We are seeking one Industrial Design PhD candidate for the Advancing Cancer Care with AI research project.
Project backgroundThe Eindhoven MedTech Innovation Center (e/MTIC) is a public-private partnership aimed at creating and growing an ecosystem that offers a fast track to high-tech health innovations. Within this ecosystem, we aim to create impactful innovations in the oncology domain, through close multidisciplinary collaboration between an academic partner (Eindhoven University of Technology), top-clinical hospital (Catharina Hospital Eindhoven) and industrial partner (Philips Research and Philips Experience Design). Our specific focus of this project is to advance clinical decision support for (lung & pancreas) cancer care with artificial intelligence (AI), taking a patient-centered and physician-centered approach to optimize physician-AI collaboration and adoption of AI in clinical practice. This project builds on prior work that has been developed within e/MTIC in recent years.
This design PhD position is one of in total 4 PhD positions in this project. The project aims to
a) iteratively define, build and validate how we can make AI algorithms 'ready' for real-world conditions under which they have to work in clinical practice,
b) explore using a research-through-design approach what is needed (from AI and physician) for an optimal collaboration between the physician and the AI, and
c) measure the holistic effect of the physician-AI collaboration solutions on adoption and use of AI in the field, i.e. appropriate use, impact on patient outcomes and physician experience. It is key to design human-centered AI solutions that encourage long-term use and trustworthy engagement, and that also focus on the patient and physicians as the central stakeholders.
You will be part of an innovative multi-disciplinary teamThis design PhD position will be embedded in a multidisciplinary team of in total 4 PhD positions covering clinical, machine learning, and design expertise. The project activities are organized in 3 tightly interlinked work packages, of which work package 2 is led by this design PhD position.
WP1. Machine Learning for robust & trustworthy AIThis activity, led by the machine learning PhD student, aims to develop robust and interpretable AI in medical imaging. It will address a subset of clinical application areas (e.g., lung cancer and pancreas cancer), by development and maturation of AI methods for the selected clinical use cases.
WP2. User experience and interface design and evaluation for optimal physician-AI collaborationThis activity, led by the design PhD student, aims to iteratively develop and evaluate UI/UX innovations to shape optimal physician-AI collaboration, as well as methods to evaluate the clinical experience with end-users. This will drive the AI models developed in WP1 and integrate AI-based outputs generated in WP1. This activity will investigate novel domain-specific quality criteria, methods and tools regarding AI integration in a clinical environment. These will be used in collaboration with WP3 to evaluate the impact of the solution on the clinical experience (e.g. trust in the AI solution and its recommendations) and outcomes (e.g. decision quality). More details of this position are provided below.
WP3: Clinical data collection, user testing and evaluationIn this activity, led by the two clinical PhD students, the AI algorithms developed in WP1, clinician-AI collaboration innovations developed in WP2 and the experience with AI will be evaluated in clinical practice through retrospective and semi-prospective clinical studies.
The 4 PhD candidates will closely collaborate and share data, AI models, technological platforms and methodologies as complementary focus points of each PhD position.
Industrial Design PhD position: designing and evaluating optimal physician-AI collaborationIn the design-research trajectory, the PhD student will explore how to design and evaluate the optimal physician-AI collaboration. This can be achieved through design contributions to machine learning challenges, such as AI explainability, interpretability and uncertainty quantification, as well as user interface (UI) and user experience (UX) design challenges, such as how and when to show AI-generated findings, explanations and visualize uncertainty for professional end-users. In fact, designing optimal physician-AI collaboration is a combined data science and UI/UX design challenge and will be treated as such in this project.
We are interested in understanding what is the optimal envisioned collaboration between physician and AI to foster adoption and appropriate trust of AI in clinical practice. Important questions are:
- What are quality criteria for the optimal physician-AI collaboration? And how can these be measured and tested in an iterative process? (e.g., physician appropriately trusts/ relies on the AI, optimally adds value to clinician and patient, seamlessly fits in workflow, regulatory and ethics).
- How to design AI and user interfaces for optimal physician-AI collaboration, and which underlying generalizable principles explain this? This will manifest in iteratively creating and evaluating data-driven prototypes embodying the AI creating a seamless clinical workflow and trusted experience (e.g., using data visualizations, medical images, and 3D anatomical renderings).
- What tools do design & development teams need to iteratively design and evaluate physician-AI collaboration over time?
The PhD student will explore these questions by applying the research through design methodology with hands-on making and prototyping in close contact with prominent users of this system such as radiologists, clinicians and surgeons. These will be closely involved in the co-creation process.
Eindhoven University of Technology (TU/e, www.tue.nl) is one of Europe's leading research universities. The Eindhoven area, in the southern part of the Netherlands, is one of Europe's top 'innovation ecosystems', with many high-tech companies and institutes. TU/e is intertwined with many of these companies and institutes, and research at TU/e is characterized by a combination of academic excellence, industrial relevance and societal interweaving. The
Department of Industrial Design (ID) of the Eindhoven University of Technology (TU/e), founded in 2001, is a maturing department with over 650 students, both Bachelor and Master, and around 40 research staff members and about 10 lecturers. The mission of the department of Industrial Design at TU/e is Research on and Education in
the Design of Systems with Emerging Technologies in a Societal Context. The PhDs will be under the supervision of Prof. dr. Lin-Lin Chen and Dr. Mathias Funk in the Department of Industrial Design at Eindhoven University of Technology. The project will be executed in collaboration with Philips Experience Design; Dr. Jon Pluyter and Dr. Saskia Bakker of Philips Experience Design are closely involved in the supervision of the PhD students. At the TU/e, the positions are situated within the research cluster of 'Future Everyday'. The Future Everyday cluster investigates the everyday interactions between individual people and the highly interconnected technology that surrounds them. Researchers measure, model and design for the user experience when individuals interact with social-technological networks in their homes, at work, in transit, while doing sports or going out.
Prospective starting date: August 2021.