Diagnosing thyroid disorders: Comparison of logistic regression and neural network models

Background: The main goal of this study was to diagnose the two most common thyroid disorders, namely, hyperthyroidism and hypothyroidism, based on multinomial logistic regression and neural network models. In addition, the study evaluated the predictive ability of laboratory tests against the individual clinical symptoms score. Materials and Methods: In this study, the data from patients with thyroid dysfunction who referred to Imam Khomeini Clinic and Shahid Beheshti Hospital in Hamadan were collected. The data contained 310 subjects in one of three classes—euthyroid, hyperthyroidism, and hypothyroidism. Collected variables included demographics and symptoms of hypothyroidism and hyperthyroidism, as well as laboratory tests. To compare the predictive ability of the clinical signs and laboratory tests, different multinomial logistic regression and neural network models were fitted to the data. These models were compared in terms of the mean of the accuracy and area under the curve (AUC). Results: The results showed better performance of neural network model than multinomial logistic regression in all cases. The best predictive performance for logistic regression (with a mean accuracy of 91.4%) and neural network models (with a mean accuracy of 96.3%) was when all variables were included in the model. In addition, the predictive performance of two models based on symptomatic variables was superior to laboratory variables. Conclusions: Both neural network and logistic regression models have a high predictive ability to diagnose thyroid disorder, although neural network performance is better than logistic regression. In addition, as achieving less error prediction model has always been a matter of concern for researchers in the field of disease diagnosis, predictive nonparametric techniques, such as neural networks, provide new opportunities to obtain more accurate predictions in the field of medical research.

[1]  M. P. König [Hypothyroidism in clinical practice]. , 1988, Schweizerische Rundschau fur Medizin Praxis = Revue suisse de medecine Praxis.

[2]  C. Dayan,et al.  Interpretation of thyroid function tests , 2001, The Lancet.

[3]  Tulay Yildirim,et al.  Diagnosis of thyroid disease using artificial neural network methods , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[4]  Lucila Ohno-Machado,et al.  Logistic regression and artificial neural network classification models: a methodology review , 2002, J. Biomed. Informatics.

[5]  Fabrizio Monaco,et al.  Classification of thyroid diseases: suggestions for a revision. , 2003, The Journal of clinical endocrinology and metabolism.

[6]  D. Ruppert The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[7]  Kemal Polat,et al.  A novel hybrid method based on artificial immune recognition system (AIRS) with fuzzy weighted pre-processing for thyroid disease diagnosis , 2007, Expert Syst. Appl..

[8]  Aytürk Keles,et al.  ESTDD: Expert system for thyroid diseases diagnosis , 2008, Expert Syst. Appl..

[9]  Fevzullah Temurtas,et al.  A comparative study on thyroid disease diagnosis using neural networks , 2009, Expert Syst. Appl..

[10]  Esin Dogantekin,et al.  An automatic diagnosis system based on thyroid gland: ADSTG , 2010, Expert Syst. Appl..

[11]  Gang Wang,et al.  A Three-Stage Expert System Based on Support Vector Machines for Thyroid Disease Diagnosis , 2012, Journal of Medical Systems.

[12]  P. Nkwo,et al.  Two logistic models for the prediction of hypothyroidism in pregnancy , 2011, BMC Research Notes.

[13]  Alan Agresti,et al.  Categorical Data Analysis , 2003 .

[14]  S. Kalra,et al.  Clinical scoring scales in thyroidology: A compendium , 2011, Indian journal of endocrinology and metabolism.

[15]  M. Teshnehlab,et al.  An Experimental Comparative Study on Thyroid Disease Diagnosis Based on Feature Subset Selection and classification , 2012 .

[16]  Mohamadi Basatini Ferdos,et al.  DETERMINATION OF THYROID GLAND STATE IN REFERRALS FROM AHVAZ UNIVERSITY JAH AD LABORATORY: USING MULTILAYER PERCEPTRON NEURAL NETWORK DISCRIMINATION IN COMPARING WITH CLASSICAL DISCRIMINATION METHODS , 2013 .

[17]  Adel M. A. Assiri,et al.  Thyroid Diagnosis based Technique on Rough Sets with Modified Similarity Relation , 2013 .

[18]  Maryam Farhadian,et al.  Predicting 5-Year Survival Status of Patients with Breast Cancer based on Supervised Wavelet Method , 2014, Osong public health and research perspectives.

[19]  Maryam Farhadian,et al.  Prediction of hearing loss among the noise-exposed workers in a steel factory using artificial intelligence approach , 2015, International Archives of Occupational and Environmental Health.

[20]  Ahmet Alkan,et al.  Expert system for thyroid disease diagnosis , 2014 .

[22]  S. Razia,et al.  Machine Learning Techniques for Thyroid Disease Diagnosis - A Review , 2016 .

[23]  A. Dewangan,et al.  Classification of Thyroid Disease with Feature Selection Technique , 2016 .

[24]  Maryam Farhadian,et al.  Dental age estimation using the pulp-to-tooth ratio in canines by neural networks , 2019, Imaging science in dentistry.

[25]  Maryam Farhadian,et al.  Diagnosis of hypothyroidism using a fuzzy rule-based expert system , 2019, Clinical Epidemiology and Global Health.

[26]  Negar Asaad Sajadi,et al.  Thyroid disorder diagnosis based on Mamdani fuzzy inference system classifier , 2020, Koomesh Journal.

[27]  Yefei Jiang,et al.  Prediction of Hypothyroidism Disease by Data Mining Technique , 2021 .