A Nigerian mHealth startup has developed an Android app, called Ubenwa, which uses artificial intelligence (AI) technology to timely diagnose birth asphyxia from a newborn baby’s cry.
Birth asphyxia occurs when a baby doesn’t receive enough oxygen before, during or just after birth. Birth asphyxia could happen for a number of reasons, such as compression of the umbilical cord and inadequate oxygen levels in the mother’s blood, among others.
According to the World Health Organisation (WHO), birth asphyxia accounts for an estimated 900,000 deaths each year and is one of the primary causes of early neonatal mortality. It can also cause stillbirths, long-term neurological disability and impairment.
It’s often a challenge for healthcare workers to detect birth asphyxia because medical expertise is required to establish a diagnosis using blood gas analysis, and to then administer oxygen support and to treat the underlying cause. In rural areas diagnostic equipment is hard to come by due to costs as well as unstable power supply.
Founder and Principle Innovator of Ubenwa, Charles Onu, started developing the Ubenwa AI platform in 2012 with the goal of helping parents and caregivers detect asphyxia earlier, without having to rely on medical experts.
Using machine learning, the platform takes an infant’s cry as input, analyses the amplitude and frequency patterns of the cry and then provides instant diagnosis of birth asphyxia. According to the startup, the test results from their diagnostic platform have shown a sensitivity of over 86% and specificity of 89%. Furthermore, the app is non-invasive and can be over 95% cheaper than existing diagnostic mechanisms.
“We want to do the tests in the hospital, interact directly with the babies, and compare how Ubenwa performs given all the new environmental challenges that would come up,” said Onu in an interview with Quartz Africa.
“We are still finalising a hybrid model. But in the meantime, we are planning to make it free for individuals and paid for organisations such as hospitals, clinics, governments, and others,” concluded Onu.
The Nigerian startup is also raising funds to acquire more data to improve accuracy and obtain clinical approval from health institutions.