Exploring new possibilities for case-based explanation of artificial neural network ensembles

Neural Networks

Volumn 22, Issue 1, 2009, Pages 75-81

  Green, Michael ^a   Ekelund, Ulf ^b   Edenbrandt, Lars ^b   Björk, Jonas ^b   Forberg, Jakob Lundager ^b   Ohlsson, Mattias ^a  

^a LUND UNIVERSITY   (Sweden)

^b LUND UNIVERSITY HOSPITAL   (Sweden)

Author keywords

Acute coronary syndrome; Case based explanation; Neural network ensembles; Sensitivity analysis

Indexed keywords

ACUTE CORONARY SYNDROME; ARTIFICIAL DATUMS; ARTIFICIAL NEURAL NETWORK ENSEMBLES; ARTIFICIAL NEURAL NETWORKS; CASE-BASED EXPLANATION; CLINICAL DECISION SUPPORT SYSTEMS; DATA SETS; DECISION BOUNDARIES; EMERGENCY DEPARTMENTS; INTERPRETABILITY; LUND UNIVERSITIES; NEURAL NETWORK ENSEMBLES; SET OF RULES;

ADMINISTRATIVE DATA PROCESSING; ARTIFICIAL INTELLIGENCE; BACKPROPAGATION; DECISION SUPPORT SYSTEMS; DECISION THEORY; ELECTROCARDIOGRAPHY; ELECTROCHROMIC DEVICES; HOSPITALS; MANAGEMENT INFORMATION SYSTEMS; SENSITIVITY ANALYSIS;

NEURAL NETWORKS;

ACUTE CORONARY SYNDROME; ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; COMPARATIVE STUDY; DECISION SUPPORT SYSTEM; ELECTROCARDIOGRAM; EMERGENCY WARD; HUMAN; PHYSICIAN; PRIORITY JOURNAL; RETROSPECTIVE STUDY; SENSITIVITY ANALYSIS;

ALGORITHMS; DATA INTERPRETATION, STATISTICAL; DIAGNOSIS, COMPUTER-ASSISTED; ELECTROCARDIOGRAPHY; HEART DISEASES; HEART RATE; HUMANS; NEURAL NETWORKS (COMPUTER); REPRODUCIBILITY OF RESULTS; RETROSPECTIVE STUDIES; SIGNAL PROCESSING, COMPUTER-ASSISTED; SOFTWARE VALIDATION;

EID: 58249094346     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neunet.2008.09.014     Document Type: Article

References (19)

1. Björk J., Forberg J.L., Ohlsson M., Edenbrandt L., Öhlin H., and Ekelund U. A simple statistical model for prediction of acute coronary syndrome in chest pain patients in the emergency department. BMC Medical Informatics and Decision Making 6 (2006) 28. http://dx.doi.org/10.1186/1472-6947-6-28
2. Breiman L. Bagging predictors. Machine Learning 24 (1996) 123-140
3. Caruana, R. (2000). Case-based explanation for artificial neural nets. In H. Malmgren, M. Borga, L. Niklasson (Eds.), Proceedings of artificial neural networks in medicine and biology conference (pp. 303-308)
4. Etchells T.A., and Lisboa P.J.G. Orthogonal search-based rule extraction (OSRE) for trained neural networks: A practical and efficient approach. IEEE Transactions on Neural Networks 17 2 (2006) 374-384
5. Forberg, J., Björk, J., Green, M., Ohlsson, M., Edenbrandt, L., & Öhlin, H. et al. (2008). In search of the best method to predict acute coronary syndrome using only the ECG from the emergency department. Journal of Electrocardiology, in press (doi:10.1016/j.jelectrocard.2008.07.010)
6. Green M., Björk J., Forberg J., Ekelund U., Edenbrandt L., and Ohlsson M. Comparison between neural networks and multiple logistic regression to predict acute coronary syndrome in the emergency room. Artificial Intelligence in Medicine 38 3 (2006) 305-318. http://dx.doi.org/10.1016/j.artmed.2006.07.006
7. Green M., Björk J., Hansen J., Ekelund U., Edenbrandt L., and Ohlsson M. Detection of acute coronary syndromes in chest pain patients using neural network ensembles. In: Fonseca J.M. (Ed). Proceedings of the 2nd international conference on computational intelligence in medicine and healthcare (2005), IEE/IEEE 182-187
8. Hanley J.A., and McNeil B.J. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143 1 (1982) 29-36
9. Haraldsson H., Edenbrandt L., and Ohlsson M. Detecting acute myocardial infarction in the 12-lead ECG using hermite expansions and neural networks. Artificial Intelligence in Medicine 32 (2004) 127-136
10. Kennedy R., and Harrison R. Identification of patients with evolving coronary syndromes by using statistical models with data from the time of presentation. Heart 92 (2006) 183-189
11. Kolman E., and Margaliot M. Are artificial neural networks white boxes?. IEEE Transactions on Neural Networks 16 4 (2005) 844-852
12. Lisboa P.J.G. A review of evidence of health benefit from artificial neural networks in medical intervention. Neural Networks 15 1 (2002) 11-39
13. Montao J.J., and Palmer A. Numeric sensitivity analysis applied to feedforward neural networks. Neural Computing & Applications 12 2 (2003) 119-125
14. Saad E.W., and Wunsch D.C. Neural network explanation using inversion. Neural Networks 20 1 (2007) 78-93. http://dx.doi.org/10.1016/j.neunet.2006.07.005
15. Tchaban T., Taylor M.J., and Griffin J.P. Establishing impacts of the inputs in a feedforward neural network. Neural Computing & Applications 7 4 (1998) 309-317
16. Thrun, S.B., Bala, J., Bloedorn, E., Bratko, I., Cestnik, B., & Cheng, J. et al. (1991). The monk's problems a performance comparison of different learning algorithms
17. Wall R., Cunningham P., Walsh P., and Byrne S. Explaining the output of ensembles in medical decision support on a case by case basis. Artificial intelligence in medicine 28 (2003) 191-206. http://linkinghub.elsevier.com/retrieve/pii/S0933365703000563
18. Wang W., Jones P., and Partridge D. Assessing the impact of input features in a feedforward neural network. Neural Computing & Applications 9 (2004) 101-112
19. Wehrens R., Putter H., and Buydens L. The bootstrap: A tutorial. Chemometrics and Intelligent Laboratory Systems 54 (2000) 35-52