Lungs
AI Research on the Lungs
Evidence at a glance
- 6 studies cited
- Human-reviewed article
- Peer-reviewed research
- Human study
- Lungs
This article is AI-assisted and human-reviewed. Drafts are generated from peer-reviewed research and checked before publishing. See our methodology.
AI research is giving scientists new ways to study the lungs and breathing. The studies below look at tools that may help track breathing problems, read lung scan information, and find lung nodules in reports. These tools are still research tools, not replacements for care from a health professional.
Real-time tracking for Sleep Apnea Disorder
One study tested an AI system for Sleep Apnea Disorder that worked with connected devices to monitor sleep apnea events in real time and from a distance. This could help researchers learn more about breathing changes during sleep outside of a lab setting. Read more in the real-time remote Sleep Apnea Disorder monitoring study.
Wearable sensing for Dyspnea
Dyspnea means feeling short of breath. A study used a forehead wearable sensor with AI to measure breathlessness in real time. This kind of work may help make a hard-to-describe symptom easier to track during research. Read more in the real-time wearable Dyspnea measurement study.
Clearer CT scan research for Lung Adenocarcinoma
For Lung Adenocarcinoma, researchers studied AI methods that improved CT scan information to better predict tumor gene changes without surgery. This points to a possible research path for learning more from lung images. Read more in the CT imaging and EGFR change prediction study in Lung Adenocarcinoma.
Finding Incidental Pulmonary Nodules in reports
Another study looked at Incidental Pulmonary Nodules found in medical reports at the primary care level. The AI tool was linked with zero missed high-risk lung nodules in that study setting. This suggests AI may help researchers explore safer ways to sort and track report findings. Read more in the primary care Incidental Pulmonary Nodules detection study.
What this does not prove yet
This research does not prove that AI can find every lung problem, predict every risk, or improve health outcomes on its own. More testing is needed across different people, clinics, and care settings before these tools can be fully understood.
Sources cited
- EvoApneaFormer: an IoT and prognostic evolutionary deep learning-based framework for real-time multi-event sleep apnea disorder detection and remote monitoring - Front Bioeng Biotechnol
- Identifying subgroups of ICU patients with high mortality rates using machine learning: A nationwide, population-based study. - Journal of critical care
- High-fidelity super-resolution CT radiomics for non-invasive EGFR mutation prediction in lung adenocarcinoma: a multi-center pooled analysis. - La Radiologia medica
- Objective dyspnea measurement in real time using a forehead wearable and artificial intelligence. - NPJ primary care respiratory medicine
- Machine learning-based ICU mortality prediction across hematologic malignancy subtypes: A comparative analysis using MIMIC-IV. - Journal of Clinical Oncology
- Association of a high-speed, knowledge-based AI tool at the primary care level with zero-miss triage and detection of incidental pulmonary nodules. - Journal of Clinical Oncology
Keep exploring
Medical disclaimer: This content is for informational purposes only and does not constitute medical advice, diagnosis, or treatment. Always consult a qualified healthcare professional.
Published July 11, 2026