EUVIMEDObjevte EUVIMED
Crossref

Multimodal Fusion of mpMRI Radiomics, Clinical Features, and Hematological Biomarkers Enhances Machine Learning‐Based Prediction of Biochemical Recurrence in Prostate Cancer Patients

Yinxing Zhu iD, Zeyu Yang iD, Zhipeng Liu iD, Shuai Xu iD, Xin Wang iD, Xiaowei Zhu iD, Lichao Qian iD

Chemical Biology & Drug Design · 2025

DOI: 10.1111/cbdd.70206 ↗

At a glance

Journal article in Chemical Biology & Drug Design, 2025. Written by Yinxing Zhu and 6 co-authors. Institution: Taizhou Affiliated Hospital of Nanjing University of Chinese Medicine, Taizhou, China. Major MEDLINE topics: Prostatic Neoplasms, Machine Learning, Biomarkers, Tumor, Neoplasm Recurrence, Local. Cited 4 times so far (Crossref); 38 references. Funded by: Postgraduate Research & Practice Innovation Program of Jiangsu Province, Traditional Chinese Medicine Science and Technology Development Project of Jiangsu Province, Young Elite Scientists Sponsorship Program by Jiangsu Association of Chinese Medicine.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

To develop and validate an interpretable machine‐learning model for early prediction of biochemical recurrence (BCR) by fusing multiparametric MRI radiomics, clinical variables, and hematological biomarkers. A total of 172 patients (115 BCR‐positive, 57 BCR‐negative), who underwent RP with a median follow‐up of 37 months, from Taizhou People's Hospital were retrospectively enrolled. Preoperative ADC and T2‐weighted images were manually segmented to extract radiomic features; laboratory and clinical data included PSA, routine blood counts, lipid profile, and coagulation indices. After LASSO selection, seven machine‐learning algorithms were trained and internally validated. The best‐performing model was interpreted with SHAP analysis to quantify feature contributions. PSA emerged as the dominant predictor, exhibiting the highest mean absolute SHAP value and thereby exerting the greatest influence on model output. Among coagulation parameters, D‐dimer and APTT were significantly associated with BCR ( p = 0.007 and p = 0.036, respectively). Integration of ADC + T2 radiomics with clinical/hematological variables via a SVM classifier yielded the highest performance: AUC 0.916 (95% CI: 0.891–0.941) in the training set and 0.820 (95% CI: 0.762–0.878) in the validation set. SHAP revealed that ADC/T2 radiomic features constituted 60% of the top‐ten predictors, while D‐dimer exhibited a paradoxical negative SHAP value, suggesting a potential protective association. Multimodal fusion of mpMRI radiomics, clinical feature, and hematological biomarkers substantially improves BCR prediction. The interpretable model highlights PSA, and coagulation dysfunction, as key recurrence drivers, offering a clinically actionable tool for personalized management.

Subjects

MeSH terms (MEDLINE)

Prostatic NeoplasmsMachine LearningBiomarkers, TumorNeoplasm Recurrence, LocalMultiparametric Magnetic Resonance ImagingHumansMaleMiddle AgedAgedRetrospective StudiesProstate-Specific AntigenMagnetic Resonance ImagingRadiomics

Author keywords

biochemical recurrence (BCR)hematological biomarkersmpMRI radiomicsprostate cancer (PCa)

Substances

Biomarkers, TumorProstate-Specific Antigen

Authors and institutions

  • Taizhou Affiliated Hospital of Nanjing University of Chinese Medicine, Taizhou, China.
  • Xi'an Jiaotong-Liverpool University, Suzhou, China.
  • Jiangsu University, Zhenjiang, China.
  • The Affiliated Taizhou People's Hospital of Nanjing Medical University, Taizhou, China.
  • Nanjing Hospital of Chinese Medicine Affiliated to Nanjing University of Chinese Medicine, Nanjing, China.

ORCID profiles: Yinxing Zhu, Zeyu Yang, Zhipeng Liu, Shuai Xu, Xin Wang, Xiaowei Zhu, Lichao Qian

Funding

  • Postgraduate Research & Practice Innovation Program of Jiangsu Province
  • Traditional Chinese Medicine Science and Technology Development Project of Jiangsu Province
  • Young Elite Scientists Sponsorship Program by Jiangsu Association of Chinese Medicine

Cite

APA

Zhu, Y., Yang, Z., Liu, Z., Xu, S., Wang, X., Zhu, X., & Qian, L. (2025). Multimodal Fusion of mpMRI Radiomics, Clinical Features, and Hematological Biomarkers Enhances Machine Learning‐Based Prediction of Biochemical Recurrence in Prostate Cancer Patients. Chemical Biology & Drug Design. https://doi.org/10.1111/cbdd.70206

Vancouver

Zhu Y, Yang Z, Liu Z, Xu S, Wang X, Zhu X, et al. Multimodal Fusion of mpMRI Radiomics, Clinical Features, and Hematological Biomarkers Enhances Machine Learning‐Based Prediction of Biochemical Recurrence in Prostate Cancer Patients. Chemical Biology & Drug Design. 2025. doi:10.1111/cbdd.70206

BibTeX
@article{Zhu2025,
  author = {Zhu, Yinxing and Yang, Zeyu and Liu, Zhipeng and Xu, Shuai and Wang, Xin and Zhu, Xiaowei and Qian, Lichao},
  title = {Multimodal Fusion of mpMRI Radiomics, Clinical Features, and Hematological Biomarkers Enhances Machine Learning‐Based Prediction of Biochemical Recurrence in Prostate Cancer Patients},
  journal = {Chemical Biology & Drug Design},
  year = {2025},
  doi = {10.1111/cbdd.70206}
}
Start for free →