{Reference Type}: Journal Article
{Title}: Reinforcement learning for individualized lung cancer screening schedules: A nested case-control study.
{Author}: Wang Z;Sui X;Song W;Xue F;Han W;Hu Y;Jiang J;
{Journal}: Cancer Med
{Volume}: 13
{Issue}: 13
{Year}: 2024 Jul
{Factor}: 4.711
{DOI}: 10.1002/cam4.7436
{Abstract}: BACKGROUND: The current guidelines for managing screen-detected pulmonary nodules offer rule-based recommendations for immediate diagnostic work-up or follow-up at intervals of 3, 6, or 12 months. Customized visit plans are lacking.
OBJECTIVE: To develop individualized screening schedules using reinforcement learning (RL) and evaluate the effectiveness of RL-based policy models.
METHODS: Using a nested case-control design, we retrospectively identified 308 patients with cancer who had positive screening results in at least two screening rounds in the National Lung Screening Trial. We established a control group that included cancer-free patients with nodules, matched (1:1) according to the year of cancer diagnosis. By generating 10,164 sequence decision episodes, we trained RL-based policy models, incorporating nodule diameter alone, combined with nodule appearance (attenuation and margin) and/or patient information (age, sex, smoking status, pack-years, and family history). We calculated rates of misdiagnosis, missed diagnosis, and delayed diagnosis, and compared the performance of RL-based policy models with rule-based follow-up protocols (National Comprehensive Cancer Network guideline; China Guideline for the Screening and Early Detection of Lung Cancer).
RESULTS: We identified significant interactions between certain variables (e.g., nodule shape and patient smoking pack-years, beyond those considered in guideline protocols) and the selection of follow-up testing intervals, thereby impacting the quality of the decision sequence. In validation, one RL-based policy model achieved rates of 12.3% for misdiagnosis, 9.7% for missed diagnosis, and 11.7% for delayed diagnosis. Compared with the two rule-based protocols, the three best-performing RL-based policy models consistently demonstrated optimal performance for specific patient subgroups based on disease characteristics (benign or malignant), nodule phenotypes (size, shape, and attenuation), and individual attributes.
CONCLUSIONS: This study highlights the potential of using an RL-based approach that is both clinically interpretable and performance-robust to develop personalized lung cancer screening schedules. Our findings present opportunities for enhancing the current cancer screening system.