본문 바로가기
KERD
논문KCI 등재

MMPI 분석도구로서 인공신경망 분석과 로지스틱 회귀분석의 비교

Comparison between logistic regression and artificial neural networks as MMPI discriminator

0

조회

0

다운로드

3

인용

0

참고문헌

키워드

주제분류정신과학

초록

Abstract

objectives:The purpose of this study is to 1) conduct a discrimination analysis of schizophrenia and bipolar affective disorder using MMPI profile through artificial neural network analysis and logistic regression analysis, 2) to make a comparison between advantages and disadvantages of the two methods, and 3) to demonstrate the usefulness of artificial neural network analysis of psychiatric data. Procedure:The MMPI profiles for 181 schizophrenia and bipolar affective disorder patients were selected. Of these profiles, 50 were randomly placed in the learning group and the remaining 131 were placed in the validation group. The artificial neural network was trained using the profiles of the learning group and the 131 profiles of the validation group were analyzed. A logistic regression analysis was then conducted in a similar manner. The results of the two analyses were compared and contrasted using sensitivity, specificity, ROC curves, and kappa index. Results:Logistic regression analysis and artificial neural network analysis both exhibited satisfactory discriminating ability at Kappa index of greater than 0.4. The comparison of the two methods revealed artificial neural network analysis is superior to logistic regression analysis in its discriminating capacity, displaying higher values of Kappa index, specificity, and AUC(Area Under the Curve) of ROC curve than those of logistic regression analysis.

참고문헌 (25)

  1. "Logistic regressionand artificial neural network classification models:a methodology review", 35, pp.352~359 (2002)
  2. "Artificial neural networks: fundamentals,computing, design, and application", 43, pp.3~31 (2000)
  3. "An artificial neural network that uses Eyetrackingperformance to identify patients with schizophrenia", 24, pp.789~799 (1999)
  4. "Neural network based automatic diagnosisof children with brain dysfunction", 11, pp.361~369 (2001)
  5. "Artificial neural networksto assist psychiatric diagnosis", 169, pp.64~47 (1996)
  6. "Classification and staging of dementia of the Alzheimertype", 54, pp.1001~1009 (1997)
  7. "Recognition of hallucinations:Anew multidimensional model and methodology", 29, pp.54~63 (1996)
  8. "Analysis ofthe symptoms of depression- a neural network approach", 87, pp.193~201 (1999)
  9. "Validation of the computerized suicide risk scale - a backpropagationneural network instrument(CSRS-BP)", 17, pp.75~81 (2002)
  10. "A neural network approach to the outcomedefinition on first treatment with sertraline in apsychiatric population", 23, pp.239~248 (2001)
  11. "Hines,Ronit Weizman", 20, pp.403~412 (1996)
  12. "Artificial neural networks:a study in clinicalpsychopharmacology", 87, pp.203~215 (1999)
  13. "Caudatesize in first-episode neuroleptic-naive schizophrenic patientsmeasured using an artificial neural network", 46, pp.712~720 (1999)
  14. "Use of artificial neural networks in clinicalpsychology and psychiatry", 37, pp.349~57 (2003)
  15. "Walters", pp.226~246
  16. "Correlations Between theMMPI and the Brief Psychiatric Rating Scales in Schizophrenicand Schizoaffective Patients", pp.135~143
  17. "Neuchterlein, JosephVentura. MMPI discriminators of deficit vs. non-deficitrecent-onset schizophrenia patients", 93, pp.111~123 (2000)
  18. "Correlations between the MMPI and thescale for the assessment of positive symptoms and thescale for the assessment of negative symptoms in schizophrenicpatients Journal of Personality Assessment 1994", pp.275~283
  19. "Borderline,depressive and schizophrenic discriminationby MMPI", 47, pp.783~789 (1991)
  20. "MMPI variables predictive of schizophreniain the Copenhagen High-Risk Project:a 25-yearfollow-up", 99, pp.432~440 (1999)
  21. "A comparisonof the MMPI and the psychosis proneness scalesin their classification of normals controls for use in schizophreniaspectrum research", 62, pp.204~212
  22. "Trait versus state aspects of the MMPI duringthe early course of schizophrenia Journal of PsychiatricResearch 1999", 33, pp.275~284 (1999)
  23. "Backpropagation:the basic theory. In: Rumelhart DE. Yves C:Backpropagation: Theory, Architecture, and ApplicationsLawrence Erlbaum", pp.1~34 (1995)
  24. "new tools for predictionand analysis in the behavioral science" (1974), HarvardUniversity
  25. "Combining the performancestrengths of the logistic regression and neural networkmodels:a medical outcomes approach", 3, pp.455~476 (2003)

관련 논문AI추천

이 간행물의 다른 논문 (16건)