Intelligent Screening and Precision Diagnosis of Prostate Cancer Based on Multimodal Data

NCT07631806 | Active Not Recruiting

• 1 other identifier: GXMU-IRB-APR-2026-034
• Study Type: observational
• Target: 500
• Locations: 1 country
• Sites: 1

Brief Summary

This project aims to develop a precision screening and diagnostic solution for prostate cancer based on multimodal artificial intelligence, focusing on addressing the diagnostic challenge in patients within the PSA "gray zone" of 4-10 ng/mL. The project will integrate multidimensional information including ctDNA liquid biopsy, routine laboratory data, and prostate ultrasound images to develop three models: a ctDNA-based multimodal AI prediction model, a routine laboratory data-assisted decision model, and an ultrasound image AI-assisted diagnostic model. On this basis, a multimodal AI fusion decision system will be established to automatically generate individualized risk assessment reports and diagnostic recommendations. Additionally, a closed-loop mechanism of "clinical use - data feedback - model optimization" will be constructed to continuously iterate model parameters using pathological gold standards, thereby improving predictive accuracy in our hospital population. The project will form a generalizable precision diagnostic workflow, reduce unnecessary biopsies in "gray zone" patients, and provide an implementable in-hospital solution for precision medicine in prostate cancer.

Conditions

Prostate Cancer With PSA Gray Zone

Keywords

Prostate cancer; Multimodal data / Multimodal artificial intelligence; PSA gray zone (4-10 ng/mL); ctDNA liquid biopsy; Artificial intelligence (AI) diagnosis; Prostate ultrasound; Unnecessary biopsy reduction; DNA methylation; Transrectal ultrasound (TRUS); Convolutional neural network (ResNet/DenseNet); Precision medicine

Outcome Measures

Primary Outcomes (1)

• Area Under the Curve (AUC) of the multimodal AI fusion diagnostic system

  The AUC of the fusion model in distinguishing clinically significant prostate cancer from non-cancer or indolent cancer, using pathological biopsy results as the gold standard.

  Measured after all participants have completed biopsy and obtained pathological diagnosis (approximately within the 2-year study period).

Secondary Outcomes (1)

• Sensitivity and Specificity of the Multimodal AI Fusion Diagnostic System

  Measured after all participants have completed biopsy and obtained pathological diagnosis (approximately within the 2-year study period).

Study Arms (2)

Training Set

Approximately 400 cases. This group will be used to develop and internally validate the three specialized models: (1) ctDNA multimodal AI prediction model, (2) routine laboratory data-assisted decision model, and (3) prostate ultrasound image AI-assisted diagnostic model. Five-fold cross-validation will be used for algorithm comparison and hyperparameter tuning.

Validation Set

Approximately 100 cases. This independent validation set will be used to evaluate the diagnostic performance of the multimodal fusion decision system. Sensitivity, specificity, positive predictive value, negative predictive value, and AUC will be calculated using pathological results as the gold standard. DeLong test will be used to compare AUC with PSA alone. Decision curve analysis (DCA) will be used to evaluate clinical net benefit. Subgroup analysis will be performed for the PSA 4-10 ng/mL gray zone.

Eligibility Criteria

• Age: 45 Years+
• Sex: male
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The study population consists of male patients aged ≥45 years with suspected prostate cancer, presenting with abnormal serum PSA (≥4 ng/mL), abnormal digital rectal examination, or suspicious lesions on prostate ultrasound, who are scheduled to undergo prostate biopsy. Participants will be prospectively enrolled from patients presenting to the hospital for PSA abnormality, lower urinary tract symptoms, or active screening. The total planned sample size is no less than 500 cases, divided into a training set (approximately 400 cases) and a validation set (approximately 100 cases) at an 8:2 ratio. Excluded are patients with prior diagnosis of prostate cancer receiving active treatment, those with other malignancies, and those with critical missing clinical data.

You may qualify if:

• Age ≥45 years, male
• Presenting with abnormal serum PSA (≥4 ng/mL), abnormal digital rectal examination, or suspicious lesions on prostate ultrasound
• Undergoing prostate biopsy with definitive pathological results
• Signed informed consent

You may not qualify if:

• Previously diagnosed with prostate cancer and receiving surgery, radiotherapy, or endocrine therapy
• With other malignancies
• Critical missing clinical data (e.g., missing PSA value, incomplete ultrasound report)

Sponsors & Collaborators

• Guangxi Medical University: lead

Study Sites (1)

Guangxi Medical University First Affiliated Hospital

Nan'ning, Guangxi, China

Location

Related Publications (16)

• Wang X, Xie Y, Zheng X, Liu B, Chen H, Li J, Ma X, Xiang J, Weng G, Zhu W, Wang G, Fang Y, Cheng H, Xie L. A prospective multi-center randomized comparative trial evaluating outcomes of transrectal ultrasound (TRUS)-guided 12-core systematic biopsy, mpMRI-targeted 12-core biopsy, and artificial intelligence ultrasound of prostate (AIUSP) 6-core targeted biopsy for prostate cancer diagnosis. World J Urol. 2023 Mar;41(3):653-662. doi: 10.1007/s00345-022-04086-0. Epub 2022 Jul 19.

  PMID: 35852595 BACKGROUND

• Ahmed HU, El-Shater Bosaily A, Brown LC, Gabe R, Kaplan R, Parmar MK, Collaco-Moraes Y, Ward K, Hindley RG, Freeman A, Kirkham AP, Oldroyd R, Parker C, Emberton M; PROMIS study group. Diagnostic accuracy of multi-parametric MRI and TRUS biopsy in prostate cancer (PROMIS): a paired validating confirmatory study. Lancet. 2017 Feb 25;389(10071):815-822. doi: 10.1016/S0140-6736(16)32401-1. Epub 2017 Jan 20.

  PMID: 28110982 BACKGROUND

• Gai W, Sun K. Epigenetic Biomarkers in Cell-Free DNA and Applications in Liquid Biopsy. Genes (Basel). 2019 Jan 9;10(1):32. doi: 10.3390/genes10010032.

  PMID: 30634483 BACKGROUND

• He WS, Bishop KS. The potential use of cell-free-circulating-tumor DNA as a biomarker for prostate cancer. Expert Rev Mol Diagn. 2016 Aug;16(8):839-52. doi: 10.1080/14737159.2016.1197121. Epub 2016 Jun 20.

  PMID: 27254598 BACKGROUND

• Jones PA, Laird PW. Cancer epigenetics comes of age. Nat Genet. 1999 Feb;21(2):163-7. doi: 10.1038/5947.

  PMID: 9988266 BACKGROUND

• Hamdy FC, Donovan JL, Lane JA, Mason M, Metcalfe C, Holding P, Davis M, Peters TJ, Turner EL, Martin RM, Oxley J, Robinson M, Staffurth J, Walsh E, Bollina P, Catto J, Doble A, Doherty A, Gillatt D, Kockelbergh R, Kynaston H, Paul A, Powell P, Prescott S, Rosario DJ, Rowe E, Neal DE; ProtecT Study Group. 10-Year Outcomes after Monitoring, Surgery, or Radiotherapy for Localized Prostate Cancer. N Engl J Med. 2016 Oct 13;375(15):1415-1424. doi: 10.1056/NEJMoa1606220. Epub 2016 Sep 14.

  PMID: 27626136 BACKGROUND

• Salman JW, Schoots IG, Carlsson SV, Jenster G, Roobol MJ. Prostate Specific Antigen as a Tumor Marker in Prostate Cancer: Biochemical and Clinical Aspects. Adv Exp Med Biol. 2015;867:93-114. doi: 10.1007/978-94-017-7215-0_7.

  PMID: 26530362 BACKGROUND

• Abraham NE, Mendhiratta N, Taneja SS. Patterns of repeat prostate biopsy in contemporary clinical practice. J Urol. 2015 Apr;193(4):1178-84. doi: 10.1016/j.juro.2014.10.084. Epub 2014 Oct 18.

  PMID: 25444971 BACKGROUND

• Serag H, Banerjee S, Saeb-Parsy K, Irving S, Wright K, Stearn S, Doble A, Gnanapragasam VJ. Risk profiles of prostate cancers identified from UK primary care using national referral guidelines. Br J Cancer. 2012 Jan 31;106(3):436-9. doi: 10.1038/bjc.2011.596. Epub 2012 Jan 12.

  PMID: 22240787 BACKGROUND

• Toren P, Razik R, Trachtenberg J. Catastrophic sepsis and hemorrhage following transrectal ultrasound guided prostate biopsies. Can Urol Assoc J. 2010 Feb;4(1):E12-4. doi: 10.5489/cuaj.785.

  PMID: 20174484 BACKGROUND

• Anderson E, Leahy O, Cheng AC, Grummet J. Risk factors for infection following prostate biopsy - a case control study. BMC Infect Dis. 2015 Dec 23;15:580. doi: 10.1186/s12879-015-1328-7.

  PMID: 26700859 BACKGROUND

• Cornford P, van den Bergh RCN, Briers E, Van den Broeck T, Brunckhorst O, Darraugh J, Eberli D, De Meerleer G, De Santis M, Farolfi A, Gandaglia G, Gillessen S, Grivas N, Henry AM, Lardas M, van Leenders GJLH, Liew M, Linares Espinos E, Oldenburg J, van Oort IM, Oprea-Lager DE, Ploussard G, Roberts MJ, Rouviere O, Schoots IG, Schouten N, Smith EJ, Stranne J, Wiegel T, Willemse PM, Tilki D. EAU-EANM-ESTRO-ESUR-ISUP-SIOG Guidelines on Prostate Cancer-2024 Update. Part I: Screening, Diagnosis, and Local Treatment with Curative Intent. Eur Urol. 2024 Aug;86(2):148-163. doi: 10.1016/j.eururo.2024.03.027. Epub 2024 Apr 13.

  PMID: 38614820 BACKGROUND

• Han B, Zheng R, Zeng H, Wang S, Sun K, Chen R, Li L, Wei W, He J. Cancer incidence and mortality in China, 2022. J Natl Cancer Cent. 2024 Feb 2;4(1):47-53. doi: 10.1016/j.jncc.2024.01.006. eCollection 2024 Mar.

  PMID: 39036382 BACKGROUND

• Kimura T, Egawa S. Epidemiology of prostate cancer in Asian countries. Int J Urol. 2018 Jun;25(6):524-531. doi: 10.1111/iju.13593. Epub 2018 May 8.

  PMID: 29740894 BACKGROUND

• Kratzer TB, Mazzitelli N, Star J, Dahut WL, Jemal A, Siegel RL. Prostate cancer statistics, 2025. CA Cancer J Clin. 2025 Nov-Dec;75(6):485-497. doi: 10.3322/caac.70028. Epub 2025 Sep 2.

  PMID: 40892160 BACKGROUND

• Zhang H, Ji J, Liu Z, Lu H, Qian C, Wei C, Chen S, Lu W, Wang C, Xu H, Xu Y, Chen X, He X, Wang Z, Zhao X, Cheng W, Chen X, Pang G, Yu G, Gu Y, Jiang K, Xu B, Chen J, Xu B, Wei X, Chen M, Chen R, Cheng J, Wang F. Artificial intelligence for the diagnosis of clinically significant prostate cancer based on multimodal data: a multicenter study. BMC Med. 2023 Jul 24;21(1):270. doi: 10.1186/s12916-023-02964-x.

  PMID: 37488510 RESULT

Biospecimen

Retention: SAMPLES WITH DNA

Urine (post-prostate massage, first-catch voided urine, 30-50 mL), collected into a specialized preservation tube containing nuclease inhibitors, stored at room temperature, and processed within 24 hours. Cell-free DNA (cfDNA) is extracted from the urine for targeted bisulfite sequencing or quantitative PCR to detect prostate cancer-related DNA methylation markers.

MeSH Terms

Conditions

Prostatic Neoplasms; Disease

Condition Hierarchy (Ancestors)

Genital Neoplasms, Male; Urogenital Neoplasms; Neoplasms by Site; Neoplasms; Genital Diseases, Male; Genital Diseases; Urogenital Diseases; Prostatic Diseases; Male Urogenital Diseases; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Doctor of Medicine

Study Record Dates

• First Submitted: June 2, 2026
• First Posted: June 8, 2026
• Study Start: May 1, 2026
• Primary Completion (Estimated): May 1, 2028
• Study Completion (Estimated): May 1, 2028
• Last Updated: June 17, 2026

Record last verified: 2026-05

Locations

CN (1)