Medical and Personal Characteristics Can Predict the Risk of Lung Metastasis.

AIMS: Understanding the correlations between underlying medical and personal characteristics of a patient with cancer and the risk of lung metastasis may improve clinical management and outcomes. We used machine learning methodologies to predict the risk of lung metastasis using readily available predictors. MATERIALS AND METHODS: We retrospectively analysed a cohort of 11 164 oncological patients, with clinical records gathered between 2000 and 2020. The input data consisted of 94 parameters, including age, body mass index (BMI), sex, social history, 81 primary cancer types, underlying lung disease and diabetes mellitus. The strongest underlying predictors were discovered with the analysis of the highest performing method among four distinct machine learning methods. RESULTS: Lung metastasis was present in 958 of 11 164 oncological patients. The median age and BMI of the study population were 63 (±19) and 25.12 (±5.66), respectively. The random forest method had the most robust performance among the machine learning methods. Feature importance analysis revealed high BMI as the strongest predictor. Advanced age, smoking, male gender, alcohol dependence, chronic obstructive pulmonary disease and diabetes were also strongly associated with lung metastasis. Among primary cancers, melanoma and renal cancer had the strongest correlation. CONCLUSIONS: Using a machine learning-based approach, we revealed new correlations between personal and medical characteristics of patients with cancer and lung metastasis. This study highlights the previously unknown impact of predictors such as obesity, advanced age and underlying lung disease on the occurrence of lung metastasis. This prediction model can assist physicians with preventive risk factor control and treatment strategies.

Lung stereotactic radiation therapy: Intercomparison of irradiation devices in terms of outcome and predictive factors.

PURPOSE: To compare three different radiotherapy devices able to perform pulmonary stereotactic radiotherapy: CyberKnife® (CK), Helical Tomotherapy® (HT), and volumetric modulated arc therapy (VMAT). This study aims to define the patients' outcome in terms of SBRT efficacy and toxicities depending of the device choice. MATERIALS AND METHODS: We retrospectively analyzed the clinical, radiological, and dosimetric data of patients treated with lung SBRT between 2016 and 2020 at Lausanne University Hospital, using the Chi2 test for proportions, the t-test for means comparisons, the Kaplan-Meier method for survival, and the Log-rank test and Cox-regression for intergroups comparisons. RESULTS: We identified 111 patients treated by either CK (59.9%), VMAT (38.0%), or HT (2.1%). Compared to other techniques, CK treated comparable gross tumor volume (GTV; 2.1 vs. 1.4cm3, P=0.84) with smaller planning treatment volume (PTV; 12.3 vs. 21.9cm3, P=0.013) and lower V5 (13.5 vs. 19.9cm3, P=0.002). Local control rates at 2years were not different whatever the irradiation device, respectively of 96.2% (range, 90.8-100) and 98.1% (range, 94.4-100), P=0.68. Toxicity incidence significantly increased with V5 value>17.2% (56.0 vs. 77.4%, P=0.021). CONCLUSION: Compared to other SBRT techniques, CK treatments permitted to treat comparable GTV with reduced PTV and V5. Toxicity incidence was less frequent when reducing the V5. CK is particularly attractive in case of multiple courses of lung SBRT or lung reirradiation.

Stereotactic body radiotherapy with helical TomoTherapy for medically inoperable early stage primary and second-primary non-small-cell lung neoplasm: 1-year outcome and toxicity analysis.

OBJECTIVE: This study investigated the effectiveness of stereotactic body radiotherapy with helical TomoTherapy (T-SBRT) for treating medically inoperable primary and second-primary early stage non-small-cell lung neoplasm (SPLN) and evaluated whether the movement of organizing pneumonia (OP) within the irradiation field (IF) can be detected via analysis of radiological changes. METHODS: Patients (n = 16) treated for 1 year (2011-12) at our hospital by T-SBRT at a total dose of 60 Gy in five fractions were examined retrospectively. Outcome and toxicity were recorded and were separately described for SPLN. CT scans were reviewed by a single radiologist. RESULTS: Of the 16 patients, 5 (31.3%) had primary lung malignancies, 10 (62.5%) had SPLN, and 1 case (6.3%) had isolated mediastinal metastasis of lung neoplasm. Pathological evidence was obtained for 72.2% of all lesions. The median radiological follow-up was 11 months (10.5 months for SPLN). For all cases, the 6- and 12-month survival rates were 100% and 77.7% (100% and 71.4%, respectively, for SPLN), and the 6- and 12-month locoregional control rates were 100% in all cases. 2 (12.5%) of 16 patients developed grade 3 late transient radiation pneumonitis following steroid therapy and 1 (6.3%) presented asymptomatic infiltrates comparable to OP opacities. CONCLUSION: T-SBRT seems to be safe and effective. ADVANCES IN KNOWLEDGE: Mild OP is likely associated with radiation-induced anomalies in the IF, identification of migrating opacities can help discern relapse of radiation-induced opacities.