dots-image

ABOUT US

Learn more about us.

The Bitterman Lab is a research group within the AI in Medicine Program at Mass General Brigham and the Department of Radiation Oncology at Brigham and Women’s Hospital/Dana-Farber Cancer Institute, Harvard Medical School. We are a multidisciplinary team focused on clinical natural language processing and AI safety and oversight in healthcare. While broadly interested in the healthcare domain, we apply our expertise in clinical oncology to develop AI methods that improve cancer patients' experiences and outcomes.

Our current areas of active research include:

  • Large language model evaluation and scalable oversight for healthcare.
  • Automated data mining from the electronic health records to accelerate cancer care and research.
  • Applying natural language processing advances to enhance health literacy and patient-provider communication.
  • Translational AI: Clinical trials of AI and frameworks for ethical, patient-centered AI implementation.

Learn more about our Research, Publications, and Team.


The Bitterman lab is grateful to recieve funding for our research from the NIH/NCI, the American Cancer Society (ACS), the American Society for Radiation Oncology (ASTRO), and the American Association for Cancer Research (AACR).

danielle

Danielle Bitterman, MD

Principal Investigator

Assistant Professor, Harvard Medical School

Translating advances in natural language processing into safer and more equitable healthcare.

Recent Publications.

NEWS AND HIGHLIGHTS

Updates from the lab.

5 min read

LLMs and VLMs for healthcare

Highlights from our year of investigations into clinical potentials and risks of LLMs and VLMs

BittermanLab

November 11, 2024

1 min read

Bitterman Lab research is featured in The New York Times!

Reporting on LLMs for patient portal messaging in the newspaper of record

BittermanLab

September 24, 2024

3 min read

Unveiling the fragility of language models to drug names

RABBITS: A new medical robustness investigation and LLM benchmark

BittermanLab

July 19, 2024

3 min read

Introducing Cross-Care

Our new benchmark to assess the healthcare implications of pre-training data on language model bias

BittermanLab

April 30, 2024

7 min read

Large language model assistance

Study out in Lancet Dig Health: How does using LLMs effect patient portal messaging?

BittermanLab

April 24, 2024

5 min read

LLMs for social determinants of health

LLM methods to detect SDoH from unstructured EHR text - published in npj Digital Medicine

BittermanLab

January 11, 2024

5 min read

LLMs for cancer treatment advice

Can ChatGPT provide guideline-concordant cancer treatment recommendations?

BittermanLab

September 1, 2023