Ubenwa, a Nigerian health startup, is developing an interesting technology to reduce infant mortality rates. Founded in 2014 by Charles Onu, Udeogu Innocent, Eyenimi Ndiomu, and Urbain Kengni, Ubenwa is tackling birth asphyxia.
Birth asphyxia is a medical condition that affects newborn infants. It is a condition of the severely deficient supply of oxygen to the body that arises from abnormal breathing. Asphyxia can last long enough during the birth process to cause physical harm, usually to the brain of a newborn baby.
900,000 newborns die annually from neonatal asphyxia! Join the fight!#newborn#children pic.twitter.com/SR9e16HNar
— Ubenwa Health | Saving Lives at Birth (@ubenwa_ai) September 13, 2017
Asphyxia afflicts millions of newborns, killing 1.2 million infants each year. According to the World Health Organisation, it is estimated to be the fifth largest cause of under-five child deaths (8.5%), after pneumonia, diarrhea, neonatal infections and complications of preterm birth.
However, infant death from asphyxia can be prevented if detected early. Yet, early detection has been a big problem in Nigeria. Most hospitals and clinics in Nigeria lack even the basic equipment for this, probably due to their high cost.
That’s where Ubenwa comes in.
With Ubenwa, Asphyxia Detection Takes 10 Seconds!
The startup developed a machine learning technology that detects in infants. Developed as an Android app, Ubenwa serves as a more friendly and interesting alternative to traditional asphyxia detection systems.
Meet Charles Onu, the Creator of Ubenwa Intelligence Solutions, this Nigerian AI health start up can analyse the amplitude and frequency patterns in the cry of a baby, to give instant diagnosis of birth asphyxia. https://t.co/eoTRBwVy4f#InterswitchSPAK #NigeriaToTheWorld
— Interswitch Group (@InterswitchGRP) June 15, 2018
Charles Onu, the founder of the startup, shares that Ubenwa’s machine learning system takes an infant’s cry as input, then analyses the amplitude and frequency patterns of the cry to provide an instant diagnosis of birth asphyxia. This detection takes just 10 seconds.
Udeogu Innocent, co-founder and Ubenwa’s Engineering Lead, says their technology borrows a lot from speech recognition technology. After achieving success with the model, the startup developed a mobile app for easier mobile diagnosis of birth asphyxia.
This is a simple yet unique solution–during its test phase, Ubenwa attained 95% prediction accuracy rates for nearly 1,400 recorded baby cries.
Tests are Still Ongoing
Tests are still being conducted through Clinical validation exercises at the University of Port Harcourt Teaching Hospital and another in Canada at the McGill University Health Centre.
Ubenwa, a mobile app using #AI to detect and prevent birth asphyxia. Amazing research from @McGillU ! #AIXPRIZEmtl
— Hacking Health Montreal (@HHMTL) November 17, 2016
“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. The reason we are able to pursue this real-time validation in the clinical setting is as a result of the success of our earlier work,” says Onu.
Monetization is still being decided as “We are still finalizing a hybrid model. But in the meantime, we are planning to make it free for individuals and paid for organizations such as hospitals, clinics, governments, and others),” Onu said.
The startup is also gaining international traction for its technology. In December, Ubenwa made the semi-finals of the ongoing IBM Watson AI XPRIZE competition.
