Precise diagnosis and risk stratification of prostate cancer by comprehensive serum metabolic fingerprints - prediction model study

Sep 21, 2026

Uploaded by Finn

Prostate cancer requires timely diagnosis and accurate staging to reduce morbidity and mortality. This study presents a novel mass-spectrometry-based approach using MALDI-TOF analysis of trace blood samples combined with machine learning to build diagnostic, stage prediction, and risk stratification models. Serum metabolic fingerprints were obtained from 181 prostate cancer patients and 186 non-cancer controls, with an external validation cohort used to confirm performance. Selected metabolic signals supported pathway enrichment and revealed insights into metabolic alterations associated with tumorigenesis.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Objectives

Methods

Results

Conclusions

Background

Clinical challenges with PSA and imaging

’Experimental Research Precise diagnosis and risk stratiﬁcation of prostate cancer by comprehensive serum metabolic ﬁ ngerprints: a prediction model study Xiaochen Fei, MDa , Xinxing Du, MSca , Jiayi Wang, MDa , Jiazhou Liu, MDa , Yiming Gong, MDa , Zejun Zhao, MScb , Zhibin Cao, PhDd , Qibo Fu, PhDd , Yinjie Zhu, MDa , Liang Dong, PhDa , Baijun Dong, PhDa , Jiahua Pan, PhDa , Wenshe Sun, PhDc,* , Shaowei Xie, MDb,* , Wei Xue, PhDa,* Objectives: Prostate cancer (PCa) is one of the most common malignancies in men worldwide and has caused increasing clinical morbidity and mortality, making timely diagnosis and accurate staging crucial. The authors introduced a novel approach based on mass spectrometry for precise diagnosis and stratiﬁcation of PCa to facilitate clinical decision-making. Methods: Matrix-assisted laser desorption ionization time-of-ﬂight (MALDI-TOF) mass spectrometry analysis of trace blood samples was combined with machine learning algorithms to construct diagnostic and stratiﬁcation models. A total of 367 subjects, comprising 181 with PCa and 186 with non-PCa were enrolled. Additional 60 subjects, comprising 30 with PCa and 30 with non-PCa were enrolled as an external cohort for validation. Subsequent metabolomic analysis was carried out using Autoﬂex MALDI-TOF, and the mass spectra were introduced into various algorithms to construct different models. Results: Serum metabolic ﬁngerprints were successfully obtained from 181 patients with PCa and 186 patients with non-PCa. The diagnostic model based on the eight signals demonstrated a remarkable area under curve of 100% and was validated in the external cohort with the area under curve of 87.3% . Fifteen signals were selected for enrichment analysis, revealing the potential metabolic pathways that facilitate tumorigenesis. Furthermore, the stage prediction model with an overall accuracy of 85.9% precisely classiﬁed subjects with localized disease and those with metastasis. The risk stratiﬁcation model, with an overall accuracy of 89 .6%, precisely classiﬁed the subjects as low-risk and high-risk. Conclusions: Our study facilitated the timely diagnosis and risk stratiﬁcation of PCa and provided new insights into the underlying mechanisms of metabolic alterations in PCa. Keywords: mass spectrometry, matrix-assisted laser desorption ionization, metabolomic, prostate neoplasms Background Prostate cancer (PCa) is one of the most common malignancies with 1 414 259 new cases each year in men globally, leading to substantial clinical mortality with ~375 304 deaths annually[1,2]. The timely identiﬁcation and proper management of PCa are crucial for enhancing long-term clinical outcomes[3–5] . Despite the widespread use of serum prostate-speciﬁc antigen (PSA) for PCascreening in clinical practice, its diagnostic accuracy may be compromised by elevated levels in certain benign conditions, resulting in suboptimal sensitivity and speciﬁcity[6,7] . Meanwhile, MRI with a high negative predictive value, can obviate unnecessary biopsy and improve the overall diagnosis[8] . Nonetheless, it is inevitable to misdiagnose some clinically signiﬁcant cancers due to aDepartment of Urology, bDepartment of Ultrasound, Ren Ji Hospital, Shanghai Jiao Tong University School of Medicine, cDepartment of Urology, Jiading District Central Hospital, Shanghai University of Medicine and Health Sciences, Shanghai and dMedical Science and Technology Innovation Center, Shandong First Medical University and Shandong Academy of Medical Sciences, Shandong, People ’s Republic of China Sponsorships or competing interests that may be relevant to content are disclosed at the end of this article. *Corresponding author. Address: Medical Science and Technology Innovation Center, Shandong First Medical University and Shandong Academy of Medical Science and Technology Innovation Center, Shandong First Medical University and Shandong Academy of Medical Sciences, Shandong 250117, People’s R

FAQs

What is the study’s objective for prostate cancer diagnosis?

To achieve precise diagnosis and risk stratification of prostate cancer using comprehensive serum metabolic fingerprints to support timely clinical decision-making.

How were the serum metabolic fingerprints generated and analyzed?

Trace blood samples were analyzed by MALDI-TOF mass spectrometry, and the resulting mass spectra were integrated with machine learning algorithms to construct diagnostic and prognostic models.

What were the main performance outcomes for diagnosis, staging, and risk grouping?

A diagnostic model using eight signals achieved an AUC of 100% and 87.3% in an external cohort. The stage prediction model reached 85.9% overall accuracy, and the risk stratification model reached 89.6% overall accuracy.

Sep 21, 2026

Uploaded by Finn