Scientists at Osaka Metropolitan University have created a sophisticated artificial intelligence (AI) model that uses chest radiographs to determine a patient's chronological age.
AI simulates how the human mind makes decisions and solves problems using computers and other technology. From ChatGPT to Apple's Siri, AI can be helpful in various ways, including healthcare.
The study group initially built a deep learning-based AI model to estimate age from chest radiographs of healthy individuals under the direction of graduate student Yasuhito Mitsuyama and associate professor, Daiju Ueda from Osaka Metropolitan University.
They then applied the model to radiographs of individuals with known disorders to examine the connection between AI-estimated age and each condition. Due to the risk of overfitting associated with AI trained on a single dataset, the researchers gathered data from other universities.
Thirty-six thousand fifty-one healthy individuals who received health screenings at three locations between 2008 and 2021 provided 67,099 chest radiographs for the creation, training, internal testing, and external testing of the AI model for age estimate.
The created model revealed a 0.95 correlation coefficient between chronological and AI-estimated ages. A correlation value of 0.9 or greater is typically considered quite firm.
An additional 34,197 chest radiographs from 34,197 patients with known disorders from two different institutions were collected to evaluate the utility of AI-estimated age using chest radiographs as a biomarker.
The findings showed that several chronic conditions, including hypertension, hyperuricemia, and chronic obstructive pulmonary disease, were positively connected with the gap between AI-estimated age and the patient's chronological age.
In other words, people were more likely to develop these illnesses the older their AI-estimated age was relative to their chronological age.
He concludes: "Our results suggest that chest radiography-based apparent age may accurately reflect health conditions beyond chronological age. We aim to further develop this research and apply it to estimate the severity of chronic diseases, to predict life expectancy, and to forecast possible surgical complications."
- The Lancet Healthy Longevity. Chest radiography as a biomarker of ageing: artificial intelligence-based, multi-institutional model development and validation in Japan.
- McKinsey & Company. What is AI?