Medical prediction has the power to chart patients' futures and to change their fate. It is extremely difficult to make predictions explicit, but it is important to do so in order to determine the best treatment for an individual patient. The challenge is to discover, model, and validate biological factors in order to capture the disease process represented by the factors, and to use the power of the disease to predict its outcome. Chen et al added bone mineral density to the Gail model and achieved an ROC of 0.62. Their research highlights how difficult it is to create clinically useful risk models.
No takes yet. Share an insight, caveat, or question.
Harry Burke (2008) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: