Mitigating Bias in Radiology Machine Learning: 3. Performance Metrics

Shahriar Faghani, Bardia Khosravi, Kuan Zhang, Mana Moassefi, Jaidip Manikrao Jagtap, Fred Nugen, Sanaz Vahdati, Shiba P. Kuanar, Seyed Moein Rassoulinejad-Mousavi, Yashbir Singh, Diana V. Vera Garcia, Pouria Rouzrokh, Bradley J. Erickson

Research output: Contribution to journalArticlepeer-review


The increasing use of machine learning (ML) algorithms in clinical settings raises concerns about bias in ML models. Bias can arise at any step of ML creation, including data handling, model development, and performance evaluation. Potential biases in the ML model can be minimized by implementing these steps correctly. This report focuses on performance evaluation and discusses model fitness, as well as a set of performance evaluation toolboxes: namely, performance metrics, performance interpretation maps, and uncertainty quantification. By discussing the strengths and limitations of each toolbox, our report highlights strategies and considerations to mitigate and detect biases during performance evaluations of radiology artificial intelligence models.

Original languageEnglish (US)
Article numbere220061
JournalRadiology: Artificial Intelligence
Issue number5
StatePublished - Sep 2022


  • Convolutional Neural Network (CNN)
  • Diagnosis
  • Segmentation

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Artificial Intelligence


Dive into the research topics of 'Mitigating Bias in Radiology Machine Learning: 3. Performance Metrics'. Together they form a unique fingerprint.

Cite this