Clinical and pathologic characteristics of familial prostate cancer in Asian population

BACKGROUND

We investigated prevalence of familial and hereditary prostate cancer (PCa) in Asian population, and compared clinical characteristics between familial and sporadic disease.

METHODS

Pedigrees of 1102 patients who were treated for PCa were prospectively acquired. Clinical and pathologic characteristics and biochemical recurrence (BCR)-free survival were compared between familial PCa and sporadic PCa in patients who underwent radical prostatectomy (RP; n = 751).

RESULTS

The prevalence of familial, first-degree familial, and hereditary PCa was found to be 8.4%, 6.7%, and 0.9%, respectively; similar result was obtained in patients who underwent RP (8.4%, 6.4%, and 0.9%). Patients with familial PCa were significantly younger than those with sporadic PCa (63.3 vs 65.6 years; P = .015). However, preoperative variables (prostate-specific antigen, clinical stage, biopsy Gleason score [GS], and percentage of positive biopsy cores) and postoperative variables (surgical GS, upgrading rate, pathologic stage, and percentage of tumor volume) did not correlate with family history (P range: .114-.982). Kaplan-Meier analysis of 5-year BCR-free survival revealed no significant difference between sporadic (82.7%), familial (89.4%; P = .594), and first-degree familial (87.1%; P = .774) PCa. Analysis of p53, Bcl-2, Ki67, and other immunohistochemistry biomarkers revealed that only increasing p53 expression and first-degree familial PCa approached significance (P = .059).

CONCLUSION

The prevalence of familial PCa was somewhat lower in the Asian population than in other ethnic groups. Clinical and pathologic variables and selected histologic biomarker abnormalities were not significantly different in patients with and without a family history of PCa. BCR-free survival following RP was also unaffected by family history.

Detection of high GS risk group prostate tumors by diffusion tensor imaging and logistic regression modelling

PURPOSE

To assess the value of joint evaluation of diffusion tensor imaging (DTI) measures by using logistic regression modelling to detect high GS risk group prostate tumors.

MATERIALS AND METHODS

Fifty tumors imaged using DTI on a 3 T MRI device were analyzed. Regions of interests focusing on the center of tumor foci and noncancerous tissue on the maps of mean diffusivity (MD) and fractional anisotropy (FA) were used to extract the minimum, the maximum and the mean measures. Measure ratio was computed by dividing tumor measure by noncancerous tissue measure. Logistic regression models were fitted for all possible pair combinations of the measures using 5-fold cross validation.

RESULTS

Systematic differences are present for all MD measures and also for all FA measures in distinguishing the high risk tumors [GS ≥ 7(4 + 3)] from the low risk tumors [GS ≤ 7(3 + 4)] (P < 0.05). Smaller value for MD measures and larger value for FA measures indicate the high risk. The models enrolling the measures achieve good fits and good classification performances (R²_adj = 0.55-0.60, AUC = 0.88-0.91), however the models using the measure ratios perform better (R²_adj = 0.59-0.75, AUC = 0.88-0.95). The model that employs the ratios of minimum MD and maximum FA accomplishes the highest sensitivity, specificity and accuracy (Se = 77.8%, Sp = 96.9% and Acc = 90.0%).

CONCLUSION

Joint evaluation of MD and FA diffusion tensor imaging measures is valuable to detect high GS risk group peripheral zone prostate tumors. However, use of the ratios of the measures improves the accuracy of the detections substantially. Logistic regression modelling provides a favorable solution for the joint evaluations easily adoptable in clinical practice.

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.

Biomarker development, from bench to bedside

This review describes studies performed by our group and other laboratories in the field aimed at development of biomarkers not only for cancer but also for other diseases. The markers covered include tumor-associated trypsin inhibitor (TATI), tumor-associated trypsin (TAT), human chorionic gonadotropin (hCG), prostate-specific antigen (PSA) and their various molecular forms, their biology and diagnostic use. The discovery of TATI was the result of a hypothesis-driven project aimed at finding new biomarkers for ovarian cancer among urinary peptides. TATI has since proved to be a useful prognostic marker for several cancers. Recently, it has been named Serine Peptidase Inhibitor Kazal Type 1 (SPINK1) after being rediscovered by several groups as a tumor-associated peptide by gene expression profiling and proteomic techniques and shown to promote tumor development by stimulating the EGF receptor. To explain why a trypsin inhibitor is strongly expressed in some cancers, research focused on the protease that it inhibited led to the finding of tumor-associated trypsin (TAT). Elevated serum concentrations of TAT-2 were found in some cancer types, but fairly high background levels of pancreatic trypsinogen-2 limited the use of TAT-2 for cancer diagnostics. However, trypsinogen-2 and its complex with α1-protease inhibitor proved to be very sensitive and specific markers for pancreatitis. Studies on hCG were initiated by the need to develop more rapid and sensitive pregnancy tests. These studies showed that serum from men and non-pregnant women contains measurable concentrations of hCG derived from the pituitary. Subsequent development of assays for the subunits of hCG showed that the β subunit of hCG (hCGβ) is expressed at low concentrations by most cancers and that it is a strong prognostic marker. These studies led to the formation of a working group for standardization of hCG determinations and the development of new reference reagents for several molecular forms of hCG. The preparation of intact hCG has been adopted as the fifth international standard by WHO. Availability of several well-defined forms of hCG made it possible to characterize the epitopes of nearly 100 monoclonal antibodies. This will facilitate design of immunoassays with pre-defined specificity. Finally, the discovery of different forms of immunoreactive PSA in serum from a prostate cancer patient led to identification of the complex between PSA and α1-antichymotrypsin, and the use of assays for free and total PSA in serum for improved diagnosis of prostate cancer. Epitope mapping of PSA antibodies and establishment of PSA standards has facilitated establishment well-standardized assays for the various forms of PSA.

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.

[How to biopsy only men with high grade prostate cancer]

INTRODUCTION

Fuzzy logic and Artificial Neural Networks (ANN) are complementary technologies that together generate neuro-fuzzy system. The aim of our study is to compare 2 models for predicting the presence of high-grade prostate cancer (Gleason score 7 or more).

METHODS

We evaluated data from 1000 men with PSA less than 50 ng/mL, who underwent prostate biopsy. A prostate cancer was found in 313 (31%), and in 172 (17.2%) we detected high-grade prostate cancer. With those data, we developed 2 Co-Active Neuro-Fuzzy Inference Systems to predict the presence of high-grade prostate cancer. The first model had four input neurons (PSA, free PSA percentage [%freePSA], PSA density, and age) and the second model had three input neurons (PSA, %freePSA, and age).

RESULTS

The model with four input neurons (PSA, %freePSA, PSA density, and age) showed better performances than the one with three input neurons (PSA, %freePSA, and age). In fact the average testing error was 0.42 for the model with four input neurons and 0.44 for the other model.

CONCLUSIONS

The addition of PSA density to the model has allowed to obtain better results for the diagnosis of high grade prostate cancer.

[Parameters to improve the specificity of the prostate-specific antigen. Early detection of prostate cancer]

PURPOSE

The aim of the study was to improve the case detection rate of prostate cancer for patients who had unremarkable palpation findings and a PSA value in the range of 4 to 10 ng/ml by combination of the parameters total PSA (tPSA), f/tPSA ratio, prostate volume, PSA density, patient's age and transrectal ultrasound findings.

METHODS

Sextant biopsy of the prostate was performed for 619 patients aged 45-75 years who had unremarkable palpation findings and PSA values in the range of 4 to 10 ng/ml. The f/tPSA ratio was determined, transrectal ultrasound examination was performed, the prostate volume was measured and the PSA density calculated. The relationship between the various test variables - and their combination - and the histology results was investigated using logistic regression.

RESULTS

Prostate cancer was detected in 131 of 619 patients. Analysis of the aforementioned test variables by means of logistic regression revealed that the combination of the parameters f/tPSA ratio, PSA density and patient's age can significantly increase the sensitivity and specificity of PSA in predicting prostate cancer compared with the use of these parameters on an individual basis. With an assumed limit value of 5% for performance of punch biopsy, 31% of biopsies could be avoided in practice. In such a case, only 3% of instances of prostate cancer would have gone undetected.

CONCLUSION

The combined use of f/tPSA ratio, PSA density and patient's age can significantly enhance the case detection sensitivity for the PSA range of 4 to 10 ng/ml.

Between-method differences in prostate-specific antigen assays affect prostate cancer risk prediction by nomograms

BACKGROUND

To date, no published nomogram for prostate cancer (PCa) risk prediction has considered the between-method differences associated with estimating concentrations of prostate-specific antigen (PSA).

METHODS

Total PSA (tPSA) and free PSA were measured in 780 biopsy-referred men with 5 different assays. These data, together with other clinical parameters, were applied to 5 published nomograms that are used for PCa detection. Discrimination and calibration criteria were used to characterize the accuracy of the nomogram models under these conditions.

RESULTS

PCa was found in 455 men (58.3%), and 325 men had no evidence of malignancy. Median tPSA concentrations ranged from 5.5 μg/L to 7.04 μg/L, whereas the median percentage of free PSA ranged from 10.6% to 16.4%. Both the calibration and discrimination of the nomograms varied significantly across different types of PSA assays. Median PCa probabilities, which indicate PCa risk, ranged from 0.59 to 0.76 when different PSA assays were used within the same nomogram. On the other hand, various nomograms produced different PCa probabilities when the same PSA assay was used. Although the ROC curves had comparable areas under the ROC curve, considerable differences were observed among the 5 assays when the sensitivities and specificities at various PCa probability cutoffs were analyzed.

CONCLUSIONS

The accuracy of the PCa probabilities predicted according to different nomograms is limited by the lack of agreement between the different PSA assays. This difference between methods may lead to unacceptable variation in PCa risk prediction. A more cautious application of nomograms is recommended.

Critical review of prostate cancer predictive tools

Prostate cancer is a very complex disease, and the decision-making process requires the clinician to balance clinical benefits, life expectancy, comorbidities and potential treatment-related side effects. Accurate prediction of clinical outcomes may help in the difficult process of making decisions related to prostate cancer. In this review, we discuss attributes of predictive tools and systematically review those available for prostate cancer. Types of tools include probability formulas, look-up and propensity scoring tables, risk-class stratification prediction tools, classification and regression tree analysis, nomograms and artificial neural networks. Criteria to evaluate tools include discrimination, calibration, generalizability, level of complexity, decision analysis and ability to account for competing risks and conditional probabilities. The available predictive tools and their features, with a focus on nomograms, are described. While some tools are well-calibrated, few have been externally validated or directly compared with other tools. In addition, the clinical consequences of applying predictive tools need thorough assessment. Nevertheless, predictive tools can facilitate medical decision-making by showing patients tailored predictions of their outcomes with various alternatives. Additionally, accurate tools may improve clinical trial design.

Techniques and predictive models to improve prostate cancer detection

The use of prostate-specific antigen (PSA) as a screening test remains controversial. There have been several attempts to refine PSA measurements to improve its predictive value. These modifications, including PSA density, PSA kinetics, and the measurement of PSA isoforms, have met with limited success. Therefore, complex statistical and computational models have been created to assess an individual's risk of prostate cancer more accurately. In this review, the authors examined the methods used to modify PSA as well as various predictive models used in prostate cancer detection. They described the mathematical underpinnings of these techniques along with their intrinsic strengths and weaknesses, and they assessed the accuracy of these methods, which have been shown to be better than physicians' judgment at predicting a man's risk of cancer. Without understanding the design and limitations of these methods, they can be applied inappropriately, leading to incorrect conclusions. These models are important components in counseling patients on their risk of prostate cancer and also help in the design of clinical trials by stratifying patients into different risk categories. Thus, it is incumbent on both clinicians and researchers to become familiar with these tools. Cancer 2009;115(13 suppl):3085-99. (c) 2009 American Cancer Society.

The value of an artificial neural network in the decision-making for prostate biopsies

PURPOSE

In majority of patients who are subjected to prostate biopsies, no prostate cancer (PCa) is found. It is important to prevent unnecessary biopsies since serious complications may occur. An artificial neural network (ANN) may be able to predict the risk of the presence of PCa.

METHODS

Included were all patients, who underwent transrectal ultrasound-guided prostate biopsies between June 2006 and June 2007 with a total PSA (tPSA) level between 2 and 20 microg/l. The patients were divided into two groups according to their tPSA level (2-10 microg/l and 10-20 microg/l). The ANN Prostataclass of the Universitätsklinikum Charité in Berlin was used. The predictions of the ANN were compared to the pathology results of the biopsies.

RESULTS

Overall 165 patients were included. PCa was diagnosed in 53 patients, whereas the ANN predicted "no risk" in 19 of these patients (36%). The ANN output receiver operator characteristic (ROC) plots for the range of tPSA 2-10 microg/l and tPSA 10-20 microg/l showed an area under the curve (AUC) of 63 and 88% for the initial biopsy group, versus 69 and 57%, respectively, for the repeat biopsy group.

CONCLUSIONS

The ANN resulted in a false negative rate of 36%, missing PCa in 19 patients. For use in an outpatient-clinical setting, this ANN is insufficient to predict the risk of presence of PCa reliably.

A [-2]proPSA-based artificial neural network significantly improves differentiation between prostate cancer and benign prostatic diseases

BACKGROUND

The aim of this study was to combine the new automated Access [-2]proPSA (p2PSA) assay with a percent free PSA (%fPSA) based artificial neural network (ANN) or logistic regression (LR) model to enhance discrimination between patients with prostate cancer (PCa) and with no evidence of malignancy (NEM) and to detect aggressive PCa.

METHODS

Sera from 311 PCa patients and 275 NEM patients were measured with the p2PSA, total PSA (tPSA) and free PSA (fPSA) assays on Access immunoassay technology (Beckman Coulter, Fullerton, CA) within the 0-30 ng/ml tPSA range. Four hundred seventy-five patients (264 PCa, 211 NEM) had a tPSA of 2-10 ng/ml. LR models and leave-one-out (LOO) ANN models with Bayesian regularization by using tPSA, %fPSA, p2PSA/fPSA (%p2PSA), age and prostate volume were constructed and compared by receiver-operating characteristic (ROC) curve analysis.

RESULTS

The ANN and LR model each utilizing %p2PSA, %fPSA, tPSA and age, but without prostate volume, reached the highest AUCs (0.85 and 0.84) and best specificities (ANN: 62.1% and 45.5%; LR: 53.1% and 41.2%) compared with tPSA (22.7% and 11.4%) and %fPSA (45.5% and 26.1%) at 90% and 95% sensitivity. The %p2PSA furthermore distinguished better than tPSA and %fPSA between pT2 and pT3, and Gleason sum <7 and >or=7 PCa.

CONCLUSIONS

The automated p2PSA assay offers a new tool to improve PCa detection, and especially aggressive PCa detection. Incorporation of %p2PSA into an ANN and LR model further enhances the diagnostic accuracy to differentiate between malignant and non-malignant prostate diseases.

Inventory of prostate cancer predictive tools

PURPOSE OF REVIEW

We created an inventory of current predictive tools available for prostate cancer. This review may serve as an initial step toward a comprehensive reference guide for physicians to locate published nomograms that apply to the clinical decision in question. Using MEDLINE a literature search was performed on prostate cancer predictive tools from January 1966 to November 2007. We describe the patient populations to which they apply and the outcomes predicted, and record their individual characteristics.

RECENT FINDINGS

The literature search generated 111 published prediction tools that may be applied to patients in various clinical stages of disease. Of the 111 prediction tools, only 69 had undergone validation. We present an inventory of models with input variables, prediction form, number of patients used to develop the prediction tools, the outcome being predicted, prediction tool-specific features, predictive accuracy, and whether validation was performed.

SUMMARY

Decision rules, such as nomograms, provide evidence-based and at the same time individualized predictions of the outcome of interest. Such predictions have been repeatedly shown to be more accurate than those of clinicians, regardless of their level of expertise. Accurate risk estimates are also required for clinical trial design, to ensure homogeneous high-risk patient groups for whom new cancer therapeutics will be investigated.

Artificial neural network (ANN) velocity better identifies benign prostatic hyperplasia but not prostate cancer compared with PSA velocity

Background

To validate an artificial neural network (ANN) based on the combination of PSA velocity (PSAV) with a %free PSA-based ANN to enhance the discrimination between prostate cancer (PCa) and benign prostate hyperplasia (BPH).

Methods

The study comprised 199 patients with PCa (n = 49) or BPH (n = 150) with at least three PSA estimations and a minimum of three months intervals between the measurements. Patients were classified into three categories according to PSAV and ANN velocity (ANNV) calculated with the %free based ANN "ProstataClass". Group 1 includes the increasing PSA and ANN values, Group 2 the stable values, and Group 3 the decreasing values.

Results

71% of PCa patients typically have an increasing PSAV. In comparison, the ANNV only shows this in 45% of all PCa patients. However, BPH patients benefit from ANNV since the stable values are significantly more (83% vs. 65%) and increasing values are less frequently (11% vs. 21%) if the ANNV is used instead of the PSAV.

Conclusion

PSAV has only limited usefulness for the detection of PCa with only 71% increasing PSA values, while 29% of all PCa do not have the typical PSAV. The ANNV cannot improve the PCa detection rate but may save 11–17% of unnecessary prostate biopsies in known BPH patients.

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.

Comparison of two different artificial neural networks for prostate biopsy indication in two different patient populations

OBJECTIVES

Different artificial neural networks (ANNs) using total prostate-specific antigen (PSA) and percentage of free PSA (%fPSA) have been introduced to enhance the specificity of prostate cancer detection. The applicability of independently trained ANN and logistic regression (LR) models to different populations regarding the composition (screening versus referred) and different PSA assays has not yet been tested.

METHODS

Two ANN and LR models using PSA (range 4 to 10 ng/mL), %fPSA, prostate volume, digital rectal examination findings, and patient age were tested. A multilayer perceptron network (MLP) was trained on 656 screening participants (Prostatus PSA assay) and another ANN (Immulite-based ANN [iANN]) was constructed on 606 multicentric urologically referred men. These and other assay-adapted ANN models, including one new iANN-based ANN, were used.

RESULTS

The areas under the curve for the iANN (0.736) and MLP (0.745) were equal but showed no differences to %fPSA (0.725) in the Finnish group. Only the new iANN-based ANN reached a significant larger area under the curve (0.77). At 95% sensitivity, the specificities of MLP (33%) and the new iANN-based ANN (34%) were significantly better than the iANN (23%) and %fPSA (19%). Reverse methodology using the MLP model on the referred patients revealed, in contrast, a significant improvement in the areas under the curve for iANN and MLP (each 0.83) compared with %fPSA (0.70). At 90% and 95% sensitivity, the specificities of all LR and ANN models were significantly greater than those for %fPSA.

CONCLUSIONS

The ANNs based on different PSA assays and populations were mostly comparable, but the clearly different patient composition also allowed with assay adaptation no unbiased ANN application to the other cohort. Thus, the use of ANNs in other populations than originally built is possible, but has limitations.

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.

Neuro-fuzzy system for prostate cancer diagnosis

OBJECTIVES

To develop a neuro-fuzzy system to predict the presence of prostate cancer. Neuro-fuzzy systems harness the power of two paradigms: fuzzy logic and artificial neural networks. We compared the predictive accuracy of our neuro-fuzzy system with that obtained by total prostate-specific antigen (tPSA) and percent free PSA (%fPSA).

METHODS

The data from 1030 men (both outpatients and hospitalized patients) were used. All men had a tPSA level of less than 20 ng/mL. Of the 1030 men, 195 (18.9%) had prostate cancer. A neuro-fuzzy system was developed using the coactive neuro-fuzzy inference system model.

RESULTS

The mean area under the receiver operating characteristic curve for the neuro-fuzzy system output was 0.799 +/- 0.029 (95% confidence interval 0.760 to 0.835), for tPSA, it was 0.724 +/- 0.032 (95% confidence interval 0.681 to 0.765), and for %fPSA, 0.766 +/- 0.024 (95% confidence interval 0.725 to 0.804). Furthermore, pairwise comparison of the area under the curves evidenced differences among %fPSA, tPSA, and neuro-fuzzy system's output (tPSA versus neuro-fuzzy system's output, P = 0.008; %fPSA versus neuro-fuzzy system's output, P = 0.032). The comparison at 95% sensitivity showed that the neuro-fuzzy system had the best specificity (31.9%).

CONCLUSIONS

This study presented a neuro-fuzzy system based on both serum data (tPSA and %fPSA) and clinical data (age) to enhance the performance of tPSA to discriminate prostate cancer. The predictive accuracy of the neuro-fuzzy system was superior to that of tPSA and %fPSA.

Development and validation of pheochromocytoma of the adrenal gland scaled score for predicting malignant pheochromocytomas

OBJECTIVES

To evaluate the diagnostic performances of the pheochromocytoma of the adrenal gland scaled score (PASS) proposed in a previous report and that of a logistic model developed in this investigation.

METHODS

In all 130 patients with malignant or assumed benign pheochromocytomas, 15 predictive variables were observed. Receiver operating characteristic (ROC) curve analysis was performed to evaluate the diagnostic performance of PASS. The logistic model was developed using the 15 predictive variables. Its performance was evaluated by calculating the area under the ROC curve and comparing it with that of the PASS.

RESULTS

The PASS had the area under the ROC curve of 0.899 (95% confidence interval 0.844 to 0.954). Of the 15 variables entered in the logistic regression analysis, 9 were retained in the model. The area under the ROC curve for the logistic model was 0.983 (95% confidence interval 0.967 to 0.998).

CONCLUSIONS

ROC analysis indicated that the PASS could be used for the diagnosis of malignant pheochromocytomas. The logistic model was able to improve the diagnostic performance of the PASS using a different variable weighting method. We emphasize, however, that a clinical prospective evaluation is needed to confirm their actual value.

Improved prostate cancer detection with a human kallikrein 11 and percentage free PSA-based artificial neural network

Human kallikrein 11 (hK11) was evaluated in a percentage free PSA-based artificial neural network (ANN) to reduce unnecessary prostate biopsies. Serum samples from 357 patients with (n=132) and without (n=225) prostate cancer (PCa) were analyzed and ANN models were constructed and compared to all parameters. The discriminatory power of hK11 was lower than that of PSA, but receiver operator characteristic (ROC) analyses demonstrated significantly larger areas under the curves for the ANN compared to all other parameters. ANNs with hK11 may lead to a further reduction in unnecessary prostate biopsies, especially when analyzing patients with less than 15% free PSA.

Role of transrectal ultrasonography in the prediction of prostate cancer: artificial neural network analysis

OBJECTIVE

The purpose of this study was to evaluate the diagnostic performance of an artificial neural network (ANN) model with and without transrectal ultrasonographic (TRUS) data.

METHODS

Six hundred eighty-four consecutive patients who had undergone TRUS-guided prostate biopsy from May 2003 to January 2005 were enrolled. We constructed 2 ANN models. One (ANN_1) incorporated patient age, digital rectal examination findings, prostate-specific antigen (PSA) level, PSA density, transitional zone volume, and PSA density in the transitional zone as input data, whereas the other (ANN_2) was constructed with the above and TRUS findings as input data. The performances of these 2 ANN models according to PSA levels (group A, 0-4 ng/mL; group B, 4-10 ng/mL; and group C, >10 ng/mL) were evaluated using receiver operating characteristic analysis.

RESULTS

Of the 684 patients who underwent prostate biopsy, 214 (31.3%) were confirmed to have prostate cancer; of 137 patients with positive digital rectal examination results, 60 (43.8%) were confirmed to have prostate cancer; and of 131 patients with positive TRUS findings, 93 (71%) were confirmed to have prostate cancer. In groups A, B, and C, the AUCs for ANN_1 were 0.738, 0.753, and 0.774, respectively; the AUCs for ANN_2 were 0.859, 0.797, and 0.894. In all groups, ANN_2 showed better accuracy than ANN_1 (P < .05).

CONCLUSIONS

According to receiver operating characteristic analysis, ANN with TRUS findings was found to be more accurate than ANN without. We conclude that TRUS findings should be included as an input data component in ANN models used to diagnose prostate cancer.

A (-5, -7) proPSA based artificial neural network to detect prostate cancer

OBJECTIVE

The pro-forms of prostate specific antigen (-2,-5,-7 proPSA) and also %free PSA based artificial neural networks (ANN) have been suggested to enhance the discrimination between prostate cancer (PCa) and no evidence of malignancy (NEM). This study reports on the combined use of proPSA within a %free PSA based ANN to enhance specificity of PCa.

METHODS

Serum samples from 898 patients with PCa (n=384) or NEM (n=514) within the PSA range 1-10 microg/l were analyzed for PSA, free PSA and (-5,-7) proPSA (Roche assays). Patient data from two centers - taken first from the Swiss site of the ERSPC (Aarau) and from a referral population (Berlin) have been analyzed. Leave-one-out ANN models with the variables PSA, %fPSA, proPSA, prostate volume and status of digital rectal examination (DRE) were constructed and compared by receiver-operating characteristic (ROC) curve analysis.

RESULTS

(-5,-7) proPSA was only significantly different between NEM and PCa in the PSA range 4-10 microg/l. Within the PSA range 4-10 microg/l (Berlin group) the ANN including only the two variables %fPSA and proPSA could reach the same performance like the conventional ANN with PSA, %fPSA, age, prostate volume and DRE (both AUCs: 0.84) However, at 95% sensitivity all ANN could not improve specificity compared to %fPSA.

CONCLUSIONS

ProPSA as single parameter did not improve specificity over %fPSA whereas proPSA and %fPSA within an ANN in the PSA range 4-10 microg/l substituted prostate volume and DRE. At 95% sensitivity only ANN with prostate volume and DRE perform significantly better than %fPSA.

Three new serum markers for prostate cancer detection within a percent free PSA-based artificial neural network

BACKGROUND

We aimed to evaluate the value of macrophage inhibitory cytokine 1 (MIC-1), human kallikrein 11 (hK11) migration inhibitor factor (MIF) in comparison to prostate-specific antigen (PSA) and % fPSA and also to develop a % fPSA-based ANN with the new input factors to determine whether these additional markers can further eliminate unnecessary prostate biopsies.

METHODS

Serum samples from 371 patients with prostate cancer (PCa, n=135) or benign prostate hyperplasia (BPH, n=236) within the PSA range 0.5-20 microg/L were analyzed for total PSA, free PSA, MIC-1, hK11, and MIF. 'Leave one out' ANN models with these variables and prostate volume were constructed and compared to logistic regression (LR) and all single parameters.

RESULTS

The discriminatory power of MIC-1, hK11, and MIF was less than that for PSA despite significant differences in BPH compared to PCa patients. At 90% and 95% sensitivity, the artificial neural networks (ANNs) were only significantly better than % fPSA if prostate volume was included.

CONCLUSIONS

ANNs with the novel input factors of MIC-1, MIF, and/or hK11 and additional use of prostate volume demonstrated significant advantage compared with % fPSA and tPSA and may lead to a reduction in unnecessary prostate biopsies.

[Significance of the PSA-concentration for the detection of prostate cancer]

Prostate cancer among adult males is the most common neoplasm in western countries. Prostate specific antigen (PSA) is now a well established tumor marker that aids in the early detection of localized prostate cancer. Increased PSA concentrations are found in the serum of patients with benign prostatic hyperplasia or patients with prostate cancer, respectively. Therefore, in general the specificity of this test is low. The diagnostic value of PSA can be improved in consideration of clinical data, patients age, the measurement of free or complexed PSA, and the measurement of PSA velocity, respectively. Furthermore, there is a high variability between commercial PSA assays. Finally, the pre-analytical laboratory procedures have a high impact on the PSA measurement.

Prostate cancer screening in high-risk men: African American Hereditary Prostate Cancer Study Network

BACKGROUND

There are scant data available on prostate cancer screening among high-risk African American men with positive family histories. It is important to determine whether or not their screening rates differ from those in the general population.

METHODS

This study computed rates of previous digital rectal examination (DRE) and prostate-specific antigen (PSA) screening for prostate cancer in cancer-free (unaffected) relatives age 40-69 years from African American families that had four or more men with prostate cancer. The rates for these 134 high-risk African American men from the African American Hereditary Prostate Cancer Study (AAHPC) were compared with nationwide estimates obtained from participants in the 1998 and 2000 National Health Interview Survey (NHIS), for which the numbers of demographically comparable subjects were 5583 (4900 Caucasians, plus 683 African Americans) and 3359 (2948 Caucasians, 411 African Americans), respectively.

RESULTS

Men in the AAHPC cohort (with a strong positive family history) had significantly less screening than both African Americans and Caucasians in the NHIS cohorts. Only about one-third (35%) of the men in the AAHPC unaffected cohort had ever had a DRE, and only about 45% of them had ever received a PSA test. These rates were much lower than those obtained for African American men in the NHIS: 45% for DRE and 65% for PSA. These discrepancies increased with age.

CONCLUSIONS

Older African American men with positive family histories report surprisingly low rates of DRE and PSA screening compared with their counterparts in the NHIS surveys. At-risk men need to be informed of the benefits and limitations of prostate cancer screening and actively involved in decision-making for or against prostate cancer screening.

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.

Algorithms based on prostate-specific antigen (PSA), free PSA, digital rectal examination and prostate volume reduce false-positive PSA results in prostate cancer screening

Our objective was to determine whether multivariate algorithms based on serum total PSA, the free proportion of PSA, age, digital rectal examination and prostate volume can reduce the rate of false-positive PSA results in prostate cancer screening more effectively than the proportion of free PSA alone at 95% sensitivity. A total of 1,775 consecutive 55- to 67-year-old men with a serum PSA of 4-10 microg/l in the European Randomized Study of Screening for Prostate Cancer were included. To predict the presence of cancer, multivariate algorithms were constructed using logistic regression (LR) and a multilayer perceptron neural network with Bayesian regularization (BR-MLP). A prospective setting was simulated by dividing the data set chronologically into one set for training and validation (67%, n = 1,183) and one test set (33%, n = 592). The diagnostic models were calibrated using the training set to obtain 95% sensitivity. When applied to the test set, the LR model, the BR-MLP model and the proportion of free PSA reached 92%, 87% and 94% sensitivity and reduced 29%, 36% and 22% of the false-positive PSA results, respectively. At a fixed sensitivity of 95% in the test set, the LR model eliminated more false-positive PSA results (22%) than the proportion of free PSA alone (17%) (p < 0.001), whereas the BR-MLP model did not (19%) (p = 0.178). The area under the ROC curve was larger for the LR model (0.764, p = 0.030) and the BR-MLP model (0.760, p = 0.049) than for the proportion of free PSA (0.718). A multivariate algorithm can be used to reduce unnecessary prostate biopsies in screening more effectively than the proportion of free PSA alone, but the algorithms will require updating when clinical practice develops with time.

Prediction of prostate cancer in extended-field biopsies of the prostate

OBJECTIVES

To assess the prediction of prostate cancer using extended-field prostatic biopsies (8-11 cores), as such biopsy protocols are recommended to increase the detection of prostate cancer, and as fewer cancers are missed this should improve the prediction of biopsy outcome from the patients' history, transrectal ultrasonography (TRUS) and serum markers.

PATIENTS AND METHODS

In all, 260 patients were prospectively evaluated and 206 with a total prostate-specific antigen (PSA) level of < 20 ng/mL were included. All patients were evaluated for age, family history, lower urinary tract symptoms (LUTS), medication for LUTS, previous prostate biopsy, the presence of cysts, a digital rectal examination, calcifications or hypoechoic lesions on TRUS, total and transitional zone volume, total PSA (tPSA), PSA density (tPSAD), total PSA transition zone density (tPSATZD), complexed PSA (cPSA), cPSA density (cPSAD), cPSA transitional zone density (cPSATZD), free/total (f/t)PSA ratio and free/complexed PSA ratio (f/cPSA). Logistic regression was used to predict the outcome; 80% of the patients were used to generate the models and 20% to test the prediction.

RESULTS

Two models were constructed; the most accurate contained family history, cPSA, cPSAD, cPSATZD, f/cPSA, PSAD and tPSATZD (sensitivity 91%, specificity 70%). A workable and concise model contained tPSATZD, cPSATZD and f/cPSA, and had a sensitivity of 93% and a specificity of 60%. The best single predictor was tPSATZD with a sensitivity of 92% and a specificity of 55%. Using regression models can produce considerable gains in specificity. This would allow unnecessary prostate biopsies to be avoided for a third of patients compared with tPSA alone.

CONCLUSIONS

The present analysis for PSA indices appeared to be slightly more accurate than those in previously published studies. Most of this improvement in diagnostic accuracy was ascribed to the use of an extended-field biopsy protocol. Prostate cancer in a first-degree relative was the only variable that contributed significantly to the regression model. tPSATZD was the best volume-adjusted PSA index. The f/tPSA appeared to be the best test with no volume adjustment, followed by f/cPSA and cPSA. Although the models are cumbersome and expensive for use in general urological practice they could be used to optimize biopsy strategies on the basis of predicted cancer probabilities in screening studies. The cost of the models may compare favourably with tPSA because of the high specificity that can be achieved.

Understanding data in clinical research: a simple graphical display for plotting data (up to four independent variables) after binary logistic regression analysis

In clinical research, suitable visualization techniques of data after statistical analysis are crucial for the researches' and physicians' understanding. Common statistical techniques to analyze data in clinical research are logistic regression models. Among these, the application of binary logistic regression analysis (LRA) has greatly increased during past years, due to its diagnostic accuracy and because scientists often want to analyze in a dichotomous way whether some event will occur or not. Such an analysis lacks a suitable, understandable, and widely used graphical display, instead providing an understandable logit function based on a linear model for the natural logarithm of the odds in favor of the occurrence of the dependent variable, Y. By simple exponential transformation, such a logit equation can be transformed into a logistic function, resulting in predicted probabilities for the presence of the dependent variable, P(Y-1/X). This model can be used to generate a simple graphical display for binary LRA. For the case of a single predictor or explanatory (independent) variable, X, a plot can be generated with X represented by the abscissa (i.e., horizontal axis) and P(Y-1/X) represented by the ordinate (i.e., vertical axis). For the case of multiple predictor models, I propose here a relief 3D surface graphic in order to plot up to four independent variables (two continuous and two discrete). By using this technique, any researcher or physician would be able to transform a lesser understandable logit function into a figure easier to grasp, thus leading to a better knowledge and interpretation of data in clinical research. For this, a sophisticated statistical package is not necessary, because the graphical display may be generated by using any 2D or 3D surface plotter.

[Predictive model for prostate cancer in patients with biopsy indication]

OBJECTIVE

Attemp to determine the probability of developing prostate carcinoma taking into acc age, digital rectal examination and PSA once a transrectal biopsy has been indicated, so that both doctors and patients have mor information to face such pathology.

MATERIAL AND METHODS

Retrospective study of 633 biopsies, taken into acc the patient's age, digital rectal examination, PSA level and histology. The data were included in a database created with Access and were put a logistic regression by mens the software program SPSS.

RESULTS

Once the biopsy is indicated, digital rectal examination is the parameter offesing a higher discriminatory valuer with an odd ratio of 5.9 (CI 95%, 3.9-8.9). The mathematical model obtained shows a sensitivity level of 57% and a level of specificity of 84%. Pre-test probability is 36%, the probability post-test increasing up to 70%, and a negative predictive value of 77% and a positive predictive value of 67%.

CONCLUSIONS

The mathematical model obtained individually determines the probability of suffering from prostatic carcinoma. Moreover, using this model the probabilities obtained re more precise than those derived from the fact of fulfilling the criteria for a prostatic biopsy. Once a biopsy is indicated, the rectal examination becomes the parameter with a higher predictive value of PC, irrespective of PSA and age. The PPV of the model is higher than of the PSA or the digital recta examination used separately.

Hereditary prostate cancer: clinical aspects

PURPOSE

We review the current epidemiological and genetic knowledge regarding hereditary prostate cancer, and outline its clinical implications.

MATERIALS AND METHODS

Published articles on hereditary prostate cancer were identified using the MEDLINE data base.

RESULTS

A risk of prostate cancer, particularly early onset disease, is strongly affected by family history (number of relatives with prostate cancer and their age at diagnosis). A family history of prostate cancer increases the positive predictive value of prostate specific antigen testing and, hence, heredity should always be assessed when deciding whether to perform biopsies in a man with a prostate specific antigen level of 3 to 10 ng./ml. Epidemiological studies indicate that dominantly inherited susceptibility genes with high penetrance cause 5% to 10% of all prostate cancer cases, and as much as 30% to 40% of early onset disease. More than a half dozen chromosome loci that may comprise such genes have been mapped, but as of May 2002 no prostate cancer susceptibility gene of major importance had been cloned. Most likely, environmental factors and comparatively common variants of several other genes affect prostate cancer risk in families with or without multiple cases of the disease. On average, hereditary prostate cancer is diagnosed 6 to 7 years earlier than sporadic prostate cancer, but does not otherwise differ clinically from the sporadic form. As a consequence of the earlier onset, a greater proportion of men with hereditary prostate cancer die of the disease than those with nonhereditary prostate cancer. At present, the only clinically applicable measure to reduce prostate cancer mortality in families with hereditary disease is screening, with the aim of diagnosing the disease when it is still in a curable stage.

CONCLUSIONS

Hereditary susceptibility is now considered the strongest risk factor for prostate cancer and has profound clinical importance. The genetic mechanism behind such susceptibility has turned out to be more complex than initially thought, and will probably not be completely understood for many years to come.

The Proportion of Prostate-specific Antigen (PSA) Complexed to α1-Antichymotrypsin Improves the Discrimination between Prostate Cancer and Benign Prostatic Hyperplasia in Men with a Total PSA of 10 to 30 μg/L

Background: The aim of this study was to assess the diagnostic accuracy of the proportion of prostate-specific antigen (PSA) complexed to α1-antichymotrypsin (PSA-α1ACT:PSA ratio) in the differential diagnosis of prostate cancer (CaP) and benign prostatic hyperplasia (BPH) in men with total PSA of 10–30 μg/L.

Methods: We used our immunoassays (ELISAs) for total PSA and PSA-α1ACT complex to study 146 men. In 123, total PSA was between 10 and 20 μg/L; 66 of these had CaP and 57 BPH. In 23 men, total PSA was between 20 and 30 μg/L; 14 of these had CaP and 9 BPH. We calculated the area under the ROC curves (AUC) for total PSA, PSA-α1ACT complex, and PSA-α1ACT:PSA ratio, and determined the cutoff points that gave sensitivities approaching 100%.

Results: In the total PSA range between 10 and 20 μg/L, the AUC was significantly higher for the PSA-α1ACT:PSA ratio (0.850) than for total PSA (0.507) and PSA-α1ACT complex (0.710; P &lt;0.0001). A cutoff ratio of 0.62 would have permitted diagnosis of all 66 patients with CaP (100% sensitivity) and avoided 19% of unnecessary biopsies (11 of 57 patients). In the total PSA range between 20 and 30 μg/L, the AUC for the PSA-α1ACT:PSA ratio (0.980; 95% confidence interval, 0.82–0.99) was greater than the AUC for total PSA (0.750; 95% confidence interval, 0.51–0.89; P = 0.042). In this range, a cutoff point of 0.64 would have permitted the correct diagnosis of all 14 patients with CaP and 6 of the 9 with BPH.

Conclusions: The diagnostic accuracy of the PSA-α1ACT:PSA ratio persists at high total PSA concentrations, increasing the specificity of total PSA. Prospective studies with large numbers of patients are needed to assess whether the ratio of PSA-α1ACT to total PSA is a useful tool to avoid unnecessary prostatic biopsy in patients with a total PSA &gt;10 μg/L.

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.

Family history and prostate cancer screening with prostate-specific antigen

PURPOSE

Early detection of prostate cancer has been recommended for men with affected first-degree relatives despite the lack of evidence for mortality reduction. We therefore evaluated the impact of family history in the Finnish prostate cancer screening trial.

PATIENTS AND METHODS

Approximately 80,000 men were identified from the population register for the first screening round. Of the 32,000 men randomized to the screening arm, 30,403 were eligible at the time of invitation. A blood sample was drawn from the participants (n = 20,716), and serum prostate-specific antigen (PSA) was determined. Men with a PSA level > or = 4.0 ng/mL were referred for prostate biopsy. Information on family history was obtained through a self-administered questionnaire at baseline.

RESULTS

A total of 964 (5%) of the 20,716 screening participants had a positive family history, and 105 (11%) were screening-positive. Twenty-nine tumors were diagnosed, corresponding to a detection rate of 3.0% (29 of 964) and a positive predictive value of 28% (29 of 105). Of the 19,347 men without a family history, 1,487 (8%) had a PSA level > or = 4.0 ng/mL. The detection rate was 2.4% (462 of 19,347) and the positive predictive value was 31% (462 of 1,487). The risk associated with a positive family history was not substantially increased (rate ratio, 1.3; 95% confidence interval, 0.9 to 1.8). The results were not affected by the age of the screenee or age at diagnosis of the affected relative. The program sensitivity was 6% (29 of 491) (ie, selective screening policy would have missed 94% of cancers in the population). No differences were seen in the characteristics of screen-detected cancers by family history.

CONCLUSION

Our findings provide no support for selective screening among men with affected relatives.

Estimation of prostate cancer risk on the basis of total and free prostate-specific antigen, prostate volume and digital rectal examination

BACKGROUND AND OBJECTIVE

Approximately 70% of the men with an elevated serum prostate-specific antigen (PSA) identified in prostate cancer screening do not have prostate cancer. Other available diagnostic variables may be utilized to reduce the number of false positive PSA results, but few algorithms for calculation of the combined impact of multiple variables are available. The objective of this study was to establish nomograms showing the probability of detecting prostate cancer at biopsy on the basis of total PSA, and the percentage of free PSA in serum, prostate volume and digital rectal examination (DRE) findings.

METHODS

In a randomized, population-based prostate cancer screening trial 10284 men aged 55-67 years were screened during 1996 and 1997 in two metropolitan areas in Finland. Results for men (n=758) with a serum PSA of 4-20 microg/l were used to establish the risk nomograms. Of these 200 (26%) had prostate cancer at biopsy.

RESULTS

Prostate cancer probability depended most strongly on the percentage of free PSA. Total PSA, prostate volume, and DRE also contributed to prostate cancer probability, whereas age and family history of prostate cancer did not. More false positive PSA results could be eliminated by using the multivariate risk model rather than the percentage of free PSA (p<0.001) or PSA density (p=0.003) alone.

CONCLUSIONS

Wide variation in probability of detecting prostate cancer among screened men with a serum PSA of 4-20 microg/l was observed. The nomograms established can be used to avoid or defer biopsy in men with a low prostate cancer probability in spite of a serum PSA level exceeding 4 microg/l.

Computer-assisted diagnostics: application to prostate cancer

Artificial neural networks (ANNs) have only recently been applied to solve problems in the diagnosis, staging, and prediction of treatment outcome in prostate cancer. A literature search provided information on 10 published journal articles that were selected for review and analysis. In all but one of the studies that compared the ANN output with logistic regression modeling, the ANN performed better. Specific training issues for neural networks are discussed and examples provided. We conclude that the continued development and refinement of computer-assisted diagnostic methodology are warranted to enhance conventional statistical approaches to the classification and pattern recognition found in data sets from men either suspected of having or known to have prostate cancer.

Screening for prostate cancer with prostate-specific antigen: beware the biases

BACKGROUND

The evidence relating to the use of prostate-specific antigen (PSA) as a screening test is a highly controversial, as demonstrated by the lack of agreement among experts. There may be biases associated with various studies.

ISSUES

The main controversy is the relatively high prevalence of prostate cancer (PC) found at autopsy compared with the relatively low death rate from the disease. The lack of modifiable risk factors has led to early detection as a strategy to reduce mortality, as there is evidence for a significant burden of disease. Important issues are the accuracy of current screening tests, some attempts to improve on them, and whether there are good prognostic markers. The consequences of PSA testing (usually further testing including biopsy) and outcomes of treatment are presented in terms of mortality and morbidity; quality of life (QOL) must also be considered. Also important are the benefits from, and the difficulties associated with the "informed choice" approach to PSA screening.

CONCLUSION

There is evidence to suggest that biases can have a significant impact on the utility of PSA as a screening test for PC.

Comparison of logistic regression and linear regression in modeling percentage data

Percentage is widely used to describe different results in food microbiology, e.g., probability of microbial growth, percent inactivated, and percent of positive samples. Four sets of percentage data, percent-growth-positive, germination extent, probability for one cell to grow, and maximum fraction of positive tubes, were obtained from our own experiments and the literature. These data were modeled using linear and logistic regression. Five methods were used to compare the goodness of fit of the two models: percentage of predictions closer to observations, range of the differences (predicted value minus observed value), deviation of the model, linear regression between the observed and predicted values, and bias and accuracy factors. Logistic regression was a better predictor of at least 78% of the observations in all four data sets. In all cases, the deviation of logistic models was much smaller. The linear correlation between observations and logistic predictions was always stronger. Validation (accomplished using part of one data set) also demonstrated that the logistic model was more accurate in predicting new data points. Bias and accuracy factors were found to be less informative when evaluating models developed for percentage data, since neither of these indices can compare predictions at zero. Model simplification for the logistic model was demonstrated with one data set. The simplified model was as powerful in making predictions as the full linear model, and it also gave clearer insight in determining the key experimental factors.