| Article ID | Journal | Published Year | Pages | File Type | 
|---|---|---|---|---|
| 10320705 | Artificial Intelligence in Medicine | 2005 | 15 Pages | 
Abstract
												FLORENCE must not undermine the NICU's hierarchical communication channels (A). The re-design of working practices to incorporate FLORENCE, reinforced through its user interface, must ensure that expert help is called on when appropriate (A). The procedures adopted with FLORENCE should ensure that the data the advice is based upon is valid (C). For example, FLORENCE could prompt staff to manually verify the data before implementing any suggested changes. FLORENCE's audible alarm should be clearly distinguishable from other NICU alarms (D); new procedures should be established to ensure that FLORENCE alarms receive attention (D), and false alarms from FLORENCE should be minimised (B, D). FLORENCE should always provide the data and reasoning underpinning its advice (A, C, D). The methods used in the CTA identified several contextual issues that could affect FLORENCE's acceptance. These issues, which extend beyond FLORENCE's capability to suggest changes to the ventilator settings, are being addressed in the design of the user interface and plans for FLORENCE's subsequent deployment.
											Keywords
												
											Related Topics
												
													Physical Sciences and Engineering
													Computer Science
													Artificial Intelligence
												
											Authors
												Gordon D. Baxter, Andrew F. Monk, Kenneth Tan, Peter R.F. Dear, Simon J. Newell, 
											