AI model using deep transfer learning accurately predicts spoken language outcomes in deaf children after cochlear implantation based on pre-implantation brain MRI scans.
Key Details
- 1Deep learning model predicted language outcomes with up to 92% accuracy 1–3 years post-implantation.
- 2Study included brain MRI scans from 278 children across Hong Kong, Australia, and the U.S., covering three languages and heterogeneous imaging protocols.
- 3AI outperformed traditional machine learning models on all outcome measures.
- 4Identifying children with poorer predicted outcomes pre-implantation may allow for earlier, intensified therapy.
- 5Research published in JAMA Otolaryngology-Head & Neck Surgery.
Why It Matters
This study highlights the growing capability of advanced AI models to predict important patient outcomes from imaging data, supporting personalized treatment plans in pediatric otolaryngology and providing a strong use case for AI in clinical prognostics.
Source
EurekAlert
Related News
•EurekAlert
AI-Powered OCT Enables Rapid 'Optical Biopsy' for Early Endometrial Cancer Detection
A team at Washington University has developed a catheter-based 3D OCT system with AI to quickly and noninvasively detect early endometrial cancers.
•EurekAlert
AI Clinical Reasoning in Diagnostics and Digital Fatigue in Healthcare
Recent JMIR features explore large language models in clinical diagnostics and digital fatigue among healthcare professionals.
•EurekAlert
KAIST, MIT, Microsoft Develop Efficient AI Image Upsampling for Robotics
KAIST, MIT, and Microsoft have created 'Upsample Anything,' a training-free AI method to restore high-resolution visual data from compressed images with up to 16x improved GPU memory efficiency.