在国家肺部查试验中基于深度学习的长期死亡率预测
Yaozhi Lu1,2, Shahab Aslani1,3, Mark Emberton4
1Centre for Medical Image Computing, University College London, London WC1V 6LJ, U.K.
IEEE access : practical innovations, open solutions
|October 9, 2023
概括
深度学习模型使用CT扫描和临床数据预测非肺癌死亡率,在心血管死亡率预测中超过人类的准确性. 这有助于识别被忽视的胸部病理,以进行有针对性的干预.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 公共卫生 公共卫生
背景情况:
- 预测长期死亡率对于预防性医疗保健至关重要.
- 传统的死亡风险评估方法存在局限性.
- 国家肺部查试验 (NLST) 数据为研究提供了宝贵的资源.
研究的目的:
- 通过深度学习研究长期死亡率.
- 开发用于预测非肺癌死亡率 (心血管和呼吸道) 的模型.
- 确定CT扫描中与死亡风险相关的关键特征.
主要方法:
- 使用神经网络模型 (3D-ResNet) 的深度学习方法.
- 在NLST中对年龄,性别和吸烟史进行匹配的队列上训练模型.
- 集成的3DCT扫描数据和临床信息用于预测.
- 使用3D突出地图用于模型解释.
主要成果:
- 实现了0.73的曲线下的面积 (AUC) 来预测死亡率.
- 在心血管死亡率预测方面表现优于人类.
- 获得了0.60的F1得分和0.38.38.3的马修斯相关系数.
- 在CT扫描上确定了特定的胸部区域,表明死亡风险.
结论:
- 深度学习模型可以有效地预测非肺癌死亡率.
- 人工智能驱动的CT扫描分析可以揭示与死亡率相关的微妙特征.
- 这种方法可以提高早期检测和指导预防性干预,减少患者的发病率.
相关概念视频
02:20Longitudinal Research
12.0K
Sometimes we want to see how people change over time, as in studies of human development and lifespan. When we test the same group of individuals repeatedly over an extended period of time, we are conducting longitudinal research. Longitudinal research is a research design in which data-gathering is administered repeatedly over an extended period of time. For example, we may survey a group of individuals about their dietary habits at age 20, retest them a decade later at age 30, and then again...
12.0K
01:20Actuarial Approach
85
The actuarial approach, a statistical method originally developed for life insurance risk assessment, is widely used to calculate survival rates in clinical and population studies. This method accounts for participants lost to follow-up or those who die from causes unrelated to the study, ensuring a more accurate representation of survival probabilities.
Consider the example of a high-risk surgical procedure with significant early-stage mortality. A two-year clinical study is conducted,...
Consider the example of a high-risk surgical procedure with significant early-stage mortality. A two-year clinical study is conducted,...
85