在津巴布韦,使用深度学习和整体机器学习模型预测与男性发生性关系的男性的性传播感染
Owen Mugurungi1, Elliot Mbunge2, Rutendo Birri-Makota3
1AIDS and TB Programme, Ministry of Health and Child Care, AIDS & TB Programme, Harare, Zimbabwe.
PLOS digital health
|July 3, 2024
概括
机器学习模型准确地预测与男性发生性关系的男性的性传播感染 (STIs). 多层感知器 (MLP) 显示了最高的准确性,有助于识别高风险个体,以改善STI监测和查.
科学领域:
- 公共卫生 公共卫生
- 传染性疾病 传染性疾病
- 医疗保健中的机器学习
背景情况:
- 性传播感染 (STIs) 构成了全球重大健康挑战,特别是在与男性发生性关系的男性 (MSM) 中.
- 促成因素包括无保护性,多个伴侣,耻辱感,物质使用,以及对查和护理的限制.
- 预测建模可以提高脆弱人群中性传播感染的早期检测和干预策略.
研究的目的:
- 使用生物行为调查数据,应用和比较机器学习模型来预测MSM中的性病.
- 确定与该人口中性传播感染风险相关的关键人口和行为预测因素.
- 评估多层感知器 (MLP),XGBoost和ExtraTrees模型在STI预测中的性能.
主要方法:
- 利用了来自津巴布韦1538名MSM的生物行为调查 (BBS) 数据.
- 采用多层感知器 (MLP),极端随机树 (ExtraTrees) 和XGBoost机器学习模型.
- 应用合成少数群体过量采样技术 (SMOTE) 用于类不平衡和用于预测因子识别的后勤回归.
主要成果:
- MLP获得了最高的精度 (87.54%),回忆 (97.29%),精度 (89.64%),F1-Score (93.31%) 和AUC (66.78%).
- XGBoost和ExtraTrees也表现出强大的预测性能,分别准确率为86.51%和85.47%.
- 年龄,同居,教育和就业状况被确定为MSM中性传播感染的重要预测因素.
结论:
- 机器学习模型,特别是MLP,是预测MSM群体中性传播感染的有效工具.
- 这些模型可以显著帮助识别高风险个体,以进行有针对性的感染性传染病监测和查.
- 改进的预测工具可以为MSM带来更好的健康结果和更有效的公共卫生干预措施.
相关概念视频
01:18Steps in Outbreak Investigation
122
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
122
01:26Sexually Transmitted Infections
294
Sexually transmitted infections (STIs) are diseases transmitted primarily through unsafe sexual interactions. Bacteria, viruses, or parasites cause them and can result in severe health complications if untreated.ChlamydiaThe bacterium Chlamydia trachomatis is responsible for the disease Chlamydia, the most common STI in the United States. This peculiar pathogen requires human cells to reproduce, residing intracellularly. The initial infection often goes unnoticed because it typically does not...
294