Thread by @moreisdifferent

I have a new @medRxivpreprint that should be of interest to the #longevity community. We show how to predict risk for cardiovascular disease & all-cause mortality from a routine abdominal CT using deep learning. Accuracy on par with CAC score. Thread cont..medrxiv.org/content/10.110…

In this case the scans were taken for CT colonoscopy. The accuracy of the risk prediction is on par with that obtained from a CAC score Cardiac CT scan, but without the additional cost & radiation dose. CT scans contain a wealth of health data which is currently mostly utilized.

Biomarkers that can be extracted from CT scans include visceral/subcutaneous fat ratio, plaque burden, vascular inflammation level, muscle bulk and density, bone mineral density, liver volume and fat fraction, pancreas volume and fat fraction... [ see moreisdifferent.com/assets/literat… ]

In the future, I hope people will be able to download their scans from their healthcare provider at home and run a bunch of AI tools to learn more about their bodies and what preventative measures they specifically might benefit from. #DecentralizedRadiology

Alternatively, the AI tools may be run in the clinic, although that requires FDA approval, a financial incentive to purchase and maintain the necessary software & hardware, and a doctor willing to provide the info to the patient.