开发并外部验证可解释机器学习模型以识别痴呆症患者吞咽困难筛查阳性结果：一项多中心横断面研究
Development and External Validation of an Explainable Machine Learning Model to Identify Positive Dysphagia Screening Results in People with Dementia: A Multicenter Cross-Sectional Study.
文献信息
| PMID | 42756555 |
|---|---|
| 原文 | 在 PubMed 查看原文 ↗ |
| 发表日期 | 2026 |
| 作者 | Jie Du |
| 作者单位 | Geriatric Psychiatry, Affiliated Mental Health Center of Jiangnan University, Wuxi, Jiangsu, People's Republic of China. |
| 期刊 | Clinical interventions in aging |
| SCI 分区 | Q2 |
| IF | 4.5 |
| 研究类型 | AI/ML · 临床 |
| 所属专科 | 咽喉科 |
中文摘要
目的： 开发并外部验证一个可解释的机器学习模型，用于识别痴呆症患者标准化吞咽评估（SSA）结果阳性的可能性，尤其是在无法 readily 进行仪器性吞咽评估的环境中。
方法： 候选变量包括临床实践中常规可获得的人口学、身体、口腔健康和心理健康变量。使用最小绝对收缩和选择算子（LASSO）回归进行变量选择。开发并比较了四种机器学习模型：逻辑回归、支持向量机、随机森林和AdaBoost。使用受试者工作特征曲线下面积（AUC）、敏感性、校准和决策曲线分析评估模型性能。应用SHAP分析以增强模型可解释性。开发了一个基于网络的概率评估工具，用于估计个体同时出现SSA阳性结果的概率。
结果： 所有四种模型均显示出良好的区分能力。AdaBoost在内部交叉验证中达到AUC 0.918，在领域和时间外部验证队列中AUC分别为0.900和0.889，敏感性范围为0.879至0.901。由于病例发现优先考虑敏感性，因此选择AdaBoost进行模型解释和在线工具开发。SHAP分析将体重指数列为对AdaBoost输出贡献最大的因素，其次是牙齿数量、进食能力、饮食类型和临床痴呆评定量表评分。
结论： 该模型在识别可能同时存在SSA筛查阳性结果的人群方面表现出良好性能。该网络工具可能支持病例发现和转诊以进行进一步吞咽评估，但不应将其用作独立的诊断或预后工具。在常规临床实施之前，需要进行前瞻性和地理多样性的验证。
英文摘要
OBJECTIVE: To develop and externally validate an interpretable machine learning model for identifying the likelihood of a positive Standardized Swallowing Assessment (SSA) result in people with dementia, particularly in settings where instrumental swallowing assessments are not readily available.
METHODS: Candidate variables included demographic, physical, oral-health, and mental health variables routinely available in clinical practice. Least absolute shrinkage and selection operator (LASSO) regression was used for variable selection. Four machine learning models were developed and compared: logistic regression, support vector machines, random forest, and AdaBoost. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity, calibration, and decision curve analysis. SHAP analysis was applied to enhance model interpretability. A web-based likelihood assessment tool was developed to estimate the individual probability of a concurrent positive SSA result.
RESULTS: All four models showed good discrimination. AdaBoost achieved an AUC of 0.918 in internal cross-validation and AUCs of 0.900 and 0.889 in the domain and temporal external validation cohorts, respectively, with sensitivities ranging from 0.879 to 0.901. Since sensitivity was prioritized for case finding, AdaBoost was selected for model interpretation and online-tool development. SHAP analysis ranked body mass index as the leading contributor to the AdaBoost output, followed by number of teeth, eating ability, dietary type, and Clinical Dementia Rating score.
CONCLUSION: The model showed good performance for identifying people likely to have a concurrent positive SSA screening result. The web-based tool may support case finding and referral for further swallowing assessment, but it should not be used as a standalone diagnostic or prognostic instrument. Prospective and geographically diverse validation is required before routine clinical implementation.