A prediction model for xerostomia in locoregionally advanced nasopharyngeal carcinoma patients receiving radical radiotherapy

Abstract

Background This study was to evaluate the predictors of xerostomia and Grade 3 xerostomia in locoregionally advanced nasopharyngeal carcinoma (NPC) patients receiving radical radiotherapy and establish prediction models for xerostomia and Grade 3 xerostomia based on the predictors. Methods Totally, 365 patients with locoregionally advanced NPC who underwent radical radiotherapy were randomly divided into the training set (n = 255) and the testing set (n = 110) at a ratio of 7:3. All variables were included in the least absolute shrinkage and selection operator regression to screen out the potential predictors for xerostomia as well as the Grade 3 xerostomia in locoregionally advanced NPC patients receiving radical radiotherapy. The random forest (RF), a decision tree classifier (DTC), and extreme-gradient boosting (XGB) models were constructed. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), area under the curve (AUC) and accuracy were analyzed to evaluate the predictive performance of the models. Results In the RF model for predicting xerostomia, the sensitivity was 1.000 (95%CI 1.000–1.000), the PPV was 0.990 (95%CI 0.975–1.000), the NPV was 1.000 (95%CI 1.000–1.000), the AUC was 0.999 (95%CI 0.997–1.000) and the accuracy was 0.992 (95%CI 0.981–1.000) in the training set. The sensitivity was 0.933 (95%CI 0.880–0.985), the PPV was 0.933 (95%CI 0.880–0.985), and the AUC was 0.915 (95%CI 0.860–0.970) in the testing set. Hypertension, age, total radiotherapy dose, dose at 50% of the left parotid volume, mean dose to right parotid gland, mean dose to oral cavity, and course of induction chemotherapy were important variables associated with the risk of xerostomia in locoregionally advanced NPC patients receiving radical radiotherapy. The AUC of DTC model for predicting xerostomia was 0.769 (95%CI 0.666–0.872) in the testing set. The AUC of the XGB model for predicting xerostomia was 0.834 (0.753–0.916) in the testing set. The RF model showed the good predictive ability with the AUC of 0.986 (95%CI 0.972–1.000) in the training set, and 0.766 (95%CI 0.626–0.905) in the testing set for identifying patients who at high risk of Grade 3 xerostomia in those with high risk of xerostomia. Conclusions An RF model for predicting xerostomia in locoregionally advanced NPC patients receiving radical radiotherapy and an RF model for predicting Grade 3 xerostomia in those with high risk of xerostomia showed good predictive ability.

Machine Learning Approaches to Predict Symptoms in People With Cancer: Systematic Review

“…Of the 42 included studies, 10 unique symptoms were reported as outcome variables in the predictions. Those included were xerostomia (9/42, 14%) [ 27 , 30 , 34 , 49 - 51 , 55 , 58 , 60 ], depression (8/42, 13%) [ 22 , 33 , 37 , 41 , 43 , 45 , 52 , 59 ], pain (8/42, 13%) [ 20 , 25 , 26 , 35 , 37 , 40 , 42 , 56 ], fatigue (6/42, 10%) [ 23 , 24 , 29 , 38 , 42 , 44 ], anxiety (3/42, 5%) [ 33 , 46 , 52 ], sleep disturbance or insomnia (3/42, 5%) [ 26 , 28 , 52 ], nausea or vomiting (3/42, 5%) [ 17 , 26 , 29 ], weight loss (2/42, 3%) [ 47 , 53 ], cognitive impairment (2/42, 3%) [ 21 , 36 ], and diarrhea (2/42, 3%) [ 29 , 42 ].…”

Neural network and spline-based regression for the prediction of salivary hypofunction in patients undergoing radiation therapy

“…Comparison of the predictive ability of the four candidate models suggests that alternative approaches to incorporating dose-volume histograms paired with modern machine learning approaches can provide improved discrimination for the prediction of post-radiation hyposalivation. These improvements are likely due to information loss in the way in which the LKB model and similar approaches which rely on simple low-dimensionality summaries of the DVH incorporate the DVH information, such as average organ dose [ 8 , 9 ].…”

“…Roesink et al [ 7 ] performed a study in 2001 in which they used a cohort of 108 patients to estimate the parameters of the LKB for parotid glands and salivary hypofunction. More recently, Beetz et al [ 8 ] and Li et al [ 9 ] developed regression models that predict salivary hypofunction using a variety of clinical and demographic information in addition to a DVH-derived mean organ dose in cohorts of size 167 and 365 respectively. Still others have attempted to predict either xerostomia or salivary hypofunction without using any data on the radiation plan [ 10 , 11 ] while others have turned to delta radiomics [ 12 ] for prediction, although these calculations cannot be performed in the radiation planning phase.…”

Predictive value of delta radiomics in xerostomia after chemoradiotherapy in patients with stage III-IV nasopharyngeal carcinoma

“…Due to the limitation of the anatomical location of NPC, the radiation field area often involves the surrounding normal tissues. The radical dose exceeds the tumor tolerance; thus, the radiotherapy-induced damage to the tissues and organs in the radiation area is extensive and lasting [ 3 ]. Parapharyngeal space is the most common site of lymph node metastasis, and the parotid gland is adjacent to the parapharyngeal space, rendering it inevitable to be exposed to high-doses radiation during radiotherapy and one of the organs at risk of radiotherapy in NPC patients.…”