Optimizing multi-domain hematologic biomarkers and clinical features for the differential diagnosis of unipolar depression and bipolar depression

Journal Title: Chinese Journal of Nervous and Mental Diseases - Year 2024, Vol 50, Issue 3

Abstract

[Objective] This study aims to build a differential diagnosis model for unipolar and bipolar depression based on clinical features and blood indicators. [Methods] According to inclusion and exclusion criteria, participants with unipolar and bipolar depression were included, and clinical data and blood test indicators of the participants were extracted. The data were randomly divided into a training set and a testing set. Classification models were trained on the training set using extreme gradient boosting based on different feature combinations, and the performance of the models was validated on the testing set. Receiver operating characteristic (ROC), area under curve (AUC), sensitivity, specificity and accuracy were used to evaluate model performance. The SHapley additive explanations (SHAP) method was used to calculate the importance of selected features for the differential diagnosis of unipolar and bipolar depression. [Results] In the unipolar and bipolar depression classification model, the XGBoost model performs the best, with an AUC of 0.889, sensitivity of 0.831, specificity of 0.839, and accuracy of 0.863. The main features in this model include duration of illness, age of onset, albumin, low-density lipoprotein, blood potassium concentration, white blood cell count, platelet/lymphocyte ratio, and monocytes. [Conclusion] Duration of illness and hematological biomarkers, which are easily obtainable in clinical settings, can provide important support for the differential diagnosis of unipolar and bipolar depression.

Authors and Affiliations

Jinkun ZENG, Minne CAO, Dandan LIU, Wei. DENG

Keywords

Related Articles

A case report of recurrent extranodal extra- and intracranial communicating Rosai-Dorfman disease after surgery

We described a case of recurrent extranodal extra- and intracranial communicating Rosai-Dorfman disease. A middle-aged female patient was admitted in May 2017 with a recurrent scalp tumor after surgery. The mass lesion a...

An intervention study of right unilateral modified electroconvulsive therapy for major depressive disorder

ObjectiveTo explore the effect and safety of right unilateral modified electroconvulsive therapy (RUL-MECT) for major depressive disorder patients (MDD).MethodsA randomized controlled trial was conducted on 70 patients w...

Prognostic factors of postoperative patients with intracerebral hemorrhage and application of event-related potentials in consciousness monitoring

[Objective] To explore the risk factors of prognosis of patients with intracerebral hemorrhage at 6 months after operation, and to study the diagnostic efficacy of event-related potential (ERP) on outcome and prognosis....

Research on the effects of NSUN2 gene knockout on the differentiation and apoptosis of PC12 cells

[Objective] To investigate the role of the NOP2/Sun RNA methyltransferase 2 (NSUN2) gene in functions such as differentiation and apoptosis in PC12 cells, with the aim of exploring the function of the NSUN2 gene in nervo...

The application of virtual avatar in anorexia nervosa

Virtual avatar possesses unique advantages such as high degree of realism, immersion and visualization, and the research on applying it to the assessment and treatment of anorexia nervosa is increasing year by year. In t...

Download PDF file
  • EP ID EP750452
  • DOI 10.3969/j.issn.1002-0152.2024.03.001
  • Views 53
  • Downloads 0

How To Cite

Jinkun ZENG, Minne CAO, Dandan LIU, Wei. DENG (2024). Optimizing multi-domain hematologic biomarkers and clinical features for the differential diagnosis of unipolar depression and bipolar depression. Chinese Journal of Nervous and Mental Diseases, 50(3), -. https://europub.co.uk/articles/-A-750452