Jiang Tianxiang, Zhao Zhou, Liu Xueting, Shen Chaoyong, Mu Mingchun, Cai Zhaolun, Zhang Bo
Department of General Surgery, West China Hospital, Sichuan University, Chengdu, China.
Gastric Cancer Center, West China Hospital, Sichuan University, Chengdu, China.
Front Oncol. 2023 Sep 4;13:1161237. doi: 10.3389/fonc.2023.1161237. eCollection 2023.
Machine learning radiomics models are increasingly being used to predict gastric cancer prognoses. However, the methodological quality of these models has not been evaluated. Therefore, this study aimed to evaluate the methodological quality of radiomics studies in predicting the prognosis of gastric cancer, summarize their methodological characteristics and performance.
The PubMed and Embase databases were searched for radiomics studies used to predict the prognosis of gastric cancer published in last 5 years. The characteristics of the studies and the performance of the models were extracted from the eligible full texts. The methodological quality, reporting completeness and risk of bias of the included studies were evaluated using the RQS, TRIPOD and PROBAST. The discrimination ability scores of the models were also compared.
Out of 283 identified records, 22 studies met the inclusion criteria. The study endpoints included survival time, treatment response, and recurrence, with reported discriminations ranging between 0.610 and 0.878 in the validation dataset. The mean overall RQS value was 15.32 ± 3.20 (range: 9 to 21). The mean adhered items of the 35 item of TRIPOD checklist was 20.45 ± 1.83. The PROBAST showed all included studies were at high risk of bias.
The current methodological quality of gastric cancer radiomics studies is insufficient. Large and reasonable sample, prospective, multicenter and rigorously designed studies are required to improve the quality of radiomics models for gastric cancer prediction.
This protocol was prospectively registered in the Open Science Framework Registry (https://osf.io/ja52b).
机器学习放射组学模型越来越多地用于预测胃癌预后。然而，这些模型的方法学质量尚未得到评估。因此，本研究旨在评估放射组学研究在预测胃癌预后方面的方法学质量，总结其方法学特征和性能。
检索PubMed和Embase数据库，查找过去5年发表的用于预测胃癌预后的放射组学研究。从符合条件的全文中提取研究特征和模型性能。使用RQS、TRIPOD和PROBAST评估纳入研究的方法学质量、报告完整性和偏倚风险。还比较了模型的判别能力得分。
在283条识别记录中，22项研究符合纳入标准。研究终点包括生存时间、治疗反应和复发，验证数据集中报告的判别值在0.610至0.878之间。RQS的平均总值得分为15.32±3.20（范围：9至21）。TRIPOD清单35项中的平均符合项数为20.45±1.83。PROBAST显示所有纳入研究都存在高偏倚风险。
目前胃癌放射组学研究的方法学质量不足。需要进行大规模、合理样本、前瞻性、多中心且设计严谨的研究，以提高用于胃癌预测的放射组学模型的质量。
本方案已在开放科学框架注册库（https://osf.io/ja52b）中进行前瞻性注册。
