Scholarlink

Background <p>Adolescent depression is a major public health concern. Physical health indicators are rarely included in risk tools. We examined whether adding dry eye disease (DED) to psychosocial and behavioral factors improves prediction of depressive symptoms.</p> Methods <p>We analyzed 2,076 adolescent questionnaires (94.5% response) covering ocular health, sleep, electronic device use, social support, and demographics. Five machine-learning classifiers were trained with cross-validation and evaluated for discrimination and calibration.</p> Results <p>Models that included DED achieved strong discrimination (AUC ≈ 0.84) and good calibration, with highest accuracy for no and severe depression and lower performance for mild/moderate categories.</p> Conclusions <p>Integrating ocular health with psychosocial factors enhances machine-learning prediction of adolescent depression and may support earlier, school-based identification and referral. Given the low-cost, questionnaire-based inputs and favorable calibration, this approach shows promise for population screening and targeted prevention, pending external validation and prospective testing.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

From dry eye to depression: a machine learning-based framework for predicting adolescent mental health

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月6日

查看全文
  • Le Han,
  • Ying Liu,
  • Peng Xian,
  • Xiao Liu,
  • Kai Cao,
  • Li Ren,
  • Yue Chang,
  • Zhangfang Ma,
  • Lei Tian,
  • Shijing Deng,
  • Xuejiao Liu,
  • Yunshuang Liu,
  • Ying Jie

摘要

Background

Adolescent depression is a major public health concern. Physical health indicators are rarely included in risk tools. We examined whether adding dry eye disease (DED) to psychosocial and behavioral factors improves prediction of depressive symptoms.

Methods

We analyzed 2,076 adolescent questionnaires (94.5% response) covering ocular health, sleep, electronic device use, social support, and demographics. Five machine-learning classifiers were trained with cross-validation and evaluated for discrimination and calibration.

Results

Models that included DED achieved strong discrimination (AUC ≈ 0.84) and good calibration, with highest accuracy for no and severe depression and lower performance for mild/moderate categories.

Conclusions

Integrating ocular health with psychosocial factors enhances machine-learning prediction of adolescent depression and may support earlier, school-based identification and referral. Given the low-cost, questionnaire-based inputs and favorable calibration, this approach shows promise for population screening and targeted prevention, pending external validation and prospective testing.