Laboratory prediction of primary postpartum haemorrhage: a comparative cohort study

Background: Postpartum haemorrhage (PPH) is the leading cause of maternal deaths, the world over. The aim of this study was to determine laboratory parameters that could serve as risk factors for primary PPH. Methods: This comparative cohort study involved 350 pregnant women at term who were recruited consecutively from the Komfo Anokye Teaching Hospital, Kumasi, Ghana. PPH was defined as a measured blood loss >= 500 ml or enough to cause haemodynamic shock. Basic demographic data was gathered and blood was collected for laboratory assays before delivery. Univariate and multivariate logistic regression models were used to identify variables that were significantly associated with primary PPH. Results: Of the total recruited study participants (350), five declined to participate and 74 went through caesarean section, episiotomy or instrumental deliveries and were excluded. Of the remaining (271) study participants who went through spontaneous vaginal delivery, fifty five (55) were diagnosed with primary PPH (Group 1) and the remaining 216 were those who did not have PPH (Group 2). Demographic characteristics did not differ between the two groups (P > 0.05). Univariate analysis showed that AST (P = 0.043), urea (P < 0.001), creatinine (P = 0.002), urea-to-creatinine ratio (P = 0.014) and the proportion of abnormal peripheral blood smear (P < 0.001) was higher among women in Group 1 compared to those in Group 2. Women in Group 1 had a significantly lower haemoglobin concentration (10.7 g/dL) compared to those in Group 2 (12.1g/dL). Upon multivariate analysis, an abnormal peripheral blood smear (AOR = 2.9672), Hb, (AOR = 0.5791), moderate to severe anaemia (Hb < 10 g/dL) (AOR = 3.1385), Urea (AOR = 3.6435) and intra-renal azotaemia (AOR = 0.1893) remained significant. Conclusion: Many laboratory parameters are associated with primary PPH but only a few are independent risk factors. A total clinical work-up including laboratory evaluation of the independent blood variables identified in this study will help a great deal to identify individuals at high risk for PPH.