A Highly Efficient Gene Expression Programming (GEP) Model for Auxiliary Diagnosis of Small Cell Lung Cancer

Abstract

Background: Lung cancer is an important and common cancer that constitutes a major public health problem, but early detection of small cell lung cancer can significantly improve the survival rate of cancer patients. A number of serum biomarkers have been used in the diagnosis of lung cancers; however, they exhibit low sensitivity and specificity.

Methods: We used biochemical methods to measure blood levels of lactate dehydrogenase (LDH), C-reactive protein (CRP), Na+, Cl-, carcino-embryonic antigen (CEA), and neuron specific enolase (NSE) in 145 small cell lung cancer (SCLC) patients and 155 non-small cell lung cancer and 155 normal controls. A gene expression programming (GEP) model and Receiver Operating Characteristic (ROC) curves incorporating these biomarkers was developed for the auxiliary diagnosis of SCLC.

Results: After appropriate modification of the parameters, the GEP model was initially set up based on a training set of 115 SCLC patients and 125 normal controls for GEP model generation. Then the GEP was applied to the remaining 60 subjects (the test set) for model validation. GEP successfully discriminated 281 out of 300 cases, showing a correct classification rate for lung cancer patients of 93.75% (225/240) and 93.33% (56/60) for the training and test sets, respectively. Another GEP model incorporating four biomarkers, including CEA, NSE, LDH, and CRP, exhibited slightly lower detection sensitivity than the GEP model, including six biomarkers. We repeat the models on artificial neural network (ANN), and our results showed that the accuracy of GEP models were higher than that in ANN. GEP model incorporating six serum biomarkers performed by NSCLC patients and normal controls showed low accuracy than SCLC patients and was enough to prove that the GEP model is suitable for the SCLC patients.

Conclusion: We have developed a GEP model with high sensitivity and specificity for the auxiliary diagnosis of SCLC. This GEP model has the potential for the wide use for detection of SCLC in less developed regions.

Fig 1. Histopathologic test of SCLC patients.

A. hematoxylin-eosin staining of biopsy specimen slice. B. CD56(+) findings in immunohistochemical method. C. Syn (+) findings in immunohistochemical method. D.TTF-1(+) findings in immunohistochemical method

Fig 2. The flowchart of the GEP modeling in this study.

Fig 3. ROC curves analyses to represent sensitivity/specificity of each biomarker, and the Area Under the Curve represents: LDH = 0.717, CRP = 0.786, CEA = 0.748, NSE = 0.670, Na⁺ = 0.279, Cl^- = 0.255.

Fig 4. Comparison of the performance (sensitivity) from combined biomarkers, A is trained with six biomarkers and B is trained with four biomarkers.

The sensitivity trained by six biomarkers combination performed better than four biomarkers.

Fig 5. The structure of the ANNs implemented.