Scholarlink

Background <p>Misdiagnosing bipolar disorder (BD) as major depressive disorder (MDD) can lead to poor treatment outcomes. This study aims to develop and validate a machine learning-based model to effectively differentiate between MDD and BD using electronic medical record (EMR) data.</p> Methods <p>This retrospective study enrolled 584 patients with BD and 1,179 patients with MDD from two medical centers between January 2022 and August 2024. Feature selection was performed using both Least Absolute Shrinkage and Selection Operator (LASSO) regression and the Boruta algorithm. Six machine learning (ML) algorithms were used to construct the model. SHapley Additive exPlanations (SHAP) analysis was conducted to improve model interpretability.</p> Results <p>Among the six machine learning models constructed based on these features, the RF model demonstrated the best overall performance, achieving the highest (AUC = 0.863) in the internal validation set and also showing moderate discriminative ability (AUC = 0.710) in the external validation set. SHAP analysis identified illness duration, creatine kinase, and age of onset as the most important predictive features.</p> Conclusions <p>The 7-predictor RF model demonstrated moderate discriminative performance, showing potential as an auxiliary decision support tool for distinguishing hospitalized BD from MDD patients. However, the reliance on the International Classification of Diseases, 10th Revision (ICD-10) criteria may result in the misclassification of latent BD, thereby limiting the model’s accuracy and generalizability. Furthermore, future work should validate the model’s generalization ability in multi-center samples and develop intuitive decision support tools to enhance clinical utility.</p> Clinical trial registration <p>Not applicable. This is a retrospective observational study that does not involve any clinical intervention; therefore, clinical trial registration was not required.</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

Development and external validation of a diagnostic model for differentiating major depressive disorder from bipolar disorder

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月28日

查看全文
  • Hongxin Zheng,
  • Xialong Cheng,
  • Wenxin Gan,
  • Shuyu Duan,
  • Yizi Liu,
  • Kun Li,
  • Chen Su,
  • Chenxi Xu,
  • Yongcan Zhou,
  • Wenwei Zhang,
  • Runbo Wu,
  • Yu Xie

摘要

Background

Misdiagnosing bipolar disorder (BD) as major depressive disorder (MDD) can lead to poor treatment outcomes. This study aims to develop and validate a machine learning-based model to effectively differentiate between MDD and BD using electronic medical record (EMR) data.

Methods

This retrospective study enrolled 584 patients with BD and 1,179 patients with MDD from two medical centers between January 2022 and August 2024. Feature selection was performed using both Least Absolute Shrinkage and Selection Operator (LASSO) regression and the Boruta algorithm. Six machine learning (ML) algorithms were used to construct the model. SHapley Additive exPlanations (SHAP) analysis was conducted to improve model interpretability.

Results

Among the six machine learning models constructed based on these features, the RF model demonstrated the best overall performance, achieving the highest (AUC = 0.863) in the internal validation set and also showing moderate discriminative ability (AUC = 0.710) in the external validation set. SHAP analysis identified illness duration, creatine kinase, and age of onset as the most important predictive features.

Conclusions

The 7-predictor RF model demonstrated moderate discriminative performance, showing potential as an auxiliary decision support tool for distinguishing hospitalized BD from MDD patients. However, the reliance on the International Classification of Diseases, 10th Revision (ICD-10) criteria may result in the misclassification of latent BD, thereby limiting the model’s accuracy and generalizability. Furthermore, future work should validate the model’s generalization ability in multi-center samples and develop intuitive decision support tools to enhance clinical utility.

Clinical trial registration

Not applicable. This is a retrospective observational study that does not involve any clinical intervention; therefore, clinical trial registration was not required.