A deep-learning model scored coronary artery calcium on the low-dose CT taken alongside myocardial perfusion imaging, which is rarely reported. No low-dose scan was labelled in training; expert scores from gated CT were carried over to degraded copies of those same scans. The model was trained at one centre and tested in 5,969 patients at two others, median age 64. Agreement was higher than for models trained on gated images alone, with Cohen's kappa of 0.86 against 0.81. Net reclassification for risk of death or myocardial infarction exceeded that of expert reading of the same scans by 0.089 (95% CI 0.051 to 0.125).
Why it is interesting: The model was taught entirely from a different, better scan type, yet read calcium scores better than experts on the routine scans. Those low-dose scans are already acquired in most PET and many SPECT perfusion studies.
Cite this item
BibTeX
Free sign-up. A digest of the new papers twice a week, grouped by domain.
Other drivers in Data, models and systems
-
Forecasts and their record
How the forecasts are made, how well they explained the past, and how well mortality can be forecast — and by whom.
None this week Earlier → -
What linked data reveals
What linked registries make it possible to know about whole populations
8 this week -
AI in medicine
Whether machine learning predicts, detects and decides better than the tools we have, and whether that has yet changed an outcome for a population.
1 this week -
Health systems and access
What the health system can provide, who gets it, and whether the gaps in health between groups are widening.
4 this week -
Value in health
What a treatment, health programme or policy is worth against what it costs, and how far the models that decide it can be trusted.
1 this week -
Revisions and new sources
What the figures are built from, what is newly available, and how much the numbers move when they are revised.
2 this week
