Incorporating Patient Preferences into Estimation of Optimal Individualized Treatment Rules

Abstract

Precision medicine seeks to provide treatment only if, when, to whom, and at the dose it is needed. Thus, precision medicine is a vehicle by which healthcare can be made both more effective and efficient. Individualized treatment rules operationalize precision medicine as a map from current patient information to a recommended treatment. An optimal individualized treatment rule is defined as maximizing the mean of a pre-specified scalar outcome. However, in settings with multiple outcomes, choosing a scalar composite outcome by which to define optimality is difficult. Furthermore, when there is heterogeneity across patient preferences for these outcomes, it may not be possible to construct a single composite outcome that leads to high-quality treatment recommendations for all patients. We simultaneously estimate the optimal individualized treatment rule for all composite outcomes representable as a convex combination of the (suitably transformed) outcomes. For each patient, we use a preference elicitation questionnaire and item response theory to derive the posterior distribution over preferences for these composite outcomes and subsequently derive an estimator of an optimal individualized treatment rule tailored to patient preferences. We prove that as the number of subjects and items on the questionnaire diverge, our estimator is consistent for an oracle optimal individualized treatment rule wherein each patient's preference is known a priori. We illustrate the proposed method using data from a clinical trial on antipsychotic medications for schizophrenia.

Keywords: Competing outcomes; Individualized treatment rules; Item response theory; Precision medicine.

Figure 1

Averaged squared difference between V̂_U(π̂_n) and V_U(π^opt). Lighter shades of gray correspond to larger error; it can be seen that the approximation improves as sample size or number of items increases.

Figure 2

Averaged squared difference between V̂_Y (π̂_Y) and $V_Y({\pi }_Y^{\text{opt}})$. Lighter shades of gray correspond to larger error; it can be seen that the quality of the approximation improves with sample size but not the number of items.

Figure 3

Averaged squared difference between V̂_Z(π̂_Z) and $V_Z({\pi }_Z^{\text{opt}})$. Lighter shades of gray correspond to larger error; it can be seen that the quality of the approximation improves with sample size but not the number of items.

Figure 4

Average percentage disagreement between π̂_n and π^opt. Lighter shades of gray correspond to higher disagreement; it can be seen that agreement generally increases as n and p increase.

Figure 5

Average percentage disagreement between π̂_n and π^oracle. Lighter shades of gray correspond to higher disagreement; it can be seen that agreement generally increases as n and p increase.