基于LASSO-logistic回归构建维持性血液透析患者睡眠障碍风险预测模型

doi:10.3969/j.issn.1004-583X.2026.02.008

摘要/Abstract

摘要：

目的探讨维持性血液透析(maintenance hemodialysis,MHD)患者睡眠障碍的危险因素,并构建风险预测模型,为临床早期识别高危人群提供参考。方法纳入2024年6月-2025年6月在常州市肿瘤医院接受MHD治疗的患者222例,收集其人口学特征、临床资料及实验室指标。采用匹兹堡睡眠质量指数(PSQI)评估近期睡眠状况,以PSQI≥7判定存在睡眠障碍。采用最小绝对收缩与选择算子(LASSO)回归进行变量压缩与筛选,将进入模型的变量纳入多因素logistic回归分析,构建列线图预测模型。通过受试者工作特征(ROC)曲线、C指数(C-index)、Bootstrap内部验证、校准曲线及决策曲线分析(DCA)综合评价模型的区分度、校准度及临床净获益。结果 MHD患者睡眠障碍发生率为56.31%(125/222)。LASSO-logistic回归结果显示,年龄、透析病程、焦虑、抑郁、尿毒症瘙痒及不安腿综合征为睡眠障碍的独立危险因素,而血钙水平为保护因素(P值均<0.05)。基于上述因素构建的列线图预测模型ROC曲线下面积为0.928(95%CI:0.894~0.962),校准曲线显示模型预测值与实际观察值拟合良好,Hosmer-Lemeshow检验(χ²=4.14,P=0.844)提示模型具有较好的校准性能。DCA显示,在阈值概率0.05~0.75范围内,该模型均可获得较高的临床净获益。结论基于年龄、透析病程、焦虑、抑郁、尿毒症瘙痒、不安腿综合征及血钙水平构建的列线图预测模型可较好预测MHD患者睡眠障碍风险,有助于实现高危人群的早期识别与干预,为临床精细化管理提供参考依据。

关键词: 睡眠觉醒障碍, 维持性血液透析, LASSO回归, Logistic回归, 列线图, 风险预测模型

Abstract:

Objective To investigate the risk factors for sleep disorders in patients undergoing maintenance hemodialysis (MHD), and to develop a risk prediction model, thus providing references for the early clinical identification of high-risk individuals. Methods A total of 222 patients who received MHD between June 2024 to June 2025 were enrolled. Demographic characteristics, clinical data, and laboratory indicators were collected. Sleep quality was assessed using the Pittsburgh Sleep Quality Index (PSQI), with PSQI ≥7 indicating the presence of sleep disorders. Candidate predictors were first screened using univariate analysis, followed by variable shrinkage and selection via the least absolute shrinkage and selection operator (LASSO) regression. Variables retained in the LASSO model were subsequently entered into a multivariable logistic regression analysis to construct a nomogram. Prediction performance of the nomogram, including discrimination, calibration, and clinical utility, was comprehensively evaluated using the receiver operating characteristic (ROC) curve, C-index, bootstrap internal validation, calibration curve, and decision curve analysis (DCA). Results The incidence of sleep disorders in this study was 56.31% (125/222). LASSO-logistic regression showed that age, dialysis duration, anxiety, depression, uremic pruritus, and restless legs syndrome were independent risk factors for sleep disorders in patients treated with MHD, whereas higher serum calcium levels played a protective role (all P<0.05). The nomogram constructed based on these factors yielded an area under the curve (AUC) of 0.928(95%CI: 0.894-0.962). The calibration curve showed good agreement between predicted and observed values, and the Hosmer-Lemeshow test (χ²=4.14, P=0.844) indicated good calibration performance. DCA demonstrated that the nomogram provided a considerable net clinical benefit across a threshold probability range of 0.05-0.75. Conclusion The nomogram constructed based on age, dialysis duration, anxiety, depression, uremic pruritus, restless legs syndrome, and serum calcium level can effectively predict the risk of sleep disorders in MHD patients, facilitating early identification and intervention for high-risk groups.

Key words: sleep disorders, maintenance hemodialysis, LASSO regression, logistic regression, nomogram, risk prediction model

中图分类号:

R749.7

汪晶晶, 江茜茜, 高炬, 周叶苹. 基于LASSO-logistic回归构建维持性血液透析患者睡眠障碍风险预测模型[J]. 临床荟萃, 2026, 41(2): 148-154.

Wang Jingjing, Jiang Qianqian, Gao Ju, Zhou Yeping. Construction of a sleep disorder risk prediction model for maintenance hemodialysis patients based on LASSO-logistic regression[J]. Clinical Focus, 2026, 41(2): 148-154.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.lchc.cn/CN/10.3969/j.issn.1004-583X.2026.02.008

https://www.lchc.cn/CN/Y2026/V41/I2/148

图/表 9

参考文献 21

[1]	Chen TK, Knicely DH, Grams ME. Chronic kidney disease diagnosis and management: A review[J]. JAMA, 2019, 322(13):1294-1304.doi: 10.1001/jama.2019.14745. pmid: 31573641
[2]	Wang L, Xu X, Zhang M, et al. Prevalence of chronic kidney disease in China: Results from the sixth China chronic disease and risk factor surveillance[J]. JAMA Intern Med, 2023, 183(4): 298-310.doi: 10.1001/jamainternmed.2022.6817. pmid: 36804760
[3]	Thurlow JS, Joshi M, Yan G, et al. Global epidemiology of end-stage kidney disease and disparities in kidney replacement therapy[J]. Am J Nephrol, 2021, 52(2): 98-107.doi: 10.1159/000514550.
[4]	Mirghaed MT, Sepehrian R, Rakhshan A, et al. Sleep quality in iranian hemodialysis patients: A systematic review and meta-analysis[J]. Iran J Nurs Midwifery Res, 2019, 24(6):403-409.doi: 10.4103/ijnmr. pmid: 31772913
[5]	Chu G, Choi P, McDonald VM. Sleep disturbance and sleep-disordered breathing in hemodialysis patients[C]Semin Dial, 2018, 31(1):48-58. doi: 10.1111/sdi.12617.
[6]	Fitzpatrick J, Kerns ES, Kim ED, et al. Functional outcomes of sleep predict cardiovascular intermediary outcomes and all-cause mortality in patients on incident hemodialysis[J]. J Clin Sleep, 2021, 17(8):1707-1715.doi: 10.5664/jcsm.9304.
[7]	Han Q, Liu B, Lin S, et al. Pittsburgh sleep quality index score predicts all-cause mortality in Chinese dialysis patients[J]. Int Urol Nephrol, 2021, 53(11):2369-2376.doi: 10.1007/s11255-021-02842-6. pmid: 33788131
[8]	So JY, Warburton KM, Rosen IM. A guide to management of sleepiness in ESKD[J]. Am J Kidney Dis, 2020, 75(5):782-792. doi: S0272-6386(19)31066-2 pmid: 31983503
[9]	Chu G, Matricciani L, Russo S, et al. Sleep disturbances in adults with chronic kidney disease: An umbrella review[J]. J Nephrol, 2025, 38(2):353-369.doi:10.1007/s40620-025-02214-8.
[10]	Sancho-Domingo C, Carballo JL, Coloma-Carmona A, et al. Brief version of the Pittsburgh Sleep Quality Index (B-PSQI) and measurement invariance across gender and age in a population-based sample[J]. Psychol Assess, 2021, 33(2):111-121.doi:10.1037/pas0000959. pmid: 33119375
[11]	吴洵, 杜文聪, 苏健. 江苏省老年人抑郁、焦虑症状及共病影响因素:基于老年心理关爱行动项目数据分析[J]. 中国公共卫生, 2025, 41(11): 1301-1308.doi:10.11847/zgggws1147665.
[12]	中华国际医学交流基金会中华肾脏病防治专项基金专家委员会. 慢性肾脏病相关瘙痒管理中国专家共识(2025年版)[J]. 中华肾脏病杂志, 2025, 41(7):555-566.doi:10.3760/cma.j.cn441217-20250110-00117.
[13]	中国医师协会神经内科医师分会睡眠学组,中华医学会神经病学分会睡眠障碍学组, 中国睡眠研究会睡眠障碍专业委员会. 中国不宁腿综合征的诊断与治疗指南(2021版)[J]. 中华医学杂志, 2021, 101(13):908-925.doi:10.3760/cma.j.cn112137-20200820-02431.
[14]	潘璐璐, 邵国建, 王泽敏, 等. 维持性血液透析患者睡眠障碍的相关危险因素分析[J]. 温州医科大学学报, 2023, 53(3):245-249.doi:10.3969/j.issn.2095-9400.2023.03.012.
[15]	孙钰欣, 王俊霞. 维持性血液透析患者睡眠障碍的现状及其影响因素分析[J]. 中国血液净化, 2025, 24(8):635-641.doi:10.3969/j.issn.1671-4091.2025.08.004.
[16]	Xu X, Liu X, Yang C, et al. Diagnosis of tuberculous pericarditis in zhejiang, China: A diagnostic prediction model based on LASSO logistic regression[J]. J Inflamm Res, 2025, 18(3): 4681-4693.doi: 10.2147/JIR.S504183.
[17]	Du Z, Chu T, Dai F, et al. Correlation analysis of anxiety, depression, and sleep quality in end-stage renal disease patients undergoing maintenance hemodialysis[J]. Medicine (Baltimore), 2025, 104(42):e44433.doi: 10.1097/MD.0000000000044433.
[18]	Almutary H. Fatigue and pruritus impact sleep quality in hemodialysis patients[J]. Nat Sci Sleep, 2024, 16(31): 2289-2298.doi: 10.2147/NSS.S496376.
[19]	Liu Y, Du Q, Jiang Y. Prevalence of restless legs syndrome in maintenance hemodialysis patients: A systematic review and meta-analysis[J]. Sleep Med, 2024, 114(2): 15-23.doi: 10.1016/j.sleep.2023.11.1138.
[20]	Jeon YS, Yu S, Kim C, et al. T. Lower serum calcium levels associated with disrupted sleep and rest-activity rhythm in shift workers[J]. Nutrients, 2022, 22, 14(15):3021.doi:10.3390/nu14153021.
[21]	Fatima Y, Doi SA, Najman JM, et al. Exploring gender difference in sleep quality of young adults: Findings from a large population study[J]. Clin Med Res, 2016, 14(3-4):138-144. doi: 10.3121/cmr.2016.1338.

变量	睡眠障碍组(n=125)	无睡眠障碍组(n=97)	t/Z/χ²值	P值
女性[例(%)]	70(56.00)	39(40.21)	5.451	0.019
年龄(岁)	60.34±12.69	51.51±12.67	5.151	<0.01
BMI(kg/m²)	22.04±3.48	22.91±3.23	-1.910	0.057
原发疾病[例(%)]
慢性肾小球肾炎	49 (39.20)	43 (44.33)
糖尿病肾病	32 (25.60)	20 (20.62)	1.095	0.778
高血压肾病	20 (16.00)	16 (16.49)
其他	24 (19.20)	18 (18.56)
透析病程(年)	5.75±4.58	3.45±3.48	4.254	<0.01
吸烟[例(%)]	34(27.20)	27(27.84)	0.011	0.920
饮酒[例(%)]	30(24.00)	20(20.62)	0.358	0.549
受教育程度≥高中[例(%)]	68(54.40)	57(58.76)	0.423	0.516
高血压[例(%)]	105(84.00)	86(88.66)	0.987	0.320
糖尿病[例(%)]	22(17.60)	17(17.53)	0.002	0.988
心脑血管疾病[例(%)]	24(19.20)	16(16.49)	0.271	0.603
Hb(g/L)	108.80±18.90	109.30±16.80	-0.251	0.842
WBC(×10⁹/L)	5.86(4.75,6.92)	5.76(5.02,7.05)	-0.220	0.826
RBC(×10¹²/L)	3.79±0.24	3.73±0.60	0.780	0.436
PLT(×10⁹/L)	156.00±61.30	162.70±67.10	-0.775	0.439
TG(mmol/L)	1.64(1.26,2.45)	1.59(1.12,2.82)	-0.430	0.669
TC(mmol/L)	4.05±0.98	4.20±0.95	-1.146	0.253
HDL-C(mmol/L)	0.88±0.17	0.91±0.15	-1.372	0.171
LDL-C(mmol/L)	2.22±0.74	2.28±0.75	-0.596	0.552
Alb(g/L)	38.00±3.60	38.80±3.80	-1.603	0.110
P(mmol/L)	1.78±0.58	1.83±0.57	-0.642	0.522
血钙(mmol/L)	2.08±0.28	2.29±0.22	-6.258	<0.01
K(mmol/L)	4.38±0.81	4.50±0.98	-0.975	0.319
Cr(μmol/L)	915.01±289.53	964.52±278.55	-1.285	0.200
BUN(mmol/L)	22.62(18.45,26.30)	22.02(18.56,23.60)	-0.580	0.561
UA(mmol/L)	420.90±90.40	439.13±98.96	-1.430	0.154
ALP(U/L)	121.03±40.47	117.34±48.88	0.615	0.539
焦虑[例(%)]	31(24.80)	8(8.25)	10.334	0.001
抑郁[例(%)]	30(24.00)	13(13.40)	3.928	0.048
尿毒症瘙痒[例(%)]	77(61.60)	30(30.93)	20.580	<0.01
RLS[例(%)]	39(31.20)	8(8.25)	17.241	<0.01

变量	睡眠障碍组(n=125)	无睡眠障碍组(n=97)	t/Z/χ²值	P值
女性[例(%)]	70(56.00)	39(40.21)	5.451	0.019
年龄(岁)	60.34±12.69	51.51±12.67	5.151	<0.01
BMI(kg/m²)	22.04±3.48	22.91±3.23	-1.910	0.057
原发疾病[例(%)]
慢性肾小球肾炎	49 (39.20)	43 (44.33)
糖尿病肾病	32 (25.60)	20 (20.62)	1.095	0.778
高血压肾病	20 (16.00)	16 (16.49)
其他	24 (19.20)	18 (18.56)
透析病程(年)	5.75±4.58	3.45±3.48	4.254	<0.01
吸烟[例(%)]	34(27.20)	27(27.84)	0.011	0.920
饮酒[例(%)]	30(24.00)	20(20.62)	0.358	0.549
受教育程度≥高中[例(%)]	68(54.40)	57(58.76)	0.423	0.516
高血压[例(%)]	105(84.00)	86(88.66)	0.987	0.320
糖尿病[例(%)]	22(17.60)	17(17.53)	0.002	0.988
心脑血管疾病[例(%)]	24(19.20)	16(16.49)	0.271	0.603
Hb(g/L)	108.80±18.90	109.30±16.80	-0.251	0.842
WBC(×10⁹/L)	5.86(4.75,6.92)	5.76(5.02,7.05)	-0.220	0.826
RBC(×10¹²/L)	3.79±0.24	3.73±0.60	0.780	0.436
PLT(×10⁹/L)	156.00±61.30	162.70±67.10	-0.775	0.439
TG(mmol/L)	1.64(1.26,2.45)	1.59(1.12,2.82)	-0.430	0.669
TC(mmol/L)	4.05±0.98	4.20±0.95	-1.146	0.253
HDL-C(mmol/L)	0.88±0.17	0.91±0.15	-1.372	0.171
LDL-C(mmol/L)	2.22±0.74	2.28±0.75	-0.596	0.552
Alb(g/L)	38.00±3.60	38.80±3.80	-1.603	0.110
P(mmol/L)	1.78±0.58	1.83±0.57	-0.642	0.522
血钙(mmol/L)	2.08±0.28	2.29±0.22	-6.258	<0.01
K(mmol/L)	4.38±0.81	4.50±0.98	-0.975	0.319
Cr(μmol/L)	915.01±289.53	964.52±278.55	-1.285	0.200
BUN(mmol/L)	22.62(18.45,26.30)	22.02(18.56,23.60)	-0.580	0.561
UA(mmol/L)	420.90±90.40	439.13±98.96	-1.430	0.154
ALP(U/L)	121.03±40.47	117.34±48.88	0.615	0.539
焦虑[例(%)]	31(24.80)	8(8.25)	10.334	0.001
抑郁[例(%)]	30(24.00)	13(13.40)	3.928	0.048
尿毒症瘙痒[例(%)]	77(61.60)	30(30.93)	20.580	<0.01
RLS[例(%)]	39(31.20)	8(8.25)	17.241	<0.01

因素	回归系数	标准误	Wald χ²值	P值	OR值	95%CI
因素	回归系数	标准误	Wald χ²值	P值	OR值	下限	上限
性别	-0.501	0.474	1.116	0.291	0.606	0.239	1.535
年龄	0.048	0.018	7.630	0.006	1.050	1.014	1.086
透析龄	0.338	0.064	27.526	<0.01	1.402	1.236	1.590
血钙	-3.297	0.547	36.320	<0.01	0.037	0.013	0.108
焦虑	1.819	0.718	6.418	0.011	6.165	1.509	25.181
抑郁	1.152	0.522	4.877	0.027	3.165	1.138	8.799
尿毒症瘙痒	1.676	0.431	15.114	<0.01	5.344	2.296	12.439
RLS	2.437	0.657	13.746	<0.01	11.442	3.154	41.506

因素	回归系数	标准误	Wald χ²值	P值	OR值	95%CI
因素	回归系数	标准误	Wald χ²值	P值	OR值	下限	上限
性别	-0.501	0.474	1.116	0.291	0.606	0.239	1.535
年龄	0.048	0.018	7.630	0.006	1.050	1.014	1.086
透析龄	0.338	0.064	27.526	<0.01	1.402	1.236	1.590
血钙	-3.297	0.547	36.320	<0.01	0.037	0.013	0.108
焦虑	1.819	0.718	6.418	0.011	6.165	1.509	25.181
抑郁	1.152	0.522	4.877	0.027	3.165	1.138	8.799
尿毒症瘙痒	1.676	0.431	15.114	<0.01	5.344	2.296	12.439
RLS	2.437	0.657	13.746	<0.01	11.442	3.154	41.506