An Efficient Way to Find Optimal Crossover Designs Using CVX for Precision Medicine

Crossover designs play an increasingly important role in precision medicine. We formulate the optimal crossover design problem as a convex optimization problem and demonstrate that the convex optimization package CVX is effective for searching a broad class of optimal crossover designs, including cases where analytical optimal crossover designs are unavailable. We also use CVX to search for N-of-1 trials frequently used in precision medicine and dual-objective optimal crossover designs to estimate treatment effects and carryover treatment effects with unequal interest. We provide CVX codes and as illustrations, use them to find optimal crossover designs under the A-optimality criterion.