跨人口队伍的持续学习与分布转移:从多队列代谢综合征识别的见解
Chang Liu1, Zhangdaihong Liu2, Jingjing Liu1
1School of Public Health, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China.
概括
持续学习 (CL) 有效地适应深度学习 (DL) 模型,用于在医院和非医院环境中识别代谢综合征 (MetS),克服灾难性遗忘和提高绩效.
科学领域:
- 医疗保健中的人工智能
- 机器学习用于医学诊断
- 深度学习模型适应
背景情况:
- 深度学习 (DL) 模型在医院和非医院数据之间的分布转移中扎,导致对代谢综合征 (MetS) 等疾病的误诊.
- 在将DL模型适应新数据环境时,灾难性遗忘是关键的挑战.
研究的目的:
- 展示持续学习 (CL) 策略的潜力,以提高DL模型在各种医疗保健环境中识别MetS的性能.
- 评估CL在减轻灾难性遗忘和在分配转移下保持预测准确性的有效性.
主要方法:
- 利用来自医院 (MIMIC) 和非医院 (NHANES,专有) 的三个医疗保健数据集.
- 开发了一个 MetS 识别管道,结合了 CL 策略.
- 基于ROC曲线 (AUROC) 和精度回忆曲线 (AUC-PR) 下的累积面积的评估性能.
主要成果:
- 临床治疗方法显著优于没有临床治疗策略的顺序训练的对照组.
- 在组合测试组中获得了0.85的累积AUROC和0.65的AUC-PR.
- 培训订单对绩效产生了重大影响,医院对非医院培训产生了7.6%的AUROC改进.
结论:
- 在不同医疗保健环境中,特别是在医院和非医院环境之间,CL显示出适应DL模型的显著前景.
- 建议的CL模型有效地减少了灾难性遗忘,提高了DL模型的性能和可扩展性.
- 培训顺序是考虑在医疗应用中最优化CL模型部署的关键因素.
相关概念视频
Longitudinal Research
11.9K
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...
11.9K
Cross-Sectional Research
11.3K
In cross-sectional research, a researcher compares multiple segments of the population at the same time. If they were interested in people's dietary habits, the researcher might directly compare different groups of people by age. Instead of following a group of people for 20 years to see how their dietary habits changed from decade to decade, the researcher would study a group of 20-year-old individuals and compare them to a group of 30-year-old individuals and a group of 40-year-old...
11.3K
Longitudinal Studies
141
Longitudinal studies are also widely used in other medical and social science fields. For instance, in cardiovascular research, they can monitor patients' health over decades to identify risk factors for heart disease, such as high cholesterol or smoking, and evaluate the long-term effectiveness of preventive measures. Similarly, in mental health studies, researchers might follow individuals from adolescence into adulthood to understand the development and progression of conditions like...
141
Mechanistic Models: Compartment Models in Individual and Population Analysis
32
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
32


