Department of Medical Physics, School of Medicine, Iran University of Medical Sciences, Tehran, Iran.
Radiation Biology Research Center, Iran University of Medical Sciences, Tehran, Iran.
Eur J Med Res. 2024 May 12;29(1):282. doi: 10.1186/s40001-024-01855-y.
Radiation induced acute skin toxicity (AST) is considered as a common side effect of breast radiation therapy. The goal of this study was to design dosiomics-based machine learning (ML) models for prediction of AST, to enable creating optimized treatment plans for high-risk individuals.
Dosiomics features extracted using Pyradiomics tool (v3.0.1), along with treatment plan-derived dose volume histograms (DVHs), and patient-specific treatment-related (PTR) data of breast cancer patients were used for modeling. Clinical scoring was done using the Common Terminology Criteria for Adverse Events (CTCAE) V4.0 criteria for skin-specific symptoms. The 52 breast cancer patients were grouped into AST 2 + (CTCAE ≥ 2) and AST 2 - (CTCAE < 2) toxicity grades to facilitate AST modeling. They were randomly divided into training (70%) and testing (30%) cohorts. Multiple prediction models were assessed through multivariate analysis, incorporating different combinations of feature groups (dosiomics, DVH, and PTR) individually and collectively. In total, seven unique combinations, along with seven classification algorithms, were considered after feature selection. The performance of each model was evaluated on the test group using the area under the receiver operating characteristic curve (AUC) and f1-score. Accuracy, precision, and recall of each model were also studied. Statistical analysis involved features differences between AST 2 - and AST 2 + groups and cutoff value calculations.
Results showed that 44% of the patients developed AST 2 + after Tomotherapy. The dosiomics (DOS) model, developed using dosiomics features, exhibited a noteworthy improvement in AUC (up to 0.78), when spatial information is preserved in the dose distribution, compared to DVH features (up to 0.71). Furthermore, a baseline ML model created using only PTR features for comparison with DOS models showed the significance of dosiomics in early AST prediction. By employing the Extra Tree (ET) classifiers, the DOS + DVH + PTR model achieved a statistically significant improved performance in terms of AUC (0.83; 95% CI 0.71-0.90), accuracy (0.70), precision (0.74) and sensitivity (0.72) compared to other models.
This study confirmed the benefit of dosiomics-based ML in the prediction of AST. However, the combination of dosiomics, DVH, and PTR yields significant improvement in AST prediction. The results of this study provide the opportunity for timely interventions to prevent the occurrence of radiation induced AST.
放射性急性皮肤毒性（AST）被认为是乳腺癌放射治疗的常见副作用。本研究的目的是设计基于剂量组学的机器学习（ML）模型来预测 AST，从而为高风险个体制定优化的治疗计划。
使用 Pyradiomics 工具（v3.0.1）提取剂量组学特征，以及与乳腺癌患者治疗计划相关的剂量体积直方图（DVH）和患者特定的治疗相关（PTR）数据，用于建模。临床评分采用通用不良事件术语标准（CTCAE）V4.0 标准进行皮肤特异性症状评估。52 名乳腺癌患者根据 AST 2+（CTCAE≥2）和 AST 2-（CTCAE<2）毒性分级分为 AST 2+和 AST 2-毒性组，以促进 AST 建模。他们被随机分为训练（70%）和测试（30%）队列。通过多变量分析评估了多种预测模型，分别和联合纳入了不同的特征组（剂量组学、DVH 和 PTR）。经过特征选择，共考虑了七个独特的组合和七种分类算法。在每个测试组中，使用接收者操作特征曲线（ROC）下的面积（AUC）和 f1 分数评估每个模型的性能。还研究了每个模型的准确性、精确性和召回率。统计分析涉及 AST 2-和 AST 2+组之间的特征差异和临界值计算。
结果表明，在 Tomotherapy 治疗后，44%的患者出现 AST 2+。与 DVH 特征（最高可达 0.71）相比，使用剂量组学特征开发的剂量组学（DOS）模型在保留剂量分布的空间信息时，AUC（最高可达 0.78）显著提高。此外，仅使用 PTR 特征创建的基线 ML 模型与 DOS 模型进行比较，表明剂量组学在早期 AST 预测中的重要性。使用 Extra Tree（ET）分类器，DOS+DVH+PTR 模型在 AUC（0.83；95%CI 0.71-0.90）、准确性（0.70）、精确性（0.74）和敏感性（0.72）方面的性能均有统计学意义提高与其他模型相比。
本研究证实了基于剂量组学的 ML 在 AST 预测中的优势。然而，剂量组学、DVH 和 PTR 的结合在 AST 预测方面有显著的提高。本研究的结果为及时干预以预防放射性 AST 的发生提供了机会。
