人工智能驱动的热图用于糖尿病足风险分层:多中心跨截面研究
Meshari F Alwashmi1, Mustafa Alghali1, Waseem Abu-Ashour2
1Amplifai Health, Riyadh, Saudi Arabia.
JMIR formative research
|November 27, 2025
概括
一个由人工智能驱动的热图系统,热足扫描 (TFScan),有效地识别了高风险的糖尿病患者. 这种非侵入性工具有助于早期发现糖尿病脚部并发症,改善患者管理.
科学领域:
- 医疗技术 医疗技术 医学技术
- 医疗保健中的人工智能
- 糖尿病学 糖尿病学
背景情况:
- 糖尿病足部并发症对健康造成重大负担,特别是在中东和北非地区.
- 现有的糖尿病足并发症查方法在客观性,侵入性和可扩展性方面存在局限性.
- 新的方法对于有效的糖尿病足风险的早期检测和管理至关重要.
研究的目的:
- 评估人工智能驱动的热脚扫描 (TFScan) 系统的有效性.
- 评估TFScan使用非侵入性热学技术识别患有糖尿病足并发症高风险的患者的能力.
- 分析温度模式和风险分层的不对称性.
主要方法:
- 这是一项多中心,横截面的研究,涉及沙特阿拉伯1120名糖尿病患者.
- 使用智能手机兼容的红外摄像头进行热成像.
- 应用AI算法来分析足部血管体温度模式和不对称性,将风险分为四类.
- 与临床风险因素,神经病症症状和热异常相关的TFScan分类.
主要成果:
- 9.3%的参与者被归类为中度或高风险,显示出糖尿病并发症的患病率明显更高.
- 高风险组的外周动脉疾病 (20.2%),心血管疾病 (57.7%),神经病变 (11.5%) 和足部形 (14.4%) 的发病率增加.
- 显著的热异常,包括温度不对称 (≥2.2°C),集中在中度和高风险组,表明 perfusion 缺陷和炎症状态.
结论:
- TFScan系统成功地将糖尿病患者分为临床相关的风险类别.
- 中等和高风险群体表现出更大的血管,神经病变和热异常负担.
- 人工智能增强的温度学显示,它是一个可扩展的,客观的工具,用于主动的糖尿病足管理,这需要进一步的纵向验证.
相关概念视频
Peripheral Arterial Disease II: Clinical Manifestations and Diagnostic Evaluation
326
Clinical manifestationsPeripheral Arterial Disease (PAD) manifests through a range of symptoms, from the characteristic intermittent claudication to atypical presentations and severe complications in advanced stages. Intermittent claudication, a hallmark symptom of PAD, presents as exercise-induced muscle pain that typically resolves within minutes of rest. This pain is reproducible and stems from inadequate blood flow, leading to the accumulation of lactic acid produced during anaerobic...
326
Peripheral Artery Disease IV: Nursing Management
321
The nursing management of a patient with peripheral artery disease (PAD) begins with a thorough assessment of the patient’s health history and clinical manifestations.AssessmentHealth History: Evaluate the patient’s history of hypertension, hyperlipidemia, family history of cardiovascular issues, and lifestyle factors such as dietary patterns, smoking, and physical activity.Physical Examination:Assess the affected extremity for decreased or absent peripheral pulses,...
321


