Abstract
There is great excitement that medical artificial intelligence (AI) based on machine learning (ML) can be used to improve decision making at the patient level in a variety of healthcare settings. However, the quantification and communication of uncertainty for individual predictions is often neglected even though uncertainty estimates could lead to more principled decision-making and enable machine learning models to automatically or semi-automatically abstain on samples for which there is high uncertainty. In this article, we provide an overview of different approaches to uncertainty quantification and abstention for machine learning and highlight how these techniques could improve the safety and reliability of current ML systems being used in healthcare settings. Effective quantification and communication of uncertainty could help to engender trust with healthcare workers, while providing safeguards against known failure modes of current machine learning approaches. As machine learning becomes further integrated into healthcare environments, the ability to say “I’m not sure” or “I don’t know” when uncertain is a necessary capability to enable safe clinical deployment.
Highlights
There has been enormous progress towards the goal of medical artificial intelligence (AI) through the use of machine learning, resulting in a new set of capabilities on a wide variety of medical applications[1,2,3]
This capability is both stated and understood: medical machine learning (ML) should have the ability to say “I don’t know” and potentially abstain from providing a diagnosis or prediction when there is a large amount of uncertainty for a given patient
Four of the most widely cited medical ML models published since 2016 do not have a mechanism for abstention when uncertain[7,8,9,10] and do not report sample level metrics such as calibration, echoing what has been observed in systematic meta-analyses[11]
Summary
There has been enormous progress towards the goal of medical artificial intelligence (AI) through the use of machine learning, resulting in a new set of capabilities on a wide variety of medical applications[1,2,3]. While there are many possibilities, this article advocates that uncertainty quantification should be near the top of this list This capability is both stated and understood: medical ML should have the ability to say “I don’t know” and potentially abstain from providing a diagnosis or prediction when there is a large amount of uncertainty for a given patient. Four of the most widely cited medical ML models published since 2016 do not have a mechanism for abstention when uncertain[7,8,9,10] and do not report sample level metrics such as calibration, echoing what has been observed in systematic meta-analyses[11] This more cautious approach to medical ML will allow safer clinical deployment and help engender trust with the human healthcare workers who use this technology, since they will have the ability to know when the model is and is not confident in the diagnostic information it is providing.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.