Department of General Surgical Specialties, The Royal Melbourne Hospital, Melbourne, Victoria, Australia.
Department of Surgery, Austin Health, Melbourne, Victoria, Australia.
Langenbecks Arch Surg. 2023 Aug 18;408(1):321. doi: 10.1007/s00423-023-03039-4.
Up to 15-27% of patients achieve pathologic complete response (pCR) following neoadjuvant chemoradiotherapy (CRT) for locally advanced rectal cancer (LARC). Deep neural learning (DL) algorithms have been suggested to be a useful adjunct to allow accurate prediction of pCR and to identify patients who could potentially avoid surgery. This systematic review aims to interrogate the accuracy of DL algorithms at predicting pCR.
Embase (PubMed, MEDLINE) databases and Google Scholar were searched to identify eligible English-language studies, with the search concluding in July 2022. Studies reporting on the accuracy of DL models in predicting pCR were selected for review and information pertaining to study characteristics and diagnostic measures was extracted from relevant studies. Risk of bias was evaluated using the Newcastle-Ottawa scale (NOS).
Our search yielded 85 potential publications. Nineteen full texts were reviewed, and a total of 12 articles were included in this systematic review. There were six retrospective and six prospective cohort studies. The most common DL algorithm used was the Convolutional Neural Network (CNN). Performance comparison was carried out via single modality comparison. The median performance for each best-performing algorithm was an AUC of 0.845 (range 0.71-0.99) and Accuracy of 0.85 (0.83-0.98).
There is a promising role for DL models in the prediction of pCR following neoadjuvant-CRT for LARC. Further studies are needed to provide a standardised comparison in order to allow for large-scale clinical application.
PROSPERO 2021 CRD42021269904 Available from: https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42021269904 .
在接受新辅助放化疗（CRT）的局部晚期直肠癌（LARC）患者中，多达 15-27%的患者可达到病理完全缓解（pCR）。深度学习（DL）算法被认为是一种有用的辅助手段，可以准确预测 pCR，并识别出可能避免手术的患者。本系统评价旨在探究 DL 算法预测 pCR 的准确性。
检索 Embase（PubMed、MEDLINE）数据库和 Google Scholar，以确定符合条件的英文研究，检索于 2022 年 7 月结束。选择报告 DL 模型预测 pCR 准确性的研究进行综述，并从相关研究中提取有关研究特征和诊断措施的信息。使用纽卡斯尔-渥太华量表（NOS）评估偏倚风险。
我们的搜索产生了 85 篇潜在的出版物。共审查了 19 篇全文，共有 12 篇文章纳入本系统评价。其中包括 6 项回顾性和 6 项前瞻性队列研究。最常用的 DL 算法是卷积神经网络（CNN）。通过单一模式比较进行性能比较。每个表现最佳算法的中位数性能为 AUC 为 0.845（范围为 0.71-0.99）和准确性为 0.85（0.83-0.98）。
DL 模型在预测新辅助 CRT 治疗 LARC 后的 pCR 方面具有有前途的作用。需要进一步的研究提供标准化的比较，以便允许大规模的临床应用。
PROSPERO 注册：PROSPERO 2021 CRD42021269904 可从以下网址获得：https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42021269904。
