Cardiovascular Outcomes Research Laboratories, Department of Surgery, David Geffen School of Medicine at UCLA, University of California Los Angeles, Los Angeles, CA.
Department of Surgery, David Geffen School of Medicine at UCLA, University of California Los Angeles, Los Angeles, CA.
Ann Surg. 2024 Aug 1;280(2):325-331. doi: 10.1097/SLA.0000000000006123. Epub 2023 Nov 10.
The aim of this study was to develop a novel machine learning model to predict clinically relevant postoperative pancreatic fistula (CR-POPF) following pancreaticoduodenectomy (PD).
Accurate prognostication of CR-POPF may allow for risk stratification and adaptive treatment strategies for potential PD candidates. However, antecedent models, such as the modified Fistula Risk Score (mFRS), are limited by poor discrimination and calibration.
All records entailing PD within the 2014 to 2018 American College of Surgeons National Surgical Quality Improvement Program (ACS NSQIP) were identified. In addition, patients undergoing PD at our institution between 2013 and 2021 were queried from our local data repository. An eXtreme Gradient Boosting (XGBoost) model was developed to estimate the risk of CR-POPF using data from the ACS NSQIP and evaluated using institutional data. Model discrimination was estimated using the area under the receiver operating characteristic (AUROC) and area under the precision recall curve (AUPRC).
Overall, 12,281 and 445 patients undergoing PD were identified within the 2014 to 2018 ACS NSQIP and our institutional registry, respectively. Application of the XGBoost and mFRS scores to the internal validation dataset revealed that the former model had significantly greater AUROC (0.72 vs 0.68, P <0.001) and AUPRC (0.22 vs 0.18, P <0.001). Within the external validation dataset, the XGBoost model remained superior to the mFRS with an AUROC of 0.79 (95% CI: 0.74-0.84) versus 0.75 (95% CI: 0.70-0.80, P <0.001). In addition, AUPRC was higher for the XGBoost model, compared with the mFRS.
Our novel machine learning model consistently outperformed the previously validated mFRS within internal and external validation cohorts, thereby demonstrating its generalizability and utility for enhancing prediction of CR-POPF.
本研究旨在开发一种新的机器学习模型，以预测胰十二指肠切除术后临床相关的胰瘘（CR-POPF）。
准确预测 CR-POPF 可能允许对潜在 PD 候选者进行风险分层和适应性治疗策略。然而，先前的模型，如改良瘘管风险评分（mFRS），其区分度和校准度较差。
在美国外科医师学会国家外科质量改进计划（ACS NSQIP）2014 年至 2018 年期间，确定所有接受胰十二指肠切除术的记录。此外，还从我们的本地数据存储库中查询了我们机构在 2013 年至 2021 年期间接受胰十二指肠切除术的患者。使用 ACS NSQIP 的数据，通过极端梯度提升（XGBoost）模型来估计 CR-POPF 的风险，并通过机构数据进行评估。使用接收者操作特征曲线下的面积（AUROC）和精确召回曲线下的面积（AUPRC）来评估模型的区分度。
在 2014 年至 2018 年 ACS NSQIP 和我们的机构登记处，分别确定了 12281 例和 445 例接受胰十二指肠切除术的患者。将 XGBoost 和 mFRS 评分应用于内部验证数据集显示，前者模型的 AUROC（0.72 对 0.68，P <0.001）和 AUPRC（0.22 对 0.18，P <0.001）显著更高。在外部验证数据集中，XGBoost 模型仍然优于 mFRS，AUROC 为 0.79（95%CI：0.74-0.84），而 mFRS 为 0.75（95%CI：0.70-0.80，P <0.001）。此外，XGBoost 模型的 AUPRC 更高。
我们的新机器学习模型在内部和外部验证队列中始终优于先前验证的 mFRS，从而证明了其在增强 CR-POPF 预测方面的通用性和实用性。
