Reducing the Price of Naivete in return-to-play from sports-related concussion

Patient-reported outcomes (PROs) play an increasingly important role in medical decision making. Yet, patients whose objectives differ from their physician's may strategically report symptoms to alter treatment decisions. For example, athletes may underreport symptoms to expedite return-to-play (RTP) from sports-related concussion (SRC). Thus, clinicians must implement treatment policies that mitigate the Price of Naivete, that is, the reduction in health outcomes due to naively believing strategically reported symptoms. In this study, we analyze dynamic treatment cessation decisions with strategic patients. Specifically, we formulate the Behavior-Aware Partially Observable Markov Decision Process (BA-POMDP), which optimizes the timing of treatment cessation decisions while accounting for known symptom-reporting behaviors. We then analytically characterize the BA-POMDP's optimal policy, leading to several practical insights. Next, we formulate the Behavior-Learning Partially Observable Markov Decision Process (BL-POMDP), which extends the BA-POMDP by learning a patient's symptom-reporting behavior over time. We show that the BL-POMDP is decomposable into several BA-POMDPs, allowing us to leverage the BA-POMDP's structural properties for solving the BL-POMDP. Then, we apply the BL-POMDP to RTP from SRC using data from 29 institutions across the United States. We estimate the Price of Naivete by comparing the BL-POMDP to naive benchmark policies. Accordingly, the BL-POMDP reduces premature RTP by over 44% and provides up to 3.63 additional health-adjusted athletic exposures per athlete compared to current practice. Overall, changing the interpretation of reported symptoms can better reduce the Price of Naivete over adjusting treatment cessation thresholds. Therefore, to improve patients' health outcomes, clinicians must understand how strategic behavior manifests in PROs.