Prostate Cancer Risk Prediction Research Articles

Machine-learning Algorithm-based Risk Prediction and Screening-detected Prostate Cancer in A Benign Prostate Hyperplasia Cohort.

Prostate cancer (PCa) is lethal. Our aim in this retrospective cohort study was to use machine learning-based methodology to predict PCa risk in patients with benign prostate hyperplasia (BPH), identify potential risk factors, and optimize predictive performance. The dataset was extracted from a clinical information database of patients at a single institute from January 2000 to December 2020. Patients newly diagnosed with BPH and prescribed alpha blockers/5-alpha-reductase inhibitors were enrolled. Patients were excluded if they had a previous diagnosis of any cancer or were diagnosed with PCa within 1 month of enrolment. The study endpoint was PCa diagnosis. The study utilized the extreme gradient boosting (XGB), support vector machine (SVM) and K-nearest neighbors (KNN) machine-learning algorithms for analysis. The dataset used in this study included 5,122 medical records of patients with and without PCa, with 19 patient characteristics. The SVM and XGB models performed better than the KNN model in terms of accuracy and area under curve. Local interpretable model-agnostic explanation and Shapley additive explanations analysis showed that body mass index (BMI) and late prostate-specific antigen (PSA) were important features for the SVM model, while PSA velocity, late PSA, and BMI were important features for the XGB model. Use of 5-alpha-reductase inhibitor was associated with a higher incidence of PCa, with similar survival outcomes compared to non-users. Machine learning can enhance personalized PCa risk assessments for patients with BPH but more research is necessary to refine these models and address data biases. Clinicians should use them as supplementary tools alongside traditional screening methods.

Comparison of Magnetic Resonance Imaging–Based Risk Calculators to Predict Prostate Cancer Risk

Magnetic resonance imaging (MRI)-based risk calculators can replace or augment traditional prostate cancer (PCa) risk prediction tools. However, few data are available comparing performance of different MRI-based risk calculators in external cohorts across different countries or screening paradigms. To externally validate and compare MRI-based PCa risk calculators (Prospective Loyola University Multiparametric MRI [PLUM], UCLA [University of California, Los Angeles]-Cornell, Van Leeuwen, and Rotterdam Prostate Cancer Risk Calculator-MRI [RPCRC-MRI]) in cohorts from Europe and North America. This multi-institutional, external validation diagnostic study of 3 unique cohorts was performed from January 1, 2015, to December 31, 2022. Two cohorts from Europe and North America used MRI before biopsy, while a third cohort used an advanced serum biomarker, the Prostate Health Index (PHI), before MRI or biopsy. Participants included adult men without a PCa diagnosis receiving MRI before prostate biopsy. Prostate MRI followed by prostate biopsy. The primary outcome was diagnosis of clinically significant PCa (grade group ≥2). Receiver operating characteristics for area under the curve (AUC) estimates, calibration plots, and decision curve analysis were evaluated. A total of 2181 patients across the 3 cohorts were included, with a median age of 65 (IQR, 58-70) years and a median prostate-specific antigen level of 5.92 (IQR, 4.32-8.94) ng/mL. All models had good diagnostic discrimination in the European cohort, with AUCs of 0.90 for the PLUM (95% CI, 0.86-0.93), UCLA-Cornell (95% CI, 0.86-0.93), Van Leeuwen (95% CI, 0.87-0.93), and RPCRC-MRI (95% CI, 0.86-0.93) models. All models had good discrimination in the North American cohort, with an AUC of 0.85 (95% CI, 0.80-0.89) for PLUM and AUCs of 0.83 for the UCLA-Cornell (95% CI, 0.80-0.88), Van Leeuwen (95% CI, 0.79-0.88), and RPCRC-MRI (95% CI, 0.78-0.87) models, with somewhat better calibration for the RPCRC-MRI and PLUM models. In the PHI cohort, all models were prone to underestimate clinically significant PCa risk, with best calibration and discrimination for the UCLA-Cornell (AUC, 0.83 [95% CI, 0.81-0.85]) model, followed by the PLUM model (AUC, 0.82 [95% CI, 0.80-0.84]). The Van Leeuwen model was poorly calibrated in all 3 cohorts. On decision curve analysis, all models provided similar net benefit in the European cohort, with higher benefit for the PLUM and RPCRC-MRI models at a threshold greater than 22% in the North American cohort. The UCLA-Cornell model demonstrated highest net benefit in the PHI cohort. In this external validation study of patients receiving MRI and prostate biopsy, the results support the use of the PLUM or RPCRC-MRI models in MRI-based screening pathways regardless of European or North American setting. However, tools specific to screening pathways incorporating advanced biomarkers as reflex tests are needed due to underprediction.

A new promising indicator in prostate cancer screening: Prostate-specific antigen fluctuation rate

ObjectivesTo evaluate whether PSA fluctuation can be used to predict the risk of prostate cancer. Materials and methodsThe study included 1244 patients who underwent prostate biopsy at Kartal Dr. Lutfi Kirdar City Hospital between 2013 and 2021 (848 in non-cancer; 396 in cancer). The patient's age, last two PSA values (PSA1 and PSA2) within three months before the biopsy, the duration between two PSAs (days), prostate size (g) and PSA density (PSAD) were all recorded. PSA fluctuation rate (PSAfr) was defined as the change rate between two PSA values. ResultsPSAfr was significantly higher in the non-cancer group than in the prostate cancer group (15.2% (20.5) and 9.6% (14.4), P=.019). A Simple linear regression was used to examine the relationship between PSAfr and other factors such as age, PSA, PSAD, and prostate volume, but it was shown that these had no effect on PSA fluctuations. ROC analysis revealed a relatively low Area Under the Curve (AUC) for PSAfr (AUC, 0.584 (0.515–0.653)). However, the cut-off value of 12.35% was found to be significant, with a sensitivity of 58% and a specificity of 59% (P:.019, 95%CI). The odds ratio, adjusted for age, PSAD, and PSA2, was calculated as 0.545 (0.33−0.89) using logistic regression analysis to show the relationship between prostate cancer and PSAfr. As a result, those with high PSAfr were found to be 1.83 times less likely to be diagnosed with prostate cancer than those with low fluctuations. ConclusionPSAfr could be used in nomograms to predict prostate cancer risk and reduce the number of unnecessary biopsies.

A non-socially-sensitive predictive model of prostate cancer for Asian males with benign prostatic hyperplasia: A multi-site cross-sectional case-control study

Background Benign prostatic hyperplasia (BPH) is common in aging Asian males and is associated with an excess risk of developing prostate cancer (PCa). However, discussions about socially-sensitive experiences such as sexual activity, which can significantly predict PCa risk, may be considered stigmatized in Asian culture. This study aimed to develop a predictive model for PCa risk in Asian males with BPH using non-socially-sensitive information. Methods A cross-sectional case-control study, with PCa patients as the cases and remaining as the controls, was conducted on a cohort of Taiwanese males with BPH from four medical institutions. Patients who met the inclusion criteria were enrolled, excluding those aged over 86 years or who had received human papillomavirus (HPV) vaccination. Non-socially-sensitive variables such as obesity, occupational exposure, HPV infection, and PCa family history score (FH score) were included in a fully adjusted logistic regression model, and depicted using a nomogram. Results Among 236 BPH patients, 45.3% had PCa. Obesity, occupational exposure, HPV infection, and family history of PCa were significantly associated with PCa risk. The FH score (OR = 1.89, 95% CI = 1.03–3.47, P = 0.041) had the highest impact, followed by HPV infection (OR = 1.47, 95% CI = 1.03–2.11, P = 0.034), occupational exposure (OR = 1.32, 95% CI = 1.15–1.51, P <0.001), and obesity (OR = 1.22, 95% CI = 1.07–1.41, P = 0.005). The nomogram accurately depicted the predictive risk, and the model demonstrated robust performance compared to individual factors. In addition, the subgroup analysis results showed elderly age group could obtain more favorable predictive performance in our proposed model (AUC = 0.712). Conclusion This non-socially-sensitive predictive model for PCa risk in Taiwanese males with BPH integrates multiple factors that could provide acceptable PCa risk-predictive performance, especially for elderly BPH patients over 70 years, aiding clinical decision-making and early cancer detection.

Tasa de fluctuación del PSA: un indicador prometedor para el cribado del cáncer de próstata

ObjectivesTo evaluate whether PSA fluctuation can be used to predict the risk of prostate cancer. Materials and methodsThe study included 1244 patients who underwent prostate biopsy at Kartal Dr. Lutfi Kirdar City Hospital between 2013 and 2021 (848 in non-cancer; 396 in cancer). The patient's age, last two PSA values (PSA1 and PSA2) within three months before the biopsy, the duration between two PSAs (days), prostate size (g) and PSA density (PSAD) were all recorded. PSA fluctuation rate (PSAfr) was defined as the change rate between two PSA values. ResultsPSAfr was significantly higher in the non-cancer group than in the prostate cancer group (15.2% [20.5] and 9.6% [14.4], P=.019). A simple linear regression was used to examine the relationship between PSAfr and other factors such as age, PSA, PSAD, and prostate volume, but it was shown that these had no effect on PSA fluctuations. ROC analysis revealed a relatively low area under the curve (AUC) for PSAfr (AUC: 0.584 [0.515-0.653]). However, the cut-off value of 12.35% was found to be significant, with a sensitivity of 58% and a specificity of 59% (P=.019). The odds ratio, adjusted for age, PSAD, and PSA2, was calculated as 0.545 (0.33-0.89) using logistic regression analysis to show the relationship between prostate cancer and PSAfr. As a result, those with high PSAfr were found to be 1.83 times less likely to be diagnosed with prostate cancer than those with low fluctuations. ConclusionPSAfr could be used in nomograms to predict prostate cancer risk and reduce the number of unnecessary biopsies.

Development and validation of a model for predicting the risk of prostate cancer.

Abnormal hematologic parameters before patients undergoing prostate biopsy play a pivotal role in guiding the surgical management of prostate cancer (PCa) incidence. This study aims to establish the first nomogram for predicting PCa risk for better surgical management. We retrospectively reviewed and analyzed the data including basic information, preoperative hematologic parameters, and imaging examination of 540 consecutive patients who underwent transrectal ultrasound (TRUS)-guided prostate biopsy for elevated prostate-specific antigen (PSA) in our medical center between 2017 and 2021. Logistic regression analysis was used to determine the risk factors for PCa occurrence, and the nomogram was constructed to predict PCa occurrence. Finally, the data including 121 consecutive patients in 2022 were prospectively collected to further verify the results. In retrospective analyses, univariate and multivariate logistic analyses identified that three variables including age, diabetes, and De Ritis ratio (aspartate transaminase/alanine transaminase, AST/ALT) were determined to be significantly associated with PCa occurrence. A nomogram was constructed based on these variables for predicting the risk of PCa, and a satisfied predictive accuracy of the model was determined with a C-index of 0.765, supported by a prospective validation group with a C-index of 0.736. The Decision curve analysis showed promising clinical application. In addition, our results also showed that the De Ritis ratio was significantly correlated with the clinical stage of PCa patients, including T, N, and M stages, but insignificantly related to the Gleason score. The increased De Ritis ratio was significantly associated with the risk and clinical stage of PCa and this nomogram with good discrimination could effectively improve individualized surgical management for patient underdoing prostate biopsy.

Patient-related characteristics predict prostate cancers in men with PI-RADS 4-5 to further optimize the diagnostic performance of MRI.

To develop a prediction model based on patient-related characteristics for detecting prostate cancer (PCa) in patients with Prostate Imaging Reporting and Data System (PI-RADS) 4-5 in multiparametric magnetic resonance imaging (mp-MRI), aiming to optimize pre-biopsy risk stratification in MRI. The patient-related characteristics including the lesion location, age, prostate-specific antigen (PSA), free prostate-specific antigen (fPSA), fPSA/PSA, prostate-specific antigen density (PSAD) and body mass index (BMI) were collected for patients who underwent mp-MRI and prostate biopsy between February 2014 and October 2022. Univariate and multivariate logistic regression analyses were conducted to select independent predictors of PCa and further create a prediction model. The diagnostic performance was evaluated using the area under the receiver operating characteristic curve (AUC). Moreover, sensitivity, specificity, positive-predictive value (PPV) and negative-predictive value (NPV) were also calculated. A total of 833 patients were included in this study. In the subgroup PI-RADS 4, the independent characteristics of lesion location, age, fPSA/PSA and PSAD were selected to create the prediction model with an AUC of 0.748 (95% CI 0.694-0.803), sensitivity of 61.88%, specificity of 85.32%, PPV of 92.52%, and NPV of 43.26%. Besides, the prediction model in PI-RADS 5 was created using PSA and PSAD with an AUC of 0.893 (95% CI 0.844-0.941), sensitivity of 81.40%, specificity of 84.85%, PPV of 98.37% and NPV of 28.87%. The patient-related clinical characteristics were significant predictors of PCa and the prediction model based on selected characteristics could achieve a medium risk prediction of PCa in PI-RADS 4-5.

Evaluating approaches for constructing polygenic risk scores for prostate cancer in men of African and European ancestry

Genome-wide polygenic risk scores (GW-PRSs) have been reported to have better predictive ability than PRSs based on genome-wide significance thresholds across numerous traits. We compared the predictive ability of several GW-PRS approaches to a recently developed PRS of 269 established prostate cancer-risk variants from multi-ancestry GWASs and fine-mapping studies (PRS269). GW-PRS models were trained with a large and diverse prostate cancer GWAS of 107,247 cases and 127,006 controls that we previously used to develop the multi-ancestry PRS269. Resulting models were independently tested in 1,586 cases and 1,047 controls of African ancestry from the California Uganda Study and 8,046 cases and 191,825 controls of European ancestry from the UK Biobank and further validated in 13,643 cases and 210,214 controls of European ancestry and 6,353 cases and 53,362 controls of African ancestry from the Million Veteran Program. Inthe testing data, the best performing GW-PRS approach had AUCs of 0.656 (95% CI= 0.635-0.677) in African and 0.844 (95%CI=0.840-0.848) in European ancestry men and corresponding prostate cancer ORs of 1.83 (95% CI= 1.67-2.00) and 2.19 (95% CI= 2.14-2.25), respectively, for each SD unit increase in the GW-PRS. Compared to the GW-PRS, in African and European ancestry men, the PRS269 had larger or similar AUCs (AUC= 0.679, 95% CI= 0.659-0.700 and AUC= 0.845, 95% CI= 0.841-0.849, respectively) and comparable prostate cancer ORs (OR= 2.05, 95% CI= 1.87-2.26 and OR= 2.21, 95% CI= 2.16-2.26, respectively). Findings were similar in the validation studies. This investigation suggests that current GW-PRS approaches may not improve the ability to predict prostate cancer risk compared to the PRS269 developed from multi-ancestry GWASs and fine-mapping.

Prostate cancer risk prediction based on clinical factors and prostate-specific antigen

IntroductionThe incidence rate of prostate cancer (PCa) has continued to rise in Korea. This study aimed to construct and evaluate a 5-year PCa risk prediction model using a cohort with PSA < 10 ng/mL by incorporating PSA levels and individual factors.MethodsThe PCa risk prediction model including PSA levels and individual risk factors was constructed using a cohort of 69,319 participants from the Kangbuk Samsung Health Study. 201 registered PCa incidences were observed. A Cox proportional hazards regression model was used to generate the 5-year risk of PCa. The performance of the model was assessed using standards of discrimination and calibration.ResultsThe risk prediction model included age, smoking status, alcohol consumption, family history of PCa, past medical history of dyslipidemia, cholesterol levels, and PSA level. Especially, an elevated PSA level was a significant risk factor of PCa (hazard ratio [HR]: 1.77, 95% confidence interval [CI]: [1.67–1.88]). This model performed well with sufficient discrimination ability and satisfactory calibration (C-statistic: 0.911, 0.874; Nam-D’Agostino test statistic:19.76, 4.21 in the development and validation cohort, respectively).ConclusionsOur risk prediction model was effective in predicting PCa in a population according to PSA levels. When PSA levels are inconclusive, an assessment of both PSA and specific individual risk factors (e.g., age, total cholesterol, and family history of PCa) could provide further information in predicting PCa.

Development and validation of a simple prostate cancer risk prediction model based on age, family history, and polygenic risk.

Accurate prostate cancer risk assessment will enable identification of men who are at increased risk of the disease. Using the UK Biobank population-based cohort, we developed and validated a simple model comprising age, family history, and a polygenic risk score (PRS) to predict 5-year risk of prostate cancer. Eligible participants were unaffected Caucasian men aged 40-69 years at their baseline assessment who had genotyping data available and had completed 6 or more weeks of follow-up. Family history was the number of affected first-degree relatives: 0, 1, or 2+. We used 264 single-nucleotide polymorphisms (SNPs) of a previously developed 269-SNP PRS and population standardized the PRS to have a mean of 1. Age was categorized into 10-year groups: 40-49, 50-59, and 60-69. In a 70% training data set, we used Cox regression with age as the time axis to model family history, PRS, and age group. The model estimates were used with prostate cancer incidences to derive 5-year risks of prostate cancer. Using 5 years of follow-up in a 30% testing data set, the model was tested in terms of its association per quintile of risk, discrimination, and calibration. Of the 198 334 eligible participants, 8996 (4.5%) were diagnosed with incident prostate cancer during follow-up and had a mean age of 67.9 (SD = 5.8) years at diagnosis. The best-fitting model included the PRS, family history, 10-year age group, interactions between age and PRS, and age and family history. In the 30% testing data set with follow-up limited to 5 years, the hazard ratioper SD of 5-year risk was 3.058 (95% confidence interval [CI], 2.720-3.438) and the Harrell's C-index was 0.811 (95% CI, 0.800-0.821). Overall, there were 1088 observed and 1159.1 expected prostate cancers, a standardized incidence ratio of 0.939 (95% CI, 0.885-0.996). Men at increased risk of prostate cancer could benefit from informed discussions around the risks and benefits of available options for screening for prostate cancer. Although the model was developed in Caucasian men, it can be used with ethnicity-specific polygenic risk and incidence rates for other populations.

How Well do Polygenic Risk Scores Identify Men at High Risk for Prostate Cancer? Systematic Review and Meta-Analysis.

Genome-wide association studies have revealed over 200 genetic susceptibility loci for prostate cancer (PCa). By combining them, polygenic risk scores (PRS) can be generated to predict risk of PCa. We summarize the published evidence and conduct meta-analyses of PRS as a predictor of PCa risk in Caucasian men. Data were extracted from 59 studies, with 16 studies including 17 separate analyses used in the main meta-analysis with a total of 20,786 cases and 69,106 controls identified through a systematic search of ten databases. Random effects meta-analysis was used to obtain pooled estimates of area under the receiver-operating characteristic curve (AUC). Meta-regression was used to assess the impact of number of single-nucleotide polymorphisms (SNPs) incorporated in PRS on AUC. Heterogeneity is expressed as I2 scores. Publication bias was evaluated using funnel plots and Egger tests. The ability of PRS to identify men with PCa was modest (pooled AUC 0.63, 95% CI 0.62-0.64) with moderate consistency (I2 64%). Combining PRS with clinical variables increased the pooled AUC to 0.74 (0.68-0.81). Meta-regression showed only negligible increase in AUC for adding incremental SNPs. Despite moderate heterogeneity, publication bias was not evident. Typically, PRS accuracy is comparable to PSA or family history with a pooled AUC value 0.63 indicating mediocre performance for PRS alone.

Assessing the Risk of Prostate Cancer with Nutritional and Environmental Factors: A Cross-Sectional Study from National Health and Nutrition Examination Survey 2001–2010

Screening for prostate cancer (PCa) using prostate-specific antigen (PSA) is common. This study aimed to identify potential nutritional variables associated with PSA levels and develop a PCa risk prediction model. A total of 5,725 participants from the 2001–2010 National Health and Nutrition Examination Survey (NHANES) database were recruited and divided into discovery and validation sets. Three machine learning (ML) algorithms were performed in discovery set to select features associated with a high-risk PSA level. Age, red blood cell (RBC), blood cholesterol, blood lead, and prognostic nutritional index (PNI) were overlapping important contributors among the three ML models. Furthermore, the relationship between the selected variables and the high-risk PSA level was verified using weighted logistic regression models and restricted cubic spline (RCS) curves. After adjustment, age and blood lead were significantly positively associated with high-risk PSA, while PNI was significantly negatively associated with high-risk PSA. A nomogram including age, RBC, blood cholesterol, and PNI was constructed for predicting the PCa risk according to PSA levels, and the area under the receiver operating characteristic curve (AUROC) of discovery and validation sets was 0.755 and 0.756, respectively. The constructed nomogram may be used for targeted PSA testing and cancer screening in community healthcare.

A Polygenic Risk Score for Prostate Cancer Risk Prediction

This retrospective cohort study compares 2 risk calculator systems that compute the probabilities of finding high-grade or any cancer on biopsy results in men undergoing a first prostate biopsy.

A synthetic data integration framework to leverage external summary-level information from heterogeneous populations.

There is a growing need for flexible general frameworks that integrate individual-level data with external summary information for improved statistical inference. External information relevant for a risk prediction model may come in multiple forms, through regression coefficient estimates or predicted values of the outcome variable. Different external models may use different sets of predictors and the algorithm they used to predict the outcome Y given these predictors may or may not be known. The underlying populations corresponding to each external model may be different from each other and from the internal study population. Motivated by a prostate cancer risk prediction problem where novel biomarkers are measured only in the internal study, this paper proposes an imputation-based methodology, where the goal is to fit a target regression model with all available predictors in the internal study while utilizing summary information from external models that may have used only a subset of the predictors. The method allows for heterogeneity of covariate effects across the external populations. The proposed approach generates synthetic outcome data in each external population, uses stacked multiple imputation to create a long dataset with complete covariate information. The final analysis of the stacked imputed data is conducted by weighted regression. This flexible and unified approach can improve statistical efficiency of the estimated coefficients in the internal study, improve predictions by utilizing even partial information available from models that use a subset of the full set of covariates used in the internal study, and provide statistical inference for the external population with potentially different covariate effects from the internalpopulation.

Individual risk prediction of high grade prostate cancer based on the combination between total prostate-specific antigen (PSA) and free to total PSA ratio.

Clinical practice guidelines endorse the stratification of prostate cancer (PCa) risk according to individual total prostate-specific antigen (tPSA) values and age to enhance the individual risk-benefit ratio. We defined two nomograms to predict the individual risk of high and low grade PCa by combining the assay of tPSA and %free/tPSA (%f/tPSA) in patients with a pre-biopsy tPSA between 2 and 10μg/L. The study cohort consisted of 662 patients that had fPSA, tPSA, and a biopsy performed (41.3% with a final diagnosis of PCa). Logistic regression including age, tPSA and %f/tPSA was used to model the probability of having high or low grade cancer by defining 3 outcome levels: no PCa, low grade (International Society of Urological Pathology grade, ISUP<3) and high grade PCa (ISUP≥3). The nomogram identifying patients with: (a)high vs. those with low grade PCa and without the disease showed a good discriminating capability (∼80%), but the calibration showed a risk of underestimation for predictive probabilities >30% (a considerable critical threshold of risk), (b)ISUP<3 vs. those without the disease showed adiscriminating capability of 63% and overestimates predictive probabilities >50%. In ISUP 5 a possible loss of PSA immunoreactivity has been observed. The estimated risk of high or low grade PCa bythe nomograms may be of aid in the decision-making process, in particular in the case of critical comorbidities andwhen the digital rectal examinations are inconclusive. The improved characterization of the risk of ISUP≥3 might enhance the use for magnetic resonance imaging in this setting.

Re: Prostate Cancer Polygenic Risk Score and Prediction of Lethal Prostate Cancer

Re: Prostate Cancer Polygenic Risk Score and Prediction of Lethal Prostate Cancer

Radiomic-based machine learning model for the accurate prediction of prostate cancer risk stratification.

To precisely predict prostate cancer (PCa) risk stratification, we constructed a machine learning (ML) model based on magnetic resonance imaging (MRI) radiomic features. Between August 2016 and May 2021, patients with histologically proven PCa who underwent pre-operative MRI and prostate-specific antigen screening were included. The patients were grouped into different risk categories as defined by the European Association of Urology-European Association of Nuclear Medicine-European Society for Radiotherapy and Oncology-European Society of Urogenital Radiology-International Society of Geriatric Oncology guidelines. Using Artificial Intelligence Kit software, PCa regions of interest were delineated and radiomic features were extracted. Subsequently, predictable models were built by utilising five traditional ML approaches: support vector machine, logistic regression, gradient boosting decision tree, k-nearest neighbour and random forest (RF) classifiers. The classification capacity of the developed models was assessed by area under the receiver operating characteristic curve (AUC) analysis. A total of 213 patients were enrolled, including 16 low-risk, 65 intermediate-risk, and 132 high-risk PCa patients. The risk stratification of PCa could be revealed by MRI radiomic features, and second-order features accounted for most of the selected features. Among the five established ML models, the RF model showed the best overall predictive performance (AUC = 0.87). After further analysis of the subgroups based on the RF model, the prediction of the high-risk group was the best (AUC = 0.89). This study demonstrated that the MR radiomics-based ML method could be a promising tool for predicting PCa risk stratification precisely. The ML models have valuable prospect for accurate PCa risk assessment, which might contribute to customize treatment and surveillance strategies.

Screening Asymptomatic Men for Prostate Cancer Using Prostate-Specific Antigen as An Early Detection Tool: A Review of Existing Literature

Prostate cancer remains the most common non-skin cancer in men. Prostate-specific antigen (PSA) is recognized as a biomarker for the diagnosis, monitoring, and risk prediction of prostate cancer. However, its role in prostate cancer screening has been controversial. While some authorities have recommended its use for screening, others have stated otherwise. Some clarity is required about its precise role in clinical practice. There need to be more consistent recommendations surrounding using PSA screening in clinical practice. Serum PSA measurements show variable reliability when screening for Prostate cancer, given the dynamics of PSA physiology and the conflicting results from two large, randomized control trials that sought to determine its role in prostate cancer screening and early detection. Hence surrogate measures like PSA density, PSA velocity, free-to-complexed PSA ratio, and percentage Pro-PSA among others, have been used to improve the predictive utility of this assay for Prostate cancer diagnosis. However, the debate on screening still lingers. The current review aims to highlight the controversies and objectively outline the current recommendations. This literature review examined scholarly papers and recommendations about the use of PSA for prostate cancer screening with the aim to rationalize the pros and cons of such approaches. We concluded that although more recent guidelines from the USPSTF recommend that screening be based on individual preference and professional judgment by the healthcare provider, differences in the specific details on how to best employ a PSA screening program still exist and require further review.

Survival analysis of localized prostate cancer with deep learning

In recent years, data-driven, deep-learning-based models have shown great promise in medical risk prediction. By utilizing the large-scale Electronic Health Record data found in the U.S. Department of Veterans Affairs, the largest integrated healthcare system in the United States, we have developed an automated, personalized risk prediction model to support the clinical decision-making process for localized prostate cancer patients. This method combines the representative power of deep learning and the analytical interpretability of parametric regression models and can implement both time-dependent and static input data. To collect a comprehensive evaluation of model performances, we calculate time-dependent C-statistics C_{text {td}} over 2-, 5-, and 10-year time horizons using either a composite outcome or prostate cancer mortality as the target event. The composite outcome combines the Prostate-Specific Antigen (PSA) test, metastasis, and prostate cancer mortality. Our longitudinal model Recurrent Deep Survival Machine (RDSM) achieved C_{text {td}} 0.85 (0.83), 0.80 (0.83), and 0.76 (0.81), while the cross-sectional model Deep Survival Machine (DSM) attained C_{text {td}} 0.85 (0.82), 0.80 (0.82), and 0.76 (0.79) for the 2-, 5-, and 10-year composite (mortality) outcomes, respectively. In addition to estimating the survival probability, our method can quantify the uncertainty associated with the prediction. The uncertainty scores show a consistent correlation with the prediction accuracy. We find PSA and prostate cancer stage information are the most important indicators in risk prediction. Our work demonstrates the utility of the data-driven machine learning model in prostate cancer risk prediction, which can play a critical role in the clinical decision system.

Application of European-specific polygenic risk scores for predicting prostate cancer risk in different ancestry populations.

Polygenic risk score (PRS) has shown promise in predicting prostate cancer (PCa) risk. However, the application of PRS in non-European ancestry was poorly studied. We constructed PRS using 68, 86, or 128 PCa-associated single-nucleotide polymorphisms (SNPs) identified through a large-scale Genome-wide association study (GWAS) in the European ancestry population. A calibration approach was performed to adjust the PRS exact value for each ancestry. The study was conducted in East Asian (ChinaPCa Consortium, n = 2379), European (UK Biobank, n = 209,172), and African American (African Ancestry Prostate Cancer Consortium, n = 6016). Individuals with the highest PRS (in >97.5th percentile) had over 2.5-fold increased risk of PCa than those with average PRS (in 40th-60th percentile) in both European (odds ratio [OR] = 3.79, 95% confidence interval [CI] = 3.46-4.16, p < 0.001) and Chinese (OR = 2.87, 95% CI = 1.29-6.40, p = 0.010), while slightly lower in African American (OR = 1.77, 95% CI = 1.22-2.58, p = 0.008). Compared with the lowest PRS (in <2.5th percentile), increased PRS was also associated with the earlier onset of PCa (All log-rank p < 0.05). The highest PRS contributed to having about 5- to 12-fold higher lifetime risk and 5-10 years earlier at disease onset than the lowest category across different ancestry populations. We demonstrated that European-GWAS-based PRS could also significantly predict PCa risk in Asian ancestry and African ancestry populations.