Chest Radiographs as a Biomarker of Aging: Insights from an AI-Based Study

Chest Radiographs as a Biomarker of Aging: Insights from an AI-Based Study

Chest Radiographs as a Biomarker of Aging: Insights from an AI-Based Study

A recent study published in The Lancet Healthy Longevity has explored the potential of using chest radiographs as a biomarker of aging. The researchers developed an artificial intelligence (AI) model based on deep learning methods to estimate the age of individuals by analyzing their chest radiographs. This AI model was trained, tuned, and tested using data from multiple institutions in Japan.

Chest radiographs are considered a promising biomarker of aging because they provide detailed information about the internal organs, bone characteristics, and overall shape of the body. The AI model developed in this study showed a strong correlation between the AI-estimated age and chronological age, as demonstrated by the root mean square error, mean square error, mean absolute error, and correlation coefficient.

Interestingly, the study found that chest radiographs captured chronic changes associated with aging rather than acute changes. This suggests that aging is a result of accumulated chronic changes over time. The researchers also developed saliency maps, which revealed specific regions in the chest radiographs that were more informative for accurate estimation of aging, such as the superior mediastinum and the lower lung fields.

Furthermore, the study investigated the correlation between the AI-estimated age and various chronic diseases. The results showed associations with conditions such as hyperuricemia, chronic obstructive pulmonary disease, hypertension, lung disease, chronic renal failure, interstitial liver cirrhosis, osteoporosis, and atrial fibrillation.

Although this study has provided valuable insights into the use of chest radiographs as a biomarker of aging, further validation is necessary. The AI model should be tested with different ethnic and racial populations to assess its applicability beyond the Japanese cohort. Additionally, prospective studies using established biological age markers would help confirm the causality and reliability of this AI model.

In conclusion, this study represents an important step toward understanding the aging process and identifying factors associated with healthy aging. The use of AI and deep learning in analyzing chest radiographs has the potential to contribute to age-related research and improve the relationship between aging and the incidence of various diseases.

Definitions:
– Biomarker: A measurable substance or characteristic that can indicate the presence or progression of a disease or the effectiveness of a treatment.
– Artificial intelligence (AI): The simulation of human intelligence in machines that are programmed to think and learn like humans.
– Deep learning: A subset of AI that uses algorithms and artificial neural networks to model and understand complex patterns in data.
– Chronological age: A person’s age measured in years since birth.
– Root mean square error (RMSE): A measure of the average deviation between predicted and actual values.
– Mean square error (MSE): The average of the squares of the differences between predicted and actual values.
– Mean absolute error (MAE): The average of the absolute differences between predicted and actual values.
– Correlation coefficient: A statistical measure that quantifies the strength and direction of the relationship between two variables.

Sources:
– Study: Chest radiography as a biomarker of ageing: artificial intelligence-based, multi-institutional model development and validation in Japan. (Source: The Lancet Healthy Longevity)



Tags: ,