基于机器学习的结直肠手术吻合口漏术前预测分析:一项瑞士先导研究
该研究回顾性分析四家瑞士医院1244例结直肠吻合手术患者的21项术前预测因子,用多种机器学习算法将患者二分类为吻合口漏组与非吻合口漏组,采用五折交叉验证(90%训练、10%验证),并用外院198例数据做外部验证。1244例中112例(9.0%)发生吻合口漏;随机森林内部测试集AUC-ROC为0.78(SD:±0.01),外部测试集降至0.60(SD:±0.05)。
要点
- 1244例结直肠吻合手术患者中112例(9.0%)发生吻合口漏。
- 随机森林内部测试集AUC-ROC为0.78(SD:±0.01),外部测试集降至0.60(SD:±0.05)。
- 作者认为需多中心数据、外部验证与更大样本量。
核心结论
- 在这项先导研究中,作者评估了结直肠术后吻合口漏的机器学习预测模型,并识别出十项与吻合口漏相关的患者相关危险因素。
- 作者强调需要多中心数据、外部验证和更大样本量,认为机器学习在改善手术结局方面具有潜力,并为未来开发可供更广泛临床使用的网络应用提供依据。
研究设计与样本
- 回顾性分析四家瑞士医院接受结直肠手术并做肠吻合的患者数据,共纳入21项预测因子。
- 应用多种机器学习算法进行吻合口漏组与非吻合口漏组的二分类,采用五折交叉验证,训练集占90%、验证集占10%。
- 另用来自外部医院的留出测试集评估模型在外部验证中的稳健性。
主要发现
- 1244例患者中112例(9.0%)发生吻合口漏。
- 随机森林模型内部测试集AUC-ROC为0.78(SD:±0.01),在包含198例患者(其中7例(3.5%)发生吻合口漏)的外部留出测试集上显著降至0.60(SD:±0.05)。
- 逻辑回归模型内部测试集AUC-ROC为0.69(SD:±0.01),外部测试集为0.61(SD:±0.05),较为一致。
- 随机森林准确率内部为0.82(SD:±0.04)、外部为0.87(SD:±0.08);逻辑回归准确率分别为0.81(SD:±0.10)和0.88(SD:±0.15)。
- 随机森林F1分数由内部0.58(SD:±0.03)变为外部0.51(SD:±0.03);逻辑回归分别为0.53(SD:±0.04)和0.51(SD:±0.02),较为稳定。
临床怎么用
- 原文未据此给出推荐。
局限性
- 作者指出需要多中心数据、外部验证和更大样本量。
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)。
原文
BACKGROUND: Anastomotic leakage (AL), a severe complication following colorectal surgery, arises from defects at the anastomosis site. This study evaluates the feasibility of predicting AL using machine learning (ML) algorithms based on preoperative data. METHODS: We retrospectively analyzed data including 21 predictors from patients undergoing colorectal surgery with bowel anastomosis at four Swiss hospitals. Several ML algorithms were applied for binary classification into AL or non-AL groups, utilizing a five-fold cross-validation strategy with a 90% training and 10% validation split. Additionally, a holdout test set from an external hospital was employed to assess the models' robustness in external validation. RESULTS: Among 1244 patients, 112 (9.0%) suffered from AL. The Random Forest model showed an AUC-ROC of 0.78 (SD: ± 0.01) on the internal test set, which significantly decreased to 0.60 (SD: ± 0.05) on the external holdout test set comprising 198 patients, including 7 (3.5%) with AL. Conversely, the Logistic Regression model demonstrated more consistent AUC-ROC values of 0.69 (SD: ± 0.01) on the internal set and 0.61 (SD: ± 0.05) on the external set. Accuracy measures for Random Forest were 0.82 (SD: ± 0.04) internally and 0.87 (SD: ± 0.08) externally, while Logistic Regression achieved accuracies of 0.81 (SD: ± 0.10) and 0.88 (SD: ± 0.15). F1 Scores for Random Forest moved from 0.58 (SD: ± 0.03) internally to 0.51 (SD: ± 0.03) externally, with Logistic Regression maintaining more stable scores of 0.53 (SD: ± 0.04) and 0.51 (SD: ± 0.02). CONCLUSION: In this pilot study, we evaluated ML-based prediction models for AL post-colorectal surgery and identified ten patient-related risk factors associated with AL. Highlighting the need for multicenter data, external validation, and larger sample sizes, our findings emphasize the potential of ML in enhancing surgical outcomes and inform future development of a web-based application for broader clinical use.
引用
- Taha-Mehlitz S, Wentzler L, Angehrn F, et al. Machine learning-based preoperative analytics for the prediction of anastomotic leakage in colorectal surgery: a swiss pilot study. Surg Endosc. 2024. PMID: 38777894. doi:10.1007/s00464-024-10926-4
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。