机器学习模型的应用用于预测印度老年人患有非传染性疾病的抑郁症
Kanchan Yadav1, Dechenla Tshering Bhutia2
1Department of Community Medicine, Sikkim Manipal Institute of Medical Sciences (SMIMS), Sikkim Manipal University (SMU), Tadong, Gangtok, 737102, Sikkim, India. yadavkanchan73@gmail.com.
Scientific reports
|October 3, 2025
概括
机器学习模型有效预测印度老年人的抑郁症. 随机森林实现了95.6%的准确性,识别了针对性干预的关键风险因素,如睡眠不足和身体不活动.
科学领域:
- 老年人的心理健康
- 计算精神病学是一种计算精神病学.
- 公共卫生信息学 公共卫生信息学
背景情况:
- 老年人的抑郁症是一个重大的公共卫生问题,特别是当与非传染性疾病 (NCD) 相伴时.
- 印度面临着人口老龄化和非传染性疾病的快速增长负担,需要可扩展的解决方案来识别有风险的个人.
研究的目的:
- 评估八种监督机器学习 (ML) 模型在预测印度老年人抑郁症的有效性.
- 通过使用数据驱动的方法,在这个人口群体中确定抑郁症的关键预测因素.
主要方法:
- 利用了印度长度衰老研究 (LASI) 波1 (2017-2018) 的数据,其中包括58,467名参与者.
- 通过使用70/30列车测试分割和10倍交叉验证,比较了8个ML模型 (随机森林,决策树,后勤回归,SVM,KNN,naive bayes,神经网络,山脊分类器).
- 通过AUROC,PR-AUC,准确度,灵敏度,特异性,F1得分和通过SHAP值的可解释性来评估模型性能.
主要成果:
- 随机森林表现出优异的性能,AUROC为0.996和准确率为95.6%,其次是决策树 (AUROC为0.915,准确率为91.5%).
- 确定的主要预测因素包括睡眠不足,年龄,BMI,日常生活工具活动 (IADL) 的限制,MPCE五分位数,宗教,吸烟,教育和身体不活动.
- 一个具有前12个预测因素的减少特征模型保持了高准确性和增强的可解释性.
结论:
- 机器学习模型,特别是随机森林,对于识别老年人抑郁风险非常有效.
- 可解释的ML技术,如SHAP与信息获取相结合,提高了对查和干预的临床相关性.
- 研究结果支持开发可扩展的查策略和政策驱动的干预措施,用于印度老年人的心理健康.
更多相关视频
相关概念视频
Classification of Illness
8.6K
The meaning of illness is individualized to each person who experiences an alteration in health. In contrast, disease is a medical term indicating a pathological change in the structure and function of the body or mind. It is a condition that has specific symptoms and boundaries.
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
8.6K
Steps in Outbreak Investigation
488
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:
488


