
Finding Chronic Lung Disease in Existing Data
Reusing existing patient data can catch chronic lung disease long before patients end up in the emergency room.
Discover the newest research about AI innovations in 🫁 Pulmonology.

Reusing existing patient data can catch chronic lung disease long before patients end up in the emergency room.

A new machine-learning model spots lung cancer from a simple urine sample, challenging the current reliance on costly scans and invasive blood draws.

A massive multi-center study reveals that the new 2026 AHA/ACC pulmonary embolism framework adds clinical complexity without improving risk prediction for the vast majority of patients.

A new deep learning model proves that combining visual breathing patterns with heart scans can predict which emergency patients will need a hospital bed.

Automating the search for mucus plugs in lung scans reveals a hidden driver of COPD mortality that human eyes routinely miss.

New AI Tool Improves Early Lung Cancer Detection 🫁💻. Late diagnosis remains a significant challenge, impacting survival rates.

AI in Chest Tube Management: CheLSEA’s 93% Accuracy in Removal Predictions 📊🤖

Revolutionary deep learning model predicts acute pulmonary embolism with 93.76% accuracy! 📊💡

Electrodermal activity shows promise in pain assessment, achieving 80% accuracy in detecting breakthrough pain. 📊💡

NICE recommends eight digital tools for asthma management, aiming to improve patient care and reduce health inequalities. 🌬️📱