EUVIMEDEUVIMED entdecken
Crossref

Development of a machine learning-based prediction model for bipolar disorder relapse via integration of 1H-NMR metabolomics and clinical features

Yan Ren, Tingting Zheng, Ruiyuan Liu, Yipeng Zhao, Zhiyong Zhang, Tianmei Si, Ruiping Zhang

Journal of Affective Disorders · 2026-03 · 396 · 120858

DOI: 10.1016/j.jad.2025.120858 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Affective Disorders, 2026-03. Verfasst von Yan Ren und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychiatry, The Fifth Hospital of Shanxi Medical University, Taiyuan, 030001, China; The Fifth Clinical Medical College of Shanxi Medic…. Hauptthemen laut MEDLINE: Bipolar Disorder, Machine Learning, Metabolomics, Proton Magnetic Resonance Spectroscopy. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 31 Literaturangaben. Gefördert von: Shanxi Provincial Department of Science and Technology, Shanxi Provincial Key Research and Development Project, Applied Basic Research Project of Shanxi Province, China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Bipolar disorder (BD) is a chronic psychiatric illness characterized by recurrent episodes of depression and mania, with a global lifetime prevalence of 0.6-1 %. Patients experience high relapse rates despite treatment, while existing prediction models show limited clinical utility. METHODS: We integrated proton nuclear magnetic resonance (1H NMR) metabolomics with multidimensional clinical variables in a cohort of BD patients (n = 89). Metabolomic data were analyzed using partial least squares-discriminant analysis (PLS-DA) and orthogonal partial least squares-discriminant analysis (OPLS-DA) to identify differential metabolites. Significant metabolites were further analyzed through pathway enrichment analysis. A multimodal prediction model was then constructed using LASSO-logistic regression. RESULTS: During follow-up, 38 patients (42.7 %) experienced relapse while 51 (57.3 %) remained stable. Six significant predictors of relapse were identified: three clinical features (disease duration, negative life events, sleep disorder) and three metabolites (acetone, O-acetylglycoprotein, choline phosphate). The model demonstrated strong predictive performance (training set AUC = 0.897,95 %CI(0.831-0.942);validation set AUC = 0.846,95 %CI(0.769-0.910)).Metabolomic analysis revealed five differentially expressed metabolites enriched in phospholipid biosynthesis pathways, suggesting dysregulated membrane metabolism may underlie relapse. CONCLUSION: Our findings demonstrate the clinical value of combining metabolomic and clinical markers for BD relapse prediction, while providing new insights into disease mechanisms. This approach may facilitate personalized intervention strategies and warrants validation in larger cohorts.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Bipolar DisorderMachine LearningMetabolomicsProton Magnetic Resonance SpectroscopyHumansMaleFemaleAdultRecurrenceMiddle Aged

Stichwörter der Autor:innen

Bipolar disorderClinical biomarkersMetabolomicsPhospholipid metabolismRelapse prediction

Autor:innen und Institutionen

  • Department of Psychiatry, The Fifth Hospital of Shanxi Medical University, Taiyuan, 030001, China; The Fifth Clinical Medical College of Shanxi Medical University, Taiyuan, 030001, China; Department of Psychiatry, Shanx…
  • Department of Health Statistics, School of Public Health, Shanxi Medical University, Taiyuan, 030001, China.
  • Academy of Medical Sciences, Shanxi Medical University, Taiyuan, 030001, China.
  • Department of Clinical Medicine, Shanxi Medical University, Taiyuan, 030001, China.
  • Department of Psychiatry, Shanxi Provincial People's Hospital, Taiyuan, 030000, China.
  • Peking University Sixth Hospital, Institute of Mental Health, Beijing, 100191, China. Electronic address: si.tian-mei@163.com.

Förderung

  • Shanxi Provincial Department of Science and Technology
  • Shanxi Provincial Key Research and Development Project
  • Applied Basic Research Project of Shanxi Province, China

Zitieren

APA

Ren, Y., Zheng, T., Liu, R., Zhao, Y., Zhang, Z., Si, T., & Zhang, R. (2026). Development of a machine learning-based prediction model for bipolar disorder relapse via integration of 1H-NMR metabolomics and clinical features. Journal of Affective Disorders, 396, 120858. https://doi.org/10.1016/j.jad.2025.120858

Vancouver

Ren Y, Zheng T, Liu R, Zhao Y, Zhang Z, Si T, et al. Development of a machine learning-based prediction model for bipolar disorder relapse via integration of 1H-NMR metabolomics and clinical features. Journal of Affective Disorders. 2026;396:120858. doi:10.1016/j.jad.2025.120858

BibTeX
@article{Ren2026,
  author = {Ren, Yan and Zheng, Tingting and Liu, Ruiyuan and Zhao, Yipeng and Zhang, Zhiyong and Si, Tianmei and Zhang, Ruiping},
  title = {Development of a machine learning-based prediction model for bipolar disorder relapse via integration of 1H-NMR metabolomics and clinical features},
  journal = {Journal of Affective Disorders},
  year = {2026},
  volume = {396},
  pages = {120858},
  doi = {10.1016/j.jad.2025.120858}
}
Kostenlos starten →