Patterns of PCB-138 Occurrence in the Breast Milk of Primiparae and Multiparae Using SHapley Additive exPlanations Analysis

Abstract

Breastfeeding provides numerous health benefits for newborns by meeting infants’ nutritional needs and supporting associated immunological protection. Maternal milk is high in fat, and therefore, represents a very suitable medium for the bioaccumulation of lipophilic pollutants, such as organochlorine pesticides (OCPs) and polychlorinated biphenyls (PCBs). This makes breast milk the infant’s primary source of postnatal exposure to persistent toxic xenobiotics. In this study, we applied a novel SHapley Additive exPlanations (SHAP) method to examine the key parameters that govern the distribution of PCB-138, an indicator of non-dioxin congeners, in the mother’s milk. According to the accuracy metrics, the eXtreme Gradient Boosting regression was employed successfully, with a predicted/observed relative error below 20% and a high correlation coefficient (r === 0.97), for modeling the relationships between PCB-138 and other non-dioxin congeners, the mother’s age, and the number of births. According to the results, PCB-156, PCB-180, HCB, HCH and PCB-118 have a major impact, while PCB-28, PCB-52 and PCB-189 have a minor impact on PCB-138 distribution in breast milk. Similar contaminant behaviors, which belong to both the indicator congener group (−28, −52, −180) and the toxicologically relevant PCBs (−118, −189), were also noted. The SHAP conclusions were only partially consistent with the results of the correlation analysis suggesting that POPs exhibit non-linear dynamics and interrelations. Therefore, current knowledge on the contamination of complex biomatrices would benefit from further detailed analyses of pollutant intermittent relationships.