Advertisement

Outcome prediction for salivary gland cancer using multivariate adaptative regression splines (MARS) and self-organizing maps (SOM)

  • Paloma Lequerica-Fernández
  • Ignacio Peña
  • Francisco Javier Iglesias-Rodríguez
  • Carlos González-Gutiérrez
  • Juan Carlos De Vicente
S.I. : AI and ML applied to Health Sciences (MLHS)
  • 18 Downloads

Abstract

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 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 modeling 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%.

Keywords

Salivary gland cancer Prognosis Data mining Multivariate adaptative regression splines (MARS) 

Notes

Acknowledgements

This work was supported by a grant for scientific research from the Ministry of Health, Spain (Instituto de Salud Carlos III, PI070675).

Compliance with ethical standards

Conflict of interest

The authors report no conflicts of interest in this work.

References

  1. 1.
    Center for Disease Control Statistics. United States cancer statistics. Available at: http://www.apps.nccd.cdc.gov./uscs/cancersbyraceandethnicity.aspx. (2014)Google Scholar
  2. 2.
    De Vicente JC, Lequerica-Fernández P, López-Arranz JS, Esteban I, Fresno MF, Astudillo A (2008) Expression of matrix metalloproteinase-9 in high grade salivary gland carcinomas is associated with their metastatic potential. Laryngoscope 118:247–251CrossRefGoogle Scholar
  3. 3.
    Lequerica-Fernández P, Astudillo A, De Vicente JC (2007) Expression of vascular endothelial growth factor in salivary gland carcinomas correlates with lymph node metastasis. Anticancer Res 27:3661–3666Google Scholar
  4. 4.
    Hashimoto K, Hayashi R, Mukaigawa T, Yamazaki M, Fujii S (2017) Concomitant expression of ezrin and HER2 predicts distant metastasis and poor prognosis of patients with salivary gland carcinomas. Hum Pathol 63:110–119CrossRefGoogle Scholar
  5. 5.
    Li Q, Huang P, Zheng C, Wang J, Ge M (2017) Prognostic significance of p53 immunohistochemical expression in adenoid cystic carcinoma of the salivary glands: a meta-analysis. Oncotarget 8:29458–29473Google Scholar
  6. 6.
    Saadatmand S, de Kruijf EM, Sajet A, Dekker-Ensink NG, van Nes JG, Putter H, Smit VT, van de Velde CJ, Liefers GJ, Kuppen PJ (2013) Expression of cell adhesion molecules and prognosis in breast cancer. Brit J Surg 100:252–260CrossRefGoogle Scholar
  7. 7.
    Carrillo JF, Vázquez R, Ramírez-Ortega MC, Cano A, Ochoa-Carrillo FJ, Oñate-Ocaña LF (2007) Multivariate prediction of the probability of recurrence in patients with carcinoma of the parotid gland. Cancer 109:2043–2051CrossRefGoogle Scholar
  8. 8.
    Lequerica-Fernández P, Peña I, Villalaín L, Rosado P, de Vicente JC (2011) Carcinoma of the parotid gland: developing prognostic indices. Int J Oral Maxillofac Surg 40:821–828CrossRefGoogle Scholar
  9. 9.
    Vander Poorten VL, Hart A, Vauterin T, Jeunen G, Schoenaers J, Hamoir M, Balm A, Stennert E, Guntinas-Lichius O, Delaere P (2009) Prognostic index for patients with parotid carcinoma. International external validation in a Belgian-German database. Cancer 1:540–550CrossRefGoogle Scholar
  10. 10.
    Friedman JH (1991) Multivariate Adaptive Regression Splines. The Annals of Statistics 19(1):1–67MathSciNetCrossRefzbMATHGoogle Scholar
  11. 11.
    Menéndez LÁ, de Cos Juez FJ, Lasheras FS, Riesgo JAÁ (2010) Artificial neural networks applied to cancer detection in a breast screening programme. Math Comput Model 52(7):983–991MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Senapati R, Panda G, Dash PK (2014) Hybrid approach using KPSO and RLS for RBFNN design for breast cancer detection. Neural Comput Appl 24(3–4):745–753CrossRefGoogle Scholar
  13. 13.
    Dawidowicz J (2017) Evaluation of a pressure head and pressure zones in water distribution systems by artificial neural networks. Neural Comput Appl.  https://doi.org/10.1007/s00521-017-2844-8 Google Scholar
  14. 14.
    Lasheras FS, de Cos Juez FJ, Sánchez AS, Krzemień A, Fernández PR (2015) Forecasting the COMEX copper spot price by means of neural networks and ARIMA models. Resour Policy 45:37–43CrossRefGoogle Scholar
  15. 15.
    Menéndez-Álvarez M, Muñíz-Sierra H, Sánchez-Lasheras F, de Cos-Juez FJ (2017) A parametric model of the LARCODEMS heavy media separator by means of multivariate adaptive regression splines. Materials 10:729CrossRefGoogle Scholar
  16. 16.
    Li Y, He Y, Su Y, Shu L (2016) Forecasting the daily power output of a grid-connected photovoltaic system based on multivariate adaptive regression splines. Appl Energ 180:392–401CrossRefGoogle Scholar
  17. 17.
    Nieto PJG, Fernández JRA, Lasheras FS, de Cos-Juez FJ, Muñiz CD (2012) A new improved study of cyanotoxins presence from experimental cyanobacteria concentrations in the Trasona reservoir (Northern Spain) using the MARS technique. Sci Total Environ 430:88–92CrossRefGoogle Scholar
  18. 18.
    De Andrés J, Sánchez-Lasheras F, Lorca P, de Cos-Juez FJ (2011) A hybrid device of self organizing maps (SOM) and multivariate adaptive regression splines (MARS) for the forecasting of firms’ bankruptcy. Account Manag Inf Syst 10(3):351Google Scholar
  19. 19.
    Leathwick JR, Elith J, Hastie T (2006) Comparative performance of generalized additive models and multivariate adaptive regression splines for statistical modelling of species distributions. Ecol Eng 199:188–196Google Scholar
  20. 20.
    Kohonen T (1990) The self-organizing map. Proc IEEE 78:1464–1480CrossRefGoogle Scholar
  21. 21.
    Ortega-Zamorano F, Molina-Cabello MA, López-Rubio E, Palomo EJ (2016) Smart motion detection sensor based on video processing using self-organizing maps. Expert Syst. Appl 64:476–489CrossRefGoogle Scholar
  22. 22.
    Valle MA, Ruz GA, Masías VH (2017) Using self-organizing maps to model turnover of sales agents in a call center. Appl Soft Comput 60:763–774CrossRefGoogle Scholar
  23. 23.
    El-Naggar AK, Chan JKC, Grandis JR, Takata T, Slootweg PJ (eds) (2017) WHO classification of head and neck tumours. International Agency for Research on Cancer, LyonGoogle Scholar
  24. 24.
    Panwar A, Kozel JA, Lydiatt WM (2015) Cancers of major salivary glands. Surg Oncol Clin N Am 24:615–633CrossRefGoogle Scholar
  25. 25.
    Andreadis D, Epivatianos A, Poulopoulos A, Nomikos A, Papazoglou G, Antoniades D, Barbatis C (2006) Detection of C-KIT (CD117) molecule in benign and malignant salivary gland tumours. Oral Oncol 42:57–65CrossRefGoogle Scholar
  26. 26.
    Bishop JA, Yonescu R, Batista D, Yemelyanova A, Ha PK, Westra WH (2014) Mucoepidermoid carcinoma does not harbor transcriptionally active high risk human papillomavirus even in the absence of the MAML2 translocation. Head Neck Pathol 8:298–302CrossRefGoogle Scholar
  27. 27.
    Liu S, Ruan M, Li S, Wang L, Yang W (2014) Increased expression of MUC1 predicts poor survival in salivary gland mucoepidermoid carcinoma. J Craniomaxillofac Surg 42:1891–1896CrossRefGoogle Scholar
  28. 28.
    Siyi L, Shengwen L, Min R, Wenjun Y, Lizheng W, Chenping Z (2014) Increased expression of MUC-1 has close relation with patient survivor in high-grade salivary gland mucoepidermoid carcinoma. J Oral Pathol Med 43:579–584CrossRefGoogle Scholar
  29. 29.
    Gonçalves CF, Morais MO, Alencar RdeC, Mota ED, Silva TA, Batista AC, Mendonça EF (2011) Expression of Ki-67 and MUC1 In mucoepidermoid carcinomas of young and adult patients: prognostic implications. Exp Mol Pathol 90:271–275CrossRefGoogle Scholar
  30. 30.
    Shemirani N, Osipov V, Kolker A, Khampang P, Kerschner JE (2011) Expression of mucin (MUC) genes in mucoepidermoid carcinoma. Laryngoscope 121:167–170CrossRefGoogle Scholar
  31. 31.
    Fukusumi T, Califano JA (2018) The NOTCH pathway in head and neck squamous cell carcinoma. J Dent Res 1:22034518760297Google Scholar
  32. 32.
    van Weert S, van der Waal I, Witte BI, Leemans CR, Bloemena E (2015) Histopathological grading of adenoid cystic carcinoma of the head and neck: analysis of currently used grading systems and proposal for a simplified grading scheme. Oral Oncol 51:71–76CrossRefGoogle Scholar
  33. 33.
    Ahmed MM, Abo-Hager EA (2010) Differential expression of c-kit and CD43 in histological subtypes of adenoid cystic carcinoma of salivary gland. Saudi Dent J 22:27–34CrossRefGoogle Scholar
  34. 34.
    Seethala RR, Pasha TL, Raghunath PN, Livolsi VA, Zhang PJ (2008) The selective expression of CD43 in adenoid cystic carcinoma. Appl Immunohistochem Mol Morphol 16:165–172CrossRefGoogle Scholar
  35. 35.
    Lewis AG, Tong T, Maghami E (2016) Diagnosis and management of malignant salivary gland tumors of the parotid gland. Otolaryngol Clin North Am 49:343–380CrossRefGoogle Scholar
  36. 36.
    Lewis JE, Olsen KD, Weiland LH (1991) Acinic cell carcinoma. Clinicopathologic review. Cancer 67:172–179CrossRefGoogle Scholar
  37. 37.
    Liu Y, Su M, Yang Y, Zhao B, Qin L, Han Z (2017) Prognostic factors associated with decreased survival in patients with acinic cell carcinoma of the parotid gland. J Oral Maxillofac Surg 75:416–422CrossRefGoogle Scholar
  38. 38.
    Wenig BM (2008) Section 4: major and minor salivary glands. Neoplasms of the salivary glands. In: Wenig BM (ed) Atlas of head and neck pathology, 2nd edn. Elsevier, Philadelphia, pp 582–702CrossRefGoogle Scholar
  39. 39.
    Hu YH, Zhang CY, Xia RH, Tian Z, Wang LZ, Li J (2016) 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. Oral Surg Oral Med Oral Pathol Oral Radiol 122:598–608CrossRefGoogle Scholar
  40. 40.
    Bjørndal K, Larsen SR, Therkildsen MH, Kristensen CA, Charabi B, Andersen E, Overgaard J, Schytte S, Pedersen HB, Andersen LI, Johansen J, Godballe C (2016) Danish Head and Neck Cancer Group (DAHANCA) and Academy of Geriatric Cancer Research (AgeCare). Does age affect prognosis in salivary gland carcinoma patients? A national Danish study. Acta Oncol 55(Suppl 1):19–22CrossRefGoogle Scholar

Copyright information

© The Natural Computing Applications Forum 2018

Authors and Affiliations

  • Paloma Lequerica-Fernández
    • 1
  • Ignacio Peña
    • 2
  • Francisco Javier Iglesias-Rodríguez
    • 3
  • Carlos González-Gutiérrez
    • 4
  • Juan Carlos De Vicente
    • 1
    • 2
  1. 1.Department of BiochemistryInstituto Universitario de Oncología del Principado de Asturias (IUOPA), Hospital Universitario Central de Asturias (HUCA)OviedoSpain
  2. 2.Department of Oral and Maxillofacial Surgery, Faculty of MedicineHospital Universitario Central de Asturias (HUCA)OviedoSpain
  3. 3.Department of Business AdministrationUniversity of OviedoOviedoSpain
  4. 4.Department of Mines Prospecting and ExploitationUniversity of OviedoOviedoSpain

Personalised recommendations