We are seeking a highly motivated candidate for a PostDoc position focused on visual analytics for explainable and trustworthy AI for risk assessment in healthcare.
This position is part of the SmartCHANGE (www.smart-change.eu
) Horizon-Europe Research & Innovation project whose overall goal is to develop trustworthy AI-based decision-support tools to help health professionals and citizens reduce long-term risk of non- communicable chronic diseases (NCDs). The aim is to accurately assessing the risk of children and youth, including those with difficult-to-detect risks, and promoting the delivery of optimized risk-lowering strategies.
The postdoc will address the human-in-the-loop aspects for model self-auditing, and prediction understanding through visual analytics. The methods will aim at model understanding by machine-learning experts and health professionals. Visual analytics solutions will develop around the concept of counterfactuals to support bias identification, uncertainty estimation, and analysis of predictive and prescriptive model results. One of the main challenges will be to develop these solutions in the context of missing and heterogeneous data.
It is expected to develop prototypes based on the proposed methods following a suitable visual design process. The evaluation will be performed in collaboration with other members of the SmartChange consortium following, e.g., co-creation design approaches.
It is expected that the Postdoc will also play a relevant role in the organization and coordination of the project with the different members of the consortium and stakeholders.
The project will be developed within the visualization cluster under the supervision of Prof. Anna Vilanova (a.vilanova[at]tue.nl) and in strong collaboration with the Data and Artificial Intelligence cluster specifically Prof. Mykola Pechenizkiy group.
The visualization cluster (https://research.tue.nl/en/organisations/visualization
) at TU/e has a strong track record in visualization and visual analytics for ML models and high- dimensional data. It has generated several award winning contributions at major visualization conferences (IEEE VIS, IEEE InfoVis, IEEE VAST, EuroVis); several successful start-up companies (MagnaView, Process Gold and SynerScope); and a number of techniques that are used on a large scale world-wide.