Dataset Information

Telomere-based risk models for the early diagnosis of clinically significant prostate cancer.

ABSTRACT:

Background

The objective of this study was to explore telomere-associated variables (TAV) as complementary biomarkers in the early diagnosis of prostate cancer (PCa), analyzing their application in risk models for significant PCa (Gleason score > 6).

Methods

As part of a larger prospective longitudinal study of patients with suspicion of PCa undergoing prostate biopsy according to clinical practice, a subgroup of patients (n = 401) with PSA 3-10 ng/ml and no prior biopsies was used to evaluate the contribution of TAV to discern non-significant PCa from significant PCa. The cohort was randomly split for training (2/3) and validation (1/3) of the models. High-throughput quantitative fluorescence in-situ hybridization was used to evaluate TAV in peripheral blood mononucleated cells. Models were generated following principal component analysis and random forest and their utility as risk predictors was evaluated by analyzing their predictive capacity and accuracy, summarized by ROC curves, and their clinical benefit with decision curves analysis.

Results

The median age of the patients was 63 years, with a median PSA of 5 ng/ml and a percentage of PCa diagnosis of 40.6% and significant PCa of 19.2%. Two TAV-based risk models were selected (TAV models 1 and 2) with an AUC ≥ 0.83 in the full study cohort, and AUC > 0.76 in the internal validation cohort. Both models showed an improvement in decision capacity when compared to the application of the PCPT-RC in the low-risk probabilities range. In the validation cohort, with TAV models 1 and 2, 33% /48% of biopsies would have been avoided losing 0/10.3% of significant PCa, respectively. The models were also tested and validated on an independent, retrospective, non contemporary cohort.

Conclusions

Telomere analysis through TAV should be considered as a new risk-score biomarker with potential to increase the prediction capacity of significant PCa in patients with PSA between 3-10 ng/ml.

SUBMITTER: Rubio Galisteo JM

PROVIDER: S-EPMC8012205 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundWith the widespread adoption of prostatic-specific antigen (PSA) screening, the detection rates of prostate cancer (PCa) have increased. Due to the low specificity and high false-positive rate of serum PSA levels, it was difficult to diagnose PCa accurately. To improve the diagnosis of PCa and clinically significant prostate cancer (CSPCa), we established novel models on the basis of the prostate health index (PHI) and multiparametric magnetic resonance imaging (mpMRI) in the Asian population.MethodsWe retrospectively collected the clinical indicators of patients with TPSA at 4-20 ng/ml. Furthermore, mpMRI was performed using a 3.0-T scanner and reported in the Prostate Imaging Reporting and Data System version 2.1 (PI-RADS). Univariable and multivariable logistic analyses were performed to construct the models. The performance of different models based on PSA derivatives, PHI derivatives, PI-RADS, and a combination of PHI derivatives and PI-RADS was evaluated.ResultsAmong the 128 patients, 47 (36.72%) patients were diagnosed with CSPCa and 81 (63.28%) patients were diagnosed with non-CSPCa. Of the 81 (63.28%) patients, 8 (6.25%) patients were diagnosed with Gleason Grade 1 PCa and 73 (57.03%) patients were diagnosed with non-PCa. In the analysis of the receiver operator characteristic (ROC) curves in TPSA 4-20 ng/ml, the multivariable model for PCa was significantly larger than that for the model based on the PI-RADS (p = 0.004) and that for the model based on the PHI derivatives (p = 0.031) in diagnostic accuracy. The multivariable model for CSPCa was significantly larger than that for the model based on the PI-RADS (p = 0.003) and was non-significantly larger than that for the model based on the PHI derivatives (p = 0.061) in diagnostic accuracy. For PCa in TPSA 4-20 ng/ml, a multivariable model achieved the optimal diagnostic value at four levels of predictive variables. For CSPCa in TPSA 4-20 ng/ml, the multivariable model achieved the optimal diagnostic value at a sensitivity close to 90% and 80%.ConclusionsThe models combining PHI derivatives and PI-RADS performed better in detecting PCa and CSPCa than the models based on either PHI or PI-RADS.

Project description:BackgroundThe introduction of multiparameter MRI and novel biomarkers has greatly improved the prediction of clinically significant prostate cancer (csPCa). However, decision-making regarding prostate biopsy and prebiopsy examinations is still difficult. We aimed to establish a quick and economic tool to improve the detection of csPCa based on routinely performed clinical examinations through an automated machine learning platform (AutoML).MethodsThis study included a multicenter retrospective cohort and two prospective cohorts with 4747 cases from 9 hospitals across China. The multimodal data, including demographics, clinical characteristics, laboratory tests, and ultrasound reports, of consecutive participants were retrieved using extract-transform-load tools. AutoML was applied to explore potential data processing patterns and the most suitable algorithm to build the Prostate Cancer Artificial Intelligence Diagnostic System (PCAIDS). The diagnostic performance was determined by the receiver operating characteristic curve (ROC) for discriminating csPCa from insignificant prostate cancer (PCa) and benign disease. The clinical utility was evaluated by decision curve analysis (DCA) and waterfall plots.ResultsThe random forest algorithm was applied in the feature selection, and the AutoML algorithm was applied for model establishment. The area under the curve (AUC) value in identifying csPCa was 0.853 in the training cohort, 0.820 in the validation cohort, 0.807 in the Changhai prospective cohort, and 0.850 in the Zhongda prospective cohort. DCA showed that the PCAIDS was superior to PSA or fPSA/tPSA for diagnosing csPCa with a higher net benefit for all threshold probabilities in all cohorts. Setting a fixed sensitivity of 95%, a total of 32.2%, 17.6%, and 26.3% of unnecessary biopsies could be avoided with less than 5% of csPCa missed in the validation cohort, Changhai and Zhongda prospective cohorts, respectively.ConclusionsThe PCAIDS was an effective tool to inform decision-making regarding the need for prostate biopsy and prebiopsy examinations such as mpMRI. Further prospective and international studies are warranted to validate the findings of this study.Trial registrationChinese Clinical Trial Registry ChiCTR2100048428. Registered on 06 July 2021.

Project description:PurposeTo establish machine learning(ML) models for the diagnosis of clinically significant prostate cancer (csPC) using multiparameter magnetic resonance imaging (mpMRI), texture analysis (TA), dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) quantitative analysis and clinical parameters and to evaluate the stability of these models in internal and temporal validation.MethodsThe dataset of 194 men was split into training (n = 135) and internal validation (n = 59) cohorts, and a temporal dataset (n = 58) was used for evaluation. The lesions with Gleason score ≥ 7 were defined as csPC. Logistic regression (LR), stepwise regression (SR), classical decision tree (cDT), conditional inference tree (CIT), random forest (RF) and support vector machine (SVM) models were established by combining mpMRI-TA, DCE-MRI and clinical parameters and validated by internal and temporal validation using the receiver operating characteristic (ROC) curve and Delong's method.ResultsEight variables were determined as important predictors for csPC, with the first three related to texture features derived from the apparent diffusion coefficient (ADC) mapping. RF, LR and SR models yielded larger and more stable area under the ROC curve values (AUCs) than other models. In the temporal validation, the sensitivity was lower than that of the internal validation (p < 0.05). There were no significant differences in specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV) and AUC (p > 0.05).ConclusionsEach machine learning model in this study has good classification ability for csPC. Compared with internal validation, the sensitivity of each machine learning model in temporal validation was reduced, but the specificity, accuracy, PPV, NPV and AUCs remained stable at a good level. The RF, LR and SR models have better classification performance in the imaging-based diagnosis of csPC, and ADC texture-related parameters are of the highest importance.

Project description:BackgroundPrevention of unnecessary biopsies and overtreatment of indolent disease remains a challenge in the management of prostate cancer. Novel non-invasive tests that can identify clinically significant (intermediate-risk and high-risk) diseases are needed to improve risk stratification and monitoring of prostate cancer patients. Here, we investigated a panel of six DNA methylation biomarkers in urine samples collected post-digital rectal exam from patients undergoing prostate biopsy, for their utility to guide decision making for diagnostic biopsy and early detection of aggressive prostate cancer.ResultsWe recruited 408 patients in risk categories ranging from benign to low-, intermediate-, and high-risk prostate cancer from three international cohorts. Patients were separated into 2/3 training and 1/3 validation cohorts. Methylation biomarkers were analyzed in post-digital rectal exam urinary sediment DNA by quantitative MethyLight assay and investigated for their association with any or aggressive prostate cancers. We developed a Prostate Cancer Urinary Epigenetic (ProCUrE) assay based on an optimal two-gene (HOXD3 and GSTP1) LASSO model, derived from methylation values in the training cohort, and assessed ProCUrE's diagnostic and prognostic ability for prostate cancer in both the training and validation cohorts. ProCUrE demonstrated improved prostate cancer diagnosis and identification of patients with clinically significant disease in both the training and validation cohorts. Using three different risk stratification criteria (Gleason score, D'Amico criteria, and CAPRA score), we found that the positive predictive value for ProCUrE was higher (59.4-78%) than prostate specific antigen (PSA) (38.2-72.1%) for all risk category comparisons. ProCUrE also demonstrated additive value to PSA in identifying GS ??7 PCa compared to PSA alone (DeLong's test p?= 0.039), as well as additive value to the PCPT risk calculator for identifying any PCa and GS ??7 PCa (DeLong's test p?=?0.011 and 0.022, respectively).ConclusionsProCUrE is a promising non-invasive urinary methylation assay for the early detection and prognostication of prostate cancer. ProCUrE has the potential to supplement PSA testing to identify patients with clinically significant prostate cancer.

Project description:BackgroundCombining targeted biopsy (TB) with systematic biopsy (SB) is currently recommended as the first-line biopsy method by the European Association of Urology (EAU) guidelines in patients diagnosed with prostate cancer (PCa) with an abnormal magnetic resonance imaging (MRI). The combined SB and TB indeed detected an additional number of patients with clinically significant prostate cancer (csPCa); however, it did so at the expense of a concomitant increase in biopsy cores. Our study aimed to evaluate if ipsilateral SB (ipsi-SB) + TB or contralateral SB (contra-SB) + TB could achieve almost equal csPCa detection rates as SB + TB using fewer cores based on a different csPCa definition.MethodsPatients with at least one positive prostate lesion were prospectively diagnosed by MRI. The combination of TB and SB was conducted in all patients. We compared the csPCa detection rates of the following four hypothetical biopsy sampling schemes with those of SB + TB: SB, TB, ipsi-SB + TB, and contra-SB + TB.ResultsThe study enrolled 279 men. The median core of SB, TB, ipsi-SB + TB, and contra-SB + TB was 10, 2, 7 and 7, respectively (P < 0.001). ipsi-SB + TB detected significantly more patients with csPCa than contra-SB + TB based on the EAU guidelines (P = 0.042). They were almost equal on the basis of the Epstein criteria (P = 1.000). Compared with SB + TB, each remaining method detected significantly fewer patients with csPCa regardless of the definition (P < 0.001) except ipsi-SB + TB on the grounds of D1 (P = 0.066). Ten additional subjects were identified with a higher Gleason score (GS) on contra-SB + TB, and only one was considered as significantly upgraded (GS = 6 on ipsi-SB + TB to a GS of 8 on contra-SB + TB).ConclusionsIpsi-SB + TB could acquire an almost equivalent csPCa detection value to SB + TB using significantly fewer cores when csPCa was defined according to the EAU guidelines. Given that there was only one significantly upgrading patient on contra-SB, our results suggested that contra-SB could be avoided.