Consistency of variety of machine learning and statistical models in predicting clinical risks of individual patients: longitudinal cohort study using cardiovascular disease as exemplar

Study of 3.6 m patients from Clinical Practice Research Datalink registered at 391 general practices in England found variety of models predicted risks for same patients very differently; survival models that consider censoring and are explainable, such as QRISK3, are preferable.

Source:

British Medical Journal