Predicting severe radiation-induced oral mucositis in head and neck cancer patients using integrated baseline CT radiomic, dosimetry, and clinical features: A machine learning approach

Razieh Agheli; Zahra Siavashpour; Reza Reiazi; Samira Azghandi; Susan Cheraghi; Reza Paydar

doi:10.1016/j.heliyon.2024.e24866

Predicting severe radiation-induced oral mucositis in head and neck cancer patients using integrated baseline CT radiomic, dosimetry, and clinical features: A machine learning approach

Heliyon. 2024 Jan 24;10(3):e24866. doi: 10.1016/j.heliyon.2024.e24866. eCollection 2024 Feb 15.

Authors

Razieh Agheli¹, Zahra Siavashpour², Reza Reiazi³, Samira Azghandi², Susan Cheraghi¹, Reza Paydar^{1

4}

Affiliations

¹ Radiation Sciences Department, Faculty of Allied Medicine, Iran University of Medical Sciences, Tehran, Iran.
² Department of Radiation Oncology, Shohada-e Tajrish Educational Hospital, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
³ Department of Radiation Physics, Division of Radiation Oncology, University of Texas MD Anderson Cancer Center, Houston, TX, 77030, USA.
⁴ Radiation Biology Research Center, Iran University of Medical Sciences, Tehran, Iran.

Abstract

Purpose: To establish the early prediction models of radiation-induced oral mucositis (RIOM) based on baseline CT-based radiomic features (RFs), dosimetric data, and clinical features by machine learning models for head and neck cancer (HNC) patients.

Methods: In this single-center prospective study, 49 HNCs treated with curative intensity modulated radiotherapy (IMRT) were enrolled. Baseline CT images (i.e., CT simulation), dosimetric, and clinical features were collected. RIOM was assessed using CTCAE v.5.0. RFs were extracted from manually-contoured oral mucosa structures. Minimum-redundancy-maximum-relevance (mRMR) method was applied to select the most informative radiomics, dosimetric, and clinical features. Then, binary prediction models were constructed for predicting acute RIOM based on the top mRMR-ranked radiomics, dosimetric, and clinical features alone or in combination, using random forest classifier algorithm. The predictive performance of models was assessed using the area under the receiver operating curve (AUC), accuracy, weighted-average based sensitivity, precision, and F1-measure.

Results: Among extracted features, the top 10 RFs, the top 5 dose-volume features, and the top 5 clinical features were selected using mRMR method. The model exploiting the integrated features (10-radiomics + 5-dosimetric + 5-clinical) achieved the best prediction with AUC, accuracy, sensitivity, precision, and F1-measure values of 91.7 %, 90.0 %, 83.0 % 100.0 %, and 91.0 %, respectively. The model developed using baseline CT RFs alone provided the best performance compared to dose-volume features or clinical features alone, with an AUC of 87.0 %.

Conclusion: Our results suggest that the integration of baseline CT radiomic features with dosimetric and clinical features showed promising potential to improve the performance of machine learning models in early prediction of RIOM. The ultimate goal is to personalize radiotherapy for HNC patients.

Keywords: Head and neck cancer; Machine learning; Oral mucositis; Radiomics; Toxicity prediction.