The escalating complexity of the hospital environment, propelled by technological advancements, necessitates a comprehensive exploration of the integration and management of diverse tools and technologies in healthcare settings. In this context, digital solutions, including the Internet of Things, robotics, mobile apps, sensors, and Artificial Intelligence (AI), play pivotal roles in enhancing treatment efficacy, ensuring patient safety, and optimising resource utilisation. The proliferation of health technologies demands a robust strategy for investigating factors affecting patient safety, necessitating interventions grounded in evidence-based approaches. This thesis delves into the critical analysis of manufacturer-recommended maintenance practices, urging Clinical Engineers and Health Technology Management professionals to adopt evidence-based methods. Real-World Data emerges as a valuable resource, offering observational insights into the effectiveness and safety of health technologies, with implications for regulatory decision-making, compliance with the EU Medical Device Regulation, and post-market surveillance. Addressing these challenges, this manuscript promotes the application of semantic ontologies to standardise data and enhance communication across healthcare systems. It highlights the role of semantic ontologies in managing the complexity of healthcare facilities, facilitating communication among various roles, and bridging gaps in data standardisation. The central focus of the work is developing a framework employing Natural Language Processing, Deep Neural Networks, and Explainable AI to extract and classify adverse events related to Health Information Technologies. Leveraging records from the US Manufacturer and User Device Experience database, the framework aims to provide a novel approach for obtaining Real-World Evidence in Clinical Engineering fields, including Evidence-Based Maintenance, Health Technology Management, and Assessment.
Designing and developing a dedicated Natural Language Processing Framework for Healthcare Information Technology Management and Assessment / Alessio Luschi. - (2024).
Designing and developing a dedicated Natural Language Processing Framework for Healthcare Information Technology Management and Assessment
Alessio Luschi
2024
Abstract
The escalating complexity of the hospital environment, propelled by technological advancements, necessitates a comprehensive exploration of the integration and management of diverse tools and technologies in healthcare settings. In this context, digital solutions, including the Internet of Things, robotics, mobile apps, sensors, and Artificial Intelligence (AI), play pivotal roles in enhancing treatment efficacy, ensuring patient safety, and optimising resource utilisation. The proliferation of health technologies demands a robust strategy for investigating factors affecting patient safety, necessitating interventions grounded in evidence-based approaches. This thesis delves into the critical analysis of manufacturer-recommended maintenance practices, urging Clinical Engineers and Health Technology Management professionals to adopt evidence-based methods. Real-World Data emerges as a valuable resource, offering observational insights into the effectiveness and safety of health technologies, with implications for regulatory decision-making, compliance with the EU Medical Device Regulation, and post-market surveillance. Addressing these challenges, this manuscript promotes the application of semantic ontologies to standardise data and enhance communication across healthcare systems. It highlights the role of semantic ontologies in managing the complexity of healthcare facilities, facilitating communication among various roles, and bridging gaps in data standardisation. The central focus of the work is developing a framework employing Natural Language Processing, Deep Neural Networks, and Explainable AI to extract and classify adverse events related to Health Information Technologies. Leveraging records from the US Manufacturer and User Device Experience database, the framework aims to provide a novel approach for obtaining Real-World Evidence in Clinical Engineering fields, including Evidence-Based Maintenance, Health Technology Management, and Assessment.File | Dimensione | Formato | |
---|---|---|---|
Luschi_PhD_Thesis.pdf
accesso aperto
Tipologia:
Tesi di dottorato
Licenza:
Open Access
Dimensione
6.78 MB
Formato
Adobe PDF
|
6.78 MB | Adobe PDF |
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.