AI-driven predictions may improve language outcomes after cochlear implants

A groundbreaking international study published in JAMA Otolaryngology-Head & Neck Surgery has demonstrated that Artificial Intelligence (AI) can predict spoken language outcomes for children. 

The AI model, using deep transfer learning, predicted spoken language outcomes at one to three years after cochlear implants with 92% accuracy.

Cochlear Implants: Only effective treatment for severe to profound hearing loss

Cochlear implantation is the only efficacious intervention to improve hearing and enable spoken language for children with severe hearing impairment; however, spoken language development after early implantation is more variable than that of children with typical hearing.

Researchers trained AI models to analyze outcomes based on pre-implantation brain MRI scans from 278 children in Hong Kong, Australia, and the US who spoke three languages (English, Spanish, and Cantonese).

It has been observed that such complex, diverse datasets pose problems for conventional machine learning; the study showed remarkable results with the deep learning model.

In this connection, senior author Nancy M. Young, MD, Medical Director said, “Our results support the feasibility of a single AI model as a robust prognostic tool for language outcomes of children served by cochlear implant programs worldwide.”

The researchers were of the view that the same methods could eventually be used to predict success for other pediatric conditions beyond hearing loss.

Nonetheless, the Children’s Cochlear Implant program is one of the largest and most experienced in the world, having performed more than 2,000 cochlear implant procedures since its inception in 1991.