on pressure-controlled ventilation. Each method was evaluated using both its original preprocessing, and a standardized preprocessing approach to assess the impact of preprocessing choices.

Results: Pendelluft prevalence was highest among hypoxemic failure patients (up to 100%), and lowest in patients with healthy lungs (as low as 20%), with agreement across methods ranging from 62-83%. Several methods showed significant positive correlations. Pendelluft intensity was significantly higher during pressure-support ventilation compared to pressure-controlled ventilation (n=15, p = 0.03).

Discussion: While agreement on pendelluft prevalence was relatively high, differences in intensity reflected underlying methodological variations in signal interpretation. Standardizing preprocessing improved comparability and reduced variability. A significant increase in pendelluft during pressure-support ventilation supports its link to patient effort. These findings highlight the need for standardized quantification protocols and emphasize the impact of preprocessing choices in advancing pendelluft research and clinical applications.

Background: Continuous monitoring in paediatric intensive care units (PICUs) generates frequent clinical alarms, 87-97% of which are nonactionable, contributing to alarm fatigue and patient safety risks. At the Erasmus MC Sophia Children’s Hospital PICU, improved alarm management is needed. Machine learning offers a promising strategy to distinguish actionable from nonactionable alarms.

Objectives: The primary objective was to develop a machine learning algorithm to classify actionable alarms from multimodal vital signs. Secondary objectives were to characterise the PICU alarm burden, capture stakeholder perspectives and evaluate model feasibility for clinical application.

Methods: Retrospective Dräger monitoring data and alarms from 2,582 PICU patients (Nov 2021 – Oct 2024) were analysed. A machine learning algorithm was developed using ART M, HR, RESP and SpO2 data from 26 patients, with alarms annotated using clinical interventions, small signal deviations and temporal associations with other parameters. Logistic regression, decision tree, random forest and XGBoost were evaluated with nested cross-validation using pre-alarm features. Performance was assessed by sensitivity, specificity, balanced accuracy, with AUROC and F1-score as complementary metrics. Semi-structured interviews with four nurses and one psychologist explored alarm experiences, impacts and reduction strategies.

Results: The best model, a decision tree, showed limited performance (sensitivity 0.36-0.49, specificity 0.51-0.70, balanced accuracy ≈0.50). No discriminative features were identified, and substantial overlap and outliers limited classification. Most alarms involved SpO2 desaturation, with unit variation and temporal patterns linked to ward activity. Interviews highlighted overstimulation and desensitisation, but also that nonactionable alarms can serve as early warnings, with interpretation requiring clinical context.

Discussion: This study provides an evaluation of machine learning-based alarm classification in the PICU and integrates clinician perspectives to guide future interventions. The machine learning model was not suitable for clinical use because of retrospective labelling, the small annotated dataset and the absence of clinical context. Future research should focus on prospective annotation, larger and more diverse datasets and complementary strategies. Alarm dashboards and daily reviews are recommended to reduce alarm burden and mitigate alarm fatigue while maintaining patient safety.

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.

When a patient is in a hospital, it is very important to monitor their vital signs. Doctors and nurses use this information to assess the condition of the patient. Most of the existing vital signs measurement devices need physical contact with the patient. This thesis focuses on a non-contact vital signs estimation method. Using a mmWave radar, one or more persons in the view of the sensor are being monitored. This monitoring consists of finding the chest region of a person, and monitoring this chest for vibrations. These vibrations are caused by breathing in and out, and the beating of the heart. Using signal processing, these vibrations can be converted to a heart rate and a respiration rate.

This thesis is about getting insight in the already available options regarding vital signs monitoring, programming the Texas Instruments IWR6843ISK mmWave radar module to estimate the vital signs of multiple persons and validating this project against trusted vital signs monitors.

The implemented solution which followed from this project is able to track multiple persons inside the radar view, and is able to measure the vital signs for up to four persons in real-time. The mean accuracy gained for one person heart rate estimation is 10.8%, the mean accuracy gained for one person respiration rate estimation is 7.6%. The mean observed accuracy for multiple person heart rate estimation is 13.4%, the multiple person respiration rate mean accuracy is 10.6%.

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.

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 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.