Jin Qingchu, Amal Saeed, Rabb Jaime B, Mazhude Felistas, Shivandi Venkatesh, Kramer Robert S, Sawyer Douglas B, Winslow Raimond L
Roux Institute at Northeastern University, Portland ME, USA.
Those authors contribute equally.
medRxiv. 2025 Feb 25:2025.02.24.25322811. doi: 10.1101/2025.02.24.25322811.
Early recognition of adverse events after cardiac surgery is vital for treatment. However, the widely used Society of Thoracic Surgery (STS) risk model has modest performance in predicting adverse events and only applies <80% of cardiac surgeries.
To develop and validate machine learning (ML) models for predicting outcomes after cardiac surgery.
ML models, referred as Roux-MMC model, were developed and validated using a retrospective cohort extracted from the STS Adult Cardiac Surgery Database (ACSD) at Maine Medical Center (MMC) between January 2012 to December 2021. It was further validated on a prospective cohort of MMC between January 2022 to February 2024. The performance of Roux-MMC model is compared with the STS model. cardiac surgery.
Postoperative outcomes: mortality, stroke, renal failure, reoperation, prolonged ventilation, major morbidity or mortality, prolonged length of stay (PLOS) and short length of stay (SLOS). Primary measure: area under the receiver-operating curve (AUROC).
A retrospective cohort of 9,841 patients (median [IQR] age, 67 [59-74] years; 7,127 [72%] males) and a prospective cohort of 2,305 patients (median [IQR] age, 67 [59-73] years; 1,707 [74%] males) were included. In the prospective cohort, the Roux-MMC model achieves performance for prolonged ventilation (AUROC 0.911 [95% CI, 0.887-0.935]), PLOS (AUROC 0.875 [95% CI, 0.848-0.898]), renal failure (AUROC 0.878 [95% CI, 0.829-0.921]), mortality (AUROC 0.882 [95% CI, 0.837-0.920]), reoperation (AUROC 0.824 [95% CI, 0.787-0.860]), SLOS (AUROC 0.818 [95% CI, 0.801-0.835]) and major morbidity or mortality (AUROC 0.859 [95% CI, 0.832-0.884]). The Roux-MMC model outperforms the STS model for all 8 outcomes, achieving 0.020-0.167 greater AUROC. The Roux-MMC model covers all cardiac surgery patients, while the STS model applies to only 65% in the retrospective and 77% in the prospective cohorts.
We developed ML models to predict 8 postoperative outcomes on all cardiac surgery patients using preoperative and intraoperative variables. The Roux-MMC model outperforms the STS model in the prospective cohort. The Roux-MMC model is built on STS ACSD, a data system used in ~1000 US hospitals, thus, it has the potential to easily applied in other hospitals.
心脏手术后不良事件的早期识别对治疗至关重要。然而，广泛使用的胸外科医师协会（STS）风险模型在预测不良事件方面表现一般，且仅适用于不到80%的心脏手术。
开发并验证用于预测心脏手术后结局的机器学习（ML）模型。
设计、设置和参与者：使用从缅因医疗中心（MMC）的STS成人心脏手术数据库（ACSD）中提取的回顾性队列，开发并验证了称为Roux-MMC模型的ML模型，时间跨度为2012年1月至2021年12月。在2022年1月至2024年2月MMC的前瞻性队列中对其进行了进一步验证。将Roux-MMC模型的性能与STS模型进行比较。心脏手术。
术后结局：死亡率、中风、肾衰竭、再次手术、通气时间延长、严重并发症或死亡、住院时间延长（PLOS）和住院时间缩短（SLOS）。主要指标：受试者操作特征曲线下面积（AUROC）。
纳入了一个包含9841例患者的回顾性队列（年龄中位数[四分位间距]，67[59 - 74]岁；7127例[72%]为男性）和一个包含2305例患者的前瞻性队列（年龄中位数[四分位间距]，67[59 - 73]岁；1707例[74%]为男性）。在前瞻性队列中，Roux-MMC模型在通气时间延长（AUROC 0.911[95%置信区间，0.887 - 0.935]）、住院时间延长（AUROC 0.875[95%置信区间，0.848 - 0.898]）、肾衰竭（AUROC 0.878[95%置信区间，0.829 - 0.921]）、死亡率（AUROC 0.882[95%置信区间，0.837 - 0.920]）、再次手术（AUROC 0.824[95%置信区间，0.787 - 0.860]）、住院时间缩短（AUROC 0.818[95%置信区间，0.801 - 0.835]）和严重并发症或死亡（AUROC 0.859[95%置信区间，0.832 - 0.884]）方面表现良好。Roux-MMC模型在所有8个结局方面均优于STS模型，AUROC高出0.020 - 0.167。Roux-MMC模型涵盖了所有心脏手术患者，而STS模型在回顾性队列中仅适用于65%的患者，在前瞻性队列中仅适用于77%的患者。
我们开发了ML模型，使用术前和术中变量预测所有心脏手术患者的8种术后结局。Roux-MMC模型在前瞻性队列中优于STS模型。Roux-MMC模型基于STS ACSD构建，这是一个在美国约1000家医院使用的数据系统，因此，它有可能轻松应用于其他医院。
