Faculty of Dentistry, University of Toronto, Toronto, Canada.
Department of Dental Oncology, Princess Margaret Cancer Centre, Toronto, Canada.
PLoS One. 2024 Jul 24;19(7):e0307531. doi: 10.1371/journal.pone.0307531. eCollection 2024.
This systematic review aimed to evaluate the performance of machine learning (ML) models in predicting post-treatment survival and disease progression outcomes, including recurrence and metastasis, in head and neck cancer (HNC) using clinicopathological structured data.
A systematic search was conducted across the Medline, Scopus, Embase, Web of Science, and Google Scholar databases. The methodological characteristics and performance metrics of studies that developed and validated ML models were assessed. The risk of bias was evaluated using the Prediction model Risk Of Bias ASsessment Tool (PROBAST).
Out of 5,560 unique records, 34 articles were included. For survival outcome, the ML model outperformed the Cox proportional hazards model in time-to-event analyses for HNC, with a concordance index of 0.70-0.79 vs. 0.66-0.76, and for all sub-sites including oral cavity (0.73-0.89 vs. 0.69-0.77) and larynx (0.71-0.85 vs. 0.57-0.74). In binary classification analysis, the area under the receiver operating characteristics (AUROC) of ML models ranged from 0.75-0.97, with an F1-score of 0.65-0.89 for HNC; AUROC of 0.61-0.91 and F1-score of 0.58-0.86 for the oral cavity; and AUROC of 0.76-0.97 and F1-score of 0.63-0.92 for the larynx. Disease-specific survival outcomes showed higher performance than overall survival outcomes, but the performance of ML models did not differ between three- and five-year follow-up durations. For disease progression outcomes, no time-to-event metrics were reported for ML models. For binary classification of the oral cavity, the only evaluated subsite, the AUROC ranged from 0.67 to 0.97, with F1-scores between 0.53 and 0.89.
ML models have demonstrated considerable potential in predicting post-treatment survival and disease progression, consistently outperforming traditional linear models and their derived nomograms. Future research should incorporate more comprehensive treatment features, emphasize disease progression outcomes, and establish model generalizability through external validations and the use of multicenter datasets.
本系统评价旨在评估使用临床病理结构化数据的机器学习 (ML) 模型在预测头颈部癌症 (HNC) 治疗后生存和疾病进展结局（包括复发和转移）方面的性能。
对 Medline、Scopus、Embase、Web of Science 和 Google Scholar 数据库进行了系统检索。评估了开发和验证 ML 模型的研究的方法学特征和性能指标。使用预测模型风险偏倚评估工具 (PROBAST) 评估了偏倚风险。
在 5560 条独特记录中，有 34 篇文章被纳入。对于生存结局，在 HNC 的时间事件分析中，ML 模型优于 Cox 比例风险模型，其一致性指数为 0.70-0.79 与 0.66-0.76，对于包括口腔（0.73-0.89 与 0.69-0.77）和喉（0.71-0.85 与 0.57-0.74）在内的所有亚部位均如此。在二分类分析中，ML 模型的接收者操作特征曲线下面积（AUROC）范围为 0.75-0.97，HNC 的 F1 分数为 0.65-0.89；口腔 AUROC 为 0.61-0.91，F1 分数为 0.58-0.86；喉 AUROC 为 0.76-0.97，F1 分数为 0.63-0.92。疾病特异性生存结局的表现优于总体生存结局，但 ML 模型的性能在 3 年和 5 年随访期之间没有差异。对于疾病进展结局，未报告 ML 模型的时间事件指标。对于二分类的口腔部位，唯一评估的亚部位，AUROC 范围为 0.67-0.97，F1 分数在 0.53-0.89 之间。
ML 模型在预测治疗后生存和疾病进展方面具有相当大的潜力，一致优于传统的线性模型及其衍生的列线图。未来的研究应纳入更全面的治疗特征，强调疾病进展结局，并通过外部验证和使用多中心数据集来建立模型的通用性。
