Can a low-cost point-of-care analytical device such as a computational model in the form of a mobile-based application (app) predict pregnant women at high risk of lead poisoning who should be prioritised for further testing or intervention?
Lead, an environmental toxicant, accounts for 0.6% of the global burden of disease. A significant contribution to an infant’s lead load is caused by maternal lead transfer during pregnancy. Lead can permeate through the foetus blood-brain barrier causing a negative impact on foetal growth and the developing brain. This acts as the first pathway to the infant’s lead exposure. Thus, the effects of lead exposure need to be characterised in detail to enable the delivery of an appropriate public healthcare system to lead-exposed women and infants. Lead poisoning is very much preventable with adequate screening and timely action. However, in the current scenario, lead toxicity is determined by a lab-based blood test that requires an expert medical/technical staff, expensive equipment, and blood samples.
This approach is inappropriate for lead screening in a large population as it will be costly, time-consuming, and infrequent. Using the aid of technology and integrating multiple disciplines, the proposed work intends to deliver a cost-effective analytical device in the form of a screening app with an embedded computational model. The model learns from the maternal data comprising blood samples and a set of questionnaires reflecting lead exposure pathways during the training phase. The built screening app will then be used for finding elevated lead content in pregnant women based on social and demographic questionnaire responses in the app as the first point of testing. The app will offer an integration of non-formal care and lead risk prevention and education in pregnant women.