scholarly journals Machine Learning Techniques in Prostate Cancer Diagnosis According to Prostate-Specific Antigen Levels and Prostate Cancer Gene 3 Score

2021 ◽  
Vol 19 (3) ◽  
pp. 164-173
Author(s):  
Roberto Passera ◽  
Stefano De Luca ◽  
Cristian Fiori ◽  
Enrico Bollito ◽  
Francesco Porpiglia
Keyword(s):  
Prostate Cancer ◽  
Machine Learning ◽  
Prostate Specific Antigen ◽  
Specific Antigen ◽  
Gradient Boosting ◽  
Cancer Gene ◽  
Free Psa ◽  
Gradient Boosting Machine ◽  
Extreme Gradient Boosting ◽  
Prostate Cancer Gene 3

Purpose: To explore the role of artificial intelligence and machine learning (ML) techniques in oncological urology. In recent years, our group investigated the prostate cancer gene 3 (PCA3) score, prostate-specific antigen (PSA), and free-PSA predictive role for prostate cancer (PCa), using the classical binary logistic regression (LR) modeling. In this research, we approached the same clinical problem by several different ML algorithms, to evaluate their performances and feasibility in a real-world evidence PCa detection trial.Materials and Methods: The occurrence of a positive biopsy has been studied in a large cohort of 1,246 Italian men undergoing first or repeat biopsy. Seven supervised ML algorithms were selected to build biomarkers-based predictive models: generalized linear model, gradient boosting machine, eXtreme gradient boosting machine (XGBoost), distributed random forest/ extremely randomized forest, multilayer artificial Deep Neural Network, naïve Bayes classifier, and an automatic ML ensemble function.Results: All the ML models showed better performances in terms of area under curve (AUC) and accuracy, when compared to LR model. Among them, an XGBoost model tuned by the autoML function reached the best metrics (AUC, 0.830), well overtaking LR results (AUC, 0.738). In the variable importance ranking coming from this XGBoost model (accuracy, 0.824), the PCA3 score importance was 3-fold and 4-fold larger, when compared to that of free-PSA and PSA, respectively.Conclusions: The ML approach proved to be feasible and able to achieve good predictive performances with reproducible results: it may thus be recommended, when applied to PCa prediction based on biomarkers fluctuations.

Emerging biomarkers in the detection and prognosis of prostate cancer

2015 ◽  
Vol 53 (7) ◽  
Author(s):  
Xavier Filella ◽  
Laura Foj
Keyword(s):  
Prostate Cancer ◽  
Early Detection ◽  
Tumor Marker ◽  
Negative Predictive Value ◽  
Prostate Specific Antigen ◽  
Predictive Value ◽  
Specific Antigen ◽  
Cancer Gene ◽  
Prostate Cancer Gene 3 ◽  
New Biomarkers

AbstractThe prostate-specific antigen (PSA) is currently the most used tumor marker in the early detection of the prostate cancer (PCa), despite its low specificity and low negative predictive value. New biomarkers, including urine prostate cancer gene 3 (

scholarly journals The Combination of Human Glandular Kallikrein and Free Prostate-specific Antigen (PSA) Enhances Discrimination Between Prostate Cancer and Benign Prostatic Hyperplasia in Patients with Moderately Increased Total PSA

1999 ◽  
Vol 45 (11) ◽  
pp. 1960-1966 ◽  
Author(s):  
Angeliki Magklara ◽  
Andreas Scorilas ◽  
William J Catalona ◽  
Eleftherios P Diamandis
Keyword(s):  
Prostate Cancer ◽  
Benign Prostatic Hyperplasia ◽  
Prostate Specific Antigen ◽  
Prostatic Carcinoma ◽  
Specific Antigen ◽  
Area Under The Curve ◽  
Prostatic Hyperplasia ◽  
Free Psa ◽  
Glandular Kallikrein ◽  
Total Psa

Abstract Background: Prostate-specific antigen (PSA) is the most reliable tumor marker available and is widely used for the diagnosis and management of prostate cancer. Unfortunately, PSA cannot distinguish efficiently between benign and malignant disease of the prostate, especially within the range of 4–10 μg/L. Among the refinements developed to enhance PSA specificity is the free/total PSA ratio, which is useful in discriminating between the two diseases within the diagnostic “gray zone”. Recent data indicate that human glandular kallikrein (hK2), a protein with high homology to PSA, may be an additional serum marker for the diagnosis and monitoring of prostate cancer. Methods: We analyzed 206 serum samples (all before treatment was initiated) from men with histologically confirmed benign prostatic hyperplasia (n = 100) or prostatic carcinoma (n = 106) with total PSA in the range of 2.5–10 μg/L. Total and free PSA and hK2 were measured with noncompetitive immunological procedures. Statistical analysis was performed to investigate the potential utility of the various markers or their combinations in discriminating between benign prostatic hyperplasia and prostatic carcinoma. Results: hK2 concentrations were not statistically different between the two groups of patients. There was a strong positive correlation between hK2 and free PSA in the whole patient population. hK2/free PSA ratio (area under the curve = 0.69) was stronger predictor of prostate cancer than the free/total PSA ratio (area under the curve = 0.64). At 95% specificity, the hK2/free PSA ratio identified 30% of patients with total PSA between 2.5–10 μg/L who had cancer. At 95% specificity, the hK2/free PSA ratio identified 25% of patients with total PSA between 2.5 and 4.5 μg/L who had cancer. Conclusions: Our data suggest that hK2 in combination with free and total PSA can enhance the biochemical detection of prostate cancer in patients with moderately increased total PSA concentrations. More specifically, the hK2/free PSA ratio appears to be valuable in identifying a subset of patients with total PSA between 2.5 and 4.5 μg/L who have high probability of cancer and who should be considered for biopsy.

scholarly journals Proenzyme Forms of Prostate-Specific Antigen in Serum Improve the Detection of Prostate Cancer

2004 ◽  
Vol 50 (6) ◽  
pp. 1017-1025 ◽  
Author(s):  
Stephen D Mikolajczyk ◽  
William J Catalona ◽  
Cindy L Evans ◽  
Harry J Linton ◽  
Lisa S Millar ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Prostate Specific Antigen ◽  
Cancer Detection ◽  
Specific Antigen ◽  
Serum Markers ◽  
Prostate Cancer Detection ◽  
Good Marker ◽  
Free Psa ◽  
Specificity And Sensitivity ◽  
Benign Prostate

Abstract Introduction: Pro or precursor forms of prostate-specific antigen (PSA) have emerged as potentially important diagnostic serum markers for prostate cancer detection. Immunoassays were developed to measure specific proPSA forms containing propeptides of 2, 4, and 7 amino acids [(-2)proPSA, (-4)proPSA, and (-7)proPSA, respectively]. Methods: Research-use dual monoclonal antibody immunoassays using europium-labeled detection monoclonal antibodies were developed for each form of proPSA. Sera from patients with prostate cancer or benign prostate disease containing 4–10 μg/L PSA were assayed and analyzed by area under the ROC curve (AUC) for specificity and sensitivity. Results: The proPSA forms had quantification limits of 0.015–0.025 μg/L in serum, with cross-reactivities <1% with PSA. The sum of the proPSA forms divided by free PSA (percentage proPSA) had a higher AUC than did percentage of (-2)proPSA, free PSA, and complexed PSA with AUC (95% confidence intervals) of 0.69 (0.64–0.74), 0.64 (0.58–0.68), 0.63 (0.58–0.68), and 0.57 (0.51–0.62), respectively. The proPSA comprised a median of 33% of the free PSA in cancer and 25% in noncancer sera (P <0.0001). One-third (33%) of cancer samples had >40% proPSA, whereas only 8% of noncancer samples did (P <0.0001). In men with cancer and >25% free PSA, the (-2)proPSA had an AUC of 0.77 (0.66–0.86), with 90% sensitivity and 36% specificity at 0.04 μg/L. Conclusions: The percentage of proPSA gave better cancer detection in the 4–10 μg/L range than did percentage of free PSA and complexed PSA. (-2)proPSA significantly discriminated cancer in men whose serum had >25% free PSA, for whom there is currently no good marker for cancer detection.

scholarly journals PREPARASI PEREAKSI KIT IMMUNORADIOMETRlCASSAY FREE PROSTATE SPECIFIC ANTIGEN UNTUK DETEKSI KANKER PROSTAT

2013 ◽  
Vol 15 (2) ◽  
pp. 14-24
Author(s):  
Puji Widayati ◽  
Gina Mondrida ◽  
Sri Setiyowati ◽  
Agus Ariyanto ◽  
V. Yulianti Susilo ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Prostate Specific Antigen ◽  
Prostate Gland ◽  
Specific Antigen ◽  
Prostatic Hyperplasia ◽  
Free Condition ◽  
Free Psa ◽  
Prostate Enlargement ◽  
Assay Design ◽  
Benign Prostate

Prostate Specific Antigen (PSA) is a glycoprotein with a molecular weight of approximately 34,000 daltons serine protease secreted exclusively by prostatic epithelial cells that lining acini and prostate gland. Increased of PSA levels can be caused by prostate cancer or benign prostate enlargement (benign prostatic hyperplasia, BPH). PSA in the blood was found in the free condition (free PSA) and most of the bound protein (complexed-PSA, c-PSA). Measuring levels of PSA was found in the blood can be done by several methods such as by immunoradiometricassay (IRMA) methods or ELISA methods. IRMA method is one of immunoassay techniques using radionuclides ,/' 125 oJ I as a tracer, so the sample in small 13 quantity can be detected The purpose of this study was obtained PSA reagent kit that includes 1251labeled PSA as a tracer, PSA coated tube and PSA standard that requirements of the kit, then it can be optimized assay design, that eventually PSA reagent kit can be used for early detection of prostate cancer. It has been done labeling of Mab PSA using 125 1with reaction time was 90 seconds, amount of PSA MAb was 75 ugram and the activity of Na_ 125I was 1000 flCi. Preaparation of PSA coated tube using 0.05 M Na2C03 solution, at pH: 9.6 with volume was 250 ml., standard PSA with 0.025 Mphosphate buffer at pH 7.4 containing 5% BSA and 0.1% NaN3, and resulting at 1,25% and 14,12% respectively of NSB and BIT that requirement of the kit.Keywords: Prostate cancer, PSA, IRMA,NSB, Maximum Binding

Sign in / Sign up

Export Citation Format

Share Document