Open Postdoctoral position, faculty mentor Emily Alsentzer

The Alsentzer Lab at Stanford is seeking a postdoctoral fellow to advance trustworthy, deployable AI methods for healthcare. 

The Alsentzer Lab is an interdisciplinary research group in the Department of Biomedical Data Science at Stanford University. Our mission is to leverage machine learning (ML) and natural language processing (NLP) to augment clinical decision-making and expand access to high-quality healthcare. Our lab develops new methods to improve model trustworthiness and leverages heterogeneous clinical data, such as electronic health records and genomic data, to provide actionable insights to clinicians, researchers, and patients. The lab bridges computer science and medicine through affiliations with Stanford’s Department of Computer Science and the Data Science team at Stanford Health Care.

Our research spans both core methodological advancements (e.g., developing novel ML architectures and evaluation metrics) and translational applications (e.g., deploying AI tools into clinical workflows). Candidates with experience in either—or both—are encouraged to apply. 

The postdoctoral fellow will work closely with Dr. Alsentzer to shape a research agenda that aligns with their interests while addressing critical challenges in AI for healthcare. Potential research directions include:

• How can we generate faithful and verifiable summaries of longitudinal EHR data?
• How can we efficiently adapt foundation models to local clinical contexts?
• How can we design multimodal foundation models to better model and predict disease progression?
• How can we better measure and mitigate the impact of biased training data for downstream clinical uses?
• Can we improve the factuality and reasoning of foundation models by integrating external biomedical knowledge? 
• Can we design models that leverage clinically useful information without relying on “shortcut” features that capture the processes of medicine? 
• How can we develop few-shot learning approaches for diagnosing and treating patients with rare diseases?
• Can we design clinically-useful metrics for evaluation and continuous monitoring after deployment?

This position is designed to equip postdocs with the skills and experience to lead interdisciplinary research at the intersection of AI and healthcare. Fellows will have access to critical resources for interdisciplinary research in ML for Health, including HIPAA-compliant compute infrastructure with high memory GPUs and access to Stanford Healthcare data, which includes EHRs for over 5M patients and 100M clinical notes.  These resources will enable the development of impactful methods that can be translated into real-world clinical applications.

We aim to foster a collaborative and inclusive research environment where interdisciplinary ideas thrive. We welcome researchers from diverse backgrounds and encourage applications from those traditionally underrepresented in AI and healthcare.