EUVIMEDEUVIMED entdecken
Open Access

Explainable Plasma Proteomics–Based Machine Learning for Osteoporosis Diagnosis, Prognosis, and Protein Biomarker Discovery in the UK Biobank

Wenxiang Zhang iD, Wenjing Zhang, Hanwen Cheng, Weijie Gong, Yuhui Kou, Baoguo Jiang

The FASEB Journal · 15.09.2026 · 40 (17)

DOI: 10.1096/fj.202600647r ↗

Kurz gefasst

Fachartikel in der Zeitschrift The FASEB Journal, online erschienen am 29.08.2026. Verfasst von Wenxiang Zhang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Shenzhen Clinical Research Center for Trauma Treatment, Shenzhen University General Hospital, Shenzhen University, Shenzhen, China. Hauptthemen laut MEDLINE: Biomarkers, Proteomics, Machine Learning, Osteoporosis. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: The National key R&D Program of China, MOST, Shenzhen Medical Research Fund, National Key R&D Program Special Projects of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Osteoporosis (OP) is often underdiagnosed, highlighting the need for tools that can both detect existing disease and predict future risk; large‐scale plasma proteomics combined with explainable machine learning enables integrated diagnostic and prognostic modeling while prioritizing clinically relevant protein markers. This study aims to develop and validate an explainable plasma proteomics machine‐learning framework for osteoporosis diagnosis, future risk prediction, and biomarker discovery. We further tested whether a combined marker panel could distinguish normal, prevalent OP, and future incident OP states from baseline samples. Using UK Biobank plasma proteomic data, we established SPX‐OP, which separately models prevalent OP and incident OP based on Extreme Gradient Boosting (XGBoost) and SHapley Additive exPlanations (SHAP), and then evaluates whether the union of diagnostic and prognostic markers supports integrated baseline stratification. In the experiments, both the diagnostic and prognostic XGBoost models showed robust discrimination for osteoporosis status and future risk, respectively. SHAP‐derived protein markers, including FSHB, ADIPOQ, SOST, COL9A1, and CHAD, were linked to osteoporosis and enriched in bone‐related pathways involving bone development and remodeling, extracellular matrix organization, and inflammatory processes. Using only these SHAP‐selected protein markers, the XGBoost model outperformed the full‐proteome models and provided robust, simultaneous diagnostic and prognostic prediction of osteoporosis. In summary, this work transforms high‐dimensional proteomic data into interpretable marker sets, paving the way for improved risk stratification and further validation of plasma protein biomarkers in osteoporosis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BiomarkersProteomicsMachine LearningOsteoporosisBlood ProteinsHumansPrognosisFemaleUnited KingdomUK BiobankMaleMiddle AgedAgedBiological Specimen BanksBoosting Machine Learning Algorithms

Stichwörter der Autor:innen

clinically relevant protein markersdiagnosis and prognosis of osteoporosisplasma proteomic

Substanzen

BiomarkersBlood Proteins

Autor:innen und Institutionen

  • Shenzhen Clinical Research Center for Trauma Treatment, Shenzhen University General Hospital, Shenzhen University, Shenzhen, China.
  • Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Shenzhen University Medical…
  • National Center for Trauma Medicine, Beijing, China.
  • Department of Orthopedics and Trauma, Peking University People's Hospital, Beijing, China.
  • Department of Family Medicine, Shenzhen University Medical School, Shenzhen, Guangdong, China.

ORCID-Profile: Wenxiang Zhang

Förderung

  • The National key R&D Program of China, MOST
  • Shenzhen Medical Research Fund
  • National Key R&D Program Special Projects of China
  • Guangdong Medical Research Fund
  • Beijing Municipal Natural Science Foundation - Fengtai Joint Fund
  • Shenzhen Clinical Research Center for Trauma Treatment

Zitieren

APA

Zhang, W., Zhang, W., Cheng, H., Gong, W., Kou, Y., & Jiang, B. (2026). Explainable Plasma Proteomics–Based Machine Learning for Osteoporosis Diagnosis, Prognosis, and Protein Biomarker Discovery in the UK Biobank. The FASEB Journal, 40(17). https://doi.org/10.1096/fj.202600647r

Vancouver

Zhang W, Zhang W, Cheng H, Gong W, Kou Y, Jiang B. Explainable Plasma Proteomics–Based Machine Learning for Osteoporosis Diagnosis, Prognosis, and Protein Biomarker Discovery in the UK Biobank. The FASEB Journal. 2026;40(17). doi:10.1096/fj.202600647r

BibTeX
@article{Zhang2026,
  author = {Zhang, Wenxiang and Zhang, Wenjing and Cheng, Hanwen and Gong, Weijie and Kou, Yuhui and Jiang, Baoguo},
  title = {Explainable Plasma Proteomics–Based Machine Learning for Osteoporosis Diagnosis, Prognosis, and Protein Biomarker Discovery in the UK Biobank},
  journal = {The FASEB Journal},
  year = {2026},
  volume = {40},
  number = {17},
  doi = {10.1096/fj.202600647r}
}
Kostenlos starten →