智慧医养平台的高职康养专业学生慢性病管理能力培养研究
Research on the Cultivation of Chronic Disease Management Ability of Higher Vocational Health Care Students Using a Smart Medical and Nursing Platform

目的：探讨智慧医养平台在提升高职康养专业学生慢性病管理能力中的应用效果。方法：采用分层抽样法选取某高职院校120名学生，随机分为实验组(智慧平台全流程教学)与三个对照组(传统教学/混合教学/常规课程)。依托“云–边–端”协同架构的智慧医养平台，集成医用可穿戴设备(BioHarness 3.0)、Unity3D虚拟养老院场景(83种情境还原度)及XGBoost能力成长模型，实施“四阶螺旋训练法”：①5G+AR虚拟仿真；②多病种案例推演；③真实数据流接入；④跨学科协作决策。通过过程性评价(平台数据追踪)与终结性评价(临床实践考核)相结合，运用多元回归分析能力提升关键因素。结果：实验组慢性病管理能力总分(85.73 ± 7.24)显著高于所有对照组(vs.对照1：75.42 ± 7.86，P < 0.01)，其中操作技能维度优势最显著(32.46 ± 3.14 vs. 27.85 ± 3.52)。平台使用频率(β = 0.425)与师生互动次数(β = 0.386)共同解释76.7%的能力变异量，高频次“数据–决策”闭环训练使技能迁移效率提升40%。伦理决策模块得分达4.32 ± 0.56 (5分制)，跨学科认知网络构建效率较传统教学提高18.7%。结论：智慧医养平台通过动态数据采集、虚拟情境还原与个性化路径规划三重机制，有效突破传统实训模式瓶颈。建议后续重点开发基于生成式AI的智能辅导系统，建立“院校–企业–社区”协同的开放平台生态，推动康养教育向数字智能范式转型，为应对老龄化社会提供可持续人才支撑。
Objective: To explore the application effect of a smart medical and nursing platform in improving the chronic disease management ability of higher vocational health care students. Methods: Using stratified sampling, 120 students from a vocational college were randomly divided into an experimental group (full-process smart platform teaching) and three control groups (traditional teaching/hybrid teaching/regular courses). Leveraging a “cloud-edge-device” collaborative smart healthcare platform integrating medical wearables (BioHarness 3.0), Unity3D virtual nursing home scenarios (83 situational restorations), and XGBoost capability growth models, we implemented the “Four-stage Spiral Training Method”: ① 5G + AR virtual simulation; ② multi-disease case deduction; ③ real data flow integration; ④ interdisciplinary collaborative decision-making. Through combined process evaluation (platform data tracking) and summative evaluation (clinical practice assessment), multiple regression analysis identified key capability improvement factors. RESULTS The experimental group’s total chronic disease management score (85.73 ± 7.24) significantly exceeded all controls (vs. control 1: 75.42 ± 7.86, P < 0.01), with operational skills showing the greatest advantage (32.46 ± 3.14 vs. 27.85 ± 3.52). Platform usage frequency (β = 0.425) and teacher-student interactions (β = 0.386) jointly explained 76.7% of capability variance. High-frequency “data-decision” loop training improved skill transfer efficiency by 40%.