Patients admitted to the Intensive Care Unit (ICU) are often treated with multiple high-risk medications. Yet, our knowledge of safety and effectiveness of pharmacotherapy in ICU patients is limited. Consequently, over- and underprescribing of indicated medications, and inappropriate choice of medications, frequently occur in ICU patients. Medication Recommender Systems (MRS) are novel systems that can assist physicians with the selection of appropriate medications and with flagging inappropriate medications by uncovering patterns and exploiting similarity among patients’ and medications’ data. MRS can provide personalized suggestions, which are inherently more useful, relevant and efficient.

You will contribute to the solution to this problem by:

1. Developing a proof-of-concept MRS for Amsterdam UMC’s ICU patients;
2. Investigating MRS potential value compared to current rule-based medication clinical decision support systems.

To achieve these goals, you will explore the use and development of recommendation techniques based on machine learning, deep learning and neurosymbolic AI to uncover potentially complex relationships between medication and patient data.

We are looking for a PhD candidate who is eager to develop and apply advanced AI systems that contribute to safer medication prescriptions in the ICU settings with the help of MRS.

• You will investigate how to develop and evaluate a suitable MRS for Amsterdam UMC’s ICU patients. This investigation will address a number of methodological topics; a non-exhaustive list includes: collaborative filtering, content-based filtering, hybrid recommender systems, multimodal recommender systems (with clinical variables, text and terminology/knowledge graphs), neurosymbolic recommender systems, autoencoder-based recommender systems, and natural language processing.
• You will provide efficient and scalable implementations of your methods and will integrate them with popular open-source systems. Via the Department of Medical Informatics and the ICU ward, you will have access to large datasets comprising tens of thousands of patient records, including clinical variables and clinical notes with free text.
• You will closely collaborate with the ICU ward, with possibilities for your research to impact the development of future medical AI tools in the ICU and other wards. You will join the Department of Medical Informatics, a vibrant community of talented researchers, with whom you will have the opportunity to interact. You will also have the opportunity to contribute to top-rated education programs.

Prerequisites

• Master's degree in computer science, machine learning, artificial intelligence, data science, medical informatics, or related fields.
• Hands-on experience in machine learning.
• Strong programming skills in Python and machine learning libraries (e.g., PyTorch, Sklearn).
• Creative and independent mindset.
• Capable of working in multidisciplinary environments.
• Fluency in English.

Not required, but helpful

• Experience with recommender systems, multimodal AI, neurosymbolic AI.
• Experience working with real-world (medical) data, e.g. having experience with data wrangling, analysis, and visualizations.
• Experience with writing and publishing scientific articles.
• Contributed to open-source projects.
• Can converse in Dutch or willingness to learn Dutch.
• Excited to work on a problem with societal impact.

• A flying start to your career in scientific research.
• Plenty of room for personal development with a wide range of training & development of academic skills.
• Working on large-scale and own research, with motivated colleagues.
• A contract for the duration of the project (4 years).
• Salary scale OIO: € 3.017 to € 3.824 gross per month (based on a fulltime workweek), depending on qualifications and experience.
• Additional benefits including an 8.3% end-of-year bonus and 8% holiday pay. Calculate your net salary here.
• Your pension is accrued at BeFrank. A modern, understandeble en fair pension.
• Excellent accessibility with public transportation and reimbursement of a large portion of your travel expenses. Additionally, we have plenty of parking spaces at the AMC location and a good bicycle scheme.

Amsterdam UMC

AMC Medical Research (AMR) is located at the AMC location. AMR supports scientific research in non-profit settings. AMR provides researchers with everything they need to excel. For example, AMR offers principal investigators (PIs) and project leaders guidance in the areas of project management, finance and human resources. Legal support is also provided for medical-scientific research projects. Watch the video below for more information.

Start your new job at AMR!

You will be appointed at the Medical Informatics department of Amsterdam UMC at the University of Amsterdam.

You will be supervised by Dr. Iacopo Vagliano and Prof. dr. Ameen Abu-Hanna. Dr. Vagliano is Assistant Professor of Artificial Intelligence and Health Data Science and works in the area of medical artificial intelligence, including health recommender systems, multimodal machine learning, deep learning, and neurosymbolic AI, notably combining structured clinical variables, unstructured clinical text and knowledge graphs. Prof. Abu-Hanna is a Principal Investigator in Methodology in Medical Informatics and has extensive experience in AI, ML, prognostic & causal modelling, and their statistical and clinical evaluation.