首页|New Artificial Intelligence Study Findings Recently Were Published by Researcher s at Cedars-Sinai Medical Center (A framework for evaluating clinical artificial intelligence systems without groundtruth annotations)
New Artificial Intelligence Study Findings Recently Were Published by Researcher s at Cedars-Sinai Medical Center (A framework for evaluating clinical artificial intelligence systems without groundtruth annotations)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on artificial intelligenc e is the subject of a new report. According to news reporting from the Cedars-Si nai Medical Center by NewsRx journalists, research stated, “A clinical artificia l intelligence (AI) system is often validated on data withheld during its develo pment.” The news correspondents obtained a quote from the research from Cedars-Sinai Med ical Center: “This provides an estimate of its performance upon future deploymen t on data in the wild; those currently unseen but are expected to be encountered in a clinical setting. However, estimating performance on data in the wild is c omplicated by distribution shift between data in the wild and withheld data and the absence of ground-truth annotations. Here, we introduce SUDO, a framework fo r evaluating AI systems on data in the wild. Through experiments on AI systems d eveloped for dermatology images, histopathology patches, and clinical notes, we show that SUDO can identify unreliable predictions, inform the selection of mode ls, and allow for the previously out-of-reach assessment of algorithmic bias for data in the wild without ground-truth annotations.”
Cedars-Sinai Medical CenterArtificial IntelligenceEmerging TechnologiesMachine Learning
NETL
NSTL
