Stephanie L. Hyland

Hello! I am a Principal Research Manager in Microsoft Research based in Cambridge, UK. I work on artificial intelligence for healthcare, which means I want to build multimodal models of human health and biology, and understand how they work.

My research has spanned a variety of topics in healthcare as well as machine learning, such as building an early-warning system for circulatory failure in intensive care patients, drafting radiology reports with a multimodal large language model, and automating biomarker discovery in histopathology with interpretable deep learning. Currently, myself and my team are thinking a lot about building multimodal models of biology as part of Quine.

I joined Microsoft Research in 2019. Before that, I received a PhD in computational biology and medicine from the Tri-Institutional PhD Program of Cornell University, during which time I was situated at the Memorial Sloan Kettering Cancer Center in NYC, and later ETH Zürich. Before that, I studied theoretical physics at Trinity College Dublin, and mathematics (Part III) at the University of Cambridge.

Some of my other interests include hiking, board games, and watching the wildlife in my garden.

selected publications

Early prediction of circulatory failure in the intensive care unit using machine learning

Stephanie L. Hyland, Martin Faltys, Matthias Hüser, Xinrui Lyu, Thomas Gumbsch, Cristóbal Esteban, Christian Bock, Max Horn, Michael Moor, Bastian Rieck, Marc Zimmermann, Dean Bodenham, Karsten Borgwardt, Gunnar Rätsch, and Tobias M. Merz

Nature medicine, 2020

Bib HTML

@article{hyland2020early,
  title = {Early prediction of circulatory failure in the intensive care unit using machine learning},
  author = {Hyland, Stephanie L. and Faltys, Martin and H{\"u}ser, Matthias and Lyu, Xinrui and Gumbsch, Thomas and Esteban, Crist{\'o}bal and Bock, Christian and Horn, Max and Moor, Michael and Rieck, Bastian and Zimmermann, Marc and Bodenham, Dean and Borgwardt, Karsten and R{\"a}tsch, Gunnar and Merz, Tobias M.},
  journal = {Nature medicine},
  volume = {26},
  number = {3},
  pages = {364--373},
  year = {2020},
  publisher = {Nature Publishing Group US New York},
}

Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing

Shruthi Bannur^*, Stephanie L. Hyland^*, Qianchu Liu, Fernando Pérez-García, Maximilian Ilse, Daniel C. Castro, Benedikt Boecking, Harshita Sharma, Kenza Bouzid, Anja Thieme, Anton Schwaighofer, Maria Wetscherek, Matthew P. Lungren, Aditya Nori, Javier Alvarez-Valle, and Ozan Oktay

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

arXiv Bib Blog Slides

@inproceedings{bannur2023learning,
  title = {Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing},
  author = {Bannur, Shruthi and Hyland, Stephanie L. and Liu, Qianchu and Pérez-García, Fernando and Ilse, Maximilian and Castro, Daniel C. and Boecking, Benedikt and Sharma, Harshita and Bouzid, Kenza and Thieme, Anja and Schwaighofer, Anton and Wetscherek, Maria and Lungren, Matthew P. and Nori, Aditya and Alvarez-Valle, Javier and Oktay, Ozan},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages = {15016--15027},
  year = {2023},
}

MAIRA-2: Grounded radiology report generation

Shruthi Bannur, Kenza Bouzid, Daniel C Castro, Anton Schwaighofer, Anja Thieme, Sam Bond-Taylor, Maximilian Ilse, Fernando Pérez-Garcı́a, Valentina Salvatelli, Harshita Sharma, Felix Meissen, Mercy Ranjit, Shaury Srivastav, Julia Gong, Noel C.F. Codella, Fabian Falck, Ozan Oktay, Matthew P. Lungren, Maria Teodora Wetscherek, Javier Alvarez-Valle, and Stephanie L. Hyland

arXiv:2406.04449, 2024

arXiv Bib

@article{bannur2024maira,
  title = {MAIRA-2: Grounded radiology report generation},
  author = {Bannur, Shruthi and Bouzid, Kenza and Castro, Daniel C and Schwaighofer, Anton and Thieme, Anja and Bond-Taylor, Sam and Ilse, Maximilian and P{\'e}rez-Garc{\'\i}a, Fernando and Salvatelli, Valentina and Sharma, Harshita and Meissen, Felix and Ranjit, Mercy and Srivastav, Shaury and Gong, Julia and Codella, Noel C.F. and Falck, Fabian and Oktay, Ozan and Lungren, Matthew P. and Wetscherek, Maria Teodora and Alvarez-Valle, Javier and Hyland, Stephanie L.},
  journal = {arXiv:2406.04449},
  year = {2024},
}

Sparse concept attribution for histomorphological hypothesis generation from whole-slide classifiers

Tristan Lazard, Kenza Bouzid, Julius Hense, Shruthi Bannur, Daniel Coelho Castro, Daniel Shao, Rajesh Jena, Drew Williamson, and Stephanie L. Hyland

arXiv:2609.02985, 2026

arXiv Bib

@article{lazard2026sparse,
  title = {Sparse concept attribution for histomorphological hypothesis generation from whole-slide classifiers},
  author = {Lazard, Tristan and Bouzid, Kenza and Hense, Julius and Bannur, Shruthi and de Castro, Daniel Coelho and Shao, Daniel and Jena, Rajesh and Williamson, Drew and Hyland, Stephanie L.},
  journal = {arXiv:2609.02985},
  year = {2026},
}