机器学习解释指导的个体化护理干预对慢性鼻窦炎患者生活质量影响的研究

doi:10.3761/j.issn.0254-1769.2026.12.009

摘要/Abstract

摘要：

目的探讨基于机器学习及沙普利可加性解释方法筛选慢性鼻窦炎核心风险特征，据此制订个体化护理干预方案，并验证其对术后生活质量未改善高风险慢性鼻窦炎患者的干预效果，为构建“从预测到干预”的临床护理流程提供参考。方法采用前瞻性单盲随机对照试验设计，依托前期构建的机器学习预测模型筛选慢性鼻窦炎生活质量高风险患者，选取2024年1—12月北京市某三级甲等综合医院耳鼻咽喉头颈外科住院治疗的102例慢性鼻窦炎患者，随机分为试验组与对照组各51例，试验组实施基于沙普利可加性解释值中贡献度前5的核心风险特征的模块化、个体化护理干预，对照组实施常规护理，比较两组术后生活质量改善率、鼻内镜评分、患者满意度及用药依从性的差异。结果两组均无样本脱落。试验组术后1、3、6个月生活质量改善率分别为56.9%、74.5%和86.3%，对照组分别为35.3%、49.0%和62.7%，各时间点试验组改善率均高于对照组（均P<0.05），且试验组术后3个月鼻内镜评分、患者满意度评分、用药依从性评分均优于对照组，差异有统计学意义（均P<0.01）。结论基于机器学习筛选风险特征的个体化护理方案，可改善慢性鼻窦炎生活质量高风险患者术后生活质量、鼻内镜评分及诊疗依从性。

关键词: 鼻窦炎, 机器学习, 护理, 沙普利可加性解释, 生活质量

Abstract:

Objective To explore the screening of core risk features using machine learning and the SHAPley Additive exPlanations（SHAP） method，formulate an individualized nursing intervention protocol based on these features，and verify the intervention effect of chronic rhinosinusitis patients at high risk for poor postoperative quality of life，thereby providing a reference for constructing a clinical nursing workflow "from prediction to intervention". Methods A prospective，single-blind，randomized controlled trial design was adopted. High-risk patients with chronic rhinosinusitis were screened by the machine learning prediction model constructed in the early stage. A total of 102 patients were recruited from January to December 2024 and randomly divided into an intervention group and a control group，with 51 cases in each group. The intervention group received modular individualized nursing based on the core risk features of SHAP force plots，while the control group received routine nursing. The quality of life improvement rate，nasal endoscopy score，patient satisfaction and medication compliance at 6 months after operation were compared between the 2 groups. Results The improvement rates of Sino-nasal Outcome Test-22（SNOT-22） scores in the intervention group at 1，3 and 6 months after surgery were 56.9%，74.5% and 86.3%，respectively，while those in the control group were 35.3%，49.0% and 62.7%，respectively. The improvement rates in the intervention group were significantly higher than those in the control group at all time points（all P<0.05）. Additionally，the improvement value of Lund-Kennedy nasal endoscopy score，patient satisfaction score and medication compliance score in the intervention group at 3 months after surgery were all significantly superior to those in the control group，with statistically significant differences（all P<0.01）. Conclusion The individualized nursing program based on risk features screened by machine learning can significantly improve the postoperative quality of life，nasal endoscopy score and diagnosis and treatment compliance of high-risk patients with chronic rhinosinusitis.

Key words: Rhinosinusitis, Machine Learning, Nursing Care, SHAPley Additive exPlanations, Quality of Life

王莹, 田晓雪, 龚俐丹, 赵喜格, 宁菲, 李顺丽. 机器学习解释指导的个体化护理干预对慢性鼻窦炎患者生活质量影响的研究[J]. 中华护理杂志, 2026, 61(12): 1651-1658.

WANG Ying, TIAN Xiaoxue, GONG Lidan, ZHAO Xige, NING Fei, LI Shunli. Application of machine learning interpretation-guided individualized nursing interventions in patients at high risk of poor quality of life after chronic sinusitis surgery[J]. Chinese Journal of Nursing, 2026, 61(12): 1651-1658.

图/表 5

表1 慢性鼻窦炎高风险特征-干预模块映射库

Table 1 Mapping library of high-risk characteristics and intervention modules for chronic rhinosinusitis

图1 个体化护理干预实施路径图注：SHAP为沙普利可加性解释；SNOT-22为鼻窦结局测试量表。

Figure 1 Implementation pathway of individualized nursing intervention

表2 两组一般资料的比较

Table 2 Comparison of general data between 2 groups

表3 两组主要结局指标的比较[例（百分率，%）]

Table 3 Comparison of primary outcomes between the 2 groups[case（percentage，%）]

表4 两组次要结局指标的比较

Table 4 Comparison of secondary outcomes between the 2 groups

参考文献 21

[1]	中华耳鼻咽喉头颈外科杂志编辑委员会鼻科组, 中华医学会耳鼻咽喉头颈外科学分会鼻科学组, 中国慢性鼻窦炎诊断和治疗指南(2018)[J]. 中华耳鼻咽喉头颈外科杂志, 2019, 54(2):81-100.
	Subspecialty Group of Rhinology,Editorial Board of Chinese Journal of Otorhinolaryngology Head and Neck Surgery; Subspecialty Group of Rhinology,Society of Otorhinolaryngology Head and Neck Surgery,Chinese Medical Association. Chinese Guideline for diagnosis and treatment of chronic rhinosinusitis(2018)[J]. Chin J Otorhinolaryngol Head Neck Surg, 2019, 54(2):81-100.
[2]	Wang L, Lü YR, Chang XW, et al. The effectiveness of evidence-based nursing intervention for nasal irrigation after endoscopic sinus surgery in patients with chronic rhinosinusitis:a randomized controlled trial[J]. Eur Arch Otorhinolaryngol, 2024, 281(5):2451-2462. DOI PMID
[3]	Bilenler ZK, Ates S. Investigating the relationship between individualized care,patient satisfaction and trust in nurses through structural equation modelling[J]. Int J Nurs Pract, 2024, 30(6):e13286. DOI URL
[4]	Gata A, Raduly L, Budisan L, et al. Machine learning model predicts postoperative outcomes in chronic rhinosinusitis with nasal polyps[J]. Clin Otolaryngol, 2024, 49(6):776-784. DOI URL
[5]	Xiong PH, Chen JL, Zhang Y, et al. Predictive modeling for eosinophilic chronic rhinosinusitis:nomogram and four machine learning approaches[J]. iScience, 2024, 27(2):108928. DOI URL
[6]	张烁妮, 王俊杰, 张波, 等. 急性中毒患者洗胃期间误吸风险预测模型的构建及验证[J]. 中华护理杂志, 2024, 59(17):2100-2107. DOI
	Zhang SN, Wang JJ, Zhang B, et al. Study of machine learning model based on ultrasound with laboratory examinations for risk prediction of severe coronary artery stenosis[J]. Chin J Nurs, 2024, 59(17):2100-2107.
[7]	吕威, 亓放, 高志强, 等. 汉化版SNOT-22评价慢性鼻-鼻窦炎患者生存质量的初步研究[J]. 中华耳鼻咽喉头颈外科杂志, 2008, 43(1):18-21.
	Lü W, Qi F, Gao ZQ, et al. Quality of life survey on patients with chronic rhinosinusitis by using Chinese version of the 22-item Sinonasal Outcome Test(SNOT-22)[J]. Chin J Otorhi-nolaryngol Head Neck Surg, 2008, 43(1):18-21.
[8]	Philpott C, Beard DJ, Saeedi E, et al. The clinical effectiveness of clarithromycin versus endoscopic sinus surgery for adults with chronic rhinosinusitis with and without nasal polyps (MACRO):a pragmatic,multicentre,three-arm,randomised,placebo-controlled phase 4 trial[J]. Lancet, 2025, 406(10506):926-939. DOI URL
[9]	Lund VJ, Kennedy DW. Staging for rhinosinusitis[J]. Otolaryngol Head Neck Surg, 1997, 117(3 Pt 2):S35-S40. DOI PMID
[10]	Lund VJ, Kennedy DW. Quantification for staging sinusitis. The Staging and Therapy Group[J]. Ann Otol Rhinol Laryngol Suppl, 1995, 167:17-21. PMID
[11]	Fokkens WJ, Lund VJ, Hopkins C, et al. European position paper on rhinosinusitis and nasal polyps 2020[J]. Rhinology, 2020, 58(Suppl 29):1-464.
[12]	Thomas LH, McColl E, Priest J, et al. Newcastle Satisfaction with Nursing Scales:an instrument for quality assessments of nursing care[J]. Qual Health Care, 1996, 5(2):67-72. DOI URL
[13]	Shi PL, Wu ZZ, Wu L, et al. Reliability and validity of the Chinese version of the eight-item Morisky Medication Adherence Scale in Chinese patients with systemic lupus erythematosus[J]. Clin Rheumatol, 2022, 41(9):2713-2720. DOI
[14]	代玉, 罗月, 杨会琼, 等. 基于即时适配干预理论的智慧护理方案在介入手术患者中的应用研究[J]. 中华护理杂志, 2025, 60(20):2437-2443. DOI
	Dai Y, Luo Y, Yang HQ, et al. Study on the application of an intelligent just-in-time adaptive nursing intervention in interventional surgery patients[J]. Chin J Nurs, 2025, 60(20):2437-2443. DOI
[15]	田思颖, 常红. 即时适配干预在慢性病患者久坐与身体活动中应用的研究进展[J]. 中华护理杂志, 2025, 60(5):619-623. DOI
	Tian SY, Chang H. Research progress on the application of just-in-time adaptive intervention in chronic illness sedentary and physical activity[J]. Chin J Nurs, 2025, 60(5):619-623. DOI
[16]	谌永毅, 郭俊晨, 丁金锋, 等. 数据驱动的安宁疗护协作模式调试及初步应用研究[J]. 中华护理杂志, 2025, 60(18):2185-2191. DOI
	Chen YY, Guo JC, Ding JF, et al. Adjustment and preliminary application of a data-driven palliative care outcomes collaboration model[J]. Chin J Nurs, 2025, 60(18):2185-2191. DOI
[17]	Pouzols S, Despraz J, Mabire C, et al. Development of a predictive model for hospital-acquired pressure injuries[J]. Comput Inform Nurs, 2023, 41(11):884-891. DOI PMID
[18]	Kandel B, Field C, Kaur J, et al. Development of a predictive hospitalization model for skilled nursing facility patients[J]. J Am Med Dir Assoc, 2025, 26(1):105288. DOI URL
[19]	雷丹, 卞薇, 王宗华, 等. 角膜溃疡患者互联网+精准症状管理方案的构建及应用研究[J]. 中华护理杂志, 2025, 60(6):688-695. DOI
	Lei D, Bian W, Wang ZH, et al. Construction and application of precision symptom management based on Internet plus in patients with corneal ulcer[J]. Chin J Nurs, 2025, 60(6):688-695. DOI
[20]	Wu Y, Fu Y, He Y, et al. The application of enhanced recovery after surgery(ERAS) in chronic rhinosinusitis patients undergoing endoscopic sinus surgery:a systematic review and meta-analysis[J]. PLoS One, 2023, 18(9):e0291835. DOI URL
[21]	Akamine A, Nagasaki Y, Tomizawa A, et al. Risk factors for non-adherence to medications that affect surgery:a Retrospective study in Japan[J]. Patient Prefer Adherence, 2022, 16:1623-1635. DOI URL