BackgroundThe diagnosis of sarcopenia relies extensively on human and equipment resources and requires individuals to personally visit medical institutions. The objective of this study was to develop a test‐free, self‐assessable approach to identify sarcopenia by utilizing artificial intelligence techniques and representative real‐world data.MethodsThis multicentre study enrolled 11 661 middle‐aged and older adults from a national survey initialized in 2011. Follow‐up data from the baseline cohort collected in 2013 (n = 9403) and 2015 (n = 10 356) were used for validation. Sarcopenia was retrospectively diagnosed using the Asian Working Group for Sarcopenia 2019 framework. Baseline age, sex, height, weight and 20 functional capacity (FC)–related binary indices (activities of daily living = 6, instrumental activities of daily living = 5 and other FC indices = 9) were considered as predictors. Multiple machine learning (ML) models were trained and cross‐validated using 70% of the baseline data to predict sarcopenia. The remaining 30% of the baseline data, along with two follow‐up datasets (n = 9403 and n = 10 356, respectively), were used to assess model performance.ResultsThe study included 5634 men and 6027 women (median age = 57.0 years). Sarcopenia was identified in 1288 (11.0%) individuals. Among the 20 FC indices, the running/jogging 1 km item showed the highest predictive value for sarcopenia (AUC [95%CI] = 0.633 [0.620–0.647]). From the various ML models assessed, a 24‐variable gradient boosting classifier (GBC) model was selected. This GBC model demonstrated favourable performance in predicting sarcopenia in the holdout data (AUC [95%CI] = 0.831 [0.808–0.853], accuracy = 0.889, recall = 0.441, precision = 0.475, F1 score = 0.458, Kappa = 0.396 and Matthews correlation coefficient = 0.396). Further model validation on the temporal scale using two longitudinal datasets also demonstrated good performance (AUC [95%CI]: 0.833 [0.818–0.848] and 0.852 [0.840–0.865], respectively). The model's built‐in feature importance ranking and the SHapley Additive exPlanations method revealed that lifting 5 kg and running/jogging 1 km were relatively important variables among the 20 FC items contributing to the model's predictive capacity, respectively. The calibration curve of the model indicated good agreement between predictions and actual observations (Hosmer and Lemeshow p = 0.501, 0.451 and 0.374 for the three test sets, respectively), and decision curve analysis supported its clinical usefulness. The model was implemented as an online web application and exported as a deployable binary file, allowing for flexible, individualized risk assessment.ConclusionsWe developed an artificial intelligence model that can assist in the identification of sarcopenia, particularly in settings lacking the necessary resources for a comprehensive diagnosis. These findings offer potential for improving decision‐making and facilitating the development of novel management strategies of sarcopenia.

中文翻译：

---

一种用于免测试识别肌肉减少症的人工智能方法


背景肌肉减少症的诊断广泛依赖于人力和设备资源，需要个人亲自前往医疗机构就诊。本研究的目的是利用人工智能技术和具有代表性的真实世界数据，开发一种无需测试、可自我评估的方法来识别肌肉减少症。方法这项多中心研究从 2011 年启动的一项全国调查中招募了 11 661 名中老年人。使用 2013 年 （n = 9403） 和 2015 年 （n = 10 356） 收集的基线队列的随访数据进行验证。使用 2019 年亚洲肌肉减少症工作组框架回顾性诊断肌肉减少症。基线年龄、性别、身高、体重和 20 个功能能力 （FC） 相关的二元指数 （日常生活活动 = 6，日常生活工具活动 = 5 和其他 FC 指数 = 9） 被视为预测因子。使用 70% 的基线数据对多个机器学习 （ML） 模型进行训练和交叉验证，以预测肌肉减少症。其余 30% 的基线数据以及两个后续数据集 （分别为 n = 9403 和 n = 10 356） 用于评估模型性能。结果该研究包括 5634 名男性和 6027 名女性 （中位年龄 = 57.0 岁）。在 1288 例 （11.0%） 个体中发现肌肉减少症。在 20 个 FC 指数中，跑步/慢跑 1 公里项目对肌肉减少症的预测价值最高 （AUC [95%CI] = 0.633 [0.620–0.647]）。从评估的各种 ML 模型中，选择了一个 24 变量梯度提升分类器 （GBC） 模型。该 GBC 模型在预测维持数据中的肌肉减少症方面表现出良好的性能 （AUC [95%CI] = 0.831 [0.808–0.853]，准确率 = 0.889，召回率 = 0.441，精确率 = 0.475，F1 分数 = 0.458，Kappa = 0。396 和 Matthews 相关系数 = 0.396）。使用两个纵向数据集在时间尺度上进一步验证模型也显示出良好的性能（AUC [95%CI]：分别为 0.833 [0.818–0.848] 和 0.852 [0.840–0.865]）。该模型的内置特征重要性排名和 SHapley 加法解释方法显示，举重 5 公斤和跑步/慢跑 1 公里分别是影响模型预测能力的 20 个 FC 项目中相对重要的变量。模型的校准曲线表明预测与实际观察之间具有良好的一致性 （三个测试集的 Hosmer 和 Lemeshow p = 0.501 、 0.451 和 0.374），决策曲线分析支持其临床有用性。该模型作为在线 Web 应用程序实现，并导出为可部署的二进制文件，从而允许进行灵活、个性化的风险评估。结论我们开发了一种人工智能模型，可以帮助识别肌肉减少症，尤其是在缺乏全面诊断必要资源的情况下。这些发现为改善决策和促进开发新的肌肉减少症管理策略提供了潜力。