Risk of malignancy evaluation through data mining technic in patients with thyroid nodules with cytology study Bethesda IV
Article Sidebar
Main Article Content
Abstract
Introduction: In the health field, each decision represents data, and data mining techniques have begun to be a promising methodology for the analysis of this information, especially in the design of predictive models. Methods: Analytical observational study; patients older than 15 years with a report of Bethesda IV after a fine needle aspiration biopsy that undergoing surgical management at the Hospital de San José in Bogotá. The data collected from those patients were included in three groups: sociodemographic-clinical information, cytology findings, and ultrasound
reports. Analysis was performed using three technics: Naive Bayes, decision trees, and neural networks. Weka tool version 3.8.2 was used. Results: 195 patients out of 427, had a thyroid carcinoma pathology (45.6%). Better results were evidenced using cross-validation (10 fold) compared with a partition (66%), the Bayes technique had
better results of correct classification (91.1%), than the tree technique (87.8%) and neural network (88.2%). Conclusions: The use of the Naive Bayes technique shows an important accuracy to determine the prediction of risk of malignancy in patients
with a Bethesda IV cytological study, which would allow an adequate guide to the surgical management of patients.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Este artículo es publicado por la Revista Acta de Otorrinolaringología & Cirugía de Cabeza y Cuello.
Este es un artículo de acceso abierto, distribuido bajo los términos de la LicenciaCreativeCommons Atribución-CompartirIgual 4.0 Internacional.( http://creativecommons.org/licenses/by-sa/4.0/), que permite el uso no comercial, distribución y reproducción en cualquier medio, siempre que la obra original sea debidamente citada.
eISSN: 2539-0856
ISSN: 0120-8411
References
Kumar R, Shaikh B, Chandio A, Ahmed J. Role of health management information system in disease reporting at a rural
district of Sindh. Pak J Public Health. 2012;2(2):10-2.
Castro M. Las técnicas de modelización estadística en la investigación educativa: minería de datos, modelos de
ecuaciones estructurales y modelos jerárquicos lineales. Rev Esp Pedag. 2012;251:131-48.
Stilou S, Bamidis PD, Maglaveras N, Pappas C. Mining association rules from clinical databases: An intelligent
diagnostic process in healthcare. Stud Health Technol Inform.2001;84(2):1399-403.
Salazar J, Espinoza C, Mindiola A, Bermúdez V. Data mining and endocrine diseases: A new way to classify? Arch Med Res.2018;49(3):213-5. doi: 10.1016/j.arcmed.2018.08.005.
Kim T, Zabaneh F, Holmes J, Disrude L, Price M, Gentry L. A practical data mining method to link hospital microbiology
and an infection control database. Am J Infect Control.2008;36(3):S18-S20. doi: 10.1016/j.ajic.2007.05.010.
Izzo CM, Prescott J, Peden A, Brown JF, Valencia F. Use of a data mining system to improve the process of public health
reporting in a large teaching facility. Am J Infect Control. 2008;36(5):E186. doi: 10.1016/j.ajic.2008.04.216.
Michie D, Spiegelhalter DJ, Taylor CC, Campbell J (editores).Machine learning, neural and statistical classification. Upper
Saddle River, NJ, EE. UU.: Ellis Horwood. 1994.
Koh HC, Tan G. Data mining applications in healthcare. J Healthc Inf Manag. 2005;19(2):64-72.
Kotsiantis S, Pierrakeas C, Pintelas P. Preventing student dropout in distance learning using machine learning techniques.Springer. 2003. p. 267-74.
Schreiner AM, Yang GC. Adenomatoid nodules are the main cause for discrepant histology in 234 thyroid fine-needle
aspirates reported as follicular neoplasm. Diagn Cytopathol.2012;40(5):375-9. doi: 10.1002/dc.21499.
Conzo G, Calò PG, Gambardella C, Tartaglia E, Mauriello C, Della Pietra C, et al. Controversies in the surgical management of thyroid follicular neoplasms. Retrospective analysis of
patients. Int J Surg. 2014;12(1):S29-34. doi: 10.1016/j.ijsu.2014.05.013.
Herrera F, Redondo K, Osorio C, Grice J, Fernández A. Utilidad de la citología obtenida mediante aspiración con aguja fina en el diagnóstico de las neoplasias foliculares de la glándula tiroides en la E.S.E Hospital Universitario del Caribe: un estudio retrospectivo. Rev Colomb Cir. 2015;30:12-7. doi: 10.30944/issn.2011-7582.
Jo VY, Stelow EB, Dustin SM, Hanley KZ. Malignancy risk for fine-needle aspiration of thyroid lesions according to
the Bethesda system for reporting thyroid cytopathology. Am J Clin Pathol. 2010;134(3):450-6. doi: 10.1309/
AJCP5N4MTHPAFXFB.
Osorio C, Fernández A, Herrera K, Marrugo Á, Ensuncho C, Redondo K, et al. Sensibilidad y especificidad de la citología
obtenida mediante aspiración con aguja fina en el diagnóstico de las neoplasias foliculares de la glándula tiroides: un estudio prospectivo. Rev Esp Patol. 2016;49(3):144-50. doi: 10.1016/j.patol.2016.01.005.
Kuru B, Kefeli M. Risk factors associated with malignancy and with triage to surgery in thyroid nodules classified as Bethesda category IV (FN/SFN). Diagn Cytopathol. 2018;46(6):489-94. doi: 10.1002/dc.23923.
Lee SH, Baek JS, Lee JY, Lim JA, Cho SY, Lee TH, et al. Predictive factors of malignancy in thyroid nodules with a
cytological diagnosis of follicular neoplasm. Endocr Pathol.2013;24(4):177-83. doi: 10.1007/s12022-013-9263-x.
Yassa L, Cibas ES, Benson CB, Frates MC, Doubilet PM,Gawande AA, et al. Long-term assessment of a multidisciplinary
approach to thyroid nodule diagnostic evaluation. Cancer.2007;111(6):508-16. doi: 10.1002/cncr.23116.
Guth S, Theune U, Aberle J, Galach A, Bamberger CM.Very high prevalence of thyroid nodules detected by high
frequency (13 MHz) ultrasound examination. Eur J Clin Invest.2009;39(8):699-706. doi: 10.1111/j.1365-2362.2009.02162.
Gharib H, Papini E, Garber JR, Duick DS, Harrell RM, HegedüsL, et al. American Asociation of Clinical Endocrinologists,
American College of Endocrinology, and Associazione Medici Endocrinologi Medical guidelines for clinical practice for the
diagnosis and management of thyroid nodules--2016 update. Endocr Pract. 2016;22(5):622-39. doi: 10.4158/EP161208.GL.
Abdul-Jabar HB, Lynn J. The surgical management of thyroid cancer. Nucl Med Commun. 2004;25(9):869-72. doi:
1097/00006231-200409000-00002.
Rodríguez González H, Pava Marín R, Castaño Herrera LF, Valencia García LV, Pava Ripoll A. Evaluación de la
precisión diagnóstica de la punción aspiración con aguja fina en pacientes con nódulo tiroideo. Biosalud. 2017;16(1):19-29.
doi: 10.17151/biosa.2017.16.1.3.
Mejía M, Rivera Delgado M, Bonilla J, Melo M, Rojas García W. Factores asociados a histopatología final benigna en
pacientes con biopsia por aspiración con aguja fina clasificados como Bethesda en IV-V-VI en Hospital de San José. Bogotá:
Fundación Universitaria de Ciencias de la Salud. 2017.
Park SY, Hahn SY, Shin JH, Ko EY, Oh YL. The diagnostic performance of thyroid US in each category of the Bethesda
system for reporting thyroid cytopathology. PLoS One. 2016;11(6):e0155898. doi: 10.1371/journal.pone.0155898.
Razia S, Narasinga MR. Machine learning techniques for thyroid disease diagnosis - A review. Indian J Sci Technol.
;9(28):1-9. doi: 10.17485/ijst/2016/v9i28/93705.
Boas FE, Liu LY, Kamaya A, Desser TS, Rubin DL. Estimating the probability of malignancy of thyroid nodules using adjusted naïve Bayes. 2012. Disponible en: http://www.edboas.com/calc/thyroid.pdf