Job offer
PhD Position: Generative AI for Simulating a Digital PD Twin

"AIPD" is a doctoral network made up of 15 Partners and funded by Marie Skłodowska-Curie Actions (MSCA) which is a part of Horizon Europe, the MSCA are the European Union's flagship funding programme for doctoral education and postdoctoral training of researchers. Funding is provided for doctoral candidates from both inside and outside Europe to carry out individual project work in a European country other than their own. AIPD Doctoral Network will train a cohort of 14 Doctoral Candidates (DCs) in an intersectoral, international and interdisciplinary setting with the aim to establish an international, interdisciplinary graduate school that educate the next generation of medical data scientists, with a strong translational focus bridging academia and industry.

AIPD established a comprehensive training program offering PhD students not only a robust foundation in data science, including AI/ML and digital health, but also a deep understanding of ethical, legal and regulatory frameworks, including GDPR, the European Health Data Space and the AI Act. Our curriculum is unique in its integration of entrepreneurial thinking and a focus on Parkinson's disease (PD) as an application field. At the same time, the methodologies and insights gained will have broader applications in various disorders, thus applicable to other areas of healthcare.

Ihre Aufgaben

The AIPD training program offers PhD candidates an interdisciplinary, translational, inter-sectoral and highly individualized training program encompassing

• Medical data collection, semantics and governance

• Statistics, data mining and AI/ML, including technical aspects of trustworthiness of AI/ML

• Practical hands-on programming

• Digital health with focus on neurology, including image analysis

• Basics of PD neuropathology and genetics

• Ethical, legal and regulatory aspects of health data science

  Our research objectives

  The AIPD research program addresses three major questions focusing on PD as a medical application field:

• How can AI/ML algorithms support physicians to earlier diagnose PD, stratify patients into relevant subgroups, prognose disease progression and assess the response to treatment on an individual basis (precision medicine)?
• How can AI/ML algorithms contribute to a more objective monitoring of disease symptoms, e.g. via digital voice and gait recordings, and neuroimaging?
• How can all of that be realized in an ethical, legally compliant and trust preserving manner in agreement to the principals of trustworthy AI? This encompasses queries about the generalisability of AI/ML, potential statistical biases, reproducibility, and societal resilience. It also touches on ethical considerations, lawful application, and the explainability of model predictions. Additionally, this scope includes exploring the causal connections between AI/ML model inputs and their respective outputs.

Our overarching vision with this program is to make a clear step towards a better individualized medicine. Our focus on PD as an indication area is motivated by its strongly increasing prevalence coupled with the fact that far less research has been conducted compared to other medical subfields like oncology., The objectives of this subproject are to: A) Implement a generative AI approach for "personalized" simulation of disease outcome trajectories (e.g. UPDRS sub-item scores). B) Develop methods to interpret the disease dynamics learned by those methods. C) Develop an approach to merge synthetic patient trajectories across studies, e.g. to generate a "global" synthetic control arm. D) Develop methods that allow a selection of synthetic controls according to user defined selection criteria.,

• development & application of innovative algorithms in the field of machine learning, specifically with focus on precision medicine, digital health and AI trustworthiness

• presentation of results via scientific publications, workshops and conferences as well as to external collaboration partners within the AIPD network and beyond

• active support of supervisor in terms of acquisition of new projects and technology transfer, Applicants must not have resided or carried out their main activity (work, studies, etc.) in the country of the recruiting beneficiary for more than 12 months in the 36 months immediately before their date of recruitment. Compulsory national service, short stays such as holidays, and time spent as part of a procedure for obtaining refugee status under the Geneva Convention are not taken into account. Date of Recruitment means the first day of the employment of the researcher for the purposes of the action (i.e. the starting date indicated in the employment contract or equivalent direct contract).

Ihr Profil

The advertised subproject is fully funded by the Marie Skłodowska-Curie European Training Network AIPD. We are seeking a highly skilled and motivated Research Scientist with a demonstrable background in Data Science (M.Sc. with excellent grades in Computer Science, Bioinformatics, Mathematics or a similar subject). The successful candidate should have a passion for research on computational methods in medicine. The candidate will work in a highly interdisciplinary environment together with leading experts from academia and industry in data science, medicine, law, and health economy. PhD students will be co-supervised by two experienced scientists, one from academia and one from industry. Each PhD student will perform at least one lab rotation to get to know different organizations.,

• Ability to work independently.

• Very good English speaking and writing skills.

• Very good communication skills., Master Degree or equivalent

  Research Field Computer science » Programming

  Education Level Master Degree or equivalent

  Research Field Medical sciences » Health sciences

  Education Level Master Degree or equivalent,

• Strong background in AI/ML

• Experience with medical data is highly desirable.

• Familiarity with XAI techniques and causal inference methods is a plus.

• Demonstrable proficiency in python programming and using libraries such as PyTorch.

  Specific Requirements

  Formal rules for PhD admission:

  Applicants hold a Master's degree and meet the admission requirements of the doctorate degree program of the corresponding university of this position.

  Applicants must be doctoral candidates, i.e. not already in possession of a doctoral degree at the date of the recruitment. Researchers who have successfully defended their doctoral thesis but who have not yet formally been awarded the doctoral degree will not be considered eligible.

  Language Skills:

  Applicants should have professional knowledge in (Scientific) English language.

Wir bieten Ihnen

• Full-time employment contracts at the selected AIPD host institution for 36 months.

• The exact salary is to be confirmed upon appointment. The basic gross amount is composed of Living Allowance = 3400 EUR/month (multiplied by the MSCA Country Correction Coefficients) AND Mobility/Family Allowance = 600 to 1260 EUR/month, depending on the family situation.

• The recruited Doctoral Candidates are expected to complete their PhD theses by the end of or shortly after their 3-year recruitment.

  The Doctoral Candidates will actively participate in a 3-year AIPD training program and deliver research results. The training includes

  a) research training through individual research projects,

  b) courses at the host institutions and events for scientific and transferable skills training,

  c) training secondments to other AIPD partners emphasizing cross-sectoral exposure.

  The Doctoral Candidates will perform excellent in-depth research under cross-sectoral supervision in the collaborative MSCA Doctoral Network.

Kontakt

Details about the selection process can be found at https://aipd-dn.eu.