AI model predicts imatinib response in GISTs using multimodal data

Researchers have developed a multimodal deep learning framework that integrates computed tomography (CT) imaging and clinical variables to predict patient response to neoadjuvant imatinib treatment for gastrointestinal stromal tumors (GISTs). The study, which involved patients from four tertiary centers, found that while cross-attention models achieved high internal performance, external prediction accuracy was moderate. Explainability analyses highlighted significant differences in feature importance between responders and non-responders, including genetic mutations like KIT and PDGFRA, as well as clinical factors such as age and sex. AI

IMPACT This research demonstrates the potential of AI in improving personalized medicine by predicting treatment response, which could lead to more effective patient care strategies.

RANK_REASON The cluster contains a research paper published on arXiv detailing a new AI model for medical prediction. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• BRAF
• computed tomography
• Fariba Tohidinezhad
• gastrointestinal stromal tumor
• imatinib
• KIT proto-oncogene, receptor tyrosine kinase
• platelet-derived growth factor receptor alpha
• SMAC3

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →