본문 바로가기
KERD
논문KCI 등재

Bayesian-Based Decision Support System for Assessing the Needs for Orthodontic Treatment

Bhornsawan Thanathornwong
대한의료정보학회 (The Korean Society Of Medical Informatics)|2018.01|Healthcare Informatics Research|제24권 제1호|pp. 22-28|DOI https://doi.org/10.4258/hir.2018.24.1.22

2

조회

0

다운로드

2

인용

0

참고문헌

키워드

Artificial IntelligenceMachine LearningMalocclusionDental InformaticsAngle’s Classification

초록

Objectives: In this study, a clinical decision support system was developed to help general practitioners assess the need fororthodontic treatment in patients with permanent dentition. Methods: We chose a Bayesian network (BN) as the underlyingmodel for assessing the need for orthodontic treatment. One thousand permanent dentition patient data sets chosen from ahospital record system were prepared in which one data element represented one participant with information for all variablesand their stated need for orthodontic treatment. To evaluate the system, we compared the assessment results based on thejudgements of two orthodontists to those recommended by the decision support system. Results: In a BN decision supportmodel, each variable is modelled as a node, and the causal relationship between two variables may be represented as a directedarc. For each node, a conditional probability table is supplied that represents the probabilities of each value of this node, giventhe conditions of its parents. There was a high degree of agreement between the two orthodontists (kappa value = 0.894) intheir diagnoses and their judgements regarding the need for orthodontic treatment. Also, there was a high degree of agreementbetween the decision support system and orthodontists A (kappa value = 1.00) and B (kappa value = 0.894). Conclusions: Thestudy was the first testing phase in which the results generated by the proposed system were compared with those suggested byexpert orthodontists. The system delivered promising results; it showed a high degree of accuracy in classifying patients intogroups needing and not needing orthodontic treatment.

Abstract

Objectives: In this study, a clinical decision support system was developed to help general practitioners assess the need fororthodontic treatment in patients with permanent dentition. Methods: We chose a Bayesian network (BN) as the underlyingmodel for assessing the need for orthodontic treatment. One thousand permanent dentition patient data sets chosen from ahospital record system were prepared in which one data element represented one participant with information for all variablesand their stated need for orthodontic treatment. To evaluate the system, we compared the assessment results based on thejudgements of two orthodontists to those recommended by the decision support system. Results: In a BN decision supportmodel, each variable is modelled as a node, and the causal relationship between two variables may be represented as a directedarc. For each node, a conditional probability table is supplied that represents the probabilities of each value of this node, giventhe conditions of its parents. There was a high degree of agreement between the two orthodontists (kappa value = 0.894) intheir diagnoses and their judgements regarding the need for orthodontic treatment. Also, there was a high degree of agreementbetween the decision support system and orthodontists A (kappa value = 1.00) and B (kappa value = 0.894). Conclusions: Thestudy was the first testing phase in which the results generated by the proposed system were compared with those suggested byexpert orthodontists. The system delivered promising results; it showed a high degree of accuracy in classifying patients intogroups needing and not needing orthodontic treatment.

참고문헌 (25)

  1. Salzmann JA, "Handicapping malocclusion assessment to establish treatment priority", Am J Orthod, 54(10), pp.749~765 (1968)[DOI]
  2. Brook PH, "The development of an index of orthodontic treatment priority", Eur J Orthod, 11(3), pp.309~320 (1989)[DOI]
  3. Richmond S, "The PAR Index (Peer Assessment Rating): methods to determine outcome of orthodontic treatment in terms of improvement and standards", Eur J Orthod, 14(3), pp.180~187 (1992)[DOI]
  4. Gardner JW, "Orthodontic treatment priority index" (1967), US Department of Health, Education, and Welfare
  5. Summers CJ, "The occlusal index: a system for identifying and scoring occlusal disorders", Am J Orthod, 59(6), pp.552~567 (1971)[DOI]
  6. Cons NC, "DAI: the dental aesthetic index" (1986), College of Dentistry, University of Iowa
  7. Richmond S, "International comparisons of professional assessments in orthodontics. Part 1. Treatment need", Am J Orthod Dentofacial Orthop, 113(2), pp.180~185 (1998)[DOI]
  8. Espeland LV, "A new Norwegian index of orthodontic treatment need related to orthodontic concern among 11-year-olds and their parents", Community Dent Oral Epidemiol, 20(5), pp.274~279 (1992)[DOI]
  9. Grippaudo C, "Comparing orthodontic treatment need indexes", Italian J Public Health, 5(3), pp.181~186 (2008)
  10. Johansson AM, "Evaluation of the Dental Health Component, of the Index of Orthodontic Treatment Need, by Swedish orthodontists", Eur J Orthod, 31(2), pp.184~188 (2009)[DOI]
  11. Shortliffe EH, "Testing reality: the introduction of decision-support technologies for physicians", Methods Inf Med, 28(1), pp.1~5 (1989)[DOI]
  12. 채영문, "The Adoption of Electronic Medical Records and Decision Support Systems in Korea", Healthcare Informatics Research, 17(3), pp.172~177 (2011), 대한의료정보학회
  13. Xie X, "Artificial neural network modeling for deciding if extractions are necessary prior to orthodontic treatment", Angle Orthod, 80(2), pp.262~266 (2010)[DOI]
  14. Akcam MO, "Fuzzy modelling for selecting headgear types", Eur J Orthod, 24(1), pp.99~106 (2002)[DOI]
  15. Pearl J, "Probabilistic reasoning in intelligent systems: networks of plausible inference" (1988), Morgan Kaufmann
  16. Suebnukarn S, "A Bayesian decision support model for assessment of endodontic treatment outcome", Oral Surg Oral Med Oral Pathol Oral Radiol Endod, 106(3), pp.e48~e58 (2008)[DOI]
  17. Thanathornwong B, "A system for predicting and preventing workrelated musculoskeletal disorders among dentists", Comput Methods Biomech Biomed Engin, 17(2), pp.177~185 (2014)[DOI]
  18. 최종필, "A Hybrid Bayesian Network Model for Predicting Breast Cancer Prognosis", Healthcare Informatics Research, 15(1), pp.49~57 (2009), 대한의료정보학회
  19. Su C, "Using Bayesian networks to discover relations between genes, environment, and disease", BioData Min, 6(1), pp.6~ (2013)[DOI]
  20. Corani G, "A Bayesian network model for predicting pregnancy after in vitro fertilization", Comput Biol Med, 43(11), pp.1783~1792 (2013)[DOI]
  21. Wang XH, "Computer-assisted diagnosis of breast cancer using a data-driven Bayesian belief network", Int J Med Inform, 54(2), pp.115~126 (1999)[DOI]
  22. Faure JC, "The influence of different facial components on facial aesthetics", Eur J Orthod, 24(1), pp.1~7 (2002)[DOI]
  23. Alcalde RE, "Cephalometric norms in Japanese adults", J Oral Maxillofac Surg, 56(2), pp.129~134 (1998)[DOI]
  24. Chu YM, "Bimaxillary protrusion: an overview of the surgical-orthodontic treatment", Semin Plast Surg, 23(1), pp.32~39 (2009)[DOI]
  25. Hayashi K, "Morphological analysis of the skeletal remains of Japanese females from the Ikenohata-Shichikencho site", Eur J Orthod, 34(5), pp.575~581 (2012)[DOI]

이 간행물의 다른 논문 (11건)

A New Online Journal Management System장혜정, 공현중pp. 1-2Enchanted Life Space: Adding Value to Smart Health by Integrating Human Desires유소영, 오지선, 김영학, 이재호, 박유랑, 김주현, 감혜진pp. 3-11Scenario-Based Assessment of User Needs for Point-of-Care Robots김정은, 이형숙pp. 12-21Comparison of Models for the Prediction of Medical Costs of Spinal Fusion in Taiwan Diagnosis-Related Groups by Machine Learning AlgorithmsChien-Lung Chan, Ching-Yen Kuo, Liang-Chin Yu, Hou-Chaung Chenpp. 29-37Evaluating the Dietary and Nutritional Apps in the Google Play StoreHarleigh Schumer, Ashish Joshi, Chioma Amadipp. 38-45
원문 보기