Identifying individualized risk profiles for radiotherapy-induced lymphopenia
A MD Anderson-led study. Using machine learning techniques, this study analyzed the retrospective data of 746 patients with esophageal cancer treated with photons (n = 500) and protons (n = 246) to determine the pretreatment clinical and radiation dosimetric risk factors of grade 4 radiation-induced lymphopenia (G4RIL). This study found that baseline absolute lymphocyte count and volumes of lung and spleen receiving ≥ 15 and ≥ 5 Gy, respectively, were the most important G4RIL risk determinants. The G4RIL risk for an average patient receiving protons increased by 19% had the patient switched to photons. Reductions in G4RIL risk were maximized with proton therapy for older patients, with lower baseline absolute lymphocyte count, and higher lung and heart dose. The authors suggested that this framework for machine learning can be applied broadly to study risk determinants of other adverse events, providing the basis for adapting treatment strategies for mitigation.