Molecular forms of prostate-specific antigen in serum with concentrations of total prostate-specific antigen <4 microg/L: are they useful tools for early detection and screening of prostate cancer?

Prostate-specific antigen and other serum and urine markers in prostate cancer

Prostate-specific antigen (PSA) is one of the most widely used tumor markers, and strongly correlates with the risk of harboring from prostate cancer (PCa). This risk is visible already several years in advance but PSA has severe limitations for PCa detection with its low specificity and low negative predictive value. There is an urgent need for new biomarkers especially to detect clinically significant and aggressive PCa. From all PSA-based markers, the FDA-approved Prostate Health Index (phi) shows improved specificity over percent free and total PSA. Other serum kallikreins or sarcosine in serum or urine show more diverging data. In urine, the FDA-approved prostate cancer gene 3 (PCA3) has also proven its utility in the detection and management of early PCa. However, some aspects on its correlation with aggressiveness and the low sensitivity at very high values have to be re-examined. The detection of a fusion of the androgen regulated TMPRSS2 gene with the ERG oncogene (from the ETS family), which acts as transcription factor gene, in tissue of ~50% of all PCa patients was one milestone in PCa research. When combining the urinary assays for TMPRSS2:ERG and PCA3, an improved accuracy for PCa detection is visible. PCA3 and phi as the best available PCa biomarkers show an equal performance in direct comparisons.

Proteomic analysis of seminal fluid from men exhibiting oxidative stress

BACKGROUND

Seminal plasma serves as a natural reservoir of antioxidants. It helps to remove excessive formation of reactive oxygen species (ROS) and consequently, reduce oxidative stress. Proteomic profiling of seminal plasma proteins is important to understand the molecular mechanisms underlying oxidative stress and sperm dysfunction in infertile men.

METHODS

This prospective study consisted of 52 subjects: 32 infertile men and 20 healthy donors. Once semen and oxidative stress parameters were assessed (ROS, antioxidant concentration and DNA damage), the subjects were categorized into ROS positive (ROS+) or ROS negative (ROS-). Seminal plasma from each group was pooled and subjected to proteomics analysis. In-solution digestion and protein identification with liquid chromatography tandem mass spectrometry (LC-MS/MS), followed by bioinformatics analyses was used to identify and characterize potential biomarker proteins.

RESULTS

A total of 14 proteins were identified in this analysis with 7 of these common and unique proteins were identified in both the ROS+ and ROS- groups through MASCOT and SEQUEST analyses, respectively. Prolactin-induced protein was found to be more abundantly present in men with increased levels of ROS. Gene ontology annotations showed extracellular distribution of proteins with a major role in antioxidative activity and regulatory processes.

CONCLUSIONS

We have identified proteins that help protect against oxidative stress and are uniquely present in the seminal plasma of the ROS- men. Men exhibiting high levels of ROS in their seminal ejaculate are likely to exhibit proteins that are either downregulated or oxidatively modified, and these could potentially contribute to male infertility.

Using specificity to strategically target proteases

Proteases are a family of naturally occurring enzymes in the body whose dysregulation has been implicated in numerous diseases and cancers. Their ability to selectively and catalytically turnover substrate adds both signal amplification and functionality as parameters for the detection of disease. This review will focus on the development of activity-based methodologies to characterize proteases, and in particular, the use of positional scanning, synthetic combinatorial libraries (PS-SCL's), and substrate activity screening (SAS) assays. The use of these approaches to better understand a protease's natural substrate will be discussed as well as the technologies that emerged.

[PSA and hK2 in the diagnosis of prostate cancer]

Serum markers for prostate carcinoma are widely applied for the purpose of early detection of cancer and the differentiation between benign and malignant disease, for the pre-treatment staging of detected prostatic cancers, and for the monitoring of prostate cancer after curative or palliative therapies. Since its discovery in 1979, serum PSA has been the most powerful marker of prostate cancer, but, when used alone, PSA is not sufficiently sensitive or specific to consider it an ideal tool for the early detection or staging of prostate cancer. To optimize the use of PSA, the concepts of PSA velocity, PSA density, and age-related PSA values were developed. Moreover, the molecular forms of PSA, especially the percentage of free PSA, seem to be useful tools for the detection of prostate cancer in men with slightly elevated total PSA. Human kallikrein 2 (hK2), a serine protease closely related to PSA that also is expressed predominantly in the prostate, is a new complementary marker to PSA for early detection of prostate cancer. In this review, we examine PSA testing and its effectiveness in the diagnosis of prostate cancer. Further, we also evaluate recent literature regarding the use of hk2.

Quantitative and label-free technique for measuring protease activity and inhibition using a microfluidic cantilever array

We report the use of a SiN x based gold coated microcantilever array to quantitatively measure the activity and inhibition of a model protease immobilized on its surface. Trypsin was covalently bound to the gold surface of the microcantilever using a synthetic spacer, and the remaining exposed silicon nitride surface was passivated with silanated polyethylene glycol. The nanoscale cantilever motions induced by trypsin during substrate turnover were quantitatively measured using an optical laser-deflection technique. These microcantilever deflections directly correlated with the degree of protease turnover of excess synthetic fibronectin substrate ( K M = 0.58 x 10 (-6) M). Inhibition of surface-immobilized trypsin by soybean trypsin inhibitor (SBTI) was also observed using this system.

An artificial neural network for five different assay systems of prostate-specific antigen in prostate cancer diagnostics

OBJECTIVE

To compare separate prostate-specific antigen (PSA) assay-specific artificial neural networks (ANN) for discrimination between patients with prostate cancer (PCa) and no evidence of malignancy (NEM).

PATIENTS AND METHODS

In 780 patients (455 with PCa, 325 with NEM) we measured total PSA (tPSA) and free PSA (fPSA) with five different assays: from Abbott (AxSYM), Beckman Coulter (Access), DPC (Immulite 2000), and Roche (Elecsys 2010) and with tPSA and complexed PSA (cPSA) assays from Bayer (ADVIA Centaur). ANN models were developed with five input factors: tPSA, percentage free/total PSA (%fPSA), age, prostate volume and digital rectal examination status for each assay separately to examine two tPSA ranges of 0-10 and 10-27 ng/mL.

RESULTS

Compared with the median tPSA concentrations (range from 4.9 [Bayer] to 6.11 ng/mL [DPC]) and especially the median %fPSA values (range from 11.2 [DPC] to 17.4%[Abbott], for tPSA 0-10 ng/mL), the areas under the receiver operating characteristic curves (AUC) for all calculated ANN models did not significantly differ from each other. The AUC were: 0.894 (Abbott), 0.89 (Bayer), 0.895 (Beckman), 0.882 (DPC) and 0.892 (Roche). At 95% sensitivity the specificities were without significant differences, whereas the individual absolute ANN outputs differed markedly.

CONCLUSIONS

Despite only slight differences, PSA assay-specific ANN models should be used to optimize the ANN outcome to reduce the number of unnecessary prostate biopsies. We further developed the ANN named 'ProstataClass' to provide clinicians with an easy to use tool in making their decision about follow-up testing.

PSA and new biomarkers within multivariate models to improve early detection of prostate cancer

This review gives an overview of the use of prostate-specific antigen (PSA) and percent free-PSA (%fPSA)-based artificial neural networks (ANNs) and logistic regression models (LR) to reduce unnecessary prostate biopsies. There is a clear advantage in including clinical data such as age, digital rectal examination and transrectal ultrasound (TRUS) variables like prostate volume and PSA density as additional factors to tPSA and %fPSA within ANNs and LR models. There is also positive impact of tPSA and fPSA assays on the outcome of ANNs. New markers provide additional value within ANNs but to prove their clinical usefulness further testing is necessary.

Assay-specific artificial neural networks for five different PSA assays and populations with PSA 2-10 ng/ml in 4,480 men

Use of percent free PSA (%fPSA) and artificial neural networks (ANNs) can eliminate unnecessary prostate biopsies. In a total of 4,480 patients from five centers with PSA concentrations in the range of 2-10 ng/ml an IMMULITE PSA-based ANN (iANN) was compared with other PSA assay-adapted ANNs (nANNs) to investigate the impact of different PSA assays. ANN data were generated with PSA, fPSA (assays from Abbott, Beckman, DPC, Roche or Wallac), age, prostate volume, and DRE status. In 15 different ROC analyses, the area under the curve (AUC) in the PSA ranges 2-4, 2-10, and 4-10 ng/ml for the nANN was always significantly larger than the AUC for %fPSA or PSA. The nANN and logistic regression models mostly also performed better than the iANN. Therefore, for each patient population, PSA assay-specific ANNs should be used to optimize the ANN outcome in order to reduce the number of unnecessary biopsies.

Resin-based micropipette tip for immunochromatographic assays in urine samples

A novel bioanalysis system based on immunochromatography was developed in connection with a nitrocellulose resin modified micropipette tip, such as ZipTip. The sandwich-type immunoassay was applied to our bioanalysis system. The simple handling of the micropipette enabled us to increase the sample volume and detect low concentrations of target antigens in urine samples. In addition, the washing procedure could also be performed easily to reduce the background signal levels. For analytical evaluations, the color intensity was captured by a flatbed scanner, and processed by a software. We have achieved the detection of human chorionic gonadotropin (hCG) and prostate-specific antigen (PSA). The detection limit of hCG was 0.5 ng/ml (0.05 ng/tip), which is comparable to that of other conventional immunochromatographic systems. Moreover, the detection of PSA was greatly improved over the existing systems with the application of different sample volumes, such as 1 ng/ml (0.2 ng/tip) in a 200 microl sample volume, and 1 ng/ml (0.3 ng/tip) in 300 microl sample volume. Our bioanalysis system is a promising candidate for application to point-of-care tests with its simple handling and high sensitivity.

Clinical utility of human glandular kallikrein 2 within a neural network for prostate cancer detection

OBJECTIVE

To assess, using artificial neural networks (ANNs), human glandular kallikrein 2 (hK2), prostate-specific antigen (PSA), and percentage free/total PSA (f/tPSA), for discriminating between prostate cancer and benign prostatic hyperplasia (BPH).

MATERIAL AND METHODS

Serum samples from 475 patients with prostate cancer (n = 347) or BPH (n = 128) within the PSA range of 1-20 ng/mL were analysed for tPSA, fPSA and hK2 (research assay, Toronto, Canada). Data were analysed in the ranges of 1-4, 2-4, 4-10, and 2-20 ng/mL tPSA. Back-propagation ANN models with the variables PSA, f/tPSA, and hK2, hK2/fPSA and hK2/(f/tPSA) were constructed. The diagnostic validity was evaluated by receiver-operating characteristic (ROC) curve analysis.

RESULTS

Whereas the median concentration of hK2 was not significantly different between patients with BPH or prostate cancer in any of the tPSA ranges, the f/tPSA, hK2/fPSA and hK2/(f/tPSA), and the hK2-based ANN outputs were always significantly different between patients with prostate cancer or BPH. Using ROC curve comparison, all variables were significantly better than hK2 in all ranges. The hK2-based ANN performed better than f/tPSA except in the 4-10 ng/mL tPSA range. At 90% and 95% sensitivity, the hK2-based ANN was also significantly better than f/tPSA in the 1-4 ng/mL tPSA range. hK2/(f/tPSA) achieved equal results to the hK2-based ANN except in the range 2-20 ng/mL tPSA.

CONCLUSIONS

The hK2-based ANN improves the outcome of f/tPSA but not hK2/(f/tPSA) in almost all analysed subgroups. When comparing the results at 90% and 95% sensitivity the hK2-based ANN only performed significantly better than f/tPSA in the lowest tPSA range. Only in lower tPSA ranges do hK2-based ANNs show an advantage for further improving prostate cancer detection.

The ratio of prostate-specific antigen (PSA) to prostate volume (PSA density) as a parameter to improve the detection of prostate carcinoma in PSA values in the range of < 4 ng/mL

BACKGROUND

The objective of this study was to evaluate the prostate specific antigen (PSA) density (PSAD) (the quotient of PSA and prostate volume) compared with the percent free PSA (%fPSA) in different total PSA (tPSA) ranges from 2 ng/mL to 20 ng/mL. Possible cut-off levels depending on the tPSA should be established.

METHODS

In total, 1809 men with no pretreatment of the prostate were enrolled between 1996 and 2004. Total and free PSA were measured with the IMMULITE PSA and Free PSA kits (Diagnostic Products, Los Angeles, CA). Prostate volume was determined by transrectal ultrasound. The diagnostic validity of tPSA, %fPSA, and PSAD was evaluated by receiver operation characteristic (ROC) curve analysis.

RESULTS

The PSAD differed significantly (P < 0.0001) between patients with prostate carcinoma and patients with benign prostatic hyperplasia in all analyzed ranges of tPSA and prostate volume. At the 90% and 95% sensitivity levels and regarding the area under the ROC curve (AUC) within the tPSA range of 2-4 ng/mL, The PSAD was significantly better than tPSA and %fPSA. Within the tPSA range of 4-10 ng/mL, the PSAD did not perform better than %fPSA.

CONCLUSIONS

PSAD showed a better performance than %fPSA at tPSA concentrations < 4 ng/mL for detecting prostate carcinoma, with a significantly larger AUC for PSAD (0.739) compared with %fPSA (0.667). PSAD did not perform better than %fPSA when the tPSA range of 4-10 ng/mL was analyzed. Different PSAD cut-off values of 0.05 at tPSA 2-4 ng/mL, 0.1 at tPSA 4-10 ng/mL, and 0.19 at 10-20 ng/mL were necessary to reach 95% sensitivity.

Antioxidant vitamin and mineral supplementation and prostate cancer prevention in the SU.VI.MAX trial

Randomized trials have shown, unexpectedly, that supplementation with selenium or vitamin E is associated with a reduction of prostate cancer risk. We assess whether a supplementation with low doses of antioxidant vitamins and minerals could reduce the occurrence of prostate cancer and influence biochemical markers. The SU.VI.MAX trial comprised 5,141 men randomized to take either a placebo or a supplementation with nutritional doses of vitamin C, vitamin E, beta-carotene, selenium and zinc daily for 8 years. Biochemical markers of prostate cancer risk such as prostate-specific antigen (PSA) and insulin-like growth factors (IGFs) were measured on plasma samples collected at enrollment and at the end of follow-up from 3,616 men. Cox regression models were used to estimate the hazard ratio and related 95% confidence interval of prostate cancer associated with the supplementation and to examine whether the effect differed among predetermined susceptible subgroups. During the follow-up, 103 cases of prostate cancer were diagnosed. Overall, there was a moderate nonsignificant reduction in prostate cancer rate associated with the supplementation (hazard ratio = 0.88; 95% CI = 0.60-1.29). However, the effect differed significantly between men with normal baseline PSA (< 3 microg/L) and those with elevated PSA (p = 0.009). Among men with normal PSA, there was a marked statistically significant reduction in the rate of prostate cancer for men receiving the supplements (hazard ratio = 0.52; 95% CI = 0.29-0.92). In men with elevated PSA at baseline, the supplementation was associated with an increased incidence of prostate cancer of borderline statistical significance (hazard ratio = 1.54; 95% CI = 0.87-2.72). The supplementation had no effect on PSA or IGF levels. Our findings support the hypothesis that chemoprevention of prostate cancer can be achieved with nutritional doses of antioxidant vitamins and minerals.

A comprehensive characterization of the peptide and protein constituents of human seminal fluid

BACKGROUND

Knowledge of the peptide and protein components of seminal fluid and their role in prostate diseases including benign prostatic hyperplasia and prostate carcinoma is scant. We have undertaken a proteomic analysis of semen as a forerunner to identifying sensitive and specific diagnostic markers of prostatic diseases; to aid in improved therapeutic intervention; and, to enhance our understanding of prostate health and disease.

METHODS

Peptide and protein components of pooled human seminal fluid (n = 5) were separated by gel electrophoresis (1D and 2D) and identified by either matrix-assisted laser desorption ionization-time-of-flight-mass spectrometry (MALDI-TOF-MS) or capillary liquid chromatography tandem mass spectrometry (LC-MS/MS).

RESULTS

Analysis by two-dimensional electrophoresis (2DE) established that there were multiple post-translational variants of the majority of the proteins. Hormones, growth factors and bioactive peptides were detected and identified.

CONCLUSIONS

We have identified over 100 protein and peptide components of normal human seminal fluid.

Complexed prostate specific antigen (PSA) reduces unnecessary prostate biopsies in the 2.6-4.0 ng/mL range of total PSA

OBJECTIVE

To compare the performance of complexed prostate-specific antigen (cPSA) to total PSA (tPSA) and percentage free PSA (f/tPSA) in the diagnosis of prostate cancer for the tPSA range 2.6-4.0 ng/mL.

PATIENTS AND METHODS

Consecutive men scheduled for prostate biopsy were enrolled prospectively at 14 different sites in two multicentre studies in Europe and the USA. Serum obtained before biopsy was tested with the ACS:180 and Immuno 1 tPSA and cPSA assays (Bayer Diagnostics, Tarrytown, NY, USA) and the Access fPSA and tPSA assays (Beckman, Inc., San Diego, CA, USA). Receiver operating characteristics (ROC) curves were generated to compare the diagnostic performance of tPSA, cPSA and f/tPSA.

RESULTS

Of 316 men with a tPSA of 2.6-4.0 ng/mL, 82 (26%) were diagnosed with prostate cancer on biopsy. ROC analysis of all 316 men showed an area under the curve (AUC) for cPSA of 0.63, significantly greater than the AUC for tPSA of 0.56 (P = 0.008). At a sensitivity of 95%, threshold values of 2.3 ng/mL for cPSA and 2.73 ng/mL for tPSA provided specificities of 20.1% and 9.8%, respectively. f/tPSA was only available for 205 of the 316 (65%) men and the AUC for cPSA was 0.63, and did not significantly differ from the f/tPSA AUC of 0.64 (P = 0.58).

CONCLUSIONS

As a single test, cPSA provides improved specificity over tPSA and comparable specificity to f/tPSA for detecting prostate cancer, and may reduce the number of unnecessary prostate biopsies in the 2.6-4.0 ng/mL tPSA range.

A Multicenter Clinical Trial On the Use of Complexed Prostate Specific Antigen in Low Prostate Specific Antigen Concentrations

PURPOSE

The determination of complexed prostate specific antigen (cPSA) has been suggested to be promising for prostate cancer (PCa) diagnosis. In a multicenter trial we evaluate the diagnostic use of PSA forms in the low total PSA (tPSA) range.

MATERIALS AND METHODS

A total of 283 white men with and 417 without PCa and tPSA concentrations between 0 and 6 ng/ml were retrospectively analyzed. All 700 untreated subjects underwent a multisector needle biopsy of the prostate. The Elecsys analyser 1010 (Roche Diagnostics, Mannheim, Germany) was used for determination of tPSA and free PSA. Determination of cPSA and tPSA was performed using immunoassays of the Bayer Immuno 1 system (Bayer Diagnostics, Tarrytown, New York).

RESULTS

Receiver operating characteristics analyses for discrimination between cases with and without PCa were performed. The areas under the curves (AUC) for cPSA, tPSA and free-to-total PSA (f/tPSA) showed no significant differences in the tPSA ranges of 0 to 6 (700 cases), 0 to 4 (510) and 0.5 to 2.5 ng/ml (253). Within the tPSA range of 2.5 to 4 ng/ml (230 cases) the AUC for cPSA (0.61) was significantly larger than that for tPSA (Roche 0.51, Bayer 0.54) but did not differ from the AUC of f/tPSA (Roche). On the basis of the cutoffs for 95% specificity or sensitivity, no significant increase in corresponding sensitivity or specificity was found between tPSA with cPSA.

CONCLUSIONS

In the tPSA range of less than 4 ng/ml no improvement in diagnostic accuracy was shown between cPSA with tPSA or the ratio of f/tPSA. The search for a useful marker in the low PSA range must continue.

Organization and evolution of the glandular kallikrein locus in Mus musculus

The gene of tissue kallikrein and closely related genes constitute the glandular kallikrein (GK) gene family. The number of members varies between species, ranging from three human to 25 murine. Recently, the gene family was extended with 12 new members, KLK4-KLK15, that were identified adjacent to the classical GK genes on human chromosome 19. In this report, the structure and phylogeny of the mouse GK gene locus are described. A comparison of the human and murine loci shows that the locations of the tissue kallikrein gene and KLK4-KLK15 are conserved. The region between the tissue kallikrein gene and KLK15, devoid of genes in human, is expanded and contains 23 classical GK genes in mouse. Downstream of KLK15, where the genes encoding PSA and hK2 are located in human, mouse carries the pseudogene PsimGK25. Phylogenetic analyses show that classical GK genes emerged after the separation of the primate and rodent lineages, forming a subgroup within the newly extended GK family.

Complexed prostate-specific antigen for early detection of prostate cancer in men with serum prostate-specific antigen levels of 2 to 4 nanograms per milliliter

Complexed PSA (cPSA) has been shown to improve specificity in the detection of prostate cancer over that of total PSA (tPSA) testing in men with tPSA values greater than the cutoff value of 4.0 ng/mL. However, recent studies have reported a 25% incidence of prostate cancer in men with tPSA values in the 2.5- to 4.0-ng/mL range. We performed a multicenter study of cPSA in a population of men who underwent prostate biopsies because of elevated PSA levels or abnormal digital rectal examination (DRE). As part of this study, we sought to assess the clinical value of cPSA in comparison to tPSA, the free/tPSA ratio (f/tPSA) and the complexed/tPSA ratio (c/tPSA) in early detection of prostate cancer in men with tPSA values in the range of 2 to 4 ng/mL. The study was performed at 7 centers. Sera were drawn from men who underwent biopsy procedures consisting of >10 prostate tissue cores. Receiver operating characteristic (ROC) analysis was performed from the results of patients with tPSA values in the range of 2 to 4 ng/mL, including men with suspicious as well as unremarkable findings on DRE. Sera were collected and tested with the Bayer tPSA and cPSA assay and the Beckman free PSA and tPSA assays. ROC analysis was performed for all samples in the 2- to 4-ng/mL PSA range. At biopsy, 158 men had no evidence of malignancy and 57 (26.5%) were diagnosed with prostate cancer. ROC analysis indicated that the area under the curve (AUC) for cPSA was 0.64, which was statistically significantly greater than that achieved for tPSA (AUC, 0.57; P <0.0001). The AUC for f/tPSA and c/tPSA were 0.60 and 0.63, respectively, which was not statistically significantly different from that of tPSA or cPSA (P >or=0.252). A cutpoint of 2.5 ng/mL for tPSA and 2.1 ng/mL for cPSA provided a specificity of 20.3% and 34.2%, respectively, and sensitivity levels of 86%. Using cutpoints of 25% for f/tPSA and 74% for c/tPSA provided a specificity of 11.0% and 21.5%, respectively, and sensitivity levels of 97%. In all, >92% of the cancers treated with radical prostatectomy were organ confined, and the histologic grading of the tumors ranged from moderately to poorly differentiated with Gleason scores from 5 to 9. These data confirm that there is a high incidence of clinically significant prostate cancer in men with tPSA levels <4.0 ng/mL. Measurement of cPSA proved useful in stratifying men with tPSA values in the 2- to 4-ng/mL range into high- and low-risk groups for prostate cancer. The use of cPSA as a single test was found to enhance detection of prostate cancer over that of testing with tPSA and PSA ratios in men with tPSA values in the range of 2 to 4 ng/mL.

Robustness of free prostate specific antigen measurements to reduce unnecessary biopsies in the 2.6 to 4.0 ng./ml. range

PURPOSE

Prostate specific antigen (PSA) cutoffs lower than 4.0 ng./ml. are being evaluated more frequently but lower PSA cutoffs increase the number of prostatic biopsies. PSA exists in several forms free and complexed to proteins. Percent free PSA is lower in men with prostate cancer. Accordingly, free PSA and complexed PSA have been used to distinguish between cancer and benign disease in the diagnostic gray zone of 4 to 10 ng./ml. to eliminate unnecessary biopsies. There are limited data on the robustness of free PSA measurements in the 2.6 to 4.0 ng./ml. total PSA range.

MATERIALS AND METHODS

We evaluated percent free PSA measurements to discriminate between cancer and benign conditions in 965 consecutive volunteers in a prostate cancer screening study who underwent prostatic biopsy for a PSA of 2.6 to 4.0 ng./ml. and had benign digital rectal examination.

RESULTS

Overall 25% of men had cancer detected. A 25% free PSA cutoff detected 85% of cancers and avoided 19% of negative (cancer-free) biopsies, while a 30% free PSA cutoff detected 93% of cancers and avoided only 9% of negative biopsies. Of those men who underwent radical prostatectomy 132 (80%) had pathologically organ confined tumors. Only 5% of these tumors fulfilled the published pathological criteria for possibly clinically unimportant tumors.

CONCLUSIONS

Percent free PSA provides risk assessment but does not eliminate many unnecessary prostatic biopsies while maintaining a high sensitivity in the narrow total PSA range of 2.6 to 4.0 ng./ml.

Multicenter Evaluation of an Artificial Neural Network to Increase the Prostate Cancer Detection Rate and Reduce Unnecessary Biopsies

Background: The percentage of free prostate-specific antigen (%fPSA) has been shown to improve specificity for the diagnosis of prostate cancer (PCa) over total PSA (tPSA). A multicenter study was performed to evaluate the diagnostic value of a %fPSA-based artificial neural network (ANN) in men with tPSA concentrations between 2 and 20 μg/L for detecting patients with increased risk of a positive prostate biopsy for cancer.

Methods: We enrolled 1188 men from six different hospitals with PCa or benign prostates between 1996 and 2001. We used a newly developed ANN with input data of tPSA, %fPSA, patient age, prostate volume, and digital rectal examination (DRE) status to calculate the risk for the presence of PCa within different tPSA ranges (2–4, 4.1–10, 2–10, 10.1–20, and 2–20 μg/L) at the 90% and 95% specificity or sensitivity cutoffs, depending on the tPSA concentration. ROC analysis and cutoff calculations were used to estimate the diagnostic improvement of the ANN compared with %fPSA alone.

Results: In the low tPSA range (2–4 μg/L), the ANN detected 72% and 65% of cancers at specificities of 90% or 95%, respectively. At 4–10 μg/L tPSA, the ANN detected 90% and 95% of cancers with specificities of 62% and 41%, respectively. Use of the ANN with 2–10 μg/L tPSA enhanced the specificity of %fPSA by 20–22%, thus reducing the number of unnecessary biopsies.

Conclusions: Enhanced accuracy of PCa detection over that obtained using %fPSA alone can be achieved with a %fPSA-based ANN that also includes clinical information from DRE and prostate volume measurements.

An artificial neural network considerably improves the diagnostic power of percent free prostate-specific antigen in prostate cancer diagnosis: results of a 5-year investigation

Our study was performed to evaluate the diagnostic usefulness of %fPSA alone and combined with an ANN at different PSA concentration ranges, including the low range 2-4 ng/ml, to improve the risk assessment of prostate cancer. A total of 928 men with prostate cancer and BPH without any pretreatment of the prostate in the PSA range 2-20 ng/ml were enrolled in the study between 1996 and 2001. An ANN with input data of PSA, %fPSA, patient's age, prostate volume and DRE status was developed to calculate the individual's risk before performing a prostate biopsy within the different PSA ranges 2-4, 4.1-10 and 10.1-20 ng/ml. ROC analysis and cut-off calculations were used to estimate the diagnostic improvement of %fPSA and ANN in comparison to PSA. At the 90% sensitivity level, %fPSA and ANN performed better than PSA in all ranges, enhancing the specificity by 15-28% and 32-44%, respectively. For the low PSA range 2-4 ng/mL, we recommend a first-time biopsy at an ANN specificity level of 90%. For PSA 4-10 ng/mL, we recommend a first-time biopsy based on the ANN at the 90% sensitivity level. Use of an ANN enhances the %fPSA performance to further reduce the number of unnecessary biopsies within the PSA range 2-10 ng/ml.