MIDRC-MetricTree; Outcome prediction.

Finding methods and metrics for AI/ML performance evaluation.

Last updated September 23, 2024

There are many oncology prognostic or outcome prediction tasks for which AI/ML algorithms may be helpful and for which performance will need to be assessed thoroughly and correctly. Here you will find examples of tasks and which branch of the MIDRC-MetricTree to investigate. These tasks include:

  • Prediction of probability of (or yes/no) progression in a fixed time or independent of time (branch: classification -> binary classification)

  • Prediction of probability of (or yes/no) response to treatment (such pathologic complete response) in a fixed time or independent of time (branch: classification -> binary classification)

  • Prediction of probability of (or yes/no) progression in a fixed time including locations for, e.g., new lesions or metastases (branches: classification -> binary classification and detection and localization)

  • Prediction of progression over time, patient outcome prediction over time (branch: time-to-event analysis)