European Randomized Study Of Screening For Prostate Cancer Research Articles

Do differences in secondary treatment explain mortality impact of prostate cancer screening? - A randomized screening trial.

Do differences in secondary treatment explain mortality impact of prostate cancer screening? - A randomized screening trial.

Influence of Regular Statin Intake on Prostate-Specific Antigen Values, Prostate Cancer Incidence and Overall Survival in a Prospective Screening Trial (ERSPC Aarau).

While statins have demonstrated a variety of antineoplastic effects in preclinical studies, several retrospective clinical studies and observational studies have not shown a consistent chemopreventive benefit against prostate cancer (PCa). Therefore, in this population-based cohort study, we examined the association of statin intake on prostate specific antigen (PSA) values and risk of development of PCa. N = 4,314 men from the Swiss section of the European Randomized Study of Screening for Prostate Cancer (ERSPC) were evaluated. N = 761 men were statin users [Stat+]. The median follow-up was 9.6 years. A transrectal prostate biopsy was performed in men with a PSA-level ≥ 3 ng/mL. Mortality and incidence data was obtained through registry linkages. PCa incidence, total serum PSA level, free-to-total PSA level, and overall survival were compared between [Stat+] and [Stat-] patients. Total PSA values were significantly lower in [Stat+] patients at baseline (1.5 vs. 1.8 ng/mL, p < 0.001) and at last follow-up (1.8 vs. 2.1 ng/mL, p < 0.001). PCa detection during the follow-up period was significantly associated with baseline PSA. The overall incidence of PCa showed no statistical difference among [Stat+] and [Stat-] groups (7.4% vs. 9.5%, p = 0.08), indicating that statin use had no effect on the risk of developing PCa during follow-up. [Stat+] patients had a significantly higher overall mortality risk compared to [Stat-] patients (HR 2.04, p < 0.001). A significant risk reduction in the development of PCa in [Stat+] patients was not found. We did observe lower PSA values among [Stat+] patients, compared to [Stat-] patients, with an increasing difference during follow-up.

Development and Validation of a Deep Learning Model Based on MRI and Clinical Characteristics to Predict Risk of Prostate Cancer Progression.

Purpose To validate a deep learning (DL) model for predicting the risk of prostate cancer (PCa) progression based on MRI and clinical parameters and compare it with established models. Materials and Methods This retrospective study included 1607 MRI scans of 1143 male patients (median age, 64 years; IQR, 59-68 years) undergoing MRI for suspicion of clinically significant PCa (csPCa) (International Society of Urological Pathology grade > 1) between January 2012 and May 2022 who were negative for csPCa at baseline MRI. A DL model was developed using baseline MRI and clinical parameters (age, prostate-specific antigen [PSA] level, PSA density, and prostate volume) to predict the time to PCa progression (defined as csPCa diagnosis at follow-up). Internal and external testing was performed. The model's ability to predict progression to csPCa was assessed by Cox regression analyses. Predictive performance of the DL model up to 5 years after baseline MRI in comparison with the European Randomized Study of Screening for Prostate Cancer (ERSPC) future-risk calculator, Prostate Cancer Prevention Trial (PCPT) risk calculator, and Prostate Imaging Reporting and Data System (PI-RADS) was assessed using the Harrell C-index. Optimized follow-up intervals were derived from Kaplan-Meier curves. Results DL scores predicted csPCa progression (internal cohort: hazard ratio [HR], 1.97 [95% CI: 1.61, 2.41; P < .001]; external cohort: HR, 1.32 [95% CI: 1.14, 1.55; P < .001]). The model identified a subgroup of patients (approximately 20%) with risks for csPCa of 3% or less, 8% or less, and 18% or less after 1-, 2-, and 4-year follow-up, respectively. DL scores had a C-index of 0.68 (95% CI: 0.63, 0.74) at internal testing and 0.56 (95% CI: 0.51, 0.61) at external testing, outperforming ERSPC and PCPT (both P < .001) at internal testing. Conclusion The DL model accurately predicted PCa progression and provided improved risk estimations, demonstrating its ability to aid in personalized follow-up for low-risk PCa. Keywords: MRI, Prostate Cancer, Deep Learning Supplemental material is available for this article. ©RSNA, 2025.

Challenges Associated With Indeterminate Prostate Nodules and Increased PSA Levels

Prostate cancer (PCa) has the highest incidence rate among all cancers (233,000 men, representing 27% of all new cases) and the fourth highest mortality rate. This prevalence necessitates significant attention in the diagnosis and treatment planning. The European Randomized Study of Screening for Prostate Cancer (ERSPC) trials, at the 11-year follow-up, demonstrated that prostate cancer-related mortality was reduced by 25-31% due to screening with PSA. Proponents of PSA screening base their arguments on the results of the ERSPC trial, where the most recent follow-up at 16 years demonstrated an increased benefit as the follow-up progressed. Imaging is frequently used as a subsequent step to evaluate the cause of elevated PSA levels. Patients with low-risk prostate cancer may appropriately choose immediate treatment instead of active surveillance, including younger patients, those with high-volume Gleason 6 cancer, and those of African American ethnicity, as these patients have a higher likelihood of disease progression during their lifetime.

Which men benefit from prostate cancer screening? Prostate cancer mortality by subgroup in the European Randomised Study of Screening for Prostate Cancer.

To evaluate whether a subgroup of men can be identified that would benefit more from screening than others. This retrospective cohort study was based on three European Randomised Study of Screening for Prostate Cancer (ERSPC) centres, Finland, the Netherlands and Sweden. We identified 126 827 men aged 55-69 years in the study who were followed for maximum of 16 years after randomisation. The primary outcome was prostate cancer (PCa) mortality. We analysed three age groups 55-59, 60-64 and 65-69 years and PCa cases within four European Association of Urology (EAU) risk groups: low, intermediate, high risk, and advanced disease. The hazard ratio (HR) for PCa mortality in the screening arm relative to the control arm for men aged 55-59 years was 0.96 (95% confidence interval [CI] 0.75-1.24) in Finland, 0.70 (95% CI 0.44-1.12) in the Netherlands and 0.42 (95% CI 0.24-0.73) in Sweden. The HR for men aged 60-64 years was 1.03 (95% CI 0.77-1.37) in Finland, 0.76 (95% CI 0.50-1.16) in the Netherlands and 0.97 (95% CI 0.64-1.48) in Sweden. The HR for men aged 65-69 years was 0.80 (95% CI 0.62-1.03) in Finland and 0.57 (95% CI 0.38-0.83) in the Netherlands, and this age group was absent in Sweden. In the EAU risk group analysis, PCa mortality rates were materially lower for men with advanced disease at diagnosis in all three countries: 0.67 (95% CI 0.56-0.82) in Finland, 0.28 (95% CI 0.18-0.44) in the Netherlands, and 0.48 (95% CI 0.30-0.78) in Sweden. We were unable to unequivocally identify the optimal age group for screening, as mortality reduction differed among centres and age groups. Instead, the screening effect appears to depend on screening duration, and the number and frequency of screening rounds. PCa mortality reduction by screening is largely attributable to stage shift.

Value of baseline PSA in predicting prostate cancer diagnosis and death. Spanish arm of the European Randomized Study of Screening for Prostate Cancer.

Several studies have suggested that prostate-specific antigen (PSA) in young men may predict the risk of developing prostate cancer (PC). Our aim is to study baseline PSA as a prognostic factor in the lifetime risk of developing PC, clinically significant PC (csPC), and metastatic PC (mPC), as well as to assess its impact on long-term mortality. This study was a retrospective analysis involving 2,415 men aged 45-70 years, all participants in the Spanish arm of the European Randomized Study of Screening for Prostate Cancer (ERSPC). These men underwent PSA testing, and prostate biopsies were performed if their PSA levels were ≥3 ng/ml. The follow-up period spanned from September 2, 1996, to February 11, 2021. Kaplan-Meier survival analysis was conducted to calculate the probability of prostate cancer diagnosis and death. The relationship between these probabilities and baseline PSA levels was assessed using the log-rank test. After 25 years of follow-up, the probability of being free of a diagnosis of PC was 95.5%, 89.6%, 80.0%, and 69.4%; and of PC death: 99.6%, 99.6%, 98.9%, and 98.3% for the categories of PSA <1 ng/ml, 1-1.9 ng/ml, 2-2.9 ng/ml, and >3 ng/ml, respectively. There is an association between baseline PSA level and the probability of PC diagnosis (which is maintained in age stratification), csPC, mPC (p <0.001), and PC death (p = 0.047). There is a clear relationship between baseline PSA and the probability of detection of PC, csPC and mPC during follow-up, as well as PC death, in a cohort belonging to the Spanish branch of the ERSPC, with a median follow-up of more than 23 years. Baseline PSA level can be used to define the most appropriate PC screening interval for everyone.

Navigating through the Controversies and Emerging Paradigms in Early Detection of Prostate Cancer: Bridging the Gap from Classic RCTs to Modern Population-Based Pilot Programs.

Over the last three decades, the European Randomized Study of Screening for Prostate Cancer (ERSPC) and the US-based Prostate, Lung, Colorectal and Ovarian (PLCO) Cancer Screening have steered the conversation around the early detection of prostate cancer. These two randomized trials assessed the effect of screening on prostate cancer disease-specific mortality. Elevated PSA levels were followed by a systematic sextant prostate biopsy. Standard repeat testing intervals were applied. After controversies from 2009 to 2016 due to contradicting results of the two trials, the results aligned in 2016 and showed that early PSA detection reduces prostate cancer-specific mortality. However, overdiagnosis rates of up to 50% were reported, and this sparked an intense debate on harms and benefits for almost 20 years. The balance between harms and benefits is highly debated and has initiated further research to investigate new ways of early detection. In the meantime, the knowledge and tools for the diagnostic algorithm improved. This is a continuously ongoing effort which focuses on individual risk-based screening algorithms that preserve the benefits of the purely PSA-based screening algorithms, while reducing the side effects. An important push towards investigating new techniques for early detection came from the European Commission on the 20th of September 2022. The European Commission published its updated recommendation to investigate prostate, lung, and gastric cancer early detection programs. This opened a new window of opportunity to move away from the trial setting to population-based early detection settings. With this review, we aim to review 30 years of historical evidence of prostate cancer screening, which led to the initiation of the 'The Prostate Cancer Awareness and Initiative for Screening in the European Union' (PRAISE-U) project, which aims to encourage the early detection and diagnosis of PCa through customized and risk-based screening programs.

From Screening to Mortality Reduction: An Overview of Empirical Data on the Patient Journey in European Randomized Study of Screening for Prostate Cancer Rotterdam After 21 Years of Follow-up and a Reflection on Quality of Life

BackgroundPrevious research quantified the effect of prostate-specific antigen (PSA)-based prostate cancer (PCa) screening on quality-adjusted life years using 11-yr follow-up data from the European Randomized Study of Screening for Prostate Cancer (ERSPC) extrapolated by the Microsimulation Screening Analysis (MISCAN). ERSPC data now matured to 21 yr of follow-up. ObjectiveTo provide an overview of the effect of PSA-based screening on tumour characteristics and PCa treatment using long-term, detailed, empirical ERSPC data. Design, setting, and participantsMen were included from the ERSPC Rotterdam who were randomised to a PSA-based screening (S) or control (C) arm. Outcome measurements and statistical analysisWe assessed the effects of PSA-based screening on the number of PCa diagnoses, tumour characteristics, treatments, and cumulative incidence of disease progression. We also evaluated the changes in tumour characteristics and treatments over time for both study arms. Results and limitationsAmong PCa patients in the S-arm, fewer patients were diagnosed with advanced tumour stages (T3/T4: 12% vs 23%; relative risk [RR] = 0.50; 95% confidence interval [CI] 0.44–0.57), less disease progression was observed, and less secondary treatment (30% vs 48%; RR = 0.61; 95% CI 0.57–0.66; p < 0.001) and less palliative treatment were needed (21% vs 55%; RR = 0.38; 95% CI 0.35–0.42) than among those in the C-arm. This was at the cost of overdiagnosis and increased local treatments (eg, radical prostatectomy: 32% vs 14%; RR = 2.18; 95% CI 1.92–2.48). Over time, the number of local treatments decreased, whereas expectant management strategies increased. The RRs of treatments were slightly different from those of the MISCAN. ConclusionsAfter 21 yr of follow-up, empirical data of the ERSPC showed that PSA-based screening reduces advanced PCa stages, disease progression, and extensive treatments at the cost of more overdiagnosis and probably more overtreatment. Our data showed reduced local treatments and increased expectant management strategies over time. Patient summaryProstate-specific antigen–based screening reduces the number of invasive prostate cancer treatments needed, however, at the cost of more overdiagnosis and probably more overtreatment. Limiting these costs remains crucial to benefit optimally from prostate cancer screening.

PROSTATE CANCER SCREENING USING THE PROSTATE-SPECIFIC ANTIGEN (PSA) TEST

We aimed to conduct a systematic review and meta-analysis on published literature extracted from PubMed/Medline, Google scholar, and Cochrane library. The results of the European Randomized Study of Screening for Prostate Cancer (ERSPC) trial showed a statistically significant 29% prostate cancer mortality reduction for the men screened in the intervention arm and a 23% negative impact on the life-years gained because of quality of life. However, alternative prostate-specific antigen (PSA) screening strategies for the population may exist, optimizing the effects on mortality reduction, quality of life, over diagnosis, and costs.

Relationship Between Baseline Prostate-specific Antigen on Cancer Detection and Prostate Cancer Death: Long-term Follow-up from the European Randomized Study of Screening for Prostate Cancer

Relationship Between Baseline Prostate-specific Antigen on Cancer Detection and Prostate Cancer Death: Long-term Follow-up from the European Randomized Study of Screening for Prostate Cancer

A Detailed Evaluation of the Effect of Prostate-specific Antigen–based Screening on Morbidity and Mortality of Prostate Cancer: 21-year Follow-up Results of the Rotterdam Section of the European Randomised Study of Screening for Prostate Cancer

A Detailed Evaluation of the Effect of Prostate-specific Antigen–based Screening on Morbidity and Mortality of Prostate Cancer: 21-year Follow-up Results of the Rotterdam Section of the European Randomised Study of Screening for Prostate Cancer

MiR-20b-5p is a novel biomarker for detecting prostate cancer.

Prostate cancer (PCa) is the second most frequently diagnosed solid tumor and the fifth leading cause of cancer mortality among men worldwide. The prostate specific antigen (PSA) test for PCa remains controversial. Therefore, the development of more effective non-invasive biomarkers for PCa is necessary. The present study evaluated the diagnostic value of microRNA (miR)-20b-5p in PCa. Tissue miR-20b-5p expression levels and their correlation with clinical parameters were assessed using The Cancer Genome Atlas (TCGA) datasets, and the diagnostic value of the miR-20b-5p expression levels in PCa tissues was assessed using receiver operating characteristic curve analysis. Reverse transcription-quantitative PCR (RT-qPCR) was used to assess the relative expression levels of miR-20b-5p in PCa tissues compared with benign prostate hyperplasia (BPH) tissues. In addition, miR-20b-5p expression levels in PCa cell lines and non-tumorigenic prostate epithelial cells were compared. In this study, exosomes were extracted from the prostatic fluid as a source of liquid biopsy for the detection of PCa. The prostatic fluid exosomal miR-20b-5p expression levels between patients with PCa and the biopsy-negative patients were compared, and the diagnostic efficiency of prostatic fluid exosomal miR-20b-5p expression levels in PCa was compared with PSA and with the European Randomized Study of Screening for Prostate Cancer (ERSPC) risk calculator. The mechanism by which miR-20b-5p may function in PCa was assessed using bioinformatic analysis and validation experiments. miR-20b-5p was expressed at a markedly higher level in PCa tissues compared with normal prostate tissues with high diagnostic efficiency (area under the curve: 0.826). The expression levels of miR-20b-5p were also significantly higher in PCa tissues compared with BPH tissues; similarly, miR-20b-5p was more highly expressed in PCa cells compared with non-tumorigenic prostate epithelial cells. Prostatic fluid exosomal miR-20b-5p expression levels in patients with PCa were significantly higher compared with confirmed to be biopsy-negative, and the diagnostic performance of miR-20b-5p was superior to PSA and ERSPC risk calculator. The results of RT-qPCR and western blotting following transfection of DU145 cells with miR-20b-5p mimics and inhibitor showed that miR-20b-5p reduced the expression of retinoblastoma-associated protein 1 (RB1). Therefore, RB1 may be a significant target gene for miR-20b-5p. In conclusion, the present study demonstrated that miR-20b-5p was upregulated in PCa at the tissue and cellular levels, as well as in prostatic fluid exosomes. Therefore, miR-20b-5p may be a promising early diagnostic biomarker for PCa and an important tool to guide the decision-making of prostate biopsy.

Detailed Evaluation of Androgen Deprivation Overtreatment in Prostate Cancer Patients Compared to the European Association of Urology Guidelines Using Long-term Data from the European Randomised Study of Screening for Prostate Cancer Rotterdam

Detailed Evaluation of Androgen Deprivation Overtreatment in Prostate Cancer Patients Compared to the European Association of Urology Guidelines Using Long-term Data from the European Randomised Study of Screening for Prostate Cancer Rotterdam

MP43-08 ACTIVE SURVEILLANCE FOR PROSTATE CANCER: UPTAKE OVER TIME AND THE IMPACT OF AN ORGANIZED PROTOCOL

MP43-08 ACTIVE SURVEILLANCE FOR PROSTATE CANCER: UPTAKE OVER TIME AND THE IMPACT OF AN ORGANIZED PROTOCOL

Improving the Early Detection of Clinically Significant Prostate Cancer in Men in the Challenging Prostate Imaging-Reporting and Data System 3 Category

Improving the Early Detection of Clinically Significant Prostate Cancer in Men in the Challenging Prostate Imaging-Reporting and Data System 3 Category

Predictors of clinically significant prostate cancer in biopsy-naïve and prior negative biopsy men with a negative prostate MRI: improving MRI-based screening with a novel risk calculator.

Purpose:A pre-biopsy decision aid is needed to counsel men with a clinical suspicion for clinically significant prostate cancer (csPCa), despite normal prostate magnetic resonance imaging (MRI).Methods:A risk calculator (RC) for csPCa (International Society of Urological Pathology grade group (ISUP) ⩾ 2) presence in men with a negative-MRI (Prostate Imaging–Reporting and Data System (PI-RADS) ⩽ 2) was developed, and its performance was compared with RCs of the European Randomized Study of Screening for Prostate Cancer (ERSPC), Prostate Biopsy Collaborative Group (PBCG), and Prospective Loyola University mpMRI (PLUM). All biopsy-naïve and prior negative biopsy men with a negative-MRI followed by systematic prostate biopsy were included from October 2015 to September 2021. The RC was developed using multivariable logistic regression with the following parameters: age (years), family history of PCa (first- or second-degree family member), ancestry (African Caribbean/other), digital rectal exam (benign/malignant), MRI field strength (1.5/3.0 Tesla), prior negative biopsy status, and prostate-specific antigen (PSA) density (ng/ml/cc). Performance of RCs was compared using receiver operating characteristic (ROC) curve analysis.Results:A total of 232 men were included for analysis, of which 18.1% had csPCa. Parameters associated with csPCa were family history of PCa (p < 0.0001), African Caribbean ancestry (p = 0.005), PSA density (p = 0.002), prior negative biopsy (p = 0.06), and age at biopsy (p = 0.157). The area under the curve (AUC) of the developed RC was 0.76 (95% CI 0.68–0.85). This was significantly better than the RCs of the ERSPC (AUC: 0.59; p = 0.001) and PBCG (AUC: 0.60; p = 0.002), yet similar to PLUM (AUC: 0.69; p = 0.09).Conclusion:The developed RC (Prostate Biopsy Cohort Amsterdam (‘PROBA’ RC), integrated predictors for csPCa at prostate biopsy in negative-MRI men and outperformed other widely used RCs. These findings require external validation before introduction in daily practice.

An analysis of three different prostate cancer risk calculators applied prior to prostate biopsy: A Turkish cohort validation study.

The study aimed to investigate the best-performing of three risk calculators (RCs) for the Turkish population in predicting cancer-free status and high-risk prostate cancer (PCa) in patients undergoing transrectal ultrasound-guided prostate biopsy. The electronic medical records of 527 patients who underwent prostate biopsy for the first time due to PSA of 0.3-50ng/dl and/or cancer suspicion at digital rectal examination (DRE) between January 2017 and December 2020 were retrieved retrospectively. The predictive power of the RCs in the biopsy and the surgical cohort was calculated by two urologists using European Randomised Study of Screening for Prostate Cancer (ERSPC) RC, the North American Prostate Cancer Prevention Trial-RC (PCPT-RC), and the Prostate Biopsy Collaborative Group (PBCG)-RC. All three RCs were successful in predicting PCa and high-risk disease at ROC analysis (p<0.0001). Of these three nomograms, PBCG-RC outperformed PCPT-RC 2.0 and ERSPC-RH in predicting benign pathology outcomes at biopsy. A better performance of PBCG-RC was also observed in terms of prediction of high-risk disease at biopsy. Using any of the available RCs prior to biopsy is of greater assistance to prostate-specific antigen and DRE than examination alone. The study results show that PBCG-RC performed before biopsy has a higher predictive power than the other two RCs.

Predicting high-grade prostate cancer at initial biopsy: clinical performance of the ExoDx (EPI) Prostate Intelliscore test in three independent prospective studies

BackgroundThe ability to discriminate indolent from clinically significant prostate cancer (PC) at the initial biopsy remains a challenge. The ExoDx Prostate (IntelliScore) (EPI) test is a noninvasive liquid biopsy that quantifies three RNA targets in urine exosomes. The EPI test stratifies patients for risk of high-grade prostate cancer (HGPC; ≥ Grade Group 2 [GG] PC) in men ≥ 50 years with equivocal prostate-specific antigen (PSA) (2–10 ng/mL). Here, we present a pooled meta-analysis from three independent prospective-validation studies in men presenting for initial biopsy decision.MethodsPooled data from two prospective multi-site validation studies and the control arm of a clinical utility study were analyzed. Performance was evaluated using the area under the receiver-operating characteristic curve (AUC), negative predictive value (NPV), positive predictive value (PPV), sensitivity, and specificity for discriminating ≥ GG2 from GG1 and benign pathology.ResultsThe combined cohort (n = 1212) of initial-biopsy subjects had a median age of 63 years and median PSA of 5.2 ng/mL. The EPI AUC (0.70) was superior to PSA (0.56), Prostate Cancer Prevention Trial Risk Calculator (PCPT-RC) (0.62), and The European Randomized Study of Screening for Prostate Cancer (ERSPC) (0.59), (all p-values <0.001) for discriminating GG2 from GG1 and benign histology. The validated cutoff of 15.6 would avoid 23% of all prostate biopsies and 30% of “unnecessary” (benign or Gleason 6/GG1) biopsies, with an NPV of 90%.ConclusionsEPI is a noninvasive, easy-to-use, urine exosome–RNA assay that has been validated across 3 independent prospective multicenter clinical trials with 1212 subjects. The test can discriminate high-grade (≥GG2) from low-grade (GG1) cancer and benign disease. EPI effectively guides the biopsy-decision process independent of PSA and other standard-of-care factors.

PD13-04 PROSTATE CANCER SPECIFIC MORTALITY IN THE ERSPC TRIAL: WHAT IS THE ROLE OF SCREENING RESULT AND ADHERENCE

PD13-04 PROSTATE CANCER SPECIFIC MORTALITY IN THE ERSPC TRIAL: WHAT IS THE ROLE OF SCREENING RESULT AND ADHERENCE

Enhancement of prostate cancer diagnosis by machine learning techniques: an algorithm development and validation study.

To investigate the value of machine learning(ML) in enhancing prostate cancer(PCa) diagnosis. Consecutive systematic prostate biopsies performed from Jan 2003-June 2017 were used as the training cohort, and prospective biopsies performed from July 2017-November 2019 were used as validation cohort. Men were included if PSA was 0.4-50 ng/mL, and information of digital rectal examination (DRE), Transrectal ultrasound(TRUS) prostate volume, TRUS abnormality were known. Clinically significant PCa(csPCa) was defined as Gleason 3 + 4 or above cancers. Area-under-curve (AUC) of receiver-operating characteristics (ROC) was compared between PSA, PSA density, European Randomized Study of Screening for Prostate Cancer (ERSPC) risk calculator (ERSPC-RC), and various ML techniques using PSA, DRE and TRUS information. ML techniques used included XGBoost, LightGBM, Catboost, Support vector machine (SVM), Logistic regression (LR), and Random Forest (RF), where cost sensitive learning was applied. Training and validation cohorts included 3881 and 778 consecutive men, respectively. RF model performed better than other ML techniques and PSA, PSA density and ERSPC-RC for prediction of PCa or csPCa in the validation cohort. In csPCa prediction, AUC of PSA, PSA density, ERSPC-RC and RF was 0.71, 0.80, 0.83 and 0.88 respectively. At 90-95% sensitivity for csPCa, RF model achieved a negative predictive value (NPV) of 97.5-98.0% and avoided 38.3-52.2% unnecessary biopsies. Decision curve analyses (DCA) showed RF model provided net clinical benefit over PSA, PSA density and ERSPC-RC. By using the same clinical parameters, ML techniques performed better than ERSPC-RC or PSA density in csPCa predictions, and could avoid up to 50% unnecessary biopsies.