关于
I’m a researcher in the Biomedical Imaging team within Microsoft Health Futures, based at Microsoft Research Cambridge (UK). My background is in human-computer interaction (HCI). I study innovative and responsible approaches for applying AI and Machine Learning in real-world healthcare contexts.
My current work in Project MAIRA leverages multimodal, frontier AI technology to enhance radiology workflows and help radiologists provide better care and achieve better outcomes for patients. Working within an interdisciplinary team of AI researchers and engineers, I follow a human-centered approach to understanding opportunities and challenges for multimodal AI design and clinical workflow integration; as well as in devising clinically relevant evaluation criteria and metrics for systematically assessing the quality of generative AI outputs.
More broadly, this work enables me to define strategy and processes that ensure AI technology is developed safely and responsibly. Working as part of Microsoft’s Aether working groups and with members of the Office of Responsible AI (ORA), a key focus of my work is the development of tools and other resources to drive forward the adoption of responsible AI practices; to advance public understanding, and to inform AI policy. This includes educational materials to appropriately communicate AI capabilities and limitations to end-users, and for considering wider socio-technical implications of AI use.
For more up-to-date information, please visit my homepage: https://designandwellbeing.com/
Past projects at Microsoft include:
- Project Talia, which investigated the use of ML models to improve the quality of care delivered through online psychotherapy programs.
- Project Tokyo that developed an interactive, computer-vision based system to extend the capabilities of people who live with vision impairments.
- Project Torino, and its commercialized counterpart Code Jumper, a collaborative learning environment for teaching children how to code independent of their visual abilities.
- Disruptive Displays, a research project that explored alternative approaches to designing and configuring digital displays (as a material that can be cut, folded, and externally imaged).
精选内容
Project MAIRA
Project MAIRA is a research project from Microsoft Health Futures that builds innovative, multimodal AI technology to assist radiologists in delivering effective patient care and to empower them in their work.
GPT-4's potential in shaping the future of radiology
This research paper is being presented at the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023), the premier conference on natural language processing and artificial intelligence. In recent years, AI has been increasingly integrated into healthcare, bringing…
AI Models vs. AI Systems: Understanding Units of Performance Assessment
As AI becomes more deeply integrated into every aspect of our lives, it is essential that AI systems perform appropriately for their intended use. We know AI models can never be perfect, so how do we decide when AI performance…