How old are you, really? AI can tell your true age by looking at your chest
Aug 24, 2023
How old are you, really? AI can tell your true age by looking at your chest
Osaka Metropolitan University scientists have developed an advanced artificial intelligence (AI) model that utilizes chest radiographs to accurately estimate a patient’s chronological age. More importantly, when there is a disparity, it can signal a correlation with chronic disease. These findings mark a leap in medical imaging, paving the way for improved early disease detection and intervention. The results are published in The Lancet Healthy Longevity.https://www.thelancet.com/journals/la …https://www.eurekalert.org/news-relea …https://www.blog.qualitypointtech.com …https://www.blog.qualitypointtech.com …
Content
0.099 -> Osaka Metropolitan University scientists have
developed an advanced artificial intelligence
5.96 -> (AI) model that utilizes chest radiographs
to accurately estimate a patient’s chronological
12.02 -> age.
13.19 -> More importantly, when there is a disparity,
it can signal a correlation with chronic disease.
19.26 -> These findings mark a leap in medical imaging,
paving the way for improved early disease
24.59 -> detection and intervention.
26.06 -> The results are published in The Lancet Healthy
Longevity.
29.279 -> The research team first constructed a deep
learning-based AI model to estimate age from
36.98 -> chest radiographs of healthy individuals.
39.68 -> They then applied the model to radiographs
of patients with known diseases to analyze
45.57 -> the relationship between AI-estimated age
and each disease.
50.44 -> Given that AI trained on a single dataset
is prone to overfitting, the researchers collected
56.89 -> data from multiple institutions.
59.14 -> For the development, training, internal and
external testing of the AI model for age estimation,
66 -> a total of 67,099 chest radiographs were obtained
between 2008 and 2021 from 36,051 healthy
76.791 -> individuals who underwent health check-ups
at three facilities.
80.86 -> The developed model showed a correlation coefficient
of 0.95 between the AI-estimated age and chronological
89.119 -> age.
90.119 -> Generally, a correlation coefficient of 0.9
or higher is considered to be very strong.
94.189 -> To validate the usefulness of AI-estimated
age using chest radiographs as a biomarker,
101.36 -> an additional 34,197 chest radiographs were
compiled from 34,197 patients with known diseases
110.4 -> from two other institutions.
112 -> The results revealed that the difference between
AI-estimated age and the patient’s chronological
118.112 -> age was positively correlated with a variety
of chronic diseases, such as hypertension,
124.479 -> hyperuricemia, and chronic obstructive pulmonary
disease.
129.06 -> In other words, the higher the AI-estimated
age compared to the chronological age, the
133.31 -> more likely individuals were to have these
diseases.
136.03 -> The researcher says that their results suggest
that chest radiography-based apparent age
141.95 -> may accurately reflect health conditions beyond
chronological age.
146.099 -> They aim to further develop this research
and apply it to estimate the severity of chronic
151.42 -> diseases, to predict life expectancy, and
to forecast possible surgical complications.
Source: https://www.youtube.com/watch?v=SauhoY03lOU
