AI-based software to detect neurological condition based on infant's cry

Toronto: Ubenwa, an AI company based in Montreal, Canada claims that an infant's cry can tell us if he or she has an underlying neurological condition. The company said that they have developed an AI-based algorithm to track cry activity, acoustic biomarker detection and anomaly prediction that will turn the cry of the infant into a potential diagnosis.

The first pilot conducted by the company to detect neurological injury caused by birth asphyxia showed that when compared to the normal physical examination done at birth, this method had a 40 per cent improvement.

"Ubenwa is building a diagnostic tool that understands when a baby's cry is actually a cry for medical attention," said Charles Onu, CEO and Co-founder of Ubenwa.

"Ultimately, our goal is to be a translator for baby cry sounds, providing a non-invasive way to monitor medical conditions everywhere you find a baby: delivery rooms, neonatal and pediatric intensive care units, nurseries, and in the home," he said in a statement late on Monday, IANS reported.

Currently, only the early signs of birth asphyxia can be identified by the AI-powered software, and based on cry triggers, it has the potential to determine learning milestones.

Ubenwa has announced a $2.5 million (US) pre-seed financing led by AI-focused Radical Ventures and AI pioneer Yoshua Bengio.

A spinout from Mila-the Quebec Artificial Intelligence Institute, Ubenwa is working with Montreal Children's Hospital and pediatric hospital networks around the world, to build a platform for sound-based diagnostic tools, combining groundbreaking AI research and clinical insights.

"AI is well-suited to deriving insights from the sound signature of an infant cry," said Yoshua Bengio, the AI pioneer who heads Mila.

"Onu's leading research into identifying biomarkers in baby cry sounds offers the promise of unlocking our understanding of what's behind a baby's cry."

For both clinicians and parents, an infant's cry is difficult to diagnose.

Babies cry for several reasons such as when they are hungry, exhausted or have colic.

But a baby's cry can also be a signal that more urgent care is required and delayed diagnosis may lead to severe, long-lasting effects or fatality.

"Cry analysis has the potential to provide critical information for identifying babies with evolving brain problems," said Dr Guilherme Sant'Anna, Neonatologist at Montreal Children's Hospital and Professor at McGill University.

"Supported by a strong clinical foundation, Ubenwa has developed a proprietary innovation for an underserved and important market," added Sanjana Basu, an investor with Radical Ventures who joins the Ubenwa board.

Understanding a baby's cry using machine learning will open many possibilities in the consumer and clinical pediatrics market, where the demand for better digital products continues to grow, she added.