Complexity in decisions involving multiple factors and variability in interpretation of data motivate the development of computerized techniques to assist humans in decision-making.Because the goal of predictive models is to estimate outcomes in new patients (who may or may not be similar to the patients used to develop the model), a critical challenge in prognostic research is to determine what evidence beyond validation is needed before practitioners can confidently apply a model to their patients. This is important to determine a patient’s individual risk.As each model is constructed using different features, parameters, and samples, specific models may work best for certain subgroups of individuals. For example, many calculators and charts use the Framingham model to estimate cardiovascular disease (CVD) risk.These models work well, but may underestimate the CVD risk in patients with diabetes. illustrates a case in which a patient can get significantly different CVD risk scores from different online risk estimation calculators. (Jiang, et, al., 2012).
In this research, they address the problem of selecting the most appropriate model for assessing the risk for a particular patient. they developed an algorithm for online model selection based on the CI of predictions so that clinicians can choose the model at the point of care for their patients.
Jiang, X., Boxwala, A. A., El-Kareh, R., Kim, J., & Ohno-Machado, L. (2012, June). A patient-driven adaptive prediction technique to improve personalized risk estimation for clinical decision support. Retrieved October 24, 2017, from https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3392846/