A path analysis of the factors associated with seasonal variation of breeding failure in sows

Data pertaining to 868 904 services of sows from 58 Canadian herds for the period 1999 to 2003 were retrieved from the PigCHAMP data share database and subjected to path analysis to evaluate the effect of number of inserninations per service (1 and >1), wean to service interval (WSI <= 5 d and > 5 d) and parity (parity 1, parities 2 to 5 and parity > 5) on the seasonality of breeding failure. Population attributable fraction (PAF) was calculated to determine the contribution of each risk factor. Overall breeding failure proportions were 23.5 and 20.9% in summer and other months, respectively. The likelihood of breeding failure was higher when sows were artificially inseminated (Al) only once, and 6 and 5% of breeding failures in the summer and other months, respectively, were attributable to single insemination. The likelihood of breeding failure was 1.5 and 1.4 times higher when WSI was > 5 d in the summer and other months, respectively, and 14% of breeding failure in summer was attributable to increase in WSI in summer, and in other months it accounted for 10%. Parity 1 sows reduced the proportion of breeding failure in the population in months other than summer [odds ratio (OR) 0.78]. Sows of parity 2-5 reduced the proportion of breeding failure in both seasons (OR 0.81 and 0.78 in summer and other months, respectively).