BabyChecker

Delft Imaging

BabyChecker

BabyChecker: AI-Powered Pregnancy Screening in Low-Resource Settings

's-Hertogenbosch, Netherlands

NLD

For-profit, including B-Corp or similar models

Every day, about 800 women die from preventable causes related to pregnancy and childbirth. Maternal mortality is a global problem, with nearly 95% of deaths occurring in low - and middle-income countries. Ultrasound can detect pregnancy-related potential risks such as fetal malposition, placenta previa and undiagnosed multiple pregnancies, among other anomalies. However, challenges such as the need for trained sonographers, high initial investment costs, and infrastructure constraints often hinder the deployment of ultrasound in resource-constrained and rural settings. In most high-income countries, routine antenatal ultrasound examinations are standard practice, often conducted in the first and second trimesters. The WHO recommends an ultrasound scan before 24 weeks of pregnancy for routine antenatal care (ANC). It has been reported that when ultrasound is accurately used in antenatal care, it can result in timely life-saving interventions in 48% of women at risk. However, in LMICs, very few women attend ANC before 24 weeks, and in rural settings, very few women receive any ultrasound scan at all. The implementation of obstetric ultrasound for ANC faces challenges in LMICs as mentioned above. This is especially true in rural settings where the incidence of maternal mortality and obstetric complications is the highest.

BabyChecker is Artificial Intelligence that analyses obstetric ultrasound scans, to identify risky pregnancies. Scans can be easily acquired with a handheld ultrasound and by any frontline health worker within 2-minutes. Any health worker, with no prior experience in ultrasound, can use BabyChecker after watching the 3-minute training video. The user is guided by the BabyChecker mobile application to perform a scan, which consists of standard sweeps across the abdomen. Once the sweeps are completed, AI analyses the scan and provides outputs for gestational age, fetal presentation and placenta localization. BabyChecker functions offline. BabyChecker is supported by an Epi-control platform from EPCON. EPCON’s expertise in real-time epidemiological insights and risk prediction ensures that the technology reaches the areas most in need. The Epi-control platform is capable of predicting TB risk at neighbourhood level, it can help guide the deployment of BabyChecker in regions where pregnant women face the highest risk for anomalies. By utilizing EPCON’s platform we can identify and prioritize high-risk areas, enabling targeted interventions for maternal health. This synergy enhances the accessibility of ultrasound services in resource-limited settings and ensure that right resources are deployed to communities that need them most and improving maternal health outcomes.

The target population of BabyChecker comprises women of reproductive age, hence the age-group that is typically defined as 15 to 49 years. BabyChecker was designed as a novel diagnostic point-of-care screening tool for conditions that affect women disproportionately in the Global South, where 800 women die every day from preventable causes related to pregnancy and childbirth. The development of BabyChecker ensured its portability, affordability, and user friendliness among non-clinical frontline healthcare workers. BabyChecker aims to serve unmet needs in women’s health, in particular targeting diagnoses for maternal health conditions in resource-constrained settings. With the combination of Epi-control platform, high-risk areas are prioritized and BabyChecker can be provided to the targeted population. BabyChecker’s AI automatically detects key risks parameters in pregnancies. The diagnostic output enables timely referrals of high-risk pregnancies to high-level health facilities, reduce preventable deaths, and ultimately enhancing the well-being of women in these underserved communities.