In this type of task, an optimal decision-maker should choose gambles with greater EV, to maximise winnings.
Furthermore, even a theoretically optimal decision-maker produced by natural selection is still expected to make systematic mistakes (Livnat and Pippenger 2008).
Together, these features will likely dictate the optimal timing of deployment in the care process, the optimal decision-maker(s) (i.e., physician, nurse, patient), and the utility of other forms of support (e.g., linked order sets) that are integral to the CDS to engage the end user.
When searching for optimal solutions, decision makers therefore inevitably must evaluate trade-offs, which call for multiattribute valuation methods.
By analyzing the obtained optimal alignments, the decision maker can understand the tradeoff between the objectives.
For the preference-free analysis, we found that secondary prevention has a very low (<0.05) first rank acceptability index, making it unlikely to be optimal for any decision maker.
For an efficient search through the solution space we use a multi objective genetic algorithm which allows us to identify a set of Pareto optimal solutions providing the decision maker with the complete spectrum of optimal solutions with respect to the various targets.
Then, the solutions satisfying specific criteria can be chosen from the set of Pareto optimal solutions by the decision maker.
This is because of the optimal threshold in the decision maker that was calculated from a subset of the training/development data and next applied to the whole set.
Finally a compromise solution is presented from a set of Pareto optimal solutions to help the decision maker.
Finally, the compromise solution has been chosen from a set of Pareto optimal solutions to help the decision maker.
