STOIC2021 baseline


Logo for STOIC2021 baseline

About

Creators:
Image Version:
a426e027-69ee-4f03-af0c-edd619bb9425
Last updated:
Sept. 22, 2022, 3:59 p.m.

Interfaces

This algorithm implements all of the following input-output combinations:

Inputs Outputs
1
  • CT Image (Image)
  • Probability COVID-19 (Float)
  • Probability Severe COVID-19 (Float)
  • Challenge Performance

    Date Challenge Phase Rank
    Dec. 22, 2021 STOIC2021 Qualification 76
    April 7, 2022 STOIC2021 Qualification (last submission) 20
    Sept. 24, 2022 STOIC2021 Final 6

    Model Facts

    Summary

    STOIC2021 baseline. Trained on the STOIC2021 Final phase training set, consisting of public and private training data. Not for clinical use.

    Mechanism

    The algorithm processes a CT scan of a suspected COVID-19 patient and produces the probability of a COVID-19 infection and a probability of severe outcome (death or intubation within one month).

    Validation and Performance

    Uses and Directions

    This algorithm was developed for research purposes only.

    Warnings

    Common Error Messages

    Information on this algorithm has been provided by the Algorithm Editors, following the Model Facts labels guidelines from Sendak, M.P., Gao, M., Brajer, N. et al. Presenting machine learning model information to clinical end users with model facts labels. npj Digit. Med. 3, 41 (2020). 10.1038/s41746-020-0253-3