Predicting the outcome of prostate biopsy in screen-positive men by a multilayer perceptron network

Finne, Patrik; Finne, Ralf; Auvinen, Anssi; Juusela, Harri; Aro, Jussi; Määttänen, Liisa; Hakama, Matti; Rannikko, S.; Tammela, Teuvo L.J.; Stenman, Ulf‐Hǎkan

doi:10.1016/s0090-4295(00)00672-5

Cited by 134 publications

(80 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…33 A further improvement for better discrimination between PCa and BPH are the so-called artificial neural networks, which usually use both parameters, %fPSA and prostate volume (PSAD), in conjunction with age, tPSA, and other factors, like DRE status. 37,44,45 Those studies consistently demonstrated a significant improvement compared with %fPSA. In the current study, we did not separate nonsuspicious and suspicious DRE results and analyzed ROC curves separately because of the large individual variability of the DRE results and the differences between investigators.…”

Section: Discussionmentioning

confidence: 80%

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

Stephan

Stroebel

Heinau

et al. 2005

Cancer

View full text Add to dashboard Cite

Nowadays, there is a strong interest in carbon nanotubes (CNTs) since these nanostructured materials have large potential applications in different technological fields. In this work, a very simple approach for synthesizing CNTs in mild conditions has been developed and investigated. In particular, the nanotubes have been obtained by thermal defluorination of poly(tetrafluoroethylene) (PTFE) by Si, which also acts as an inorganic catalyst for the CNT growth. Fine powders of PTFE and Si were homogeneously mixed together and then compacted by cold pressing. The obtained composite pills were placed into a quartz tube furnace at 650°C, and a vacuum was applied to remove the gaseous by‐product (SiF4). The obtained pyrolysis product consisted of CNTs, wrapping the surface of silicon grains. CNTs have been characterized by scanning electron microscopy, Raman spectroscopy, and large angle x‐ray powder diffraction. © 2012 Wiley Periodicals, Inc. Adv Polym Techn 31: 246–251, 2012; View this article online at wileyonlinelibrary.com. DOI 10.1002/adv.21267

show abstract

Section: Discussionmentioning

confidence: 80%

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

Stephan

Stroebel

Heinau

et al. 2005

Cancer

View full text Add to dashboard Cite

show abstract

“…Another possible detection bias results from the fact that multiple studies, including the current, found that obese men have larger prostates (23,24,27). Prostatic enlargement would make detection of an existent cancer less likely, given an equal-sized tumor and an equal number of biopsy cores were obtained (32,33). Combining lower PSA concentrations and prostatic enlargement would represent an inherent bias against detecting cancers among obese men.…”

Section: Discussionmentioning

confidence: 89%

Stronger Association between Obesity and Biochemical Progression after Radical Prostatectomy among Men Treated in the Last 10 Years

Freedland¹,

Isaacs

Mangold³

et al. 2005

Clinical Cancer Research

View full text Add to dashboard Cite

Background: Prior prospective cohort studies found that obesity was associated with increased risk of prostate cancer death. However, in the last 20 years dramatic changes in both the extent of obesity and prostate cancer screening and treatment have occurred.Whether the association between obesity and aggressive disease has changed as a result of these temporal changes is unclear. Methods: The study population consisted of 2,832 men treated by anatomic radical retropubic prostatectomy between 1985 and 2004 by a single surgeon. We evaluated the associations of obesity (body mass index z30 kg/m 2 )with tumor stage and grade using logistic regression and with biochemical progression using Cox proportional hazards regression. We examined whether these associations have changed over the last 20 years. Results: On multivariable analysis, the strength of the positive association between obesity and high-grade disease increased over time whereas the strength of the positive association between obesity and positive surgical margins decreased over time.The strength of the positive association between obesity and extraprostatic extension fluctuated over time, although the strongest and only statistically significant association was among men treated since 2000. The association between obesity and biochemical progression was strongest among men treated since1995 (relative risk, 1.90; 95% confidence interval, 1.09-3.30; P = 0.02).Conclusions: In the current study, with the exception of positive surgical margins, the positive association between obesity and high-grade disease, advanced stage, and biochemical progression after radical retropubic prostatectomy was in general strongest among men treated in the last 10 years.The reasons for these findings are not clear, although factors possibly related to prostatespecific antigen^based screening and/or other temporal changes in prostate cancer diagnosis and treatment may play a role.

show abstract

“…The artificial neural network used was a multilayer perceptron with Bayesian regularization (BR-MLP). 15 Preprocessed values of total PSA, the proportion of free PSA, prostate volume, DRE and age were used as input variables. Various models with 2-5 neurons in one hidden layer and one output neuron, were evaluated.…”

Section: Methodsmentioning

confidence: 99%

“…Combined use of several variables has been shown to reduce the number of false-positive PSA results more efficiently than single use of the proportion of free PSA. [12][13][14][15][16][17][18][19] However, LR or neural network algorithms for prostate cancer detection have not been studied prospectively; i.e., use of algorithm outcomes for making real-life biopsy decisions has not been reported. We simulated a prospective setting by using earlier subjects as training data and later ones for testing of the algorithms.…”

Section: Abstract: Prostate Cancer; Screening; Logistic Regression; mentioning

confidence: 99%

“…DISCUSSION Earlier studies showed that algorithms based on total PSA, free PSA, DRE and prostate volume can be used to reduce the number of false-positive PSA results in screening for prostate cancer more efficiently than the proportion of free PSA alone. [12][13][14][15][16][17][18][19] Despite this, there are no reports on the use of such algorithms in a prospective setting. Our study included 1,775 screen-positive men from the 3 largest participating centers in the European Randomized Study of Screening for Prostate Cancer, 20 -22 making it the largest study on predicting prostate biopsy results in the PSA range 4 -10 g/l using LR and neural networks.…”

Section: Clinical Stage and Histopathologic Gradementioning

confidence: 99%

See 1 more Smart Citation

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

Finne

Finne²,

Bangma

et al. 2004

Intl Journal of Cancer

Self Cite

View full text Add to dashboard Cite

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 g/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 Key words: prostate cancer; screening; logistic regression; neural network; prostate-specific antigenProstate cancer is the cancer with the highest incidence among men in most industrialized countries. 1 PSA is increasingly used for early detection and screening, even though it has not been shown to reduce prostate cancer mortality and may lead to overdiagnosis of the disease. A principal problem with prostate cancer screening is that only approximately a third of men with elevated serum PSA (Ն4 g/l) have cancer in prostate biopsies. Most false-positive PSA results are caused by benign prostatic hyperplasia (BPH). False-positive results cause unnecessary prostate biopsies, generating anxiety, discomfort and costs. 2,3 Various approaches have been suggested to identify, among screening positive men, a low-risk group that could be spared unnecessary prostate biopsies. The proportion of free PSA in serum is lower in men with prostate cancer than in those with BPH, 4 -7 and determination of the proportion of free PSA has been shown to reduce Ͼ30% of false-positive PSA results at 90% sensitivity. 8,9 Prostate volume is usually smaller in prostate cancer cases than in other men with elevated serum PSA, 10 -12 and the ratio between total PSA and prostate volume (PSA density) can also be used to reduce false-positive PSA results. 9 Logistic regression (LR) and neural networks have been applied to produce diagnostic algorithms based mainly on total PSA, free PSA, prostate volume and digital rectal examination (DRE). Combined use of several variables has been shown to reduce the number of false-positive PSA results more efficiently than single use of the proportion of free PSA. [12][13][14][15][16][17][18][19] However, LR or neural network algorithms for prostate cancer detection have not been studied prospectively; i.e., use of algorithm outcomes for making real-life biopsy decisions has not been reported. We simulated a prospective setting by using earlier subjects as trai...

show abstract

Predicting the outcome of prostate biopsy in screen-positive men by a multilayer perceptron network

Cited by 134 publications

References 21 publications

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

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

Stronger Association between Obesity and Biochemical Progression after Radical Prostatectomy among Men Treated in the Last 10 Years

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

Contact Info

Product

Resources

About