Year: 2024
Type: article
Abstract: The rising popularity of artificial intelligence in healthcare is highlighting the problem that a computational model achieving super-human clinical performance at its training sites may perform substantially worse at new sites. In this perspective, we argue that we should typically expect this failure to transport, and we present common sources for it, divided into those under the control of the experimenter and those inherent to the clinical data-generating process. Of the inherent sources we look a little deeper into site-specific clinical practices that can affect the data distribution, and propose a potential solution intended to isolate the imprint of those practices on the data from the patterns of disease cause and effect that are the usual target of probabilistic clinical models.
Source: npj Digital Medicine
Institution: Vanderbilt University Medical Center
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $3,790
Awards: G1703650811, G2132286325, G666629622, G6764608945, Data-Driven Guidance for Timing Repeated Inpatient Laboratory Tests, G7688528035, Genome and Phenome to Define Disease Risk with Antinuclear Antibodies, G8385529010, G8885470238, Novel Integrative Approach for the Early Detection of Lung Cancer using Repeated Measures
OpenAlex ID: W4392363501