Assessment of Bayesian Estimators for Osteoporosis Analysis
Keywords:medical informatics, artificial intelligence, data mining, bayes theorem, osteoporosis
Background: Bayesian classifiers have the advantage of determining the class to which a given record belongs compared to traditional classifiers, taking as base the probability of an element belonging to a class. Thus, the diagnosis of diseases such as osteoporosis and osteopenia can become faster and precise.This paper presents an assessment of the accuracy of the Bayesian classifiers Bayes Net, Naive Bayes and Averaged One-Dependence Estimators to support diagnoses of osteopenia and osteoporosis. Method: The methodology that guided the development of this research relied on the choice of database, the study of the Bayes Net, Naive Bayes and Averaged One-Dependence Estimators algorithms, and the description of the experiments. Results: The algorithm with the highest specificity was Bayes Net, (53.0Â±0.27). The highest accuracy was obtained using the AODE classifier (83.0Â±0.17). Our results showed higher mean instances correctly classified using the Naive Bayes algorithm (82.84Â±14.42), and the average of incorrectly classified instances was higher for Bayes Net (17.46Â±14.76). Conclusion: Based on the statistical measures analyzed in the experiments (instances classified correctly and incorrectly, the kappa coefficient, mean absolute error, sensitivity, specificity, accuracy, recall, F-measure, and Area Under Curve (AUC)), all classifiers showed good results, thus, given these data, it is possible to produce a reasonably accurate estimate of the diagnosis.
Kanis JA, McCloskey EV, Johansson H, Cooper C, Rizzoli R, Reginster J-Y. European guidance for the diagnosis and management of osteoporosis in postmenopausal women. Osteoporos Int 2012: 24 :23â€“57.
Fontes MPF; AraÃºjo LFB; Soares PRG. Osteoporose no climatÃ©rio I: epidemiologia, definiÃ§Ã£o, rastreio e diagnÃ³stico. Femina 2012: 40(2): 109-116.
Eriksen FE. Treatment of osteopenia. Rev Endocr Metab Disord 2011: 13:209â€“223.
Warriner HA, Saag GK. Osteoporosis Diagnosis and Medical Treatment.Orthop Phys Ther Clin N Am 2013: 44: 125-135.
Kaufman JM, Lapauw B, Goemaere S. Current and future treatments of osteoporosis in men. Best Pract Res Clin Endocrinol Metab 2014: 28(6):871-884.
Rodrigues FA, Amaral LR. AplicaÃ§Ã£o de MÃ©todos Computacionais de MineraÃ§Ã£o de Dados na ClassificaÃ§Ã£o e SeleÃ§Ã£o de Oncogenes Medidos por Microarray. Rev bras cancerol 2012: 58(2): 241-249.
Rezende, SO. Sistemas inteligentes: fundamentos e aplicaÃ§Ãµes. Barueri, SP: Manole, 2005.
Mello, LC. Descoberta de conhecimento em banco de dados (mineraÃ§Ã£o de dados) e redes bayesianas: estado da arte, 2001.
Santos EB. A OrdenaÃ§Ã£o das VariÃ¡veis no Processo de OtimizaÃ§Ã£o de ClassificaÃ§Ã£o Bayesianos: Uma Abordagem Evolutiva [masterâ€™s thesis]. [SÃ£o Carlos]: Universidade Federal de SÃ£o Carlos. Curso CiÃªncia da ComputaÃ§Ã£o; 2007.
Cruz-RamÃrez N, Acosta-Mesa HG, Carrillo-Calvet H, Nava-FernÃ¡ndez LA, Barrientos-MartÃnez RE. Diagnosis of breast cancer using Bayesian networks: a case study. Comput Biol Med 2007: 37(11):1553-64.
Friedman N, Geiger D, Goldszmidt M. Bayesian network classifiers. Mach Learn 1997: 29:131-163.
Htike ZZ, Win LS. Classification of eukaryotic splice-junction genetic sequences using Averaged One-Dependence Estimators with subsumption resolution. Procedia Comput Sci 2013: 23:36-43.
MartÃnez-Morales M, Cruz-RamÃrez N, JimÃ©nez-Andrade JL, Garza-DomÃnguez R. Bayes-N: An Algorithm for Learning Bayesian Networksfrom Data Using Local Measures of Information Gain Applied to Classification Problems. Veracruz, MÃ©xico: MICAI; 2004. pp. 527-535.
World Health Organization. Burden of disease in DALYs by cause, sex and mortality stratum in WHO regions, estimates for 2002. Geneva: World Health Organization, 2004.
Abrahamsen B, Rejnmark L, Nielsen SP, Rud B, Nissen N, Mosekilde L, BÃ¤renholdt O, Jensen JE. Ten-year prediction of osteoporosis from baseline bone mineral density: development of prognostic thresholds in healthy postmenopausal women. The Danish Osteoporosis Prevention Study. Osteoporos Int 2006: 17(2):245-51.
Ferreira D, Oliveira A, Freitas A. Applying data mining techniques to improve diagnosis in neonatal jaundice. BMC Med Inform Decis Mak 2012: 12:143.
Ng SYS, Xing Y, Tsui LK. A naive Bayes model for robust remaining useful life prediction of lithium-ion battery. Appl Energy 2014: 118: 114-123.
Li L, Zhang Q, Ding Y, Jiang H, Thiers BH, Wang JZ. Automatic diagnosis of melanoma using machine learning methods on a spectroscopic system. BMC Med Imaging 2014: 14(1):36.
Wang KJ, Makond B, Wang KM. Modeling and predicting the occurrence of brain metastasis from lung cancer by Bayesian network: a case study of Taiwan. ComputBiol Med 2014: 47:147-60.
Chimieski BF, Fagundes RDR. Association and Classification Data Mining Algorithms Comparison over Medical Datasets. J. Health Inform 2013: 5(2): 44-51.
Amorim JVM, Barone D, Mansur UA. TÃ©cnicas de Aprendizado de MÃ¡quina Aplicadas na PrevisÃ£o de EvasÃ£o AcadÃªmica. XIX SimpÃ³sio Brasileiro de InformÃ¡tica na EducaÃ§Ã£o; Nov 12-14; Fortaleza, CE. Rio de Janeiro, 2008.
TenÃ³rio JM, Hummel AD, Cohrs FM, Sdepanian VL, Pisa IT, de FÃ¡tima Marin H. Artificial intelligence techniques applied to the development of a decision-support system for diagnosing celiac disease. Int J Med Inform 2011: 80(11):793-802.
Flores JM, GÃ¡mez AJ, MartÃnez MA. Domains of competence of the semi-naive Bayesian network classifiers. Inf Sci 2014: 260: 120-148.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under aÂ Creative Commons Attribution LicenseÂ that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (SeeÂ The Effect of Open AccessÂ and Benefits of Publishing Open Access).