The Multidimensional Assessment for Pediatric Patients in Radiotherapy (M.A.P.-RT) Tool for Customized Treatment Preparation: RADAR Project

Abstract

Aims: Pediatric patients may experience considerable distress during radiotherapy. Combining psychological interventions with standard therapies can reduce the need for sedation. The RADAR Project aims to use a systematic method of recording data that can reveal patients' difficulties and fragility during treatment. In this context, the aim of our study was to investigate the ability of a multidimensional assessment tool (M.A.P.-RT schedule) to predict the need for sedation during radiotherapy. The schedule, which is administered during the first evaluation, was created to collect information on patients and their families in a standardized way. Materials and Methods: The study enrolled pediatric patients (aged 0-18 years or 18-21 with cognitive impairment). Data were collected by means of the M.A.P.-RT module; this explores various thematic areas, and is completed by the radiation oncologist, psychologist and nurse during their first evaluation. Features were selected by means of the Boruta method (random forest classifier), and the totals of the significant partial scores on each subsection of the module were inserted into a logistic model in order to test for their correlation with the use of anesthesia and with the frequency of psychological support. The results of logistic regression (LR) were used to identify the best predictors. The AUC was used to identify the best threshold for the scores in the evaluation. Results: A total of 99 patients were considered for this analysis. The feature that best predicted both the need for anesthesia and the frequency of psychological support was the total score (TS), the AUC of the ROC being 0.9875 for anesthesia and 0.8866 for psychological support. Conclusion: During the first evaluation, the M.A.P.-RT form can predict the need for anesthesia in pediatric patients, and is a potential tool for personalizing therapeutic and management procedures.

Keywords: anesthesia; children; distress; pediatrics; psychological support; radiotherapy.

Figure 1

Plot of Boruta feature selection process for the “anesthesia” outcome: the red boxes represent the not relevant items, the yellow are the uncertain ones, the green are the relevant items. Blue boxes are calculated as reference levels during the run of Boruta algorithm.

Figure 2

Plot of ROC curve for the “anesthesia” model (AUC = 0.9875), showing possibility to identify patients who need anesthesia support with regards to the total score, achieved putting into the model the value of relevant items of M.A.P.-RT.

Figure 3

Distribution plot of “anesthesia” predictive model score (y axis) in the two groups of patients undergoing (YES) or not (NO) to anesthesia procedure. The red dots represent each patient in the two groups, the threshold line chosen to best split the two categories is the score 0.

Figure 4

Plot of Boruta feature selection process for the “intensive psychological support” outcome: the red boxes represent the not relevant items, the yellow are the uncertain ones, the green are the relevant items. Blue boxes are calculated as reference levels during the run of Boruta algorithm.

Figure 5

Plot of ROC curve for the “psychological support” model (AUC = 0.8866), showing possibility to identify patients who need intensive support with regards to the total score, achieved putting into the model the value of relevant items of M.A.P.-RT.

Figure 6

Distribution plot of “psychological support” predictive model score (y axis) in the two groups of patients undergoing (YES) or not (NO) to intensive psychological support. The blue dots represent each patient in the two groups. Differently from “anesthesia” model no threshold line has been plotted, being wide overlapping between the two categories of patients despite fair model performances.