Timezone: »
Deep learning approaches are increasingly used in healthcare due to their seemingly remarkable performance. However, they can be notoriously brittle, often with little ability to generalize outside their training data. Using real life examples from ophthalmology, oncology and radiology, we will first discuss practical examples of distribution shifts. We will then highlight how even seemingly subtle distribution shifts can lead to catastrophic failures of models. We will highlight the need for constant vigilance of the input data and better metrics to quantify distribution shifts. We will conclude with a plea to the ICML/PODS community to work with clinical community on this critically important topic.
Author Information
Jayashree Kalpathy-Cramer (University of Colorado Anchutz Campus)
More from the Same Authors
-
2021 : Evaluating subgroup disparity using epistemic for breast density assessment in mammography »
charlie lu · Andreanne Lemay · Katharina Hoebel · Jayashree Kalpathy-Cramer -
2022 : Estimating Test Performance for AI Medical Devices under Distribution Shift with Conformal Prediction »
charlie lu · Syed Rakin Ahmed · Praveer Singh · Jayashree Kalpathy-Cramer -
2022 : Discussion Panel »
Percy Liang · Léon Bottou · Jayashree Kalpathy-Cramer · Alex Smola