通过公共卫生镜头了解个人和社会/环境因素的交叉数据动态:可解释的机器学习方法
Siwoo Jeong1,2, Sung Bum Yun3, Soon Yong Park3
1Convergence Institute of Human Data Technology, Jeonju University, Jeonju, Republic of Korea.
通过了解个人和社区因素如何相互作用,可以改善首尔的肥胖预防策略. 机器学习模型揭示了关键预测因素,指导了有针对性的公共卫生干预.
科学领域:
- 公共卫生 公共卫生
- 城市规划 城市规划
- 数据科学数据科学数据科学
背景情况:
- 肥胖率的上升是一个重大的公共卫生挑战.
- 有效的预防需要了解多方面的促成因素.
研究的目的:
- 调查个人和社会/环境因素对首尔肥胖的综合影响.
- 应用先进的机器学习来预测肥胖和因素重要性分析.
主要方法:
- 利用了社区健康调查,信用卡数据和首尔开放数据.
- 采用随机森林,沙普利添加式解释 (SHAP) 和地理加权最小绝对收缩和选择操作员 (GWLASSO) 模型.
主要成果:
- 随机森林模型在肥胖预测中实现了>90%的准确性.
- SHAP分析确定了关键的个人因素,如"对肥胖的自我意识"和"体重控制经验".
- GWLASSO显示了社会/环境因素影响的地区特定变化.
结论:
- 研究结果支持有针对性的肥胖预防计划,整合个人和社会环境因素.
- 强调可解释机器学习在城市卫生战略制定中的有用性.
- 建议各地区根据已识别的差异因素量身定制肥胖预算.
更多相关视频
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
06:52Using Cholesky Decomposition to Explore Individual Differences in Longitudinal Relations between Reading Skills
Published on: September 17, 2019
相关概念视频
Mechanistic Models: Compartment Models in Individual and Population Analysis
Strategies for Assessing and Addressing Confounding
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
Steps in Outbreak Investigation
Confounding in Epidemiological Studies
Human Genetics
The complex relationship between genetics and psychology is observable through common biological components such...
Dimensions of Health and Illness
