Development and evaluation of a multimodal feature-based predictive model for radiotherapy-induced oral mucositis in nasopharyngeal carcinoma

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Extra Trees algorithm: AUC 0.956 ± 0.046; Logistic Regression: accuracy 0.832 ± 0.155

• Primary Outcome: Prediction of radiation-induced oral mucositis grades

• Nnt Or Sensitivity: 1D-CNN achieved AUC 0.900 ± 0.072 with accuracy 0.732 ± 0.140

• Confidence Interval: Cohen's kappa 0.82 (95% CI: 0.73-0.91) for inter-rater reliability

Clinical Application

Requires multimodal data integration (CT imaging, dosimetry, clinical features) which may limit routine implementation Relevant to Australian radiation oncology practice, though validation in local populations needed. Could inform TGA-approved treatment planning systems and support RANZCR radiotherapy guidelines Nasopharyngeal carcinoma patients receiving radiotherapy, though generalisability limited by small single-centre cohort

Abstract

BACKGROUND: Accurate prediction of radiation-induced oral mucositis is crucial for personalized treatment in head and neck cancer. However, developing robust predictive models utilizing high-dimensional multimodal data (CT imaging, dose distribution, and clinical features) remains challenging, particularly in cohorts with limited sample sizes. OBJECTIVE: This study aimed to rigorously evaluate and compare the multi-class predictive performance of traditional machine learning algorithms and deep learning architectures under a small-cohort setting. METHODS: Multimodal data from 108 patients were collected. A comprehensive evaluation framework incorporating nine traditional machine learning algorithms and two deep learning models (a dimensionality-reduced 1D-CNN and a multimodal 3D-CNN) was established. To ensure robust evaluation, a stratified 5-fold cross-validation was employed. Model performance was comprehensively quantified using mean ± standard deviation (SD) across multiple metrics, including the Area Under the Curve (AUC), accuracy, and Matthews Correlation Coefficient (MCC). RESULTS: Inter-rater reliability for RIOM grading was excellent (Cohen's kappa = 0.82, 95% CI: 0.73-0.91). Among traditional machine learning approaches, the Extra Trees (ET) algorithm achieved the highest discriminative capacity (AUC: 0.956 ± 0.046), while Logistic Regression (LR) demonstrated optimal overall accuracy (0.832 ± 0.155) and stability. Regarding deep learning, the lightweight 1D-CNN utilizing fused low-dimensional features exhibited highly competitive and robust performance (AUC: 0.900 ± 0.072; Accuracy: 0.732 ± 0.140). In stark contrast, the high-dimensional multimodal 3D-CNN suffered from severe overfitting and mode collapse phenomenon, yielding significantly inferior results (AUC: 0.568 ± 0.090; MCC: -0.025 ± 0.031). CONCLUSIONS: For small-cohort radiomics and dosimetric analyses, ensemble learning models (e.g., ET) and appropriately regularized linear models (e.g., LR) remain highly effective. While deep learning holds promise, high-dimensional architectures like 3D-CNNs are highly susceptible to mode collapse without massive datasets. Instead, employing feature dimensionality reduction combined with lightweight networks (1D-CNN) is a vastly superior strategy to extract reliable predictive patterns from limited clinical data.

References

1. 1.Li, L., Li, L., Guo, R., Fang, S., Wang, K., Yuan, G., Jiang, D., & Huang, J. (2026). Development and evaluation of a multimodal feature-based predictive model for radiotherapy-induced oral mucositis in nasopharyngeal carcinoma. PLoS One. https://doi.org/10.1371/journal.pone.0346251