Foundation Model

EHRSHOT releases the weights and code of a 141M-parameter foundation model pretrained on 2.57 million deidentified EHRs from Stanford Hospital.

Access#

• Model

Additional Details#

The foundation model is based on the CLMBR architecture (Steinberg et al. 2021), which uses a next token prediction task to learn representations for patients.

For more information, please read the original EHRSHOT paper.

Questions?#

For questions and feedback, please open an Issue on Github