Trustworthy AI Multi Objective framework for digital health
Internship period: February to July 2027
School : University of Lyon 2
Laboratory: DISP lab
Required profil: master’s degree in computer science (or equivalent, such as an engineering school), Analytical mindset, Curiosity
Skills: Python, Machine Learning, Deep Learning, Data Sciences, Génie Logiciel.
In view of the AI adoption challenges, a considerable volume of research has been conducted in the areas of explainable
AI, fair AI and privacy-preserving AI. Innovative AI models, algorithms, and techniques are being proposed and developed.
However, the current research efforts to tackle the three challenges are remain fragmented and have culminated in a
variety of solutions with heterogeneous, non-interoperable, or even conflicting capabilities. Explainability, fairness and
privacy are inherently intertwined with a complex conflicting and/or complementary relationship between any two of
them. In the light of the complex intertwining relations across explainability, fairness and privacy, fragmented research
in each individual area without interacting with one another is not a sustainable pathway to achieve trustworthy AI.
However, the realization of trustworthy AI must be built in ways that ensure humans are always in ultimate control and
responsible for what the AI system will do. This is particularly crucial for digital health applications which involve
decisions that affect a person’s life, health and quality of life.
To this end, the MSCA SE HarmonicAI (https://harmonicai-project.uevora.pt/) is therefore aimed at building a multi-
objective co-design methodology which can take the three conflicting and/or complementary objectives together into
account to develop a coherent AI system that meets individual requirements, and at the same time settles on an agreed
trade-off. In this context, the WP6 proposed a multi-objective model selection algorithm to achieve a coherently
explainable, fair and private AI system. The evaluation metrics established in WP3-5 have been exploited to translate
healthcare stakeholders’ qualitative requirements into measurable quantitative objectives regarding explainability,
fairness and privacy.
The main objective of this proposal is to draw inspiration from the results achieved and focus on the implementation,
testing and evaluation of the developed trustworthy AI solutions in real-world digital health use cases. This proposal
serves as a focal point for the activities of all other WPs of the HarmonicAI project. It integrates the research outputs from
WP2-WP6 into three proof-of-concept AI-powered digital health use cases in France, UK and Thailand, to illustrate the
feasibility and evaluate the effectiveness of the proposed solutions. The use cases have been planned to cover the hospital resources management in France, the physiotherapy rehabilitation in the UK and the elderly mobility disorder prevention in Thailand.
Objectives of the proposal:
• Implement the proposed explainable, fair and private AI solutions in use cases.
• Evaluate the proposed human-machine collaborative multi-objective design framework for trustworthy AI.
• Evaluate the proposed guidelines for AI practitioners and healthcare stakeholders.
Proposed Work Plan:
• Understanding the HarmonicAI project’s results and conduct a brief literature review on Trustworthy AI Multi Objective framework in health care, guidelines and norms (1 month)
• Implement the proposed trustworthy AI paradigm, models and frameworks for use cases (1 months)
• Test and evaluate the trustworthy AI solutions (1 months)
• Evaluate the proposed guidelines in the cases (1 month)
• Writing a scientific article to highlight the results obtained (final 3 months)
Submit your application (CV, motivation letter, transcripts M1 and M2, recommendation letters) to: aicha.sekhari@univ-lyon2.fr