Host institution: ACADEMISCH MEDISCH CENTRUM BIJ DE UNIVERSITEIT VAN AMSTERDAM, Netherlands
In digitized health environments, there is a large amount of health data that could be exploited so as to ease the decision making of the involved stakeholders, and which currently remain unused. The combination of efficient data analytics with Multi-access Edge Computing (MEC) capabilities can be very beneficial especially in acute care, where urgent decisions should be made. In parallel, the European General Data Protection Regulation (GDPR) obliges healthcare organizations to safeguard access to Electronic Medical Records (EMRs) with procedures to control, track and monitor every access to the data. This obligation includes guaranteeing transparency regarding what happened to the patient data and data breaches detection. However, the technical means for complying with these obligations are still limited, hampering trust among stakeholders for medical data sharing in this interconnected healthcare ecosystem. As a result, there is a need for secure medical data analytics techniques that, on the one hand, ensure secure data sharing among the involved entities, while on the other hand, exploit it to derive useful well-informed insights quickly requiring all, often distributed sources of data, thus increasing the efficacy of acute healthcare services.
Doctoral Candidate’s (DC) role: The DC will develop and validate novel solutions that comply with GDPR in terms of transparency for enhanced data sharing and Artificial Intelligence (AI)-based decision support, allowing multi-modal AI-based solutions. The integrated solution will present, in a simple-to-understand manner, how the available and accessed medical data indicate prognosis and treatment decisions, while ensuring full control and recording of access (what, when, why, how, & who had access), offering data access transparency for stakeholders with 50% more information shown to patients about accesses to their EMRs than State-of-the-Art (SoA), without jeopardizing system security, by leveraging modern blockchain approaches. AI methods to improve stroke triage will be developed (based on simulated datasets generated by initial anonymized gender agnostic-data) utilizing remote access to EMRs, while targeting at higher data privacy processing automation with 50% decrease in the manual work required for data collection than SoA. The solutions will be evaluated in the context of acute care in collaboration with ambulance personnel, emergency control room, general practitioners, and peripheral/specialized hospitals, measuring how the secure information handling and AI data analysis accelerate diagnosis, treatment decisions, and hospital selection.
|A.1. Living allowance (per month)
|A.2. Mobility allowance (per month)
|A.3. Family allowance (per month if applicable)
Doctoral Candidate (DC) is recruited under a Type A employment contract. The living allowance is a gross amount, including compulsory deductions under national law, such as employer and employee social security contributions and direct taxes. Moreover, the DC will be eligible to receive mobility allowance and family allowance (if applicable) that could also be subject to taxation.