The effect of machine learning tools for evidence synthesis on resource use and time-to-completion: protocol for a retrospective pilot study

Table 1 Shell table illustrating how results will be presented

	Type of ML use	Sample mean^a	Effect estimate^b	p-value
Resource use	Recommended	XXX	XXX (XXX to XXX)	0.XXX
	None	XXX	XXX (XXX to XXX)	0.XXX
	Recommended	XXX	XXX (XXX to XXX)	0.XXX
	Non-recommended	XXX	XXX (XXX to XXX)	0.XXX
	Any	XXX	XXX (XXX to XXX)	0.XXX
	None	XXX	XXX (XXX to XXX)	0.XXX
Time-to-completion	Recommended	XXX	XXX (XXX to XXX)	0.XXX
	None	XXX	XXX (XXX to XXX)	0.XXX
	Recommended	XXX	XXX (XXX to XXX)	0.XXX
	Non-recommended	XXX	XXX (XXX to XXX)	0.XXX
	Any	XXX	XXX (XXX to XXX)	0.XXX
	None	XXX	XXX (XXX to XXX)	0.XXX

^aData are the mean number of person-hours or weeks to completion. The sample mean resource use may be underestimated due to the right-censoring of ongoing projects
^bEstimates are presented with 95% confidence intervals and adjusted as described in the statistical analysis section

ISSN: 2046-4053