心脏术后患者谵妄风险预测模型的应用研究

doi:10.3761/j.issn.0254-1769.2026.06.007

摘要/Abstract

摘要：

目的对心脏术后患者谵妄风险预测模型进行外部验证研究，为临床筛选合适的预测模型提供依据。方法回顾性分析四川省西南地区某三级甲等综合医院2023年10月至2025年1月于心脏大血管外科接受手术患者的相关资料。对前期经系统评价筛选出的3个心脏术后患者谵妄风险预测模型进行外部验证。通过绘制并计算受试者操作特征曲线下面积（area under curve，AUC）评价模型预测性能，采用Hosmer-Lemeshow检验、绘制校准曲线评价模型预测准确度，应用决策曲线分析评价模型临床效用。结果共纳入562例心脏手术患者，其中76例发生术后谵妄，心脏术后谵妄发生率为13.52%。验证结果显示，3个心脏术后患者谵妄风险预测模型的AUC为0.710~0.859；Hosmer-Lemeshow检验结果显示，其中2个模型校准度良好（P=0.865，P=0.270），决策曲线分析表明，围手术期心脏手术谵妄筛查评分模型的临床净获益最大。结论 3个预测模型均展现中等及以上的区分效能（AUC值均>0.700），但仅2个模型校准度良好，决策曲线分析显示所有模型均具备一定效用。综合模型性能与临床可操作性，经外部验证，最终得出围手术期心脏手术谵妄筛查评分模型相比其余2个模型更具优势。未来还需进一步通过多中心研究优化模型普适性，并开发智能化辅助系统推动预测模型在临床应用。

关键词: 心脏手术, 谵妄, 预测模型, 外部验证, 护理

Abstract:

Objective To conduct an external validation study of the postoperative cardiac delirium patients risk prediction model to provide a basis for clinical screening of appropriate prediction models. Methods The data of patients who underwent cardiac surgery from October 2023 to January 2025 in a tertiary general hospital in southwest Sichuan Province were retrospectively collected. Totally 3 postoperative cardiac delirium patients risk prediction models screened by systematic evaluation were externally validated. The predictive performance of the models was evaluated by plotting and calculating the Area Under Curve（AUC）；the predictive accuracy of the models was evaluated by the Hosmer-Lemeshow test and plotting calibration curves；the clinical utility of the model was evaluated by applying Decision Curve Analysis（DCA）. Results A total of 562 cardiac surgery patients were included，of which 76 had postoperative delirium，and the incidence rate of postoperative cardiac delirium was 13.52%. The results of external validation showed that the AUC of the 3 postoperative cardiac delirium patients risk prediction models ranged from 0.710 to 0.859；the results of the Hosmer-Lemeshow test showed that the predictive accuracy of 2 of the models was better（P=0.865，P=0.270），and the DCA indicated that the net clinical benefit of the perioperative delirium screening in cardiac surgery model had the greatest net clinical benefit. Conclusion All 3 predictive models demonstrated moderate or above discriminatory efficacy（all AUC values >0.700），but only 2 models were well calibrated，and DCA analysis showed some utility for all models. Combining model performance and clinical applicability，external validation concluded that the perioperative delirium screening in cardiac surgery model was superior to the remaining 2 models. Further multicenter studies are needed to optimize the generalizability of the model and to develop intelligent assistive systems to promote clinical application.

Key words: Cardiac Surgical Procedures, Delirium, Prediction Model, External Validation, Nursing Care

郑燕, 曾永珂, 陈静, 罗小琴, 夏良香, 郑思琳. 心脏术后患者谵妄风险预测模型的应用研究[J]. 中华护理杂志, 2026, 61(6): 768-774.

ZHENG Yan, ZENG Yongke, CHEN Jing, LUO Xiaoqin, XIA Liangxiang, ZHENG Silin. Application research of postoperative cardiac delirium patients risk prediction models[J]. Chinese Journal of Nursing, 2026, 61(6): 768-774.

图/表 4

表1 3个心脏术后患者谵妄风险预测模型的基本信息

Table 1 Basic information on the 3 included models for predicting risk of delirium after cardiac surgery patients

表2 两组一般资料的比较

Table 2 Comparison of 2 sets of general information

图1 3个心脏术后患者谵妄预测模型外部验证的ROC曲线

Figure 1 ROC curves for external validation of 3 postoperative delirium prediction models for cardiac surgery patients

表3 心脏术后患者谵妄风险预测模型的相关预测指标

Table 3 Relevant predictive indicators of delirium risk prediction model after cardiac surgery patients

参考文献 22

[1]	中国医疗保健国际交流促进会心脏重症分会. 心脏及大血管术后谵妄的防治中国专家共识[J]. 中华医学杂志, 2023, 103(45):3635-3644.
	China Association for the Promotion of International Exchange of Medical Care Cardiac Critical Care Branch. Chinese expert consensus on the prevention and treatment of postoperative delirium of cardiovascular surgery[J]. Chin Med J, 2023, 103(45):3635-3644.
[2]	Majewski P, Zegan-Barańska M, Karolak I, et al. Current evidence regarding biomarkers used to aid postoperative delirium diagnosis in the field of cardiac surgery-review[J]. Medicina, 2020, 56(10):493. DOI URL
[3]	Wueest AS, Berres M, Bettex DA, et al. Independent external validation of a preoperative prediction model for delirium after cardiac surgery:a prospective observational cohort study[J]. J Cardiothorac Vasc Anesth, 2023, 37(3):415-422. DOI URL
[4]	Deeken F, Sánchez A, Rapp MA, et al. Outcomes of a delirium prevention program in older persons after elective surgery:a stepped-wedge cluster randomized clinical trial[J]. JAMA Surg, 2022, 157(2):e216370. DOI URL
[5]	吴前胜, 曾莹, 王兰, 等. 体外循环下心脏手术患者术后谵妄管理的循证实践[J]. 中华护理杂志, 2024, 59(3):292-299. DOI
	Wu QS, Zeng Y, Wang L, et al. Evidence-based nursing practice of postoperative delirium management during cardiac surgery under cardiopulmonary bypass[J]. Chin J Nurs, 2024, 59(3):292-299. DOI
[6]	Han C, Kim HI, Soh S, et al. Machine learning with clinical and intraoperative biosignal data for predicting postoperative delirium after cardiac surgery[J]. iScience, 2024, 27(6):109932. DOI URL
[7]	Nagata C, Hata M, Miyazaki Y, et al. Development of postoperative delirium prediction models in patients undergoing cardiovascular surgery using machine learning algorithms[J]. Sci Rep, 2023, 13(1):21090. DOI PMID
[8]	陈敏, 杨阿敏, 孙璐. 成人心脏术后谵妄风险预测模型的系统评价与Meta分析[J/OL]. 中国胸心血管外科临床杂志:1-11[2025-07-06]. http://kns.cnki.net/kcms/detail/51.1492.R.20250226.1603.004.html.
	Chen M, Yang AM, Sun L. Systematic review and meta-analysis of risk prediction models for postoperative delirium in adult patients after cardiac surgery[J/OL]. Chin J Clin Thor Cardiov Surg:1-11[2025-07-06]. http://kns.cnki.net/kcms/detail/51.1492.R.20250226.1603.004.html.
[9]	Han QY, Hu ZD. Clinical prediction model construction and evaluation:a challenge for clinical researchers[J]. Ann Transl Med, 2020, 8(4):74. DOI URL
[10]	Ramspek CL, Jager KJ, Dekker FW, et al. External validation of prognostic models:what,why,how,when and where?[J]. Clin Kidney J, 2020, 14(1):49-58. DOI URL
[11]	Krzych LJ, Wybraniec MT, Krupka-Matuszczyk I, et al. Delirium screening in cardiac surgery(DESCARD):a useful tool for non-psychiatrists[J]. Can J Cardiol, 2014, 30(8):932-939.
[12]	White N, Parsons R, Collins G, et al. Evidence of questionable research practices in clinical prediction models[J]. BMC Med, 2023, 21(1):339. DOI PMID
[13]	Liu C, Zhang LF, Tang WF, et al. A nomogram for predicting the risk of postoperative delirium in individuals undergoing cardiovascular surgery[J]. Eur J Neurol, 2024, 31(12):e16483. DOI URL
[14]	First MB. Diagnostic and statistical manual of mental disorders,5th edition,and clinical utility[J]. J Nerv Ment Dis, 2013, 201(9):727-729. DOI URL
[15]	Lee A, Mu JL, Joynt GM, et al. Risk prediction models for delirium in the intensive care unit after cardiac surgery:a systematic review and independent external validation[J]. Br J Anaesth, 2017, 118(3):391-399. DOI PMID
[16]	Petersson NB, Hansen MH, Hjelmborg JVB, et al. Incidence and assessment of delirium following open cardiac surgery:a systematic review and meta-analysis[J]. Eur J Cardiovasc Nurs, 2024, 23(8):825-832. DOI URL
[17]	Ho MH, Nealon J, Igwe E, et al. Postoperative delirium in older patients:a systematic review of assessment and incidence of postoperative delirium[J]. Worldviews Evid Based Nurs, 2021, 18(5):290-301.
[18]	Greaves D, Psaltis PJ, Davis DHJ, et al. Risk factors for delirium and cognitive decline following coronary artery bypass grafting surgery:a systematic review and meta-analysis[J]. J Am Heart Assoc, 2020, 9(22):e017275. DOI URL
[19]	沈佩烨, 兰岚, 王佳琪, 等. 老年心脏手术患者住院期间功能下降评估及影响因素研究进展[J]. 中华护理杂志, 2023, 58(19):2345-2352. DOI
	Shen PY, Lan L, Wang JQ, et al. The assessment and influencing factors of hospital-acquired functional decline in elderly cardiac surgery patients[J]. Chin J Nurs, 2023, 58(19):2345-2352. DOI
[20]	龚翠颖, 王建宁, 李立群, 等. 主动脉夹层患者术后谵妄危险因素和预测模型的研究进展[J]. 中华护理杂志, 2023, 58(2):179-185. DOI
	Gong CY, Wang JN, Li LQ, et al. Research progress of risk factors and prediction models of postoperative delirium after aortic dissection[J]. Chin J Nurs, 2023, 58(2):179-185. DOI
[21]	王宇, 张诚, 吴庆琛. 心脏外科手术患者术后谵妄的发生率及其可干预危险因素:一项基于倾向性评分匹配的前瞻性观察研究[J]. 解放军医学杂志, 2024, 49(10):1110-1116.
	Wang Y, Zhang C, Wu QC. Incidence and modifiable risk factors of postoperative delirium in patients undergoing cardiac surgery:a prospective observational study based on propensity score matching[J]. Med J Chin PLA, 2024, 49(10):1110-1116.
[22]	宋亚敏, 杨满青, 凌云, 等. 重症监护室预防谵妄的护理干预方案在心脏外科术后患者中的应用[J]. 中国护理管理, 2022, 22(4):507-511.
	Song YM, Yang MQ, Ling Y, et al. Effects of nursing delirium preventive interventions in the intensive care unit on delirium management in patients after cardiac surgery[J]. Chin Nurs Manag, 2022, 22(4):507-511.