Benign prostatic hyperplasia-associated free prostate-specific antigen improves detection of prostate cancer in an artificial neural network

Current biomarkers for diagnosing of prostate cancer

Prostate cancer (PCa) is mostly detected by prostate-specific antigen (PSA) as one of the most widely used tumor markers. But PSA is limited with its low specificity. The prostate health index (phi) can improve specificity over percent free and total PSA and correlates with aggressive cancer. The urinary PCA3 also shows its utility to detect PCa but its correlation with aggressiveness and the low sensitivity at high values are limitations. While the detection of alterations of the androgen-regulated TMPRSS2 and ETS transcription factor genes in tissue of ˜50% of all PCa patients was one research milestone, the urinary assay should only be used in combination with PCA3. Both US FDA-approved markers phi and PCA3 perform equally.

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.

Prostate cancer biomarkers: an update

Many aspects of prostate cancer diagnosis and treatment could be greatly advanced with new, effective biomarkers. Prostate-specific antigen (PSA) has multiple weaknesses as a biomarker, such as not distinguishing well between cancer and benign prostatic hyperplasia or between indolent and aggressive cancers, thus leading to overtreatment, especially unnecessary biopsies. PSA also often fails to indicate accurately which patients are responding to a given treatment. Yet PSA is the only prostate cancer biomarker routinely used by urologists. Here, we provide updated information on the most relevant of the other biomarkers currently in use or in development for prostate cancer. Recent research shows improvement over using PSA alone by comparing total PSA (tPSA) or free PSA (fPSA) with new, related markers, such as prostate cancer antigen (PCA) 3, the individual molecular forms of PSA (proPSA, benign PSA, and intact PSA), and kallikreins other than PSA. Promising results have also been seen with the use of the fusion gene TMPRSS2:ERG and with various forms of the urokinase plasminogen activation receptor. Initially, there were high hopes for early PCA, but those data were not reproducible and thus research on early PCA has been abandoned. Much work remains to be done before any of these biomarkers are fully validated and accepted. Currently, the only markers discussed in this paper with Food and Drug Administration-approved tests are PCA 3 and an isoform of proPSA, [-2]proPSA. Assays are in development for most of the other biomarkers described in this paper. While the biomarker validation process can be long and filled with obstacles, the rewards will be great-in terms of both patient care and costs to the health care system.

Artificial neural networks and prostate cancer--tools for diagnosis and management

Artificial neural networks (ANNs) are mathematical models that are based on biological neural networks and are composed of interconnected groups of artificial neurons. ANNs are used to map and predict outcomes in complex relationships between given 'inputs' and sought-after 'outputs' and can also be used find patterns in datasets. In medicine, ANN applications have been used in cancer diagnosis, staging and recurrence prediction since the mid-1990s, when an enormous effort was initiated, especially in prostate cancer detection. Modern ANNs can incorporate new biomarkers and imaging data to improve their predictive power and can offer a number of advantages as clinical decision making tools, such as easy handling of distribution-free input parameters. Most importantly, ANNs consider nonlinear relationships among input data that cannot always be recognized by conventional analyses. In the future, complex medical diagnostic and treatment decisions will be increasingly based on ANNs and other multivariate models.

Combined application of information theory on laboratory results with classification and regression tree analysis: analysis of unnecessary biopsy for prostate cancer

BACKGROUND

The probability of a prostate cancer-positive biopsy result varies with PSA concentration. Thus, we applied information theory on classification and regression tree (CART) analysis for decision making predicting the probability of a biopsy result at various PSA concentrations.

METHODS

From 2007 to 2009, prostate biopsies were performed in 664 referred patients in a tertiary hospital. We created 2 CART models based on the information theory: one for moderate uncertainty (PSA concentration: 2.5-10 ng/ml) and the other for high uncertainty (PSA concentration: 10-25 ng/ml).

RESULTS

The CART model for moderate uncertainty (n=321) had 3 splits based on PSA density (PSAD), hypoechoic nodules, and age and the other CART for high uncertainty (n=160) had 2 splits based on prostate volume and percent-free PSA. In this validation set, the patients (14.3% and 14.0% for moderate and high uncertainty groups, respectively) could avoid unnecessary biopsies without false-negative results.

CONCLUSIONS

Using these CART models based on uncertainty information of PSA, the overall reduction in unnecessary prostate biopsies was 14.0-14.3% and CART models were simplified. Using uncertainty of laboratory results from information theoretic approach can provide additional information for decision analysis such as CART.

Multicenter evaluation of [-2]proprostate-specific antigen and the prostate health index for detecting prostate cancer

BACKGROUND

Total prostate-specific antigen (tPSA) is flawed for prostate cancer (PCa) detection. [-2]proprostate-specific antigen (p2PSA), a molecular isoform of free PSA (fPSA), shows higher specificity compared with tPSA or percentage of free PSA (%fPSA). The prostate health index (Phi), a measure based on p2PSA and calculated as p2PSA/fPSA × √tPSA, was evaluated in a multicenter study for detecting PCa.

METHODS

A total of 1362 patients from 4 different study sites who had tPSA values of 1.6-8.0 μg/L (668 patients with PCa, 694 without PCa) underwent ≥10 core biopsies. Serum concentrations of tPSA, fPSA (both calibrated against a WHO reference material), and p2PSA were measured on Access2 or DxI800 analyzers (Beckman Coulter).

RESULTS

The percentage ratio of p2PSA to fPSA (%p2PSA) and Phi were significantly higher in all PCa subcohorts (positive initial or repeat biopsy result or negative digital rectal examination) (P < 0.0001) compared with patients without PCa. Phi had the largest area under the ROC curve (AUC) (AUC = 0.74) and provided significantly better clinical performance for predicting PCa compared with %p2PSA (AUC = 0.72, P = 0.018), p2PSA (AUC = 0.63, P < 0.0001), %fPSA (AUC = 0.61) or tPSA (AUC = 0.56). Significantly higher median values of Phi were observed for patients with a Gleason score ≥7 (Phi = 60) compared with a Gleason score <7 (Phi = 53; P = 0.0018). The proportion of aggressive PCa (Gleason score ≥7) increased with the Phi score.

CONCLUSIONS

The results of this multicenter study show that Phi, compared with tPSA or %fPSA, demonstrated superior clinical performance in detecting PCa at tPSA 1.6-8.0 μg/L (i.e., approximately 2-10 μg/L in traditional calibration) and is better able to detect aggressive PCa.

Benign prostate specific antigen distribution and associations with urological outcomes in community dwelling black and white men

PURPOSE

We describe cross-sectional associations of benign prostate specific antigen with clinical urological measures and examined the risk of future urological outcomes in 2 population based cohorts of black and white men, respectively.

MATERIALS AND METHODS

Two population based cohort studies were established to characterize the natural history of and risk factors for prostate disease progression in white and black male residents of Olmsted County, Minnesota, and Genesee County, Michigan, respectively.

RESULTS

The benign prostate specific antigen distribution was similar in black men at a median of 32.9 pg/ml (25th, 75th percentiles 17.3, 68.0) and white men at a median of 32.2 pg/ml (25th, 75th percentiles 16.6, 68.9, respectively). However, it was much lower than in previous reports. For Olmsted County men in the upper quartile of benign prostate specific antigen there was a fifteenfold increased risk of prostate cancer (HR 14.6, 95% CI 3.1-68.6) and a twofold higher risk of treatment for benign prostatic hyperplasia (HR 2.2, 95% CI 1.2-4.2) after adjusting for age. After additional adjustment for baseline prostate specific antigen the association between benign prostate specific antigen and prostate cancer risk was attenuated but remained almost ninefold higher for men in the upper quartile of benign prostate specific antigen (HR 8.7, 95% CI 1.8-42.4). The twofold higher risk of treatment for benign prostatic hyperplasia also remained after adjusting for baseline prostate specific antigen for men in the upper benign prostate specific antigen quartile (HR 1.9, 95% CI 0.9-4.0).

CONCLUSIONS

Results suggest that increased benign prostate specific antigen may help identify men with prostate cancer and those at risk for benign prostatic hyperplasia treatment.

Outcome assessment of patients with metastatic renal cell carcinoma under systemic therapy using artificial neural networks

BACKGROUND

The outcome of patients with advanced renal cell carcinoma (RCC) under systemic therapy shows remarkable variability, and there is a need to identify prognostic parameters that allow individual prognostic stratification and selection of optimal therapy. Artificial neural networks (ANN) are software systems that can be trained to recognize complex data patterns. In this study, we used ANNs to identify poor prognosis of patients with RCC based on common clinical parameters available at the beginning of systemic therapy.

PATIENTS AND METHODS

Data from patients with RCC who started systemic therapy were collected prospectively in a single center database; 175 data sets with follow-up data (median, 36 months) were available for analysis. Age, sex, body mass index, performance status, histopathologic parameters, time interval between primary tumor and detection of metastases, type of systemic therapy, number of metastases, and metastatic sites were used as input data for the ANN. The target variable was overall survival after 36 months. Logistic regression models were constructed by using the same variables.

RESULTS

Death after 36 months occurred in 26% of the patients in the tyrosine kinase inhibitors group and in 37% of the patients in the immunotherapy group (P = .22). ANN achieved 95% overall accuracy and significantly outperformed logistic regression models (78% accuracy). Pathologic T classification, invasion of vessels, and tumor grade had the highest impact on the network's decision.

CONCLUSION

ANN is a promising approach for individual risk stratification of patients with advanced RCC under systemic therapy, based on clinical parameters, and can help to optimize the therapeutic strategy.

Pilot study on developing a decision support tool for guiding re-administration of chemotherapeutic agent after a serious adverse drug reaction

Background

Currently, there are no standard guidelines for recommending re-administration of a chemotherapeutic drug to a patient after a serious adverse drug reaction (ADR) incident. The decision on whether to rechallenge the patient is based on the experience of the clinician and is highly subjective. Thus the aim of this study is to develop a decision support tool to assist clinicians in this decision making process.

Methods

The inclusion criteria for patients in this study are: (1) had chemotherapy at National Cancer Centre Singapore between 2004 to 2009, (2) suffered from serious ADRs, and (3) were rechallenged. A total of 46 patients fulfilled the inclusion criteria. A genetic algorithm attribute selection method was used to identify clinical predictors for patients' rechallenge status. A Naïve Bayes model was then developed using 35 patients and externally validated using 11 patients.

Results

Eight patient attributes (age, chemotherapeutic drug, albumin level, red blood cell level, platelet level, abnormal white blood cell level, abnormal alkaline phosphatase level and abnormal alanine aminotransferase level) were identified as clinical predictors for rechallenge status of patients. The Naïve Bayes model had an AUC of 0.767 and was found to be useful for assisting clinical decision making after clinicians had identified a group of patients for rechallenge. A platform independent version and an online version of the model is available to facilitate independent validation of the model.

Conclusion

Due to the limited size of the validation set, a more extensive validation of the model is necessary before it can be adopted for routine clinical use. Once validated, the model can be used to assist clinicians in deciding whether to rechallenge patients by determining if their initial assessment of rechallenge status of patients is accurate.

Tumor markers in prostate cancer I: blood-based markers

The introduction of total prostate specific antigen (total PSA) testing in blood has revolutionized the detection and management of men with prostate cancer (PCa). The objective of this review was to discuss the challenges of PCa biomarker research, definition of the type of PCa biomarkers, the statistical considerations for biomarker discovery and validation, and to review the literature regarding total PSA velocity and novel blood-based biomarkers.

METHODS

An English-language literature review of the Medline database (1990 to August 2010) of published data on blood-based biomarkers and PCa was undertaken.

RESULTS

The inherent biological variability of total PSA levels affects the interpretation of any single result. Men who will eventually develop PCa have increased total PSA levels years or decades before the cancer is diagnosed. Total PSA velocity improves predictiveness of total PSA only marginally, limiting its value for PCa screening and prognostication. The combination of PSA molecular forms and other biomarkers improve PCa detection substantially. Several novel blood-based biomarkers such as human glandular kallikrein 2 (hK2), urokinase plasminogen activator (uPA) and its receptor (uPAR), transforming growth factor-beta 1 (TGF-β1); interleukin-6 (IL-6) and its receptor (IL-6R) may help PCa diagnosis, staging, prognostication, and monitoring. Panels of biomarkers that capture the biologic potential of PCa are in the process of being validated for PCa prognostication.

CONCLUSIONS

PSA is a strong prognostic marker for long-term risk of clinically relevant cancer. However, there is a need for novel biomarkers that aid clinical decision making about biopsy and initial treatment. There is no doubt that progress will continue based on the integrated collaboration of researchers, clinicians and biomedical firms.

Immunoassay for the discrimination of free prostate-specific antigen (fPSA) forms with internal cleavages at Lys(₁₄₅) or Lys(₁₄₆) from fPSA without internal cleavages at Lys(₁₄₅) or Lys(₁₄₆)

Total levels of circulating prostate-specific antigen (tPSA) are strongly associated with prostate cancer (PCa) risk and outcome but benign prostate disease is the most frequent cause of a moderately elevated PSA level. Free PSA (fPSA) forms are independently associated with PCa risk and contribute modest diagnostic enhancements above and beyond tPSA alone. We developed an immunoassay for fPSA subfractions containing internal cleavages at Lys(145) or Lys(146) (fPSA-N). The assay was based on blocking intact single-chain fPSA (fPSA-I) with antibody 4D4 which does not detect PSA containing internal cleavages at Lys(145) or Lys(146). We also measured fPSA-N in blood from healthy volunteers and in anti-coagulated plasma from 76 men with or without evidence of PCa at biopsy. The analytical and functional detection limits of this assay were 0.016 ng/mL and 0.10 ng/mL, respectively. The median recovery of male fPSA-N from female plasma was 95.0%. All 12 female samples (average age 28 years) had fPSA-N concentrations at or below the analytical detection limit. The median fPSA-N concentration (0.050 ng/mL) in 9 healthy male volunteers (age<40 years) was below the functional detection limit, 0.420 ng/mL in 27 patients with benign prostate conditions and 0.239 ng/mL in 49 patients with PCa. Deming regression analysis of the patient samples showed that the measured fPSA-N concentrations were generally 23% lower than the previously calculated (fPSA minus fPSA-I) concentrations, likely due to differences in the antibody combinations used. In conclusion, we have developed a sensitive, specific and direct immunoassay for fPSA-N which can be used to study the clinical relevance of this PSA isoform.

Prostate-specific antigen (PSA) isoform p2PSA in combination with total PSA and free PSA improves diagnostic accuracy in prostate cancer detection

BACKGROUND

Novel markers for prostate cancer (PCa) detection are needed. Total prostate-specific antigen (tPSA) and percent free prostate-specific antigen (%fPSA=tPSA/fPSA) lack diagnostic specificity.

OBJECTIVE

To evaluate the use of prostate-specific antigen (PSA) isoforms p2PSA and benign prostatic hyperplasia-associated PSA (BPHA).

DESIGN, SETTING, AND PARTICIPANTS

Our study included 405 serum samples from the Rotterdam arm of the European Randomised Study of Screening for Prostate Cancer and 351 samples from the Urology Department of Innsbruck Medical University.

MEASUREMENTS

BPHA, tPSA, fPSA, and p2PSA levels were measured by Beckman-Coulter Access Immunoassay. In addition, the Beckman Coulter Prostate Health Index was calculated: phi=(p2PSA/fPSA)×√(tPSA).

RESULTS AND LIMITATIONS

The p2PSA and phi levels differed significantly between men with and without PCa. No difference in BPHA levels was observed. The highest PCa predictive value in both cohorts was achieved by phi with areas under the curve (AUCs) of 0.750 and 0.709, a significant increase compared to tPSA (AUC: 0.585 and 0.534) and %fPSA (AUC: 0.675 and 0.576). Also, %p2PSA (p2PSA/fPSA) showed significantly higher AUCs compared to tPSA and %fPSA (AUC: 0.716 and 0.695, respectively). At 95% and 90% sensitivity, the specificities of phi were 23% and 31% compared to 10% and 8% for tPSA, respectively. In both cohorts, multivariate analysis showed a significant increase in PCa predictive value after addition of p2PSA to a model consisting of tPSA and fPSA (increase in AUC from 0.675 to 0.755 and from 0.581 to 0.697, respectively). Additionally, the specificity at 95% sensitivity increased from 8% to 24% and 7% to 23%, respectively. Furthermore, %p2PSA, phi, and the model consisting of tPSA and fPSA with or without the addition of p2PSA missed the least of the tumours with a biopsy or pathologic Gleason score ≥7 at 95% and 90% sensitivity.

CONCLUSIONS

This study shows significant increases in PCa predictive value and specificity of phi and %p2PSA compared to tPSA and %fPSA. p2PSA has limited additional value in identifying aggressive PCa (Gleason score ≥7).