A Scoring System Contributing to the Detection of Radiation Pneumonitis in Elderly Patients with Lung Cancer—Results of the POLCAR Trial

Background/Objectives: A symptom-based scoring system (0–9 points) for the identification of radiation pneumonitis was previously evaluated in lung cancer patients without age restrictions. A threshold of five points appeared optimal to detect pneumonitis. Since elderly patients have a higher pneumonitis risk, this threshold may not be valid for this group. The POLCAR trial evaluated performance and threshold selection in elderly patients. Methods: Diagnostic discrimination was assessed by receiver operating characteristic analysis. The areas under the curve (AUCs) and a null hypothesis that AUC equaled 0.7 were evaluated. Youden indices were used to identify candidate thresholds. In addition, the change from baseline and patient satisfaction were assessed. The dissatisfaction rate should be <20%. Results: Thirty new patients, plus 31 patients from another prospective trial with an almost identical design, qualified for analyses. The AUC for the pneumonitis score was 0.85 (95% confidence interval: 0.73–0.97). The highest Youden index (0.535) was observed for a threshold of four points. A threshold of five points led to a similar Youden index, a lower sensitivity, and higher specificity. An increase from the baseline by two points had a Youden index of 0.566 and a sensitivity of 100%, while an increase by three points had a Youden index of 0.550 and a specificity of 92.5%. Statistically superior discrimination for the change-from-baseline approach was not observed. The dissatisfaction rate was 5.4%. Conclusions: The scoring system showed good discrimination and high acceptance by patients. A threshold of four points appeared appropriate use in routine screening for the early detection of pneumonitis, whereas the change from baseline was considered useful as an exploratory tool when baseline data were available. Since only eight pneumonitis events occurred, threshold estimates require external validation.