Scholarlink

<p><b>Objectives.</b> To establish differences in and to identify the prognostic value of biological markers PDGF-AA, PDGF-BB, and BDNF for the differential diagnosis of patients with unipolar and bipolar depression using machine learning. <b>Materials and methods.</b> The study included 79 patients (median age 48 [34; 57] years), including 35 with depression within the framework of bipolar affective disorder (F31) and 44 with unipolar depression (F32–33). Clinical assessment of patients was carried out using psychometric tools: the Hamilton Depression Rating Scale (HDRS-17) and the Hamilton Anxiety Rating Scale (HARS). Serum concentrations of growth factors were determined on Magpix and Luminex 200 multiplex analyzers (Luminex, USA). The support vector machine method was used to build a predictive model. <b>Results.</b> Patients with depression within the framework of bipolar affective disorder demonstrated statistically significantly higher concentrations of PDGF-AA and PDGF-BB, along with lower concentrations of BDNF. Construction of a predictive model allowed patients with unipolar and bipolar depression to be distinguished in terms of all three of the biomarkers studied here; the sensitivity and specificity of the model were 0.96 ± 0.06 and 0.95 ± 0.05 respectively. <b>Conclusions.</b> Studies of the brain-derived neurotrophic factor and platelet-derived growth factor concentrations showed statistically significant differences in indicators in unipolar and bipolar depression, so they can potentially be used as prognostic biomarkers for differential diagnosis in appropriate clinical cases.</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

Growth Factors PDGF-AA, PDGF-BB, and BDNF as Potential Differential Biomarkers of Unipolar and Bipolar Depression

  • 期刊论文

  • 发表日期：

    2025年3月1日

查看全文
  • U. V. Ryazantseva,
  • A. S. Boiko,
  • L. A. Levchuk,
  • S. N. Vasileva,
  • G. G. Simutkin,
  • S. A. Ivanova,
  • O. V. Roschina,
  • N. A. Bokhan

摘要

Objectives. To establish differences in and to identify the prognostic value of biological markers PDGF-AA, PDGF-BB, and BDNF for the differential diagnosis of patients with unipolar and bipolar depression using machine learning. Materials and methods. The study included 79 patients (median age 48 [34; 57] years), including 35 with depression within the framework of bipolar affective disorder (F31) and 44 with unipolar depression (F32–33). Clinical assessment of patients was carried out using psychometric tools: the Hamilton Depression Rating Scale (HDRS-17) and the Hamilton Anxiety Rating Scale (HARS). Serum concentrations of growth factors were determined on Magpix and Luminex 200 multiplex analyzers (Luminex, USA). The support vector machine method was used to build a predictive model. Results. Patients with depression within the framework of bipolar affective disorder demonstrated statistically significantly higher concentrations of PDGF-AA and PDGF-BB, along with lower concentrations of BDNF. Construction of a predictive model allowed patients with unipolar and bipolar depression to be distinguished in terms of all three of the biomarkers studied here; the sensitivity and specificity of the model were 0.96 ± 0.06 and 0.95 ± 0.05 respectively. Conclusions. Studies of the brain-derived neurotrophic factor and platelet-derived growth factor concentrations showed statistically significant differences in indicators in unipolar and bipolar depression, so they can potentially be used as prognostic biomarkers for differential diagnosis in appropriate clinical cases.