Development and Validation of Interpretable Machine Learning Models for Clinically Significant Prostate Cancer Diagnosis in Patients With Lesions of PI-RADS v2.1 Score ≥3.

BACKGROUND: For patients with PI-RADS v2.1 ≥ 3, prostate biopsy is strongly recommended. Due to the unsatisfactory positive rate of biopsy, improvements in clinically significant prostate cancer (csPCa) risk assessments are required. PURPOSE: To develop and validate machine learning (ML) models based on clinical and imaging parameters for csPCa detection in patients with PI-RADS v2.1 ≥ 3. STUDY TYPE: Retrospective. SUBJECTS: One thousand eighty-three patients with PI-RADS v2.1 ≥ 3, randomly split into training (70%, N = 759) and validation (30%, N = 324) datasets, and 147 patients enrolled prospectively for testing. FIELD STRENGTH/SEQUENCE: 3.0 T scanners/T2-weighted fast spin echo sequence and DWI with diffusion-weighted single-shot gradient echo planar imaging sequence. ASSESSMENT: The factors evaluated for csPCa detection were age, prostate specific antigen, prostate volume, and the diameter and location of the index lesion, PI-RADSv2.1. Five ML models for csPCa detection were developed: logistic regression (LR), extreme gradient boosting, random forest (RF), decision tree, and support vector machines. The csPCa was defined as Gleason grade ≥2. STATISTICAL TESTS: Univariable and multivariable LR analyses to identify parameters associated with csPCa. Area under the receiver operating characteristic curve (AUC), Brier score, and DeLong test were used to assess and compare the csPCa diagnostic performance with the LR model. The significance level was defined as 0.05. RESULTS: The RF model exhibited the highest AUC (0.880-0.904) and lowest Brier score (0.125-0.133) among the ML models in the validation and testing cohorts, however, there was no difference when compared to the LR model (P = 0.453 and 0.548). The sensitivity and negative predictive values in the validation and testing cohorts were 93.8%-97.6% and 82.7%-95.1%, respectively, at a threshold of 0.450 (99% sensitivity of the RF model). DATA CONCLUSION: The RF model might help for assessing the risk of csPCa and preventing overdiagnosis and unnecessary biopsy for men with PI-RADSv2.1 ≥ 3. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2.

A novel biopsy scheme for prostate cancer: targeted and regional systematic biopsy.

PURPOSE: To explore a novel biopsy scheme for prostate cancer (PCa), and test the detection rate and pathological agreement of standard systematic (SB) + targeted (TB) biopsy and novel biopsy scheme. METHODS: Positive needles were collected from 194 patients who underwent SB + TB (STB) followed by radical prostatectomy (RP). Our novel biopsy scheme, targeted and regional systematic biopsy (TrSB) was defined as TB + regional SB (4 SB-needles closest to the TB-needles). The McNemar test was utilized to compare the detection rate performance for clinical significant PCa (csPCa) and clinical insignificant PCa (ciPCa). Moreover, the accuracy, positive predictive value (PPV) and negative predictive value (NPV) were investigated. The agreement between the different biopsy schemes grade group (GG) and RP GG were assessed. The concordance between the biopsy and the RP GG was evaluated using weighted κ coefficient analyses. RESULTS: In this study, the overall detection rate for csPCa was 83.5% (162 of 194) when SB and TB were combined. TrSB showed better NPV than TB (97.0% vs. 74.4%). Comparing to STB, the TB-detection rate of csPCa had a significant difference (p < 0.01), while TrSB showed no significant difference (p > 0.999). For ciPCa, the overall detection rate was 16.5% (32 of 194). TrSB showed better PPV (96.6% vs. 83.3%) and NPV (97.6% vs. 92.9%) than TB. Comparing to STB, the detection rate of both schemes showed no significant difference (p = 0.077 and p = 0.375). All three schemes GG showed poor agreement with RP GG (TB: 43.3%, TrSB: 46.4%, STB: 45.9%). Using weighted κ, all three schemes showed no difference (TB: 0.48, TrSB: 0.51, STB: 0.51). In our subgroup analysis (PI-RADS = 4/5, n = 154), all three schemes almost showed no difference (Weighted κ: TB-0.50, TrSB-0.51, STB-0.50). CONCLUSION: Our novel biopsy scheme TrSB (TB + 4 closest SB needles) may reduce 8 cores of biopsy compared with STB (standard SB + TB), which also showed better csPCa detection rate than TB only, but the same as STB. The pathological agreement between three different biopsy schemes (TB/TrSB/STB) GG and RP GG showed no difference.

[Diagnostic efficacy of targeted biopsy combined with regional systematic biopsy in prostate cancer in patients with PI-RADS 4-5].

OBJECTIVE: To investigate the diagnostic efficacy of targeted biopsy combined with regional systematic biopsy in prostate cancer (PCa) in patients with prostate imaging reporting and data system v2.1 (PI-RADS v2.1) 4-5. METHODS: From January 2023 to October 2023, patients who underwent prostate biopsy for the first time with total prostate specific antigen (tPSA) ≤ 20 ng/mL and had a multi-parametric magnetic resonance imaging (mpMRI) PI-RADS of 4-5 in Peking University First Hospital were prospectively collected. All the patients underwent transrectal ultrasound-guided cognitive fusion targeted biopsy (3 cores) followed by systematic biopsy (12 cores). Various hypothetical biopsy schemes were defined based on different biopsy sites. The detection effectiveness of targeted biopsy combined with regional systematic biopsy and other biopsy schemes for prostate cancer were compared using Cochran's Q and McNemar tests. RESULTS: A total of 255 patients were enrolled, of whom 204 (80.0%) were detected with prostate adenocarcinoma and 187 (73.3%) were clinically significant with prostate cancer (csPCa). The detection rate of PCa with targeted biopsy was significantly lower than that of targeted biopsy combined with 12-core system biopsy (77.3% vs. 80.0%, P=0.016), and 71.4% (5/7) of the missed patients was csPCa. There was no significant difference in the detection rate between targeted biopsy combined with 4-core regional system biopsy and 12-core system biopsy (P>0.999), and 1 case of csPCa and clinically insignificant prostate cancer (cisPCa) were missed. There was no significant difference in the detection rate of PCa between targeted combined regional system biopsy and targeted combined lateral or traditional 6-core system biopsy and the number of cores were reduced. Missed diagnosis of targeted biopsy was correlated with the maximum diameter of the lesion (OR=0.086, 95%CI: 0.013-0.562, P=0.010). For the patients with PI-RADS 5, only 1 case of PCa was missed in 122 cases by targeted biopsy alone. For patients with PI-RADS 4, 6 PCa cases were missed among the 133 patients with targeted biopsy alone, and 1 case of csPCa and cisPCa were missed by targeted biopsy combined with regional system biopsy. The statistics of positive core counts for different biopsy schemes indicated that targeted combined regional systematic biopsy had a higher proportion of positive cores second only to targeted biopsy alone. CONCLUSION: Targeted biopsy combined with regional systematic biopsy has high diagnostic efficacy in patients with PI-RADS 4-5 and can be considered as one of the improved schemes for combined biopsy. Targeted biopsy alone is also a feasible option for patients for patients with a PI-RADS score of 5.

[Predictive effect of the dual-parametric MRI modified maximum diameter of the lesions with PI-RADS 4 and 5 on the clinically significant prostate cancer].

OBJECTIVE: To assess the rationality of the maximum lesion diameter of 15 mm in prostate imaging reporting and data system (PI-RADS) as a criterion for upgrading a lesion from category 4 to 5 and improve it to enhance the prediction of clinically significant prostate cancer (csPCa). METHODS: In this study, the patients who underwent prostate magnetic resonance imaging (MRI) and prostate biopsy at Peking University First Hospital from 2019 to 2022 as a development cohort, and the patients in 2023 as a validation cohort were reviewed. The localization and maximum diameter of the lesion were fully evaluated. The area under the curve (AUC) and the cut-off value of the maximum diameter of the lesion to predict the detection of csPCa were calculated from the receiver operating characteristics (ROC) curve. Confounding factors were reduced by propensity score matching (PSM). Diagnostic efficacy was compared in the validation cohort. RESULTS: Of the 589 patients in the development cohort, 358 (60.8%) lesions were located in the peripheral zone and 231 (39.2%) were located in the transition zone, and 496 (84.2%) patients detected csPCa. The median diameter of the lesions in the peripheral zone was smaller than that in the transition zone (14 mm vs. 19 mm, P < 0.001). In the ROC analysis of the maximal diameter on the csPCa prediction, there was no statistically significant difference between the peri-pheral zone (AUC=0.709) and the transition zone (AUC=0.673, P=0.585), and the cut-off values were calculated to be 11.5 mm for the peripheral zone and 16.5 mm for the migrating zone. By calcula-ting the Youden index for the cut-off values in the validation cohort, we found that the categorisation by lesion location led to better predictive results. Finally, the net reclassification index (NRI) was 0.170. CONCLUSION: 15 mm as a criterion for upgrading the PI-RADS score from 4 to 5 is reasonable but too general. The cut-off value for peripheral zone lesions is smaller than that in transitional zone. In the future consideration could be given to setting separate cut-off values for lesions in different locations.

How Many Targeted Biopsy Cores are Needed for Clinically Significant Prostate Cancer Detection during Transperineal Magnetic Resonance Imaging Ultrasound Fusion Biopsy?

PURPOSE: In this study we determined the optimal number of transperineal magnetic resonance imaging ultrasound fusion targeted biopsy cores per lesion needed for the detection of clinically significant prostate cancer. MATERIALS AND METHODS: A total of 101 patients with at least 1 lesion with a PI-RADS® (Prostate Imaging Reporting and Data System) score of 3 or greater were recruited prospectively. At least 4 transperineal magnetic resonance imaging ultrasound fusion targeted biopsy cores per lesion were performed, followed by systematic biopsy. The Kappa test was used to evaluate the consistency of the clinically significant prostate cancer detection rate between different targeted biopsy cores and 4 or more cores, which was regarded as reference standard. RESULTS: In the total cohort of 101 patients 49 (48.5%), 55 (54.5%) and 57 (56.4%) were diagnosed with clinically significant prostate cancer by systematic biopsy, targeted biopsy or targeted biopsy plus systematic biopsy, respectively. As for the total of 161 lesions, the clinically significant prostate cancer detection rate based on 1, 2, 3, or 4 or more targeted biopsy cores was made in 27.3%, 32.9%, 37.3% and 39.1%, respectively. Three cores showed great consistency with 4 or more cores in clinically significant prostate cancer detection rate (Kappa coefficient of 0.961, p <0.001) with a sensitivity of 95.2% (95% CI 85.8-98.8), and only missed 3 lesions harboring clinically significant prostate cancer. Similar results were obtained in cases with PI-RADS 3 or 4 or maximal diameter of less than 1.5 cm. CONCLUSIONS: Three targeted biopsies per lesion were suitable during transperineal magnetic resonance imaging ultrasound fusion biopsy, especially for lesions of PI-RADS 3 or 4, or small lesions (maximal diameter less than 1.5 cm), which may help to tailor targeted prostate biopsy procedures.

ZNF471 Interacts with BANP to Reduce Tumour Malignancy by Inactivating PI3K/AKT/mTOR Signalling but is Frequently Silenced by Aberrant Promoter Methylation in Renal Cell Carcinoma.

Background: Renal cell carcinoma (RCC) is one of the most common malignant tumours of the urinary system. However, the aetiology and pathogenesis of RCC remain unclear. The C2H2 zinc finger protein (ZNF) family is the largest transcriptional regulatory factor family found in mammals, and Krüppel-associated box domain-containing zinc finger proteins (KRAB-ZFPs) constitute the largest subfamily of the C2H2 zinc finger protein family and play an important role in the occurrence and development of tumours. The aim of this study was to explore the role of abnormal methylation of ZNF471 in the development of renal carcinoma. Methods: In this study, we first used the TCGA and EWAS Data Hub databases to analyse the expression and methylation levels of ZNF471 in renal carcinoma tissues and adjacent normal tissues. Second, we collected samples of renal cancer and adjacent normal tissues at Peking University First Hospital to investigate the expression and methylation level of ZNF471 in renal cancer tissues and the relationships between these levels and the clinicopathological features and prognosis of patients with renal cancer. Next, we investigated the effects of ZNF471 on the proliferation, metastasis, cell cycle progression, and apoptosis of renal cell carcinoma cells by cell biology experiments. Finally, we elucidated the underlying molecular mechanisms of ZNF471 in renal cell carcinoma by transcriptome sequencing, bioinformatics analysis and molecular biology experiments. Results: The expression of ZNF471 in renal carcinoma tissues and cell lines was significantly lower than that in adjacent normal tissues and cell lines due to abnormal promoter CpG methylation. Furthermore, the expression of ZNF471 in renal carcinoma tissues was negatively correlated with tumour stage and grade in patients with renal carcinoma. The results of the cell biology experiments showed that ZNF471 could significantly inhibit the proliferation, migration and cell cycle progression of renal cell carcinoma cells and promote apoptosis in these cells. In addition, ZNF471 could interact with BANP and suppress the malignant phenotype of RCC by inactivating the PI3K/AKT/mTOR signalling pathway. Conclusions: As an important tumour suppressor, ZNF471 can interact with BANP in renal cancer cells and inhibit the activation of the PI3K/AKT/mTOR signalling pathway, thereby inhibiting the occurrence and development of renal cancer.

PP2A inhibition causes synthetic lethality in BRCA2-mutated prostate cancer models via spindle assembly checkpoint reactivation.

Mutations in the BRCA2 tumor suppressor gene have been associated with an increased risk of developing prostate cancer. One of the paradoxes concerning BRCA2 is the fact that its inactivation affects genetic stability and is deleterious for cellular and organismal survival, while BRCA2-mutated cancer cells adapt to this detriment and malignantly proliferate. Therapeutic strategies for tumors arising from BRCA2 mutations may be discovered by understanding these adaptive mechanisms. In this study, we conducted forward genetic synthetic viability screenings in Caenorhabditis elegans brc-2 (Cebrc-2) mutants and found that Ceubxn-2 inactivation rescued the viability of Cebrc-2 mutants. Moreover, loss of NSFL1C, the mammalian ortholog of CeUBXN-2, suppressed the spindle assembly checkpoint (SAC) activation and promoted the survival of BRCA2-deficient cells. Mechanistically, NSFL1C recruited USP9X to inhibit the polyubiquitination of AURKB and reduce the removal of AURKB from the centromeres by VCP, which is essential for SAC activation. SAC inactivation is common in BRCA2-deficient prostate cancer patients, but PP2A inhibitors could reactivate the SAC and achieve BRCA2-deficient prostate tumor synthetic lethality. Our research reveals the survival adaptation mechanism of BRCA2-deficient prostate tumor cells and provides different angles for exploring synthetic lethal inhibitors in addition to targeting DNA damage repair pathways.

Novel sampling scheme with reduced cores in men with multiparametric MRI-visible lesions undergoing prostate biopsy.

PURPOSE: To investigate the effects of various prostate biopsy protocols with reduced cores on the detection of clinically significant prostate cancer (csPCa) in individuals with MRI-visible lesions (Prostate Imaging Reporting and Data System ≥ 3). METHODS: A total of 464 patients with MRI-visible lesions were recruited. All patients underwent two or more targeted biopsies (TB) and systematic biopsies (SB). Several hypothetical biopsy schemes were set-up: TB alone, TB+ipsilateral SB, TB+contralateral SB, TB+SB of the targeted sector (TB+t-SB), and TB+SB of the non-targeted sector (TB+n-SB). A subgroup analysis of patients with multiple MRI-visible lesions was performed. The standard of reference was defined as TB+SB. McNemar test was used to compare csPCa detection rates between various sampling schemes. RESULTS: The detection rates for prostate cancer and csPCa were 72.8% (338 of 464) and 62.1% (288 of 464), respectively. There were 8.0%, 0.3%, 6.3%, 1.0%, and 4.5% cases in which TB alone, TB+ipsilateral SB, TB+contralateral SB, TB+t-SB, and TB+n-SB would have missed csPCa, respectively. All hypothetical schemes, with the exception of TB+contralateral SB (p = 0.063), significantly outperformed TB alone in terms of csPCa detection (p < 0.05). As for the multi-focus cohort, which included 48 cases, none of the non-index lesions had a higher Gleason grade than the index lesions within the same patients. CONCLUSION: TB+ipsilateral SB might be the optimal biopsy scheme for detecting csPCa. As for the multi-focus cohort, the biopsy of the non-index lesions provided limited pathological information.

A prospective study of the prostate health index density and multiparametric magnetic resonance imaging in diagnosing clinically significant prostate cancer.

PURPOSE: To evaluate the predictive performance of the prostate health index (PHI) and PHI density (PHID), for clinically significant prostate cancer (csPCa) in patients with a PI-RADS score ≤3. MATERIALS AND METHODS: Patients tested for total prostate-specific antigen (tPSA, ≤100 ng/mL), free PSA (fPSA), and p2PSA at Peking University First Hospital were prospectively enrolled. Possible predictive factors of csPCa were analyzed using the receiver operating characteristic (ROC) curve. Results were expressed as area under the curve (AUC) with 95% confidence intervals (CI). The cutoff values of PHI and PHID were determined. RESULTS: We enrolled 222 patients in this study. The prevalence of csPCa in the PI-RADS ≤3 subgroup (n=89) was 22.47% (20/89). Age, tPSA, F/T, prostate volume, PSA density, PHI, PHID, and PI-RADS score were significantly associated with csPCa. PHID (AUC: 0.829 [95% CI: 0.717-0.941]) was the best predictor of csPCa. PHID >0.956 was set as the threshold of suspicious csPCa with a sensitivity of 85.00% and a specificity of 73.91%, avoiding 94.44% of unnecessary biopsies but missing 15.00% csPCa. A threshold of PHI ≥52.83 showed the same sensitivity but a rather lower specificity of 65.22% that avoided 93.75% of unnecessary biopsies. CONCLUSIONS: PHI and PHID have the best predictive performance of csPCa in patients with PI-RADS score ≤3. A threshold value of PHID ≥0.956 may be used as the criterion for biopsy in these patients.

Predictive model containing PI-RADS v2 score for postoperative seminal vesicle invasion among prostate cancer patients.

BACKGROUND: Seminal vesicle invasion (SVI) is considered to be one of most adverse prognostic findings in prostate cancer, affecting the biochemical progression-free survival and disease-specific survival. Multiparametric magnetic resonance imaging (mpMRI) has shown excellent specificity in diagnosis of SVI, but with poor sensitivity. The aim of this study is to create a model that includes the Prostate Imaging Reporting and Data System version 2 (PI-RADS v2) score to predict postoperative SVI in patients without SVI on preoperative mpMRI. METHODS: A total of 262 prostate cancer patients without SVI on preoperative mpMRI who underwent radical prostatectomy (RP) at our institution from January 2012 to July 2019 were enrolled retrospectively. The prostate-specific antigen levels in all patients were <10 ng/mL. Univariate and multivariate logistic regression analyses were used to assess factors associated with SVI, including the PI-RADS v2 score. A regression coefficient-based model was built for predicting SVI. The receiver operating characteristic curve was used to assess the performance of the model. RESULTS: SVI was reported on the RP specimens in 30 patients (11.5%). The univariate and multivariate analyses revealed that biopsy Gleason grade group (GGG) and the PI-RADS v2 score were significant independent predictors of SVI (all P<0.05). The area under the curve of the model was 0.746 (P<0.001). The PI-RADS v2 score <4 and Gleason grade <8 yielded only a 1.8% incidence of SVI with a high negative predictive value of 98.2% (95% CI, 93.0-99.6%). CONCLUSIONS: The PI-RADS v2 score <4 in prostate cancer patients with prostate-specific antigen level <10 ng/mL is associated with a very low risk of SVI. A model based on biopsy Gleason grade and PI-RADS v2 score may help to predict SVI and serve as a tool for the urologists to make surgical plans.

Cutoff Values of Prostate Imaging Reporting and Data System Version 2.1 Score in Men With Prostate-specific Antigen Level 4 to 10 ng/mL: Importance of Lesion Location.

INTRODUCTION: Multiparametric magnetic resonance imaging (mpMRI) has been shown to have a good performance in predicting cancer among patients with a prostate-specific antigen (PSA) level of 4 to 10 ng/mL. However, lesion location on mpMRI has never been separately considered. PATIENTS AND METHODS: Patients with PSA level of 4 to 10 ng/mL were prospectively enrolled and underwent transrectal ultrasound-guided prostate biopsy. Patient information was collected, and logistic regression analysis was performed to determine the predictive factors of clinically significant prostate cancer (csPCa). Patients were grouped by lesion location to determine the Prostate Imaging Reporting and Data System (PI-RADS) v2.1 cutoff value in predicting csPCa. RESULTS: Among 222 patients, 121 were diagnosed with PCa and 92 had csPCa. Age, prostate volume, PSA density, location (peripheral zone, csPCa only), and PI-RADS v2.1 score were correlated with PCa and csPCa, and PI-RADS v2.1 score was the best predictor. A PI-RADS v2.1 score of 4 was the best cutoff value for predicting csPCa in patients with lesions only in the transitional zone with respect to the Youden index (0.5896) and negative predictive value (93.10%) with acceptable sensitivity (81.82%) and specificity (77.14%). An adjustment of the cutoff value to 3 for lesions in the peripheral zone would increase the negative predictive value (92.00%) and decrease the false negative rate (2.90%) with an acceptable sensitivity (97.10%) and specificity (30.67%). CONCLUSION: PI-RADS v2.1 score is an effective predictor of csPCa in patients with PSA levels of 4 to 10 ng/mL. Patients with transitional zone or peripheral zone lesions should undergo biopsy if the PI-RADS v2.1 score is ≥ 4 or ≥ 3, respectively.

Can fewer transperineal systematic biopsy cores have the same prostate cancer detection rate as of magnetic resonance imaging/ultrasound fusion biopsy?

BACKGROUND: Due to the discomfort and incidence of complications increases with the increasing number of biopsy cores, the protocol of prostate biopsy has been promoted from systematic biopsy (SB) to targeted biopsy (TB) in many studies. However, the optimal prostate sampling scheme to balance the incidence of biopsy complications and accuracy of biopsy remains controversial. Our objective is to explore an optimal prostate cancer (PCa) sampling scheme with fewer SB cores. METHODS: Patients with at least one lesion of Prostate Imaging Reporting and Data System ≥3 were prospectively enrolled. TB and SB were performed for each patient as reference. The hypothetical biopsy sampling schemes were TB only, SB only, and TB followed by SB of the nontargeted sector (TB+nSB). The PCa and clinically significant PCa (csPCa) detection rates and cores of the three hypothetical biopsy schemes were compared with TB+SB. RESULTS: Among 165 patients, 107 (64.8%) were diagnosed with PCa and 91 (55.2%) with csPCa via TB+SB. There were 54 (50.5%) and 42 (46.2%) magnetic resonance imaging (MRI) true negative cases and 53 (49.5%) and 49 (53.8%) false negative cases of nontargeted sectors among PCa and csPCa patients, respectively. The maximal cancer proportion in positive biopsy cases differed significantly between the true and false groups of these cohorts. There was no difference between TB+nSB and TB+SB for PCa or csPCa detection. CONCLUSIONS: The optimal sampling scheme TB+nSB with fewer SB cores showed same PCa and csPCa detection rates as that of standard TB+SB with MRI/ultrasound fusion biopsy.

Predictive model using prostate MRI findings can predict candidates for nerve sparing radical prostatectomy among low-intermediate risk prostate cancer patients.

BACKGROUND: In order to improve postoperative functional outcome, including urinary continence and erectile function, nerve sparing surgery is recommended for patients with clinically localized prostate cancer (PCa). However, due to poor diagnosis accuracy at the preoperative stage, upstaging occurs in a considerable proportion of patients. Multiparametric magnetic resonance imaging (mpMRI) and the Prostate Imaging Reporting and Data System version 2 (PI-RADS v2) have recently shown excellent performance in diagnosis and staging of PCa. The aim of this study was to develop a predictive model based on PI-RADS v2 for postoperative upstaging in patients with low-intermediate risk PCa. METHODS: The medical records of 314 patients with low-intermediate risk PCa [prostate-specific antigen (PSA) level ≤20 ng/mL, Gleason score (GS) <8, and clinical stage < T3] who underwent preoperative mpMRI and radical prostatectomy in the Department of Urology, Peking University First Hospital between January 2012 and July 2019 were reviewed retrospectively. Clinicopathological characteristics were collected. All MRI reports were done at our institution as part of routine clinical practice before prostate biopsy and there was no re-reporting occurred. Using PI-RADS v2, the mpMRI results were assigned to three groups: "negative", "suspicious", and "positive". Multivariate logistic regression analysis was used to assess factors associated with postoperative pathological upstaging, defined as the presence of pT3 at final pathology. A regression coefficient based model for predicting postoperative upstaging was constructed and internally validated using 1,000 bootstrap resamples. The performance of the model was assessed using the area under the receiver operating characteristic curve (AUC). With the optimal cutoff point the performance of the model was assessed through analysis of sensitivity, specificity, positive predictive value, and negative predictive value. RESULTS: Upstaging was observed in 119 (37.9%) patients. The univariate and multivariate analyses revealed that PSA density, biopsy Gleason grade group (GGG), and mpMRI findings were significantly independent predictors for postoperative upstaging (all P<0.05). A predictive model showing very favorable calibration characteristics and higher accuracy than the single variables was constructed (AUC =0.74; P<0.001). At the optimal cutoff point, the model demonstrated a sensitivity and negative predictive value of 87.4% and 87.0%, respectively. CONCLUSIONS: PI-RADS v2 assessment proved to be one of the most valuable predictors for postoperative upstaging in patients with low-intermediate risk PCa. The predictive model, based on PI-RADS v2 assessment, PSA density, and biopsy GGG, may help to select suitable candidates for nerve sparing radical prostatectomy among patients with low-intermediate risk PCa.