Back

Clinician Readiness to Adopt A.I. for Critical Care Prioritisation

Kennedy, G.; Gallego, B.

2021-02-15 health informatics
10.1101/2021.02.11.21251604 medRxiv
Show abstract

There is a wide chasm between what has been shown to be feasible in the application of artificial intelligence to data from the electronic medical record, and what is currently available. The reasons for this are complex and understudied, and vary across technical, ethical and sociocultural domains. This work addresses the gap in the literature for studies that determine the readiness of clinical end-users to adopt such tools and the way in which they are perceived to affect clinical practice itself. In this study, we present a novel, credible AI system for predicting in-patient deterioration to likely end users. We gauge their readiness to adopt this technology using a modified version of the technology adoption model. Users are found to be moderately positive towards the potential introduction of this technology in their workflow, although they demonstrate particular concern for the appropriateness of the clinical setting into which it is deployed.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.