Artificial neural network to predict skeletal metastasis in patients with prostate cancer

Jainn Shiun Chiu, Yuh Feng Wang, Yu Cheih Su, Ling Huei Wei, Jian Guo Liao, Yu Chuan Li

研究成果: 雜誌貢獻文章

9 引文 (Scopus)

摘要

The application of an artificial neural network (ANN) in prediction of outcomes using clinical data is being increasingly used. The aim of this study was to assess whether an ANN model is a useful tool for predicting skeletal metastasis in patients with prostate cancer. Consecutive patients with prostate cancer who underwent the technetium-99m methylene diphosphate (Tc-99m MDP) whole body bone scintigraphies were retrospectively analyzed between 2001 and 2005. The predictors were the patient's age and radioimmunometric serum PSA concentration. The outcome variable was dichotomous, either skeletal metastasis or non-skeletal metastasis, based on the results of Tc-99m MDP whole body bone scintigraphy. To assess the performance for classification model in clinical study, the discrimination and calibration of an ANN model was calculated. The enrolled subjects consisted of 111 consecutive male patients aged 72.41∈±∈7.69 years with prostate cancer. Sixty-seven patients (60.4%) had skeletal metastasis based on the scintigraphic diagnosis. The final best architecture of neural network model was four-layered perceptrons. The area under the receiver-operating characteristics curve (0.88∈±∈0. 07) revealed excellent discriminatory power (p∈∈0.05), which represented a good-fit calibration. These results suggest that an ANN, which is based on limited clinical parameters, appears to be a promising method in forecasting of the skeletal metastasis in patients with prostate cancer.

原文英語
頁(從 - 到)91-100
頁數10
期刊Journal of Medical Systems
33
發行號2
DOIs
出版狀態已發佈 - 四月 2009
對外發佈Yes

指紋

Prostatic Neoplasms
Neural Networks (Computer)
Neoplasm Metastasis
Neural networks
Technetium
Diphosphates
Radionuclide Imaging
Calibration
Bone
Bone and Bones
ROC Curve
Serum

ASJC Scopus subject areas

  • Medicine (miscellaneous)
  • Health Informatics
  • Health Information Management
  • Information Systems

引用此文

Artificial neural network to predict skeletal metastasis in patients with prostate cancer. / Chiu, Jainn Shiun; Wang, Yuh Feng; Su, Yu Cheih; Wei, Ling Huei; Liao, Jian Guo; Li, Yu Chuan.

於: Journal of Medical Systems, 卷 33, 編號 2, 04.2009, p. 91-100.

研究成果: 雜誌貢獻文章

Chiu, Jainn Shiun ; Wang, Yuh Feng ; Su, Yu Cheih ; Wei, Ling Huei ; Liao, Jian Guo ; Li, Yu Chuan. / Artificial neural network to predict skeletal metastasis in patients with prostate cancer. 於: Journal of Medical Systems. 2009 ; 卷 33, 編號 2. 頁 91-100.
@article{3eb4f89b2b7c4c6ea5b7898ecb9ee08e,
title = "Artificial neural network to predict skeletal metastasis in patients with prostate cancer",
abstract = "The application of an artificial neural network (ANN) in prediction of outcomes using clinical data is being increasingly used. The aim of this study was to assess whether an ANN model is a useful tool for predicting skeletal metastasis in patients with prostate cancer. Consecutive patients with prostate cancer who underwent the technetium-99m methylene diphosphate (Tc-99m MDP) whole body bone scintigraphies were retrospectively analyzed between 2001 and 2005. The predictors were the patient's age and radioimmunometric serum PSA concentration. The outcome variable was dichotomous, either skeletal metastasis or non-skeletal metastasis, based on the results of Tc-99m MDP whole body bone scintigraphy. To assess the performance for classification model in clinical study, the discrimination and calibration of an ANN model was calculated. The enrolled subjects consisted of 111 consecutive male patients aged 72.41∈±∈7.69 years with prostate cancer. Sixty-seven patients (60.4{\%}) had skeletal metastasis based on the scintigraphic diagnosis. The final best architecture of neural network model was four-layered perceptrons. The area under the receiver-operating characteristics curve (0.88∈±∈0. 07) revealed excellent discriminatory power (p∈∈0.05), which represented a good-fit calibration. These results suggest that an ANN, which is based on limited clinical parameters, appears to be a promising method in forecasting of the skeletal metastasis in patients with prostate cancer.",
keywords = "Artificial intelligence, Bone metastasis, Computer assisted, Image interpretation, Prostatic neoplasm, Radionuclide imaging",
author = "Chiu, {Jainn Shiun} and Wang, {Yuh Feng} and Su, {Yu Cheih} and Wei, {Ling Huei} and Liao, {Jian Guo} and Li, {Yu Chuan}",
year = "2009",
month = "4",
doi = "10.1007/s10916-008-9168-2",
language = "English",
volume = "33",
pages = "91--100",
journal = "Journal of Medical Systems",
issn = "0148-5598",
publisher = "Springer New York",
number = "2",

}

TY - JOUR

T1 - Artificial neural network to predict skeletal metastasis in patients with prostate cancer

AU - Chiu, Jainn Shiun

AU - Wang, Yuh Feng

AU - Su, Yu Cheih

AU - Wei, Ling Huei

AU - Liao, Jian Guo

AU - Li, Yu Chuan

PY - 2009/4

Y1 - 2009/4

N2 - The application of an artificial neural network (ANN) in prediction of outcomes using clinical data is being increasingly used. The aim of this study was to assess whether an ANN model is a useful tool for predicting skeletal metastasis in patients with prostate cancer. Consecutive patients with prostate cancer who underwent the technetium-99m methylene diphosphate (Tc-99m MDP) whole body bone scintigraphies were retrospectively analyzed between 2001 and 2005. The predictors were the patient's age and radioimmunometric serum PSA concentration. The outcome variable was dichotomous, either skeletal metastasis or non-skeletal metastasis, based on the results of Tc-99m MDP whole body bone scintigraphy. To assess the performance for classification model in clinical study, the discrimination and calibration of an ANN model was calculated. The enrolled subjects consisted of 111 consecutive male patients aged 72.41∈±∈7.69 years with prostate cancer. Sixty-seven patients (60.4%) had skeletal metastasis based on the scintigraphic diagnosis. The final best architecture of neural network model was four-layered perceptrons. The area under the receiver-operating characteristics curve (0.88∈±∈0. 07) revealed excellent discriminatory power (p∈∈0.05), which represented a good-fit calibration. These results suggest that an ANN, which is based on limited clinical parameters, appears to be a promising method in forecasting of the skeletal metastasis in patients with prostate cancer.

AB - The application of an artificial neural network (ANN) in prediction of outcomes using clinical data is being increasingly used. The aim of this study was to assess whether an ANN model is a useful tool for predicting skeletal metastasis in patients with prostate cancer. Consecutive patients with prostate cancer who underwent the technetium-99m methylene diphosphate (Tc-99m MDP) whole body bone scintigraphies were retrospectively analyzed between 2001 and 2005. The predictors were the patient's age and radioimmunometric serum PSA concentration. The outcome variable was dichotomous, either skeletal metastasis or non-skeletal metastasis, based on the results of Tc-99m MDP whole body bone scintigraphy. To assess the performance for classification model in clinical study, the discrimination and calibration of an ANN model was calculated. The enrolled subjects consisted of 111 consecutive male patients aged 72.41∈±∈7.69 years with prostate cancer. Sixty-seven patients (60.4%) had skeletal metastasis based on the scintigraphic diagnosis. The final best architecture of neural network model was four-layered perceptrons. The area under the receiver-operating characteristics curve (0.88∈±∈0. 07) revealed excellent discriminatory power (p∈∈0.05), which represented a good-fit calibration. These results suggest that an ANN, which is based on limited clinical parameters, appears to be a promising method in forecasting of the skeletal metastasis in patients with prostate cancer.

KW - Artificial intelligence

KW - Bone metastasis

KW - Computer assisted

KW - Image interpretation

KW - Prostatic neoplasm

KW - Radionuclide imaging

UR - http://www.scopus.com/inward/record.url?scp=61349119390&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=61349119390&partnerID=8YFLogxK

U2 - 10.1007/s10916-008-9168-2

DO - 10.1007/s10916-008-9168-2

M3 - Article

C2 - 19397093

AN - SCOPUS:61349119390

VL - 33

SP - 91

EP - 100

JO - Journal of Medical Systems

JF - Journal of Medical Systems

SN - 0148-5598

IS - 2

ER -