(Draft) Machine learning to detect and quantify low-value care#

Paper: Mullainathan, S., & Obermeyer, Z. (2019). A machine learning approach to low-value health care: wasted tests, missed heart attacks and mis-predictions. National Bureau of Economic Research.

The authors seek to detect and estimate low value care – care that provides little health benefit in light of its costs: in particular over-testing and under-testing.
They focus on Acute Coronary Syndrom (heart attack) which is difficult to detect: the more conclusive test being stress testing and catheterization.

They use a machine learning algorithm to model the individual risk of having a heart attack in the tested population. These estimates of the risk are plugged into cost-effectiveness estimates based on benefits of the subsequent intervention induced by testing positive –revascularization. Taking as a cost-effective threshold 150,000$, they conclude than half of the tests are not cost-effective.

Various Notes:#

  • The paper makes a smart usage of the tail of the AUC curve to detect meaningfull differences between models. When considering the 1% riskiest patients given each model, how many experienced the outcome? I thinks that it is the same kind of idea than judging models by their calibration.