Despite the potential of AI to significantly improve diagnostic accuracy, patient care, and operational efficiency in healthcare, ethical challenges such as biases inherent in AI systems can lead to unfair outcomes and exacerbate existing healthcare disparities. Drawing on insights from existing literature, this research aims to address the critical literature gap in the strategic and comprehensive integration of stakeholder collaboration with bias mitigation methodologies. Through a qualitative research design incorporating semi-structured expert interviews and literature analysis, this study searches to contribute valuable insights into the effective implementation of collaborative ethical AI development in healthcare. The result of this study presents an inclusive stakeholder collaboration framework designed to serve as a proactive guidance tool for stakeholders throughout the AI healthcare tool's lifecycle, with a focus on bias mitigation and ethical development. This framework outlines each phase of the AI lifecycle, and in each phase the algorithm's susceptibility to certain biases, bias mitigation strategies, ethical design strategies, and the responsible stakeholders are included.

WiECG aims to create a prototype device which enable ambulance personnel to perform a 12-lead ECG without wires connecting the patient to the monitor. The proposed solution consists of a transmitter and a receiver device. The transmitter transmits the measured signals, the receiver sends the measured signals to the monitor, which shows the measured signals.
This thesis describes the design and implementation process for the hardware. This concerns the amplification and filtering of the signals produced by the heart of the patient as well as the reconstruction
and attenuation at the output of the receiver module. These processes should be done for 9 signals. Furthermore, component selection, design decisions and the process of implementing this analog signal processing on a printed circuit board is described including the interfaces with the modules used by the other subgroups of this thesis. The prototype built during this project was able to filter the 9 signals and send it from transmitter to receiver while only adding 1.572 V RMS noise to the output ECG signal.

The goal of the WiECG project is to create a prototype device that makes it possible to perform a 12-lead ECG measurement on patients without wires from the patient to a monitor. The solution consists of a transmitter and receiver, one of which is close or on the patients body and the other is connected to a monitor.

This thesis describes the design and implementation of a subsystem of the prototype device that performs digitization, digital processing and reconstruction of the measured 12-lead ECG signal. This concerns converting nine 0 to 3.3V analog signals to the digital domain by using Analog-to-Digital converters, real-time filtering of nine signals with multiple digital IIR filters and reconstructing nine digital signals to the analog domain using Digital-to-Analog converters. Furthermore, component selection, design decisions and the implementation process will be detailed in this document.

The subsystem proposed in this paper is able to successfully sample, efficiently filter and reconstruct nine signals in real time. Recommendations on improving the implementation to better adhere to the lower power requirements for a longer battery life are provided as future research prospects.

Background & Objective: The unprecedented value and long­term uncertainties of gene therapies have challenged established health technology assessment (HTA) methods. Real-world data (RWD) and real-world evidence (RWE) may mitigate the encountered uncertainties. However, empirical evidence appears to be lacking in the literature. This research aimed to provide this evidence and identify implications for EU-wide gene therapy joint clinical assessments.

Methods: An initial literature review laid the theoretical foundation for the research. A retrospective comparative analysis delivered empirical evidence on RWD/RWE usage in gene therapy HTAs. Preliminary findings were probed in three use cases and verified in semi­structured interviews.

Results: Nineteen HTA reports published by the HTA bodies G­BA (Germany) and NICE (England) were identified for the ten in­scope gene therapies.
Whereas NICE had an average inclusion of 14 sources per HTA report (with an acceptance rate of 56%), G­BA had 8 (with 32% acceptance rate).
While RWD/RWE supporting evidence on an external comparator had the lowest acceptance rate, RWD/RWE on intervention effectiveness had the highest acceptance rate. Insufficient information to substantiate the choice of RWD/RWE and inappropriate RWE study design was the most common exclusion rationales for RWD/RWE.

Conclusions: The presented empirical evidence adds to the current knowledge base in two ways; it provides empirical evidence on HTAs of gene therapies (1) and RWD/RWE usage in gene therapy HTAs (2). This work provides insights into how RWD/RWE usage differs between HTA bodies and explicates relevant considerations for gene therapy manufacturers when using RWD/RWE in future HTA submissions. It also proposes that alignment on evidentiary requirements and assessment elements will optimise the transferability of future joint clinical assessment outcomes to national HTA bodies. Knowledge transfer and knowledge sharing initiatives will play a pivotal role in achieving such a consensus.

With healthcare systems being regarded as one of the critical infrastructure sectors, evaluated as a multi-trillion-dollar industry, and with 5 % to 10 % of total health expenditures allocated to medical devices, it is important to pay special attention to what and how technologies are brought into hospitals. This is heavily influenced by good procurement practices, but which are still inefficient in many countries across the world. This study aims to understand and analyse the current barriers and problems in Romanian healthcare procurement, in an attempt to determine what is needed to update the e-procurement of capital medical equipment. By combining a thorough literature review and semi-structured interviews, the research provides an in-depth understanding of the barriers faced by the Romanian acquisition system in public healthcare. The results indicate that an updated e-procurement platform would offer advantages to the relevant stakeholders, however this should not be seen as the go-to solution for the current context. Other human factors, as well as system-wide problems should be addressed before implementing technological solutions, such as a digital platform for procurement of capital medical equipment.