Literature DB >> 12142385

Multicenter evaluation of an artificial neural network to increase the prostate cancer detection rate and reduce unnecessary biopsies.

Carsten Stephan1, Henning Cammann, Axel Semjonow, Eleftherios P Diamandis, Leon F A Wymenga, Michael Lein, Pranav Sinha, Stefan A Loening, Klaus Jung.   

Abstract

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 microg/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 microg/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 microg/L), the ANN detected 72% and 65% of cancers at specificities of 90% or 95%, respectively. At 4-10 microg/L tPSA, the ANN detected 90% and 95% of cancers with specificities of 62% and 41%, respectively. Use of the ANN with 2-10 microg/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.

Entities:  

Mesh:

Substances:

Year:  2002        PMID: 12142385

Source DB:  PubMed          Journal:  Clin Chem        ISSN: 0009-9147            Impact factor:   8.327


  31 in total

1.  [New serum markers in prostate carcinoma and their application to artificial neural networks].

Authors:  C Stephan; K Jung; H Cammann; J Kramer; G Kristiansen; S A Loening; M Lein
Journal:  Urologe A       Date:  2007-09       Impact factor: 0.639

2.  Using biopsy to detect prostate cancer.

Authors:  Shahrokh F Shariat; Claus G Roehrborn
Journal:  Rev Urol       Date:  2008

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

Authors:  R P Meijer; E F A Gemen; I E W van Onna; J C van der Linden; H P Beerlage; G C M Kusters
Journal:  World J Urol       Date:  2009-06-28       Impact factor: 4.226

Review 4.  Artificial neural networks and prostate cancer--tools for diagnosis and management.

Authors:  Xinhai Hu; Henning Cammann; Hellmuth-A Meyer; Kurt Miller; Klaus Jung; Carsten Stephan
Journal:  Nat Rev Urol       Date:  2013-02-12       Impact factor: 14.432

5.  Cancer Progress and Priorities: Prostate Cancer.

Authors:  Kevin H Kensler; Timothy R Rebbeck
Journal:  Cancer Epidemiol Biomarkers Prev       Date:  2020-02       Impact factor: 4.254

6.  Pre-operative prediction of advanced prostatic cancer using clinical decision support systems: accuracy comparison between support vector machine and artificial neural network.

Authors:  Sang Youn Kim; Sung Kyoung Moon; Dae Chul Jung; Sung Il Hwang; Chang Kyu Sung; Jeong Yeon Cho; Seung Hyup Kim; Jiwon Lee; Hak Jong Lee
Journal:  Korean J Radiol       Date:  2011-08-24       Impact factor: 3.500

7.  Data mining nursing care plans of end-of-life patients: a study to improve healthcare decision making.

Authors:  Fadi Almasalha; Dianhui Xu; Gail M Keenan; Ashfaq Khokhar; Yingwei Yao; Yu-C Chen; Andy Johnson; R Ansari; Diana J Wilkie
Journal:  Int J Nurs Knowl       Date:  2012-08-17       Impact factor: 1.222

8.  "Finding the needle in a haystack": oncologic evaluation of patients treated for LUTS with holmium laser enucleation of the prostate (HoLEP) versus transurethral resection of the prostate (TURP).

Authors:  Annika Herlemann; Kerstin Wegner; Alexander Roosen; Alexander Buchner; Philipp Weinhold; Alexander Bachmann; Christian G Stief; Christian Gratzke; Giuseppe Magistro
Journal:  World J Urol       Date:  2017-05-17       Impact factor: 4.226

Review 9.  Critical review of prostate cancer predictive tools.

Authors:  Shahrokh F Shariat; Michael W Kattan; Andrew J Vickers; Pierre I Karakiewicz; Peter T Scardino
Journal:  Future Oncol       Date:  2009-12       Impact factor: 3.404

10.  Image-based clinical decision support for transrectal ultrasound in the diagnosis of prostate cancer: comparison of multiple logistic regression, artificial neural network, and support vector machine.

Authors:  Hak Jong Lee; Sung Il Hwang; Seok-Min Han; Seong Ho Park; Seung Hyup Kim; Jeong Yeon Cho; Chang Gyu Seong; Gheeyoung Choe
Journal:  Eur Radiol       Date:  2009-12-17       Impact factor: 5.315

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.