Yesil Science / Blog
Blog
Every article we have published: research summaries, product thinking and developments in health AI.
Latest articles

Developing a transfer learning model for the prediction of Down syndrome from first-trimester ultrasound images.
AI model predicts Down syndrome from first-trimester ultrasounds with 98.3% accuracy! 🤖📊 Key features: nuchal translucency & nasal bone.

Chain-of-Thought reasoning versus linguistic optimization for artificial intelligence models on the prosthodontics section of a dental licensing examination.
AI models in dental exams: CoT reasoning outperforms others, achieving 80.54% accuracy vs. human average 79.51%. 📊🦷

Personalized Approaches to Cancer Vaccines Using AI
AI aids in developing personalized cancer vaccines by identifying neoantigens, enhancing immune response against tumors. 🧬💉

Deep learning-assisted aortic stenosis detection and grading based on multiview versus single-view echocardiography.
Deep learning enhances aortic stenosis detection: AUC 0.942, severe AS AUC 0.976. Promising for clinical workflows! 📊❤️

Biomedical philanthropy promises dramatic expansion and AI focus.
Biomedical philanthropy expands with AI focus, as Chan Zuckerberg Initiative prioritizes science for impactful funding. 💡💰

Weekly Health & AI Digest – November 10, 2025
Here are the latest breakthroughs in health & AI (November 10, 2025 week) 🔹 Task optimized vision transformer for diabetic retinopathy detection...

Task optimized vision transformer for diabetic retinopathy detection and classification in resource constrained early diagnosis settings.
Task-Optimized Vision Transformer achieves 99% accuracy in diabetic retinopathy detection on low-cost hardware. 🩺👁️

Developments in diagnosis and treatment of early hypopharyngeal carcinoma and precancerous lesions: A review.
Early hypopharyngeal carcinoma: AI and ME-NBI enhance detection; minimally invasive surgery improves outcomes. 📈🔍

ResNet-EfficientNet powered framework for high-precision cough-based classification of infectious diseases.
Deep learning models like ResNet achieve 98.5% accuracy in COVID-19 cough sound classification. 📊🤒

A Prompt Engineering Framework for Large Language Model-Based Mental Health Chatbots: Conceptual Framework.
Exploring MIND-SAFE: A Framework for Ethical AI in Mental Health Chatbots 🤖🧠

Exploring an LLM’s Use in Supporting Journal Club Preparation and Discussion Among Residents.
LLMs enhance journal club engagement for dental residents, improving comprehension and confidence. Key skills: prompt-writing, critical thinking. 📚🤖

Children’s drug research and development incentives and market pricing optimization based on medical imaging.
Children's drug development: 32.7% tumor reduction via imaging data. Optimized pricing ensures accessibility and R&D efficiency. 📉💊
Also on LinkedIn
AI Health Hub posts the same research summaries on LinkedIn every day. More than 3,000 people follow it there.