Outcome Prediction for Salivary Gland Cancer Using Multivariate Adaptative Regression Splines (MARS) and Self-Organizing Maps (SOM)

Over the last decades, advances in diagnosis and tissue microsurgical reconstruction of soft tissues have modified the therapeutic approach to salivary gland cancers, but long term survival rates have increased only marginally. Due to the relatively low frequency of these tumors together with their diverse histopathological types, it is not easy to perform a prognosis assessment. Multivariate adaptative regression splines (MARS) is a data mining technique with a well-known ability to describe a response starting from a large number of predictors. In this work MARS was used for determining the prognosis of cancers of salivary glands using clinical and histological variables, as well as molecular markers. Here, we have generated four different models combining different sets of variables, with sensitivities and specificities that ranging from 95.45 to 100%. Specifically, one of these models which combined five clinical variables (Tumor size – T-, neck node metastasis – N-, distant metastasis – M-, age, and number of tumor recurrences) plus one molecular factor (gelatinase B -MMP-9-) showed a sensitivity and a specificity of 100%. Therefore, the MARS model was applied to the modelling of the influence of several clinical and molecular variables on the prognosis of salivary gland cancers with success. A self-organizing map (SOM) is a type of neural network what was used here to determine a prognostic model composed for four variables: N, M, number of recurrences and tumor type. The sensitivity of this model was that of 97%, and its specificity was that of 94.7%.

[1]  P. Lequerica-Fernández,et al.  Expression of Matrix Metalloproteinase‐9 in High‐Grade Salivary Gland Carcinomas is Associated With Their Metastatic Potential , 2008, The Laryngoscope.

[2]  P. J. García Nieto,et al.  Prediction of work-related accidents according to working conditions using support vector machines , 2011, Appl. Math. Comput..

[3]  M. Ge,et al.  Prognostic significance of p53 immunohistochemical expression in adenoid cystic carcinoma of the salivary glands: a meta-analysis , 2017, Oncotarget.

[4]  P. Rosado,et al.  Carcinoma of the parotid gland: developing prognostic indices. , 2011, International journal of oral and maxillofacial surgery.

[5]  K. Olsen,et al.  Acinic cell carcinoma. Clinicopathologic review , 1991, Cancer.

[6]  J. Califano,et al.  The NOTCH Pathway in Head and Neck Squamous Cell Carcinoma , 2018, Journal of dental research.

[7]  Mauricio A. Valle,et al.  Using self-organizing maps to model turnover of sales agents in a call center , 2017, Appl. Soft Comput..

[8]  E. Maghami,et al.  Diagnosis and Management of Malignant Salivary Gland Tumors of the Parotid Gland. , 2016, Otolaryngologic clinics of North America.

[9]  Zhengxue Han,et al.  Prognostic Factors Associated With Decreased Survival in Patients With Acinic Cell Carcinoma of the Parotid Gland. , 2017, Journal of oral and maxillofacial surgery : official journal of the American Association of Oral and Maxillofacial Surgeons.

[10]  Francisco Javier de Cos Juez,et al.  Artificial neural networks applied to cancer detection in a breast screening programme , 2010, Math. Comput. Model..

[11]  L. Bottaci,et al.  Artificial neural networks applied to outcome prediction for colorectal cancer patients in separate institutions , 1997, The Lancet.

[12]  P. J. García Nieto,et al.  A new improved study of cyanotoxins presence from experimental cyanobacteria concentrations in the Trasona reservoir (Northern Spain) using the MARS technique. , 2012 .

[13]  F. J. D. C. Juez,et al.  Forecasting the COMEX copper spot price by means of neural networks and ARIMA models , 2015 .

[14]  Francisco Javier de Cos Juez,et al.  Application of neural networks to the study of the influence of diet and lifestyle on the value of bone mineral density in post-menopausal women , 2011, Math. Comput. Model..

[15]  J. Grandis,et al.  WHO classification of head and neck tumours , 2017 .

[16]  G. Rousset,et al.  Open-loop tomography with artificial neural networks on CANARY: on-sky results , 2014, 1405.6862.

[17]  R. Seethala,et al.  The Selective Expression of CD43 in Adenoid Cystic Carcinoma , 2008, Applied immunohistochemistry & molecular morphology : AIMM.

[18]  P. J. García Nieto,et al.  Non-linear numerical analysis of a double-threaded titanium alloy dental implant by FEM , 2008, Appl. Math. Comput..

[19]  R. Xia,et al.  Prognostic factors of carcinoma ex pleomorphic adenoma of the salivary glands, with emphasis on the widely invasive carcinoma: a clinicopathologic analysis of 361 cases in a Chinese population. , 2016, Oral surgery, oral medicine, oral pathology and oral radiology.

[20]  Wenjun Yang,et al.  Increased expression of MUC1 predicts poor survival in salivary gland mucoepidermoid carcinoma. , 2014, Journal of cranio-maxillo-facial surgery : official publication of the European Association for Cranio-Maxillo-Facial Surgery.

[21]  C. Balch,et al.  AJCC Cancer Staging Manual. 6th ed , 2002 .

[22]  Jacek Dawidowicz,et al.  Evaluation of a pressure head and pressure zones in water distribution systems by artificial neural networks , 2017, Neural Computing and Applications.

[23]  W. Lydiatt,et al.  Cancers of major salivary glands. , 2015, Surgical oncology clinics of North America.

[24]  B. Wenig.  NEOPLASMS OF THE SALIVARY GLANDS , 2008 .

[25]  M. Ahmed,et al.  Differential expression of c-kit and CD43 in histological subtypes of adenoid cystic carcinoma of salivary gland. , 2010, The Saudi dental journal.

[26]  J. Overgaard,et al.  Does age affect prognosis in salivary gland carcinoma patients? A national Danish study , 2016, Acta oncologica.

[27]  Orlando Guntinas-Lichius,et al.  Prognostic index for patients with parotid carcinoma , 2009, Cancer.

[28]  D. Winchester,et al.  The National Cancer Data Base report on patterns of hospital reporting , 1996, Cancer.

[29]  J. Carrillo,et al.  Multivariate prediction of the probability of recurrence in patients with carcinoma of the parotid gland , 2007, Cancer.

[30]  S. Fujii,et al.  Concomitant expression of ezrin and HER2 predicts distant metastasis and poor prognosis of patients with salivary gland carcinomas. , 2017, Human pathology.

[31]  H Putter,et al.  Expression of cell adhesion molecules and prognosis in breast cancer , 2013, The British journal of surgery.

[32]  C. Barbatis,et al.  Detection of C-KIT (CD117) molecule in benign and malignant salivary gland tumours. , 2006, Oral oncology.

[33]  J. Friedman.  Multivariate adaptive regression splines , 1990 .

[34]  Z. Chenping,et al.  Increased expression of MUC-1 has close relation with patient survivor in high-grade salivary gland mucoepidermoid carcinoma. , 2014, Journal of oral pathology & medicine : official publication of the International Association of Oral Pathologists and the American Academy of Oral Pathology.

[35]  Teuvo Kohonen,et al.  The self-organizing map , 1990, Neurocomputing.

[36]  J. Kerschner,et al.  Expression of mucin (MUC) genes in mucoepidermoid carcinoma , 2011, The Laryngoscope.

[37]  Ganapati Panda,et al.  Hybrid approach using KPSO and RLS for RBFNN design for breast cancer detection , 2012, Neural Computing and Applications.

[38]  Álvaro Herrero,et al.  Features and models for human activity recognition , 2015, Neurocomputing.

[39]  Francisco Javier de Cos Juez,et al.  A Parametric Model of the LARCODEMS Heavy Media Separator by Means of Multivariate Adaptive Regression Splines , 2017, Materials.

[40]  Miguel A. Molina-Cabello,et al.  Smart motion detection sensor based on video processing using self-organizing maps , 2016, Expert Syst. Appl..

[41]  J. Bishop,et al.  Mucoepidermoid Carcinoma Does Not Harbor Transcriptionally Active High Risk Human Papillomavirus Even in the Absence of the MAML2 Translocation , 2014, Head and Neck Pathology.

[42]  T. Silva,et al.  Expression Of Ki-67 and MUC1 In mucoepidermoid carcinomas of young and adult patients: prognostic implications. , 2011, Experimental and molecular pathology.

[43]  Yan Su,et al.  Forecasting the daily power output of a grid-connected photovoltaic system based on multivariate adaptive regression splines , 2016 .

[44]  Víctor M. González Suárez,et al.  Generalized Models for the Classification of Abnormal Movements in Daily Life and its Applicability to Epilepsy Convulsion Recognition , 2016, Int. J. Neural Syst..

[45]  Elif Derya íbeyli.  Implementing automated diagnostic systems for breast cancer detection , 2007 .

[46]  T. Hastie,et al.  Comparative performance of generalized additive models and multivariate adaptive regression splines for statistical modelling of species distributions , 2006 .

[47]  C. Leemans,et al.  Histopathological grading of adenoid cystic carcinoma of the head and neck: analysis of currently used grading systems and proposal for a simplified grading scheme. , 2015, Oral oncology.

[48]  P. Lequerica-Fernández,et al.  Expression of vascular endothelial growth factor in salivary gland carcinomas correlates with lymph node metastasis. , 2007, Anticancer research.

[49]  Francisco Javier de Cos Juez,et al.  A Hybrid Device of Self Organizing Maps (SOM) and Multivariate Adaptive Regression Splines (MARS) for the Forecasting of Firms’ Bankruptcy , 2011 .