som-shahlab/INSPECT_public

Stars
22
Rank 1,043,324 (Top 21 %)
Language
Python
License
Apache License 2.0
Created 11 months ago
Updated 4 months ago

som-shahlab/INSPECT_public

som-shahlab

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

INSPECT dataset/benchmark paper, accepted by NeurIPS 2023

ehrshot-benchmark

A benchmark for few-shot evaluation of foundation models for electronic health records (EHRs)

Jupyter Notebook

femr

FEMR (Framework for Electronic Medical Records) provides tooling for large-scale, self-supervised learning using electronic health records

medalign

MedAlign is a clinician-generated dataset for instruction following with electronic medical records.

trove

Weakly supervised medical named entity classification

ehr-rwe

Weak supervision methods for extracting real world evidence from EHRs

Clinfo.AI

This is Clinfo.AI Demo Instruction

Jupyter Notebook

psych-nlp

Methods for measuring and analyzing therapist language

ehr_ml

Code for doing machine learning with various EHRs

psych-audio

Analyzing the language of psychotherapy

aplusml

APLUS ML = A Python Library for Usefulness Simulations of Machine Learning models

Jupyter Notebook

survlearners

Metalearners for Survival Data

fairness_benchmark

Benchmarking fairness methods

Jupyter Notebook

motor_tutorial

Tutorial repository for the official MOTOR release

Jupyter Notebook

TrialProbe

Jupyter Notebook

ITE-model-selection

Jupyter Notebook

findFH_aphrodite

Code repository for EHR FIND FH model

clinical_trial_patient_matching-website

Public facing website for zero-shot CT patient matching paper

mimic_tutorial

temp_ds_shift_robustness

Jupyter Notebook

manitest

ManiTest: A lightweight version of the Eleuther AI eval harness built on top of Manifest

motor_code_release

clinical_trial_patient_matching

Zero-shot clinical trial matching with LLMs

net_benefit_ascvd

slurmtool

HTE_SL_Prediction

ehrshot-website

Public website for EHRSHOT

RATE-experiments

Code for reproducing the analyses that appear in "Evaluating Treatment Prioritization Rules via Rank-Weighted Average Treatment Effects"

ACEapi