RESUMO
Purpose: Radiation-induced skin toxicity is a common and distressing side effect of breast radiation therapy (RT). We investigated the use of quantitative spectrophotometric markers as input parameters in supervised machine learning models to develop a predictive model for acute radiation toxicity. Methods and materials: One hundred twenty-nine patients treated for adjuvant whole-breast radiotherapy were evaluated. Two spectrophotometer variables, i.e. the melanin (IM) and erythema (IE) indices, were used to quantitatively assess the skin physical changes. Measurements were performed at 4-time intervals: before RT, at the end of RT and 1 and 6 months after the end of RT. Together with clinical covariates, melanin and erythema indices were correlated with skin toxicity, evaluated using the Radiation Therapy Oncology Group (RTOG) guidelines. Binary group classes were labeled according to a RTOG cut-off score of ≥ 2. The patient's dataset was randomly split into a training and testing set used for model development/validation and testing (75%/25% split). A 5-times repeated holdout cross-validation was performed. Three supervised machine learning models, including support vector machine (SVM), classification and regression tree analysis (CART) and logistic regression (LR), were employed for modeling and skin toxicity prediction purposes. Results: Thirty-four (26.4%) patients presented with adverse skin effects (RTOG ≥2) at the end of treatment. The two spectrophotometric variables at the beginning of RT (IM,T0 and IE,T0), together with the volumes of breast (PTV2) and boost surgical cavity (PTV1), the body mass index (BMI) and the dose fractionation scheme (FRAC) were found significantly associated with the RTOG score groups (p<0.05) in univariate analysis. The diagnostic performances measured by the area-under-curve (AUC) were 0.816, 0.734, 0.714, 0.691 and 0.664 for IM, IE, PTV2, PTV1 and BMI, respectively. Classification performances reported precision, recall and F1-values greater than 0.8 for all models. The SVM classifier using the RBF kernel had the best performance, with accuracy, precision, recall and F-score equal to 89.8%, 88.7%, 98.6% and 93.3%, respectively. CART analysis classified patients with IM,T0 ≥ 99 to be associated with RTOG ≥ 2 toxicity; subsequently, PTV1 and PTV2 played a significant role in increasing the classification rate. The CART model provided a very high diagnostic performance of AUC=0.959. Conclusions: Spectrophotometry is an objective and reliable tool able to assess radiation induced skin tissue injury. Using a machine learning approach, we were able to predict grade RTOG ≥2 skin toxicity in patients undergoing breast RT. This approach may prove useful for treatment management aiming to improve patient quality of life.
RESUMO
BACKGROUND: Depression and low-grade systemic inflammation are associated risk factors for hospitalizations and mortality, although the nature of this relationship is under-investigated. METHODS: We performed multivariable Cox regressions of first hospitalization/mortality for all and specific causes vs depression severity, in an Italian population cohort (N=13,176; age≥35 years; 49.4% men), incrementally adjusting for sociodemographic, health and lifestyle factors. We tested potential mediation, additive and interactive effects of INFLA-score, a composite circulating inflammation index, and potential concurrent mediations of main lifestyles and chronic conditions. RESULTS: Over 4,856 hospitalizations (median follow-up 7.28 years), we observed an increased incident risk of events by 24% (CI=17-32%) and 59% (30-90%) for moderate and severe depression, which also showed a 125% (33-281%) increased risk of all-cause mortality (over 471 deaths, 8.24 years). These remained stable after adjustment for lifestyles, health conditions and INFLA-score, which explained 2.1%, 7.6%, 16.3% and 8%, 14.9% and 12% of depression influence on hospitalizations and mortality risk, respectively. These proportions remained substantially stable after reciprocal adjustments. INFLA-score showed significant additive (but not interactive) effects on both hospitalizations and mortality risk. LIMITATIONS: Depression severity was defined using a sub-version of Patient Health Questionnaire 9, which was validated here. Directionality links among exposures could not be established since they were collected simultaneously. CONCLUSIONS: These findings suggest a combined influence of depression and low-grade inflammation on health, which is partly intertwined and dependent on lifestyles and chronic conditions. This suggests the existence of pathways other than inflammation through which depression may play its detrimental effect.