You need to agree to share your contact information to access this model
This repository is publicly accessible, but you have to accept the conditions to access its files and content.
You agree to all terms outlined in 'The EHRSHOT Credentialed Health Data License' (see https://shahlab.stanford.edu/ehrshot_license). Access requires a verified CITI training certificate using the same process outlined by PhysioNet (see https://physionet.org/about/citi-course/) Please provide proof via the verification URL, which takes the form https://www.citiprogram.org/verify/?XXXXXX. You agree to not use the model to conduct experiments that cause harm to human subjects.
Log in or Sign Up to review the conditions and access this model content.
MOTOR-T-Base
This is a 143 million parameter autoregressive foundation model pretrained on 2.57 million deidentified EHRs from Stanford Medicine.
This is the model from (Steinberg et al. 2023).
As input, this model expects a sequence of coded medical events that have been mapped to Standard Concepts within the OMOP-CDM vocabulary. The model generates representations of patients which can then be used for downstream prediction tasks.
Model Details
Model Description
- Developed by: Shah lab @ Stanford University
- Funded by: Stanford Healthcare
- Shared by: Shah lab @ Stanford University
- Model type: MOTOR (Steinberg et al. 2023)
- Language(s) (NLP): Electronic health record codes
- License: CC-BY NC 4.0
- Finetuned from model: N/A -- trained from scratch
Model Sources
Uses
This model is intended to generate representations for patients based on the structured data within their electronic health record. These representations are ideally used for time-to-even-modeling, but can also be used for other downstream tasks such as predicting diagnoses, detecting anomalies, or doing propensity score matching for causal inference.
Direct Use
You will likely want to tune the model for your downstream use case.
Out-of-Scope Use
This model is for research purposes only. It is not for use in any real-world decision making that impacts patients, providers, or hospital operations.
Bias, Risks, and Limitations
This model was trained on a corpus of 2.57 million patients from Stanford Medicine. The model will thus reflect the patterns of how care is delivered at Stanford Medicine, in addition to the racial and socioeconomic makeup of Stanford Medicine's patient base. This model may not generalize well to other hospitals and demographic mixes.
How to Get Started with the Model
We recommend getting started by looking at our tutorial repository: https://github.com/som-shahlab/motor_tutorial
Training Details
Full training details are provided in our accompanying paper, MOTOR: A Time-To-Event Foundation Model For Structured Medical Records.
Training Data
The model is trained on 2.57 million patients from the Stanford Medicine Research Data Repository (STARR), which contains EHR data from both Stanford Health Care (primarily adult care) and Lucile Packard Children’s Hospital (primarily pediatric care). The dataset contains only structured data (i.e. no clinical text or images) and covers demographics (e.g. age, sex, race), diagnoses, procedures, laboratory results, medication prescriptions, and other coded clinical observations. The data is formatted according to the Observational Medical Outcomes Partnership Common Data Model (OMOP-CDM). All data that we work with is deidentified.
Training Procedure
We train our model using an time-to-event pretraining objective, i.e. predict the time until a particular code appears in a patient's timeline.
Preprocessing
We use the FEMR Python library for data preprocessing.
Training Hyperparameters
- Learning rate: 1e-5
- Context window size: 496
- Internal dropout: 0
- Layers: 12
- Hidden dimension: 768
Evaluation
We evaluate this model on Stanford data, see MOTOR: A Time-To-Event Foundation Model For Structured Medical Records.
Technical Specifications
This model uses the MOTOR architecture from MOTOR: A Time-To-Event Foundation Model For Structured Medical Records.
Citation
BibTeX:
@misc{steinberg2023motor,
title={MOTOR: A Time-To-Event Foundation Model For Structured Medical Records},
author={Ethan Steinberg and Jason Fries and Yizhe Xu and Nigam Shah},
year={2023},
eprint={2301.03150},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
Model Card Authors
Ethan Steinberg, Michael Wornow
Model Card Contact
Ethan Steinberg ([email protected])