English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Estimating the test performance of software AI-based medical devices underdistribution shifts is crucial for evaluating the safety, efficiency, andusability prior to clinical deployment. Due to the nature of regulated medicaldevice software and the difficulty in acquiring large amounts of labeledmedical datasets, we consider the task of predicting the test accuracy of anarbitrary black-box model on an unlabeled target domain without modification tothe original training process or any distributional assumptions of the originalsource data (i.e. we treat the model as a "black-box" and only use thepredicted output responses). We propose a "black-box" test estimation techniquebased on conformal prediction and evaluate it against other methods on threemedical imaging datasets (mammography, dermatology, and histopathology) underseveral clinically relevant types of distribution shift (institution, hardwarescanner, atlas, hospital). We hope that by promoting practical and effectiveestimation techniques for black-box models, manufacturers of medical deviceswill develop more standardized and realistic evaluation procedures to improvethe robustness and trustworthiness of clinical AI tools.

Estimating Test Performance for AI Medical Devices under Distribution Shift with Conformal Prediction