2026-10-12T15:03:52Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33948226 2026-09-21T03:06:11Z category_7 category_12 category_15 category_21 category_873 category_46 category_734 category_811 category_122 category_128 category_132 category_135 portal_87 item_type_3 month_year_09_2026

Serum BDNF and cognitive risk in maintenance hemodialysis: a machine learning study Qiong Tang (285953) Jiakun Tian (15399912) Xinyu Ying (25079173) Yanyun Zhang (145529) Yanqiao Huo (25079176) Daiyao Liu (14189030) Yongping Zhang (474940) Medicine Cell Biology Neuroscience Biotechnology Chemical Sciences not elsewhere classified Immunology Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Mental Health Hematology Infectious Diseases Computational Biology Maintenance hemodialysis cognitive impairment brain-derived neurotrophic factor machine learning risk prediction kidney failure <p>Cognitive impairment is common in maintenance hemodialysis, but practical risk-assessment tools remain limited. We evaluated the association between baseline serum brain-derived neurotrophic factor (BDNF) and 1-year screening-defined incident cognitive impairment and examined whether BDNF added predictive information beyond routine clinical, laboratory, and baseline cognitive variables. This single-center prospective cohort included 130 maintenance hemodialysis patients with baseline Montreal Cognitive Assessment (MoCA) scores ≥26. The primary outcome was screening-defined incident cognitive impairment, defined as follow-up MoCA <26. Serum BDNF was measured by enzyme-linked immunosorbent assay. Five models were assessed using repeated 5-fold cross-validation; repeated nested cross-validation was added as a sensitivity analysis. During follow-up, 70 patients (53.8%) met the screening-defined outcome. Each 1-SD higher BDNF level was associated with lower odds of the outcome [adjusted OR, 0.52 (95% CI, 0.34–0.80); <i>p</i> = 0.003]. In the primary analysis, random forest and extreme gradient boosting (XGBoost) had AUCs of 0.798 and 0.797, respectively. Adding BDNF to the XGBoost base model changed AUC from 0.770 to 0.797 (DeLong <i>p</i> = 0.236), PR-AUC from 0.746 to 0.779, and Brier score from 0.190 to 0.181. In nested validation, XGBoost AUC was 0.782 (SD 0.019), while paired Base and Base + BDNF AUCs were 0.761 and 0.782, respectively. Lower BDNF was associated with the screening-defined outcome, but its added predictive value was small and statistically uncertain. Serum BDNF may therefore have value as an adjunctive marker for refining risk estimates rather than as a stand-alone predictor; independent multicenter external validation is required before clinical use.</p> <p></p><p>In maintenance hemodialysis patients with baseline MoCA scores ≥26, lower serum brain-derived neurotrophic factor was associated with a higher 1-year risk of screening-defined incident cognitive impairment.</p><p>Adding serum brain-derived neurotrophic factor to routine baseline variables produced a small and statistically uncertain improvement in discrimination (area under the curve 0.770 to 0.797; DeLong <i>p</i> = 0.236), suggesting a modest adjunctive contribution rather than stand-alone predictive value.</p><p>Serum brain-derived neurotrophic factor may have value as an adjunctive biomarker for cognitive risk stratification in maintenance hemodialysis, but independent multicenter external validation is needed before clinical use.</p><p></p> <p>In maintenance hemodialysis patients with baseline MoCA scores ≥26, lower serum brain-derived neurotrophic factor was associated with a higher 1-year risk of screening-defined incident cognitive impairment.</p> <p>Adding serum brain-derived neurotrophic factor to routine baseline variables produced a small and statistically uncertain improvement in discrimination (area under the curve 0.770 to 0.797; DeLong <i>p</i> = 0.236), suggesting a modest adjunctive contribution rather than stand-alone predictive value.</p> <p>Serum brain-derived neurotrophic factor may have value as an adjunctive biomarker for cognitive risk stratification in maintenance hemodialysis, but independent multicenter external validation is needed before clinical use.</p> 2026-09-21T03:06:11Z Dataset Dataset 10.6084/m9.figshare.33948226.v1 https://figshare.com/articles/dataset/Serum_BDNF_and_cognitive_risk_in_maintenance_hemodialysis_a_machine_learning_study/33948226 CC BY 4.0