{"title":"Comparison of Neural Network and Logistic Regression Methods to Predict Xerostomia after Radiotherapy","authors":"Hui-Min Ting, Tsair-Fwu Lee, Ming-Yuan Cho, Pei-Ju Chao, Chun-Ming Chang, Long-Chang Chen, Fu-Min Fang","volume":79,"journal":"International Journal of Biomedical and Biological Engineering","pagesStart":413,"pagesEnd":418,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/16509","abstract":"
To evaluate the ability to predict xerostomia after
\r\nradiotherapy, we constructed and compared neural network and
\r\nlogistic regression models. In this study, 61 patients who completed a
\r\nquestionnaire about their quality of life (QoL) before and after a full
\r\ncourse of radiation therapy were included. Based on this questionnaire,
\r\nsome statistical data about the condition of the patients’ salivary
\r\nglands were obtained, and these subjects were included as the inputs of
\r\nthe neural network and logistic regression models in order to predict
\r\nthe probability of xerostomia. Seven variables were then selected from
\r\nthe statistical data according to Cramer’s V and point-biserial
\r\ncorrelation values and were trained by each model to obtain the
\r\nrespective outputs which were 0.88 and 0.89 for AUC, 9.20 and 7.65
\r\nfor SSE, and 13.7% and 19.0% for MAPE, respectively. These
\r\nparameters demonstrate that both neural network and logistic
\r\nregression methods are effective for predicting conditions of parotid
\r\nglands.<\/p>\r\n","references":"
[1] T. F. Lee, P. J. Chao, H. M. Ting, S. H. Lo, Y. W. Wang, C. C. Tuan, F.\r\nM. Fang, and T. J. Su, "Comparative analysis of SmartArc-based dual arc\r\nvolumetric-modulated arc radiotherapy (VMAT) versus\r\nintensity-modulated radiotherapy (IMRT) for nasopharyngeal\r\ncarcinoma," J Appl Clin Med Phys, vol. 12, p. 3587, 2011.\r\n[2] C. Y. Hsiung, H. M. Ting, H. Y. Huang, C. H. Lee, E. Y. Huang, and H. C.\r\nHsu, "Parotid-sparing intensity-modulated radiotherapy (IMRT) for\r\nnasopharyngeal carcinoma: preserved parotid function after IMRT on\r\nquantitative salivary scintigraphy, and comparison with historical data\r\nafter conventional radiotherapy," Int J Radiat Oncol Biol Phys, vol. 66,\r\npp. 454-61, 2006.\r\n[3] M. Agulnik and J. B. Epstein, "Nasopharyngeal carcinoma: current\r\nmanagement, future directions and dental implications," Oral Oncol, vol.\r\n44, pp. 617-27, 2008.\r\n[4] Y. P. Talmi, Z. Horowitz, L. Bedrin, M. Wolf, G. Chaushu, J.\r\nKronenberg, and M. R. Pfeffer, "Quality of life of nasopharyngeal\r\ncarcinoma patients," Cancer, vol. 94, pp. 1012-7, 2002.\r\n[5] V. W. Wu, M. T. Ying, and D. L. Kwong, "Evaluation of\r\nradiation-induced changes to parotid glands following conventional\r\nradiotherapy in patients with nasopharygneal carcinoma," Br J Radiol,\r\nvol. 84, pp. 843-9, 2011.\r\n[6] J.-C. Shyu and H.-Y. Liou, " The financial distress prediction model\r\nunder consideration of business cycle and industry factors - the\r\napplication of logistic regression model and DEA-DA model " Journal of\r\nRisk Management, vol. 12, pp. 157-183, 2010.\r\n[7] J. O. Deasy, J. R. Alaly, and K. Zakaryan, "Obstacles and advances in\r\nintensity-modulated radiation therapy treatment planning," Front Radiat\r\nTher Oncol, vol. 40, pp. 42-58, 2007.\r\n[8] M. Isaksson, J. Jalden, and M. J. Murphy, "On using an adaptive neural\r\nnetwork to predict lung tumor motion during respiration for radiotherapy\r\napplications," Med Phys, vol. 32, pp. 3801-9, 2005.\r\n[9] L. Zhang, L. Jia, and W. Zhu, "Overview of traffic flow hybrid ANN\r\nforecasting algorithm study," in 2010 International Conference on\r\nComputer Application and System Modeling (ICCASM), , 2010, pp.\r\nV1-615-V1-619.\r\n[10] M. H. Zweig and G. Campbell, "Receiver-operating characteristic (ROC)\r\nplots: a fundamental evaluation tool in clinical medicine," Clin Chem, vol.\r\n39, pp. 561-77, 1993.\r\n[11] H.-L. Chen and D.-W. Tsai, "A study of predictive abilities for different\r\nmodels," Journal of Soil and Water Conservation, vol. 37, pp. 127-138,\r\n2005.\r\n[12] M. Z. Liu, L. L. Tang, J. F. Zong, Y. Huang, Y. Sun, Y. P. Mao, L. Z. Liu,\r\nA. H. Lin, and J. Ma, "Evaluation of sixth edition of AJCC staging system\r\nfor nasopharyngeal carcinoma and proposed improvement," Int J Radiat\r\nOncol Biol Phys, vol. 70, pp. 1115-23, 2008.\r\n[13] A. Lin, H. M. Kim, J. E. Terrell, L. A. Dawson, J. A. Ship, and A.\r\nEisbruch, "Quality of life after parotid-sparing IMRT for head-and-neck\r\ncancer: a prospective longitudinal study," Int J Radiat Oncol Biol Phys,\r\nvol. 57, pp. 61-70, 2003.\r\n[14] F. M. Fang, W. L. Tsai, T. F. Lee, K. C. Liao, H. C. Chen, and H. C. Hsu,\r\n"Multivariate analysis of quality of life outcome for nasopharyngeal\r\ncarcinoma patients after treatment," Radiother Oncol, vol. 97, pp. 263-9,\r\n2010.\r\n[15] I. Beetz, C. Schilstra, A. van der Schaaf, E. R. van den Heuvel, P.\r\nDoornaert, P. van Luijk, A. Vissink, B. F. van der Laan, C. R. Leemans,\r\nH. P. Bijl, M. E. Christianen, R. J. Steenbakkers, and J. A. Langendijk,\r\n"NTCP models for patient-rated xerostomia and sticky saliva after\r\ntreatment with intensity modulated radiotherapy for head and neck\r\ncancer: the role of dosimetric and clinical factors," Radiother Oncol, vol.\r\n105, pp. 101-6, 2012.\r\n[16] A. Borque, G. Sanz, C. Allepuz, L. Plaza, P. Gil, and L. A. Rioja, "The\r\nuse of neural networks and logistic regression analysis for predicting\r\npathological stage in men undergoing radical prostatectomy: a population\r\nbased study," J Urol, vol. 166, pp. 1672-8, 2001.\r\n[17] J. H. Song, S. S. Venkatesh, E. A. Conant, P. H. Arger, and C. M. Sehgal,\r\n"Comparative analysis of logistic regression and artificial neural network\r\nfor computer-aided diagnosis of breast masses," Acad Radiol, vol. 12, pp.\r\n487-95, 2005.\r\n[18] B. Eftekhar, K. Mohammad, H. E. Ardebili, M. Ghodsi, and E. Ketabchi,\r\n"Comparison of artificial neural network and logistic regression models\r\nfor prediction of mortality in head trauma based on initial clinical data,"\r\nBMC Medical Informatics and Decision Making, vol. 5, p. 3, 2005.<\/p>\r\n","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 79, 2013"}