维持性血液透析患者透析中低血压风险预测模型的系统评价

doi:10.3761/j.issn.0254-1769.2024.02.007

摘要/Abstract

摘要：

目的系统检索和评价维持性血液透析患者透析中低血压的风险预测模型，以期为临床医护人员选择或开发适合的风险评估工具提供参考。方法系统检索PubMed、Embase、Web of Science、Cochrane Library、CINAHL、中国知网、维普数据库、万方数据库和中国生物医学文献数据库中相关研究，检索时限为建库至2023年5月29日。由2名研究者独立进行文献筛选、资料提取、并应用预测模型偏倚风险评估工具评估研究的方法学质量。结果共纳入20项研究，涉及25个模型，样本量为68~9 292例，结局事件发生率为2.1%~51%。基线收缩压、年龄、超滤率、糖尿病和透析时长是模型重复报告的前5名预测变量。20个模型报告了受试者操作特征曲线下面积（0.649~0.969），仅5个模型报告了校准度。9项研究进行内部验证，4项研究内外部验证相结合。20项研究总体适用性较好，但均存在较高的偏倚风险，主要集中在数据分析领域。结论维持性血液透析患者透析中低血压风险预测模型的研究尚处于发展阶段。未来的研究应完善研究设计和报告流程，并对现有模型进行验证，进一步评估模型在临床实践中的有效性和可行性。

关键词: 低血压, 血液透析, 预测模型, 系统评价, 循证护理学

Abstract:

Objective To systematically review the risk prediction models for intradialytic hypotension in maintenance hemodialysis patients，with a view to provide references for clinical practice. Methods PubMed，Embase，Web of Science，Cochrane Library，CINAHL，CNKI，VIP，Wanfang and CBM were searched from inception to May 29，2023. 2 reviewers independently screened the literature，extracted information and assessed methodological quality using the Prediction Model Risk of Bias Assessment Tool. Results A total of 20 studies and 25 models were included with the sample size of 68~9 292 cases and the incidence of outcome events of 2.1~51%. Baseline systolic blood pressure，age，ultrafiltration rate，diabetes and dialysis duration were the top 5 predictors of repeated reporting of the models. 20 models reported the area under the curve of ranging from 0.649 to 0.969，and 5 models reported calibration metrics. There were 9 internal validations and 4 combined internal and external validation models. The overall applicability of the 20 studies was good，but all had a high risk of bias，mainly in data analysis. Conclusion Research on risk prediction models for intradialytic hypotension in maintenance hemodialysis patients is still in the developmental stage. Future studies should improve the research design and reporting process，and validation studies of existing models should be carried out to further evaluate the effectiveness and feasibility in clinical practice.

Key words: Hypotension, Hemodialysis, Forecasting Model, Systematic Review, Evidence-Based Nursing

朱东阁, 王菊子, 赵倩, 何亚鹏, 张转转, 杨雨桐. 维持性血液透析患者透析中低血压风险预测模型的系统评价[J]. 中华护理杂志, 2024, 59(2): 174-183.

ZHU Dongge, WANG Juzi, ZHAO Qian, HE Yapeng, ZHANG Zhuanzhuan, YANG Yutong. Systematic review of risk prediction models for intradialytic hypotension in patients with maintenance hemodialysis[J]. Chinese Journal of Nursing, 2024, 59(2): 174-183.

图/表 4

图1 文献筛选流程注:IDH为透析中低血压。

Figure 1 Literature screening flowchart

表1 纳入研究的基本信息及预测结局（n=20）

Table 1 Basic information and predicted outcomes of included studies（n=20）

表2 维持性血液透析患者IDH风险预测模型的建立、验证、变量及模型性能情况（n=25）

Table 2 Establishment, validation, variables and model performance of IDH risk prediction models in maintenance hemodialysis（n=25）

表3 纳入研究的偏倚风险及适用性评价（n=20）

Table 3 Evaluation of risk of bias and applicability of included studies（n=20）

参考文献 36

[1]	Flythe JE, Chang TI, Gallagher MP, et al. Blood pressure and volume management in dialysis:conclusions from a kidney disease:improving global outcomes(KDIGO) controversies conference[J]. Kidney Int, 2020, 97(5):861-876. DOI URL
[2]	Ngankem LSQ, Larizza C, Nocera A, et al. A comparative study of the definitions of intradialytic hypotension correlated with increased mortality to identify universal predictors[J]. Int J Med Inform, 2023, 173:104975. DOI URL
[3]	Sohn P, Narasaki Y, Rhee CM. Intradialytic hypotension:is timing everything?[J]. Kidney Int, 2021, 99(6):1269-1272. DOI URL
[4]	Keane DF, Raimann JG, Zhang HJ, et al. The time of onset of intradialytic hypotension during a hemodialysis session associates with clinical parameters and mortality[J]. Kidney Int, 2021, 99(6):1408-1417. DOI PMID
[5]	Yu JB, Chen XH, Li Y, et al. High ultrafiltration rate induced intradialytic hypotension is a predictor for cardiac remodeling:a 5-year cohort study[J]. Ren Fail, 2021, 43(1):40-48. DOI URL
[6]	Mizuiri S, Nishizawa Y, Doi T, et al. Associations of body compositions,intradialytic hypotension,and mortality in hemodialysis patients[J]. J Am Soc Nephr,2022,33:706-707.
[7]	Wang JH, Yao J, Zhu XY, et al. Impact of frequent intradialytic hypotension on quality of life in patients undergoing hemodialysis[J]. BMC Nephrol, 2023, 24(1):209. DOI PMID
[8]	Moons KG, Hooft L, Williams K, et al. Implementing systematic reviews of prognosis studies in Cochrane[J]. Cochrane Database Syst Rev, 2018, 10:ED000129.
[9]	Moons KG, de Groot JA, Bouwmeester W, et al. Critical appraisal and data extraction for systematic reviews of prediction modelling studies:the CHARMS checklist[J]. PLoS Med, 2014, 11(10):e1001744. DOI URL
[10]	Moons KGM, Wolff RF, Riley RD, et al. PROBAST:a tool to assess risk of bias and applicability of prediction model studies:explanation and elaboration[J]. Ann Intern Med, 2019, 170(1):W1. DOI URL
[11]	Gabutti L, Vadilonga D, Mombelli G, et al. Artificial neural net-works improve the prediction of Kt/V,follow-up dietary pro-tein intake and hypotension risk in haemodialysis patients[J]. Nephrol Dial Transplant, 2004, 19(5):1204-1211. DOI URL
[12]	Bossola M, Laudisio A, Antocicco M, et al. Intradialytic hypo-tension is associated with dialytic age in patients on chronic hemodialysis[J]. Ren Fail, 2013, 35(9):1260-1263. DOI URL
[13]	Sangala N, Gangaram V, Atkins K, et al. Intra-dialytic hypotension:identifying patients most at risk[J]. J Ren Care, 2017, 43(2):92-97. DOI URL
[14]	Lin CJ, Chen CY, Wu PC, et al. Intelligent system to predict intradialytic hypotension in chronic hemodialysis[J]. J Formos Med Assoc, 2018, 117(10):888-893. DOI URL
[15]	Park S, Kim WJ, Cho NJ, et al. Predicting intradialytic hypo-tension using heart rate variability[J]. Sci Rep, 2019, 9(1):2574. DOI
[16]	Huang J, Tsai Y, Wu P, et al. Predictive modeling of blood pre-ssure during hemodialysis:a comparison of linear model,random forest,support vector regression,XGBoost,LASSO regres-sion and ensemble method[J]. Comput Methods Programs Bio-med, 2020, 195:105536.
[17]	Chen JB, Wu KC, Moi SH, et al. Deep learning for intradialy-tic hypotension prediction in hemodialysis patients[J]. IEEE Access, 2020, 8:82382-82390. DOI URL
[18]	Lee H, Yun D, Yoo J, et al. Deep learning model for real-time prediction of intradialytic hypotension[J]. Clin J Am Soc Nephrol, 2021, 16(3):396-406. DOI URL
[19]	Gómez-Pulido JA, Gómez-Pulido JM, Rodríguez-Puyol D, et al. Predicting the appearance of hypotension during hemodialysis Sessions using machine learning classifiers[J]. Int J Environ Res Public Health, 2021, 18(5):2364. DOI URL
[20]	林丽桑, 何丽芳, 应秀红. 维持性血液透析患者透析中低血压风险预测模型的构建[J]. 中华护理杂志, 2021, 56(10):1466-1471. DOI
	Lin LS, He LF, Ying XH. Development of a risk prediction model for intradialytic hypotension in patients with maintenance hemodialysis[J]. Chin J Nurs, 2021, 56(10):1466-1471. DOI
[21]	Kim HW, Heo SJ, Kim M, et al. Deep learning model for predicting intradialytic hypotension without privacy infringement:a retrospective two-center study[J]. Front Med(Lausanne), 2022, 9:878858.
[22]	Bae TW, Kim MS, Park JW, et al. Multilayer perceptron-based real-time intradialytic hypotension prediction using patient baseline information and heart-rate variation[J]. Int J Environ Res Public Health, 2022, 19(16):10373. DOI URL
[23]	Son HE, Ryu JY, Lee K, et al. The importance of muscle mass in predicting intradialytic hypotension in patients undergoing maintenance hemodialysis[J]. Kidney Res Clin Pract, 2022, 41(5):611-622. DOI PMID
[24]	Mendoza-Pitti L, Gomez-Pulido JM, Vargas-Lombardo M, et al. Machine-learning model to predict the intradialytic hypotension based on clinical-analytical data[J]. IEEE Access, 2022, 10:72065-72079. DOI URL
[25]	Yang X, Zhao D, Yu FH, et al. Boosted machine learning model for predicting intradialytic hypotension using serum biomarkers of nutrition[J]. Comput Biol Med, 2022, 147:105752. DOI URL
[26]	郭雪梅, 朱朕男, 罗佳懿, 等. 维持性血液透析患者透析中低血压风险预测模型的构建及验证[J]. 中国血液净化, 2022, 21(6):408-412.
	Guo XM, Zhu ZN, Luo JY, et al. Construction and validation of a prediction model for the risk of intradialytic hypotension in maintenance hemodialysis patients[J]. Chin J Blood Purif, 2022, 21(6):408-412.
[27]	何鑫. 基于人工智能的透析中低血压的早期预警模型构建[D]. 泸州: 西南医科大学, 2022.
	He X. Construction of early warning model of hypotension in dialysis based on artificial intelligence[D]. Luzhou: Southwest Medical University, 2022.
[28]	王仁伴, 胡文雯, 邵国建. 维持性血液透析患者透析中低血压发生的列线图预测模型构建与评估[J]. 现代实用医学, 2022,34(4):439-441,473.
	Wang RB, Hu WW, Shao GJ. Construction and evaluation of a nomogram prediction model for the occurrence of intradialysis hypotension in maintenance hemodialysis patients[J]. Mod Pract Med, 2022, 34(4):439-441,473.
[29]	Zhang HJ, Wang LC, Chaudhuri S, et al. Real-time prediction of intradialytic hypotension using machine learning and cloud computing infrastructure[J]. Nephrol Dial Transplant, 2023, 38(7):1761-1769. DOI URL
[30]	Lee HB, Moon SJ, Kim SW, et al. Prediction of intradialytic hypotension using pre-dialysis features:a deep learning-based artificial intelligence model[J]. Nephrol Dial Transplant, 2023:gfad064.
[31]	俞晓慧, 章新琼, 杨胜菊, 等. 糖尿病患者低血糖发生风险预测模型的系统评价[J]. 中华护理杂志, 2022, 57(15):1830-1839. DOI
	Yu XH, Zhang XQ, Yang SJ, et al. The risk prediction models for the occurrence of hypoglycemia in patients with diabetes mellitus:a systematic review and critical appraisal[J]. Chin J Nurs, 2022, 57(15):1830-1839.
[32]	Collins GS, Reitsma JB, Altman DG, et al. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis(TRIPOD):the TRIPOD statement[J]. BMJ, 2015, 350(jan07 4):g7594.
[33]	Fotiadou E, Georgianos PI, Chourdakis M, et al. Eating during the hemodialysis session:a practice improving nutritional status or a risk factor for intradialytic hypotension and reduced dialysis adequacy?[J]. Nutrients, 2020, 12(6):1703. DOI URL
[34]	Rhee SY, Song JK, Hong SC, et al. Intradialytic exercise improves physical function and reduces intradialytic hypotension and depression in hemodialysis patients[J]. Korean J Intern Med, 2019, 34(3):588-598. DOI PMID
[35]	中国医药教育协会肾病与血液净化专业委员会血液透析低血压防治专家组. 血液透析中低血压防治专家共识(2022)[J]. 中华内科杂志, 2022, 61(3):269-281.
	Intradialytic Hypotension Prevention and Treatment Expert Working Group,Renal and Blood Purification Committee,Chinese Medicine Education Society. Expert consensus on the prevention and treatment of intradialytic hypotension(2022)[J]. Chin J Intern Med, 2022, 61(3):269-281.
[36]	Kim KY, Park HS, Kim JS, et al. Comparison of intradialytic blood pressure metrics as predictors of all-cause mortality[J]. Clin Kidney J, 2021, 14(12):2600-2605. DOI PMID