24 Aug AI Model Uses Healthy Chest X-Rays to Predict Age
MedicalResearch.com Interview with:
Dr. Ueda
Dr. Daiju Ueda
Department of Diagnostic and Interventional Radiology
Graduate School of Medicine
Osaka Metropolitan University
Osaka, Japan
MedicalResearch.com: What is the background for this study?
Response: We were inspired by the potential of chest radiography as a biomarker for aging. Previous research had utilized chest radiographs for age estimation, but these studies often involved cohorts with diseases.
MedicalResearch.com: What are the main findings?
Response: Our AI model demonstrated a strong correlation between Xp-age (the age predicted by the AI) and the actual chronological age. In the chest radiographs, the AI predominantly focused on the top of the mediastinum and the bilateral lower lung fields as areas showing age-related changes. Additionally, the age difference between Xp-age and actual age was associated not with acute diseases but with chronic diseases.
MedicalResearch.com: What should readers take away from your report?
Response: We have developed an AI model that utilizes healthy chest radiographs to estimate age. Unlike previous studies, the innovative aspect of this research is the use of chest radiographs from multi-institutional health checkups.
The difference between Xp-age and actual age showed a correlation with various chronic diseases. Xp-age has the potential to serve as a valuable biomarker for aging.
The AI’s saliency maps highlighted areas such as the mediastinum and lower lung fields as crucial for age-related changes.
The AI-estimated age could prove valuable in detecting chronic diseases, predicting the prognosis of various illnesses, and assessing the risk of complications from surgeries and other procedures.
MedicalResearch.com: What recommendations do you have for future research as a results of this study?
Response: Moving forward, we will further validate the usefulness of the AI-estimated age in predicting disease prognosis and evaluating the risk of complications in various diseases, including malignancies and trauma.
Citation: Chest radiography as a biomarker of ageing: artificial intelligence-based, multi-institutional model development and validation in Japan
Mitsuyama, Yasuhito et al.
The Lancet Healthy Longevity, Volume 0, Issue 0
https://pubmed.ncbi.nlm.nih.gov/37597530/
The information on MedicalResearch.com is provided for educational purposes only, and is in no way intended to diagnose, cure, or treat any medical or other condition. Some links may be sponsored. Products are not endorsed.
Always seek the advice of your physician or other qualified health and ask your doctor any questions you may have regarding a medical condition. In addition to all other limitations and disclaimers in this agreement, service provider and its third party providers disclaim any liability or loss in connection with the content provided on this website.