Research Article | Open Access
Weizeng Ni, Samuel H. Huang, Qiang Su, Jinghua Shi, "Model-Independent Evaluation of Tumor Markers and a Logistic-Tree Approach to Diagnostic Decision Support", Journal of Healthcare Engineering, vol. 5, Article ID 391407, 18 pages, 2014. https://doi.org/10.1260/2040-2222.214.171.1243
Model-Independent Evaluation of Tumor Markers and a Logistic-Tree Approach to Diagnostic Decision Support
Sensitivity and specificity of using individual tumor markers hardly meet the clinical requirement. This challenge gave rise to many efforts, e.g., combing multiple tumor markers and employing machine learning algorithms. However, results from different studies are often inconsistent, which are partially attributed to the use of different evaluation criteria. Also, the wide use of model-dependent validation leads to high possibility of data overfitting when complex models are used for diagnosis. We propose two model-independent criteria, namely, area under the curve (AUC) and Relief to evaluate the diagnostic values of individual and multiple tumor markers, respectively. For diagnostic decision support, we propose the use of logistic-tree which combines decision tree and logistic regression. Application on a colorectal cancer dataset shows that the proposed evaluation criteria produce results that are consistent with current knowledge. Furthermore, the simple and highly interpretable logistic-tree has diagnostic performance that is competitive with other complex models.
- H. Özkan, M. Kaya, and A. Cengiz, “Comparison of tumor marker CA 242 with CA 19-9 and carcinoembryonic antigen (CEA) in pancreatic cancer,” Hepato-Gastroenterology, vol. 50, pp. 1669–1674, 2003.
- M. Moghimi and I. Ghodosi, “Clinical efficacy of combined use of CEA-CA19-9 in patients with pancreatic malignancy,” Journal of Medical Sciences, vol. 7, pp. 625–629, 2007.
- X. G. Ni, X. F. Bai, Y. L. Mao, Y. F. Shao, J. X. Wu, Y. Shan et al., “The clinical value of serum CEA, CA19-9, and CA242 in the diagnosis and prognosis of pancreatic cancer,” European Journal of Surgical Oncology, vol. 31, pp. 164–169, 2005.
- Z. Sun, X. Fu, L. Zhang, X. Yang, F. Liu, and G. Hu, “A Protein Chip System for Parallel Analysis of Multi-tumor Markers and its Application in Cancer Detection,” Anticancer Research, vol. 24, pp. 1159–1165, 2004.
- L. M. McShane, D. G. Altman, W. Sauerbrei, S. E. Taube, M. Gion, and G. M. Clark, “Reporting recommendations for tumor marker prognostic studies,” Journal of Clinical Oncology, vol. 23, pp. 9067–9072, 2005.
- D. Marrelli, S. Caruso, A. Neri, C. Pedrazzani, L. Capuano, M. A. Mazzei et al., “Clinical utility of serum tumor markers in the diagnosis of malignant intestinal occlusion. A prospective observational study,” International Journal of Biological Markers, vol. 26, pp. 58–64, 2011.
- X. L. Qin, Z. R. Wang, J. S. Shi, M. Lu, L. Wang, and Q. R. He, “Utility of serum CA19-9 in diagnosis of cholangiocarcinoma: In comparison with CEA,” World Journal of Gastroenterology, vol. 10, pp. 427–432, 2004.
- M. Carpelan-Holmström, J. Louhimo, U. H. Stenman, H. Alfthan, H. Järvinen, and C. Haglund, “Estimating the probability of cancer with several tumor markers in patients with colorectal disease,” Oncology, vol. 66, pp. 296–302, 2004.
- T. C. W. Poon, A. T. C. Chan, B. Zee, S. K. W. Ho, T. S. K. Mok, T. W. T. Leung et al., “Application of classification tree and neural network algorithms to the identification of serological liver marker profiles for the diagnosis of hepatocellular carcinoma,” Oncology, vol. 61, pp. 275–283, 2001.
- H. J. Song, Y. S. Kim, K. W. Choi, J. D. Kim, C. Y. Park, E. Lee et al., “Building Biomarker Combinations for Korean Ovarian Cancer Screening Using Statistics and Machine Learning,” Applied Mechanics and Materials, vol. 145, pp. 229–233, 2012.
- S. M. Winkler, M. Affenzeller, W. Jacak, and H. Stekel, “Identification of cancer diagnosis estimation models using evolutionary algorithms: a case study for breast cancer, melanoma, and cancer in the respiratory system,” in Proceedings of the 13th annual conference companion on Genetic and evolutionary computation, pp. 503–510, ACM, 2011.
- Winkler*, S. M., Affenzeller, M., Kronberger, G., Kommenda, M., Wagner, S., Dorfer, V. et al. “On the use of estimated tumour marker classifications in tumour diagnosis prediction-a case study for breast cancer,” International Journal of Simulation and Process Modelling. 2013, 8:29-41.
- L. Bottaci, P. J. Drew, J. E. Hartley, M. B. Hadfield, R. Farouk, P. W. R. Lee et al., “Artificial neural networks applied to outcome prediction for colorectal cancer patients in separate institutions,” Lancet, vol. 350, pp. 469–472, 1997.
- R. N. G. Naguib, M. C. Robinson, D. E. Neal, and F. C. Hamdy, “Neural network analysis of combined conventional and experimental prognostic markers in prostate cancer: A pilot study,” British Journal of Cancer, vol. 78, pp. 246–250, 1998.
- Y. Wu, Y. Wu, J. Wang, Z. Yan, L. Qu, B. Xiang et al., “An optimal tumor marker group-coupled artificial neural network for diagnosis of lung cancer,” Expert Systems with Applications, vol. 38, pp. 11329–11334, 2011.
- J. Flores, E. Herrera, G. Leal, M. González, F. Sánchez, A. Rojas et al., “Artificial neural network-based serum biomarkers analysis improves sensitivity in the diagnosis of lung cancer,” in V Latin American Congress on Biomedical Engineering CLAIB 2011, pp. 882–885, Springer, Habana, Cuba, May 16-21, 2011.
- J. M. Flores-Fernández, E. J. Herrera-López, F. Sánchez-Llamas, A. Rojas-Calvillo, P. A. Cabrera-Galeana, G. Leal-Pacheco et al., “Development of an optimized multi-biomarker panel for the detection of lung cancer based on principal component analysis and artificial neural network modeling,” Expert Systems with Applications, vol. 39, pp. 10851–10856, 2012.
- T. Casas Pina, I. Tovar Zapata, J. Bermejo López, J. Latour Pérez, P. P. Paricio, and P. Martínez Hernández, “Tumor markers in lung cancer: Does the method of obtaining the cut-off point and reference population influence diagnostic yield?” Clinical Biochemistry, vol. 32, pp. 467–472, 1999.
- H. Körner, K. Söreide, P. J. Stokkeland, and J. A. Söreide, “Diagnostic accuracy of serum-carcinoembryonic antigen in recurrent colorectal cancer: A receiver operating characteristic curve analysis,” Annals of Surgical Oncology, vol. 14, pp. 417–423, 2007.
- H. L. Weiss, S. Niwas, W. E. Grizzle, and C. Piyathilake, “Receiver operating characteristic (ROC) to determine cut-off points of biomarkers in lung cancer patients,” Disease Markers, vol. 19, pp. 273–278, 2003.
- H.-J. Song, J.-K. Yim, C.-Y. Park, Y.-S. Kim, and J.-D. Kim, “Comparison of the Diagnostic Performances of CA125 and Multiple Marker Combinations for Early Diagnosis of Ovarian Cancer,” International Journal of Bio-Science & Bio-Technology, vol. 5, 2013.
- K. Kira and L. A. Rendell, “A Practical Approach to Feature Selection,” in Proceedings of the Ninth International Workshop on Machine Learning, pp. 249–256, Morgan Kaufmann Publishers Inc, 1992.
- M. Robnik-Šikonja and I. Kononenko, “Theoretical and Empirical Analysis of ReliefF and RReliefF,” Machine Learning, vol. 53, pp. 23–69, 2003.
- J. Shi, Q. Su, C. Zhang, G. Huang, and Y. Zhu, “An intelligent decision support algorithm for diagnosis of colorectal cancer through serum tumor markers,” Computer Methods and Programs in Biomedicine, vol. 100, pp. 97–107, 2010.
- R. C. Bast Jr., P. Ravdin, D. F. Hayes, S. Bates, H. Fritsche Jr., J. M. Jessup et al., “Update of recommendations for the use of tumor markers in breast and colorectal cancer: Clinical practice guidelines of the American Society of Clinical Oncology,” Journal of Clinical Oncology, vol. 19, pp. 1865–1878, 2000.
- N. Calonge, D. B. Petitti, T. G. DeWitt, A. J. Dietrich, K. D. Gregory, R. Harris et al., “Screening for colorectal cancer: U.S. Preventive Services Task Force recommendation statement,” Annals of Internal Medicine, vol. 149, pp. 627–637, 2008.
Copyright © 2014 Hindawi Publishing Corporation. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.