Journal of Clinical Medicine Research, ISSN 1918-3003 print, 1918-3011 online, Open Access
Article copyright, the authors; Journal compilation copyright, J Clin Med Res and Elmer Press Inc
Journal website https://jocmr.elmerjournals.com

Original Article

Volume 18, Number 9, September 2026, pages 623-631


Radiation-Induced Xerostomia in Patients With Head and Neck Cancer Treated With Comprehensive Salivary Gland-Sparing Helical Tomotherapy Technique Based on a Back Propagation Artificial Neural Network

Figures

↓  Figure 1. Illustration of target volume and salivary glands (fixed four layers). Panels a–d display different anatomical structures of the head and neck across four fixed layers, with each panel presenting a different view of the tumor volume, target volumes, and key salivary glands. Red line: GTVnx; brown line: GTVnd; pink line: CTV1; orange line: oral cavity; blue and green blocks: parotid glands; bright red and bright blue blocks: submandibular glands; yellow and faint yellow blocks: tubarial glands. GTVnx: gross tumor volume of nasopharynx; GTVnd: gross tumor volume of lymph nodal; CTV1: clinical target volume 1.
Figure 1.
↓  Figure 2. Topology diagrams of the BPANN prediction models at (a) 1 year and (b) 2 years post-radiotherapy. The input layer consists of the selected predictors including age, gender, tumor type, and bilateral radiation doses of parotid, submandibular, oral cavity and tubarial glands; the middle hidden layers represent the multilayer neural network architecture capturing nonlinear interactions among variables; the output layer generates three categories of predicted xerostomia risk (no xerostomia, mild xerostomia, moderate/severe xerostomia).Model training metrics are listed as follows: (a) 1-year prediction model: error = 0.37836, training steps = 85,429; (b) 2-year prediction model: error = 0.175809, training steps = 187,816. BPANN: back propagation artificial neural network.
Figure 2.
↓  Figure 3. ROC curves of the BPANN prediction models for xerostomia risk at (a) 1 year and (b) 2 years post-radiotherapy. Blue curves represent the discrimination performance for patients without xerostomia, green curves for mild xerostomia, and red curves for moderate/severe xerostomia, with corresponding AUC values marked on each curve. AUC results: (a) 1-year model: no xerostomia = 0.8835, mild xerostomia = 0.9474, moderate/severe xerostomia = 0.9650; (b) 2-year model: no xerostomia = 0.9417, mild xerostomia = 0.9000, moderate/severe xerostomia = 0.8901. BPANN: back propagation artificial neural network; ROC: receiver operating characteristic.
Figure 3.

Tables

↓  Table 1. Patient Characteristics (N = 222)
 
CharacteristicsNumber of patients (%)
XQ score categories: 0–5, no xerostomia; 6–10, mild xerostomia; 11–20, moderate xerostomia; and 21–30, severe xerostomia. XQ: xerostomia questionnaire; PG: parotid gland; SMG: submandibular gland; OC: accessory salivary glands in the oral cavity; TG: tubarial gland; R: right; L: left.
Age (years)
  Mean49
  Median (range)52 (10–83)
Gender
  Male164 (73.87)
  Female58 (26.13)
Tumor type
  Nasopharyngeal cancer181 (81.53)
  Oral cavity and oropharyngeal cancer12 (5.41)
  Hypopharyngeal and laryngeal cancer19 (8.56)
  Nasal cavity and paranasal sinuses cancer10 (4.50)
PG-R/L (Gy)
  Mean29.86/29.75
  Median (ranged)29.52/29.59 (19.45–62.86/18.28–47.79)
SMG-R/L (Gy)
  Mean42.78/45.04
  Median (range)33.49/39.97 (21.37–71.63/22.38–69.56)
OC (Gy)
  Mean32.39
  Median (range)31.91 (19.15–54.10)
TG-R/L (Gy)
  Mean62.84/63.18
  Median (range)67.54/67.64 (9.46–71.73/9.41–71.74)
XQ score, 1 year
  Mean8.74
  Median (range)8.00 (0–23)
  No xerostomia50 (22.52)
  Mild xerostomia105 (47.30)
  Moderate/severe xerostomia67 (30.18)
XQ score, 2 years
  Mean4.44
  Median (range)3.00 (0–24)
  No xerostomia155 (69.82)
  Mild xerostomia46 (20.72)
  Moderate/severe xerostomia21 (9.46)

 

↓  Table 2. Spearman’s Rank Correlation Test for Association Between XQ Score and Relevant Characteristics
 
VariablesXQ score (1 year)XQ score (2 years)
RP valueRP value
XQ score categories: 0–5, no xerostomia; 6–10, mild xerostomia; 11–20, moderate xerostomia; 21–30, severe xerostomia. Supplementary subgroup sizes for correlation analysis (full cohort, n = 222): 1-year: no xerostomia = 50, mild = 105, moderate/severe = 67; 2-year: no xerostomia = 155, mild = 46, moderate/severe = 21. XQ: xerostomia questionnaire; PG: parotid gland; SMG: submandibular gland; OC: accessory salivary glands in the oral cavity; TG: tubarial gland; R: right; L: left; Dmean: mean dose.
Gender0.0980.1440.1540.022
Tumor type−0.0700.302−0.0480.475
Age0.1800.0070.241< 0.001
PG-R Dmean−0.0500.459−0.0730.279
PG-L Dmean0.0630.348−0.0100.882
SMG-R Dmean0.0930.1660.1280.037
SMG-L Dmean0.1200.0750.1530.022
OC Dmean0.0200.762−0.0050.941
TG-R Dmean0.0210.757−0.0520.444
TG-L Dmean0.0940.163−0.0110.873

 

↓  Table 3. BPANN Model Predictions for Xerostomia at Different Follow-up Times Post-Radiotherapy
 
Predicted valueTrue value
No xerostomiaMild xerostomiaModerate/severe xerostomiaSum
1 year2 years1 year2 years1 year2 years1 year2 years
The total test set sample size is 63; true subgroup counts: 1-year true group: no xerostomia = 13, mild = 34, moderate/severe = 16; 2-year true group: no xerostomia = 45, mild = 11, moderate/severe = 7. BPANN: back propagation artificial neural network.
No xerostomia94511221248
Mild xerostomia303010413711
Moderate/severe xerostomia1030104144
Total134534111676363