Artificial neural network for predicting pathological stage of clinically localized prostate cancer in a Taiwanese population

Chih-Wei Tsao; Ching-Yu Liu; Tai-Lung Cha; Sheng-Tang Wu; Guang-Huan Sun; Dah-Shyong Yu; Hong-I Chen; Sun-Yran Chang; Shih-Chang Chen; Chien-Yeh Hsu

doi:10.1016/j.jcma.2014.06.014

Artificial neural network for predicting pathological stage of clinically localized prostate cancer in a Taiwanese population

J Chin Med Assoc. 2014 Oct;77(10):513-8. doi: 10.1016/j.jcma.2014.06.014. Epub 2014 Aug 27.

Authors

Affiliations

¹ Division of Urology, Department of Surgery, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, ROC; Graduate Institute of Biomedical Informatics, and Center of Excellence for Cancer Research, Taipei Medical University, Taipei, Taiwan, ROC.
² Department of Nutritional Science, Fu Jen Catholic University, New Taipei City, Taiwan, ROC.
³ Division of Urology, Department of Surgery, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, ROC.
⁴ Division of Urology, Department of Surgery, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, ROC; Graduate Institute of Medical Sciences, Chang Jung Christian University, Tainan, Taiwan, ROC.
⁵ Division of Urology, Department of Surgery, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, ROC; Taipei City Hospital, Taipei, Taiwan, ROC.
⁶ Graduate Institute of Patent, National Taiwan University of Science and Technology, Taipei, Taiwan, ROC.
⁷ Graduate Institute of Biomedical Informatics, and Center of Excellence for Cancer Research, Taipei Medical University, Taipei, Taiwan, ROC. Electronic address: cyhsu@tmu.edu.tw.

PMID: 25175002
DOI: 10.1016/j.jcma.2014.06.014

Abstract

Background: We developed an artificial neural network (ANN) model to predict prostate cancer pathological staging in patients prior to when they received radical prostatectomy as this is more effective than logistic regression (LR), or combined use of age, prostate-specific antigen (PSA), body mass index (BMI), digital rectal examination (DRE), trans-rectal ultrasound (TRUS), biopsy Gleason sum, and primary biopsy Gleason grade.

Methods: Our study evaluated 299 patients undergoing retro-pubic radical prostatectomy or robotic-assisted laparoscopic radical prostatectomy surgical procedures with pelvic lymph node dissection. The results were intended to predict the pathological stage of prostate cancer (T2 or T3) after radical surgery. The predictive ability of ANN was compared with LR and validation of the 2007 Partin Tables was estimated by the areas under the receiving operating characteristic curve (AUCs).

Results: Of the 299 patients we evaluated, 109 (36.45%) displayed prostate cancer with extra-capsular extension (ECE), and 190 (63.55%) displayed organ-confined disease (OCD). LR analysis showed that only PSA and BMI were statistically significant predictors of prostate cancer with capsule invasion. Overall, ANN outperformed LR significantly (0.795 ± 0.023 versus 0.746 ± 0.025, p = 0.016). Validation using the current Partin Tables for the participants of our study was assessed, and the predictive capacity of AUC for OCD was 0.695.

Conclusion: ANN was superior to LR at predicting OCD in prostate cancer. Compared with the validation of current Partin Tables for the Taiwanese population, the ANN model resulted in larger AUCs and more accurate prediction of the pathologic stage of prostate cancer.

Keywords: Partin Tables; artificial neural network; capsule invasion; prostate neoplasm.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Aged
Humans
Logistic Models
Male
Middle Aged
Neoplasm Staging
Neural Networks, Computer*
Prostate-Specific Antigen / blood
Prostatic Neoplasms / pathology*

Substances

Prostate-Specific Antigen