Ingham Institute for Applied Medical Research, Sydney, Australia; Southwest Sydney Clinical Campus, University of New South Wales, Sydney, Australia; Liverpool and Macarthur Cancer Therapy Centres, Sydney, Australia.
Laboratory of Radiation Physics, Odense University Hospital, Odense, Denmark; Department of Clinical Research, University of Southern Denmark, Odense, Denmark; Danish Centre for Particle Therapy, Aarhus University Hospital, Denmark; Institute of Medical Physics, School of Physics, University of Sydney, Sydney, Australia.
Radiother Oncol. 2023 Jun;183:109629. doi: 10.1016/j.radonc.2023.109629. Epub 2023 Mar 18.
Multiple outcome prediction models have been developed for Head and Neck Squamous Cell Carcinoma (HNSCC). This systematic review aimed to identify HNSCC outcome prediction model studies, assess their methodological quality and identify those with potential utility for clinical practice. Inclusion criteria were mucosal HNSCC prognostic prediction model studies (development or validation) incorporating clinically available variables accessible at time of treatment decision making and predicting tumour-related outcomes. Eligible publications were identified from PubMed and Embase. Methodological quality and risk of bias were assessed using the checklist for critical appraisal and data extraction for systematic reviews of prediction modelling studies (CHARMS) and prediction model risk of bias assessment tool (PROBAST). Eligible publications were categorised by study type for reporting. 64 eligible publications were identified; 55 reported model development, 37 external validations, with 28 reporting both. CHARMS checklist items relating to participants, predictors, outcomes, handling of missing data, and some model development and evaluation procedures were generally well-reported. Less well-reported were measures accounting for model overfitting and model performance measures, especially model calibration. Full model information was poorly reported (3/55 model developments), specifically model intercept, baseline survival or full model code. Most publications (54/55 model developments, 28/37 external validations) were found to have high risk of bias, predominantly due to methodological issues in the PROBAST analysis domain. The identified methodological issues may affect prediction model accuracy in heterogeneous populations. Independent external validation studies in the local population and demonstration of clinical impact are essential for the clinical implementation of outcome prediction models.
已经开发出了多种用于头颈部鳞状细胞癌（HNSCC）的结局预测模型。本系统评价旨在确定 HNSCC 结局预测模型研究，评估其方法学质量，并确定那些对临床实践具有潜在应用价值的研究。纳入标准为黏膜 HNSCC 预后预测模型研究（开发或验证），纳入了治疗决策时可获得的临床可用变量，并预测肿瘤相关结局。从 PubMed 和 Embase 中确定了合格的出版物。使用关键评估清单和预测模型风险评估工具（PROBAST）评估了方法学质量和偏倚风险，并对预测模型进行了数据提取。根据研究类型对合格出版物进行了报告分类。确定了 64 篇合格的出版物；55 篇报告了模型开发，37 篇报告了外部验证，其中 28 篇报告了两者。CHARMS 清单中与参与者、预测因子、结局、缺失数据处理以及一些模型开发和评估程序有关的项目通常报告得较好。但报告较差的是考虑模型过度拟合和模型性能指标的措施，尤其是模型校准。完整的模型信息报告得很差（55 个模型开发中的 3 个），特别是模型截距、基线生存率或完整模型代码。大多数出版物（55 个模型开发中的 54 篇，37 个外部验证中的 28 篇）被发现存在高偏倚风险，主要是由于 PROBAST 分析领域的方法学问题。已确定的方法学问题可能会影响异质人群中预测模型的准确性。在当地人群中进行独立的外部验证研究，并证明其对临床的影响，对于结局预测模型的临床应用至关重要。
