Cao (Danica) Xiao
Google Scholar: https://scholar.google.com/citations?user=ahaV25EAAAAJ&hl=en&oi=ao
https://www.linkedin.com/in/caoxiao/
Email: cao.xiao@gehealthcare.com
Current Position:
VP of AI, GE Healthcare
Previous Experience:
VP of AI/ML, Relativity
Senior Director of AI/ML, Amplitude
Global Head of Machine Learning, IQVIA
Research Lead, MIT-IBM Watson AI Lab
Research Staff Member, IBM Research
-------------------------------------------------------- Education:
Ph.D. in Machine Learning,
University of Washington, Seattle
Our textbook was published!
Please check it out. https://link.springer.com/book/10.1007/978-3-030-82184-5.
About The Textbook:
In collaboration with Professor Jimeng Sun from UIUC, we wrote this textbook to Introduce the concepts of deep learning models in the context of healthcare to students and professionals who have interest. It took us 2 years of hard work to write it but totally worth it.
Sunstella Foundation
We founded the Sunstella Foundation, and will donate the book income to help grow students in the field of technology and engineering.
Summary
Cao (Danica) Xiao is the VP of AI at GE Healthcare. At GE Healthcare, she is leading the AI science and AI engineering teams in developing medical imaging foundation models, large language models for patient care and operational efficiencies, as well as responsible AI in GE Healthcare’s AI transformation. Previously she has held leadership positions at multiple technology and healthcare companies, including VP of AI/ML at Relativity, Senior Director of Machine Learning of Amplitude, Global Head of Machine Learning of IQVIA, and research lead of MIT-IBM Watson AI Lab at IBM Research. She has successfully driven the creation of machine learning innovation for industry AI transformation, particularly in healthcare and medicine. Besides, she is a passionate machine learning researcher and thought leader with over 160+ highly cited papers (citation 9876, h-index 41, i10-index 85) published in leading AI/ML venues, with strong focus on the topic of AI for healthcare (EHR analysis, RWE, clinical trials, health monitoring, medical imaging, and drug discovery ). She also co-authored a textbook on deep learning for healthcare which is used in top CS graduate programs such as UIUC, GaTech, and PSU. Recently she was named by the largest Chinese internet company Baidu as “Top Chinese Young Scholars in Artificial Intelligence” in 2022 and “Top Chinese Female Scholars in Artificial Intelligence” in 2023. Danica got her Ph.D. degree in machine learning from University of Washington, Seattle in 2016.
News
[NeurIPS 2024] Our paper "Knowledge Graph Fine-Tuning Upon Open-World Knowledge from Large Language Models" has been accepted by NeurIPS 2024!
[EMNLP 2024] We've got one paper accepted by EMNLP Main conference, and two papers accepted by EMNLP Findings!
[KDD 2024] Our paper on "Synthesizing Multimodal Electronic Health Records via Predictive Diffusion Models" has been accpted by KDD 2024!
[ACL 2024] Our paper on "Unity in Diversity: Collaborative Pre-training Across Multimodal Medical Sources" has been accepted by ACL 2024!
[ICML 2024] Our paper on federated conformal prediction that address both data privacy and data quality issues for predictive models especially for healthcare tasks has been accepted by ICML 2024!
[IJCAI 2024] Our survey paper on AI for healthcare has been accepted by IJCAI 2024!
[IJCAI 2024] Our foundation framework on scaling medical tabular data predictors via data consolidation, enrichment, and refinement using LLM has been accepted by IJCAI 2024!
[NAACL 2024] Two papers accepted by NAACL 2024!
[ICLR 2024] Our paper "GraphCare: enhancing healthcare predictions with personalized knowledge graphs" has been accepted by ICLR 2024!
[AAAI 2024] Our paper "ConSequence: Synthesizing Sequences for Electronic Health Record Generation" has been accepted at the 38th AAAI Conference on Artificial Intelligence (AAAI-24).
[EMNLP 2023] Our paper "AutoTrial: Prompting Language Models for Clinical Trial Design" got accepted by The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023).
[Nature Communications 2023] Our paper "Synthesize high-dimensional longitudinal electronic health records via hierarchical autoregressive language model" got published in Nature Communications!
[ACM BCB' 2023] Three papers accepted by The 14th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM BCB) 2023.
[KDD 2023] Our paper "MedLink: De-Identified Patient Health Record Linkage" is accepted by KDD 2023.
[ICML 2023] Our paper "Fast Online Value-Maximizing Prediction Sets with Conformal Cost Control" is accepted by ICML 2023.
Named by Baidu as Top Chinese Female Scholars in Artificial Intelligence, March, 2023
[Nature Chemical Biology 2022] Nov 2022, our paper on Artificial Intelligence Foundation for Therapeutic Science was published on Nature Chemical Biology.
[NeurIPS 2022] Sept 2022, our paper on augmented tensor decomposition to adapt data construction toward downstream tasks is accepted by NeurIPS 2022.
Awards
The Top 50 Women Leaders of Washington for 2024, Women We Admire, 2024
Top Chinese Female Scholars in Artificial Intelligence, Baidu, 2023
Top Chinese Young Scholars in Artificial Intelligence”, Baidu, 2022
Best paper published in 2018 in “AI in Health”. IMIA Yearbook on Medical Informatics, 2019.
First runner-up for IEEE-TASE best paper of 2019, 2019
Manager's Choice Award, IBM Research, 2018
Winner of the 2016 Parkinson's Disease PPMI Data Challenge, Michael. J. Fox Foundation, 2016
Third Place of National IIE-CIS mHealth App Competition, IISE, 2016
Outstanding Female Award, Society of Women Engineers (SWE), 2015-2016
GSFEI Top Scholar Award, University of Washington, Seattle, 2012-2014
Spring Research Scholarship, American Statistical Association/Society for Industrial and Applied Mathematics, Chicago IL, 2016
Research Interest
ML/DL for user behavioral data modeling
ML/DL for marketing cohort targeting and product recommendation
ML/DL for online experimentation based on user data
knowledge graph and graph inference for SaaS solutions
Auto-ML for scalable SaaS model serving
ML for scalable and automatic customer success monitoring and business growth