关于基于人工智能的新型心血管风险评分 (AICVD) 的多中心研究的开发和验证
Shiv Kumar Jalepalli1, Prashant Gupta2, Andre L A J Dekker3
1Apollo Hospitals, Hyderabad, Telangana, India.
Family medicine and community health
|January 18, 2024
概括
一个新的基于人工智能的心血管疾病 (CVD) 风险评分显示,与FHRS和QRisk3.3等传统方法相比,印度人口心脏事件的预测准确度更高.
科学领域:
- 心脏病学 心脏病学
- 人工智能的人工智能
- 公共卫生 公共卫生
背景情况:
- 心血管疾病 (CVD) 占印度近30%的死亡人数.
- 现有的心血管疾病风险评分显示印度人口的性能和可重现性有限.
- 需要改进风险预测模型,以适应印度人口结构.
研究的目的:
- 开发基于人工智能的风险评分 (AICVD) 以预测10年内心血管疾病事件.
- 将AICVD的预测性能与弗雷明翰心脏风险评分 (FHRS) 和QRisk3.3进行比较.
- 通过印度和荷兰的独立队伍验证AICVD模型.
主要方法:
- 在31599名印度参与者的大型数据集上使用多层神经网络开发了一个深度学习危险模型.
- 通过涉及斯皮尔曼相关性和倾向性得分匹配的多步骤过程选择了21个风险因素.
- 该模型在独立的回顾性队列中得到验证,并与FHRS和QRisk3.3进行了比较.
主要成果:
- 在初级队列中,AICVD模型实现了0.853的曲线下的高面积 (AUC).
- 验证显示AUC从0.84到0.92不等,比FHRS和QRisk3.3显著更好的正概率比率和准确性.
- 在荷兰队列中,AICVD的表现优于弗雷明汉心脏风险模型 (AUC 0.737与0.707).
结论:
- 基于AI的新型心血管疾病风险评分 (AICVD) 显示了印度人口心脏事件的优异预测性能.
- 与传统评分相比,AICVD为心血管风险评估提供了更准确,更可靠的工具.
- 这种人工智能驱动的方法在改善印度心血管疾病预防策略方面具有重大潜力.
相关概念视频
Pre-Procedural Guidelines for Assessing Blood Pressure
565
Accurate blood pressure assessment is crucial for diagnosing and managing various health conditions. To ensure the reliability of these measurements, healthcare professionals must adhere to standardized pre-procedural guidelines. These guidelines enhance patient safety and improve the overall quality of healthcare. The following steps are essential for obtaining accurate and consistent blood pressure readings, from using the appropriate tools to ensuring effective communication with the...
565
Assessment of blood pressure in brachial artery(two-step method)
711
Measuring blood pressure is a fundamental skill in healthcare that aids in diagnosing and monitoring hypertension and other cardiovascular conditions. An aneroid sphygmomanometer, commonly used in clinical settings, offers a manual and precise method for blood pressure measurement. The technique for using this instrument involves specific steps that must be carefully executed to ensure accuracy. The following detailed description outlines a two-step technique for assessing blood pressure using...
711


