Detection of Clostridium difficile infection clusters, using the temporal scan statistic, in a community hospital in southern Ontario, Canada, 2006–2011

Table 4 **Univariable regression analysis* of variables associated with the rate of CDI cases**

Variable	Description	IRR	95% CI	P-value
Year	2006	Referent
	2007	0.48	0.26 – 0.89	0.019
	2008	0.13	0.05 – 0.32	< 0.001
	2009	0.16	0.07 – 0.36	< 0.001
	2010	0.49	0.27 – 0.90	0.022
Season	Fall	Referent
	Winter	0.54	0.25 – 1.18	0.121
	Spring	1.33	0.73 – 2.42	0.356
	Summer	1.15	0.63 – 2.07	0.652
Month	January	Referent
	February	4.19	0.47 – 37.55	0.200
	March	4.76	0.54 – 41.95	0.160
	April	7.52	0.89 – 62.97	0.063
	May	8.70	1.09 – 69.11	0.041
	June	7.55	0.92 – 61.69	0.059
	July	6.36	0.75 – 53.59	0.089
	August	6.19	0.77 – 50.00	0.087
	September	7.95	1.01 – 62.47	0.049
	October	5.01	0.59 – 41.95	0.137
	November	6.90	0.86 – 55.33	0.069
	December	6.11	0.76 – 49.29	0.089
Service	Medicine¹	Referent
	Surgery	1.29	0.27 – 6.31	0.747
	Other²	1.02	0.29 – 3.61	0.973

*Multilevel negative binomial regression model with a random intercept for ward.
CDI = Clostridium difficile infection.
IRR = Incidence rate ratio.
CI = Confidence interval.
¹Included the following departments: intensive care (adult and neonatal), oncology, pediatrics, and internal medicine.
²Included the following departments: psychiatry, rehabilitation, hospice, childbirth, and nursery.

ISSN: 1471-2334