机器学习和深度学习模型用于结直肠癌术前淋巴结转移检测的系统评价与Meta分析
该研究系统检索了截至2024年2月16日的四个数据库,纳入12项研究、8321例患者,评估机器学习和深度学习模型对结直肠癌术前淋巴结转移的诊断性能。汇总AUC为0.87,敏感度78%、特异度77%,均显著高于放射科医生(P < 0.001)。作者认为机器学习模型在术前淋巴结转移分期和治疗计划方面具有强大潜力,但需进一步前瞻性多中心研究验证。
要点
- 机器学习模型预测结直肠癌淋巴结转移的汇总AUC为0.87,敏感度78%,特异度77%。
- 机器学习模型AUC显著高于初级和高年资放射科医生(P < 0.001)。
- T2-T4期特异度95%显著高于T1-T2期61%(P < 0.01),AUC和敏感度无显著差异。
核心结论
- 机器学习模型在结直肠癌术前淋巴结转移分期和治疗计划方面显示出强大潜力,可能减少额外手术及相关健康和经济负担,但需进一步前瞻性多中心研究验证。
研究设计与样本
- 系统评价与Meta分析,遵循PRISMA-DTA和AMSTAR-2指南,检索PubMed、Web of Science、Embase和Cochrane Library截至2024年2月16日,纳入12项研究共8321例患者,使用QUADAS-2评估质量,STATA v18随机效应模型分析。
诊断标准与关键数值
- 机器学习模型预测结直肠癌淋巴结转移的汇总AUC为0.87(95%CI:0.82-0.91,I²=86.17),敏感度78%(95%CI:69-87%),特异度77%(95%CI:64-90%)。
- 前瞻性研究AUC为0.95(95%CI:0.87-1)高于回顾性研究0.85(95%CI:0.81-0.89),P=0.03。
- 无外部验证研究的AUC显著高于有外部验证研究(P < 0.01)。
- T2-T4期特异度为95%(95%CI:92-98%),T1-T2期为61%(95%CI:44-78%),P < 0.01;两组AUC和敏感度无显著差异。
- 放射科医生(初级和高年资)AUC表现相似,均显著低于机器学习模型(P < 0.001)。
临床应用与阅片要点
- 原文结论认为机器学习模型在结直肠癌术前淋巴结转移分期和治疗计划方面具有强大潜力,可能减少额外手术及相关健康和经济负担。
- 原文建议需进一步前瞻性多中心研究,并标准化报告算法、模态参数和淋巴结转移分期,以验证这些发现。
局限性
- 汇总AUC的异质性I²=86.17。
- 无外部验证的研究AUC显著高于有外部验证的研究(P < 0.01)。
- 需进一步前瞻性多中心研究,并标准化报告算法、模态参数和淋巴结转移分期,以验证这些发现。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVE: To evaluate the diagnostic performance of Machine Learning (ML) and Deep Learning (DL) models for predicting preoperative Lymph Node Metastasis (LNM) in Colorectal Cancer (CRC) patients.
METHODS: A systematic review and meta-analysis were conducted following PRISMA-DTA and AMSTAR-2 guidelines. We searched PubMed, Web of Science, Embase, and Cochrane Library databases until February 16, 2024. Study quality and risk of bias were assessed using the QUADAS-2 tool. Data were analyzed using STATA v18, applying random-effects models to all analyses.
RESULTS: Twelve studies involving 8321 patients were included, with most published in 2021-2024 (9/12). The pooled AUC of ML models for predicting LNM in CRC patients was 0.87 (95% CI: 0.82-0.91, I2:86.17) with a sensitivity of 78% (95% CI: 69-87%) and a specificity of 77% (95% CI: 64%-90%). In addition, when assessing the AUC reported by radiologists, both junior and senior radiologists had similar performance, significantly lower than the ML models. (P < 0.001). Subgroup analysis revealed higher AUCs in prospective studies (0.95, 95% CI: 0.87-1) compared to retrospective studies (0.85, 95% CI: 0.81-0.89) (P = 0.03). Studies without external validation exhibited significantly higher AUCs than those with external validation (P < 0.01). While there was no significant difference in AUC and sensitivity between the T1-T2 and T2-T4 stages, specificity was significantly higher in the T2-T4 stages than the low stages of T1 and T2 (95%, 95% CI: 92-98% vs. 61%, 95% CI: 44-78%; P < 0.01).
CONCLUSION: ML models demonstrate strong potential for preoperative LNM staging and treatment planning in CRC, potentially reducing the need for additional surgeries and related health and financial burdens. Further prospective multicenter studies, with standardized reporting of algorithms, modality parameters, and LNM staging, are needed to validate these findings.
引用
- Abbaspour E, Mansoori B, Karimzadhagh S, et al. Machine learning and deep learning models for preoperative detection of lymph node metastasis in colorectal cancer: a systematic review and meta-analysis. Abdom Radiol (NY). 2024. PMID: 39522103. doi:10.1007/s00261-024-04668-z
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。