Breaking the ‘intellectual bottleneck’: How AI is computing the previously uncomputable in healthcare
1 min read
Summary
A simple algorithm, trained to scan for incidental coronary artery calcification (iCAC), a strong predictor of cardiovascular risk, has been used at the University of Texas Medical Branch to conduct cardiac risk screening across a range of CT scans.
AI is being used to detect stroke and pulmonary embolism by looking for obstructed blood flows or abrupt blood vessel cutoff.
Once the relevant indicators have been found, the programme immediately notifies the care team, improving the speed of treatment.
AI can also be used to determine whether inpatient admissions are justified and identify any gaps in care, such as musculoskeletal impairment.
UTMB’s chief AI officer, Peter McCaffrey, said the facility is using AI to provide “preventative care”, which allows it to make better use of the large amount of data it collects.
He added that, while the cases flagged by AI are not complex, they are “high-volume” and provide a lot of value, as patients who would otherwise have gone undiagnosed can be treated.