The Effect of Artificial Neural Network Model Combined with Six Tumor Markers in Auxiliary Diagnosis of Lung Cancer
- 1 September 2011
- journal article
- Published by Springer Science and Business Media LLC in Journal of Medical Systems
- Vol. 36 (5), 2973-2980
- https://doi.org/10.1007/s10916-011-9775-1
Abstract
To evaluate the diagnosis potential of artificial neural network (ANN) model combined with six tumor markers in auxiliary diagnosis of lung cancer, to differentiate lung cancer from lung benign disease, normal control, and gastrointestinal cancers. Serum carcino-embryonic antigen (CEA), gastrin, neurone specific enolase (NSE), sialic acid (SA), Cu/Zn, Ca were measured through different experimental procedures in 117 lung cancer patients, 93 lung benign disease patients, 111 normal control, 47 gastric cancer patients, 50 patients with colon cancer and 50 esophagus cancer patients, 19 parameters of basic information were surveyed among lung cancer, lung benign disease and normal control, then developed and evaluated ANN models to distinguish lung cancer. Using the ANN model with the six serum tumor markers and 19 parameters to distinguish lung cancer from benign lung disease and healthy people, the sensitivity was 98.3%, the specificity was 99.5% and the accuracy was 96.9%. Another three ANN models with the six serum tumor markers were employed to differentiate lung cancer from three gastrointestinal cancers, the sensitivity, specificity and accuracy of distinguishing lung cancer from gastric cancer by the ANN model of lung cancer-gastric cancer were 100%, 83.3% and 93.5%, respectively; The sensitivity, specificity and accuracy of discriminating lung cancer by lung cancer-colon cancer ANN model were 90.0%, 90.0%, and 90.0%; And which were 86.7%, 84.6%, and 86.0%, respectively, by lung cancer-esophagus cancer ANN model. ANN model built with the six serum tumor markers could distinguish lung cancer, not only from lung benign disease and normal people, but also from three common gastrointestinal cancers. And our evidence indicates the ANN model maybe is an excellent and intelligent system to discriminate lung cancer.Keywords
This publication has 23 references indexed in Scilit:
- An optimal tumor marker group-coupled artificial neural network for diagnosis of lung cancerExpert Systems with Applications, 2011
- Combined use of biomarkers for detection of ovarian cancer in high-risk womenTumor Biology, 2010
- A review of novel biological tools used in screening for the early detection of lung cancerPostgraduate Medical Journal, 2009
- Highly sensitive detection of melanoma based on serum proteomic profilingZeitschrift für Krebsforschung und Klinische Onkologie, 2009
- XRCC1 polymorphisms, cooking oil fume and lung cancer in Chinese women nonsmokersLung Cancer, 2008
- Erythrocyte and Platelet Phospholipid Fatty Acids as Markers of Advanced Non-Small Cell Lung Cancer: Comparison with Serum Levels of Sialic Acid, TPS and Cyfra 21-1Cancer Investigation, 2008
- Combining multiple serum tumor markers improves detection of stage I epithelial ovarian cancerGynecologic Oncology, 2007
- Biomarkers for lung cancer: clinical usesCurrent Opinion in Pulmonary Medicine, 2007
- Prognostic accuracy of an artificial neural network in patients undergoing radical cystectomy for bladder cancer: a comparison with logistic regression analysisBJU International, 2007
- Elucidation of a protein signature discriminating six common types of adenocarcinomaInternational Journal of Cancer, 2006