用智能手表数据实时无创筛查糖尿病，准确率达82.5%。
SweetDeep: A Wearable AI Solution for Real-Time Non-Invasive Diabetes Screening
- 基于手表生理与人口统计数据，设计轻量神经网络模型
- 在真实生活场景下实现82.5%患者级准确率，仅需约20次采样
- 适合可穿戴设备部署，支持低置信度预测规避，提升可靠性
全球2型糖尿病患病率上升，亟需可扩展且低成本的筛查手段。当前诊断依赖侵入性生化检测，成本高昂。消费级可穿戴设备的发展为机器学习疾病检测提供了新可能，但以往研究局限于受控环境。本文提出SweetDeep，一个基于285名参与者（含糖尿病与非糖尿病）的生理与人口统计数据训练的紧凑神经网络，数据来自欧盟与中东北非地区用户在自由生活条件下使用三星Galaxy Watch 7连续六天采集，每人每日多段2分钟传感器记录，总计约20次/人。模型参数少于3,000个，在三折交叉验证下达到82.5%患者级准确率（宏平均F1为82.1%，敏感性79.7%，特异性84.6%），预期校准误差为5.5%。允许模型对低于10%低置信度患者预测进行回避后，剩余样本准确率达84.5%。结果表明，结合工程特征与轻量架构，可在真实可穿戴场景中实现精准、快速、泛化的2型糖尿病检测。
原文摘要 · Abstract (English)
The global rise in type 2 diabetes underscores the need for scalable and cost-effective screening methods. Current diagnosis requires biochemical assays, which are invasive and costly. Advances in consumer wearables have enabled early explorations of machine learning-based disease detection, but prior studies were limited to controlled settings. We present SweetDeep, a compact neural network trained on physiological and demographic data from 285 (diabetic and non-diabetic) participants in the EU and MENA regions, collected using Samsung Galaxy Watch 7 devices in free-living conditions over six days. Each participant contributed multiple 2-minute sensor recordings per day, totaling approximately 20 recordings per individual. Despite comprising fewer than 3,000 parameters, SweetDeep achieves 82.5% patient-level accuracy (82.1% macro-F1, 79.7% sensitivity, 84.6% specificity) under three-fold cross-validation, with an expected calibration error of 5.5%. Allowing the model to abstain on less than 10% of low-confidence patient predictions yields an accuracy of 84.5% on the remaining patients. These findings demonstrate that combining engineered features with lightweight architectures can support accurate, rapid, and generalizable detection of type 2 diabetes in real-world wearable settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。