Comparison of the Possibilities of Logistic Regression and Artificial Neural Networks in Predicting the Results of Research on f Small Sample
https://doi.org/10.36107/hfb.2019.i3.s238
Abstract
Currently, attempts are increasingly being made to compare various quantitative models to solve specific data classification problems. Moreover, in the literature there is no data on the comparison of mathematical models in small samples and complex clinical situations. Purpose of work. Compare the performance of artificial neural network models and logistic regression in predicting research results in a small sample. Materials and methods. The simulation included a group of patients of 50 people who underwent plastic surgery on the mitral valve. Five independent variables were selected for the simulation: gender, age, body mass index, and papillary muscle approximation technique. The dependent variable is regurgitation on the mitral valve in a distant period. Results. According to the logistic regression, a phenomenon of data separation arose and a huge mean square error was obtained. According to the analysis of the ROC curve, a relationship was revealed between the predictor age and regurgitation on the mitral valve, the area under the curve indicates the average level of relationship. The results of the analysis of predictors using artificial neural networks indicate that the main contribution as a predictor of the absence of regurgitation is made by the approximation of papillary muscles. Using the De-Long test, we compared the ROC regression curves and neural networks by age factor: z = 10.71, p <0.0001, statistically significant differences were revealed, which indicates the advantage of STI in identifying predictors. Conclusion. In a small sample with a small number of events, artificial neural networks have an advantage over other methods in determining predictors of influence on the dependent variable.
About the Authors
V. V. Bazylev
Federal Center Cardiovascular Surgery
Russian Federation
Russian Federation
Vladlen V. Bazylev
6, Stasova str., Penza, 440071
V. A. Karnakhin
Federal Center Cardiovascular Surgery
Russian Federation
Russian Federation
Vadim A. Karnakhin
6, Stasova str., Penza, 440071
References
1. Nosovskiy, A. M., Pihlak, A. E., Logachev, V. A., Churcinova, I. I., & Muteva, N.A. (2013). Statistics of small samples in medical research. Rossiiskiy medicinskiy gurnal [Russian medical journal], 6.
2. Adavi, M., Salehi, M., & Roudbari, M. (2016). Artificial neural networks versus bivariate logistic regression in prediction diagnosis of patients with hypertension and diabetes. Medical Journal of The Islamic Republic of Iran, 30, 312.
3. Albert, A., & Anderson, J. A. (1984). On the existence of maximum likelihood estimates in logistic regression models. Biometrika, 71(1), 1-10.
4. Anjali, D. N.,& Bossaerts, P. (2014). Risk and Reward Preferences under Time Pressure. Review of Finance, 18, 999-1022.
5. Bamber, D. (1975). The Area above the Ordinal Dominance Graph and the Area belowthe Receiver Operating Characteristic Graph. Journal of Mathematical Psychology, 12,387-415.
6. Bazrafkan, S., Thavalengal, S., & Corcoran, P. (2018). An end to end Deep Neural Network for iris segmentation in unconstrained scenarios. Neural Networks, 106, 79-95. https://doi.org/10.1016Zj.neunet.2018.06.01
7. Bhatikar, S. R., DeGroff, C., & Mahajan, R. L. (2005). A classifier based on the artificial neural network approach for cardiologic auscultation in pediatrics. Artificial Intelligence in Medicine, 33(3), 251-260. https://doi.org/10.1016Zj.artmed.2004.07.008
8. Boutin, A., Pinsard, B., Bore, A., Carrier, J., Fogel, S. M., & Doyon, J. (2018). Transient synchronization of hippocampo-striato-thalamo-cortical networks during sleep spindle oscillations induces motor memory consolidation. NeuroImage, 169, 419-430.
9. Carole, C-F. and T.J. Putnins. (2014). Stock Price Manipulation: Prevalence and Determinants. Review of Finance, 18, 23-66.
10. Cire^an, D. (2012). Multi-column deep neural network for traffic sign classification. Neural Networks, 32, 333-338. https://doi.org/10.1016/j.neunet.2012.02.023
11. Coninck, E. De, Bohez, S., Leroux, S., Verbelen, T., Vankeirsbilck, B., Simoens, P., & Dhoedt, B. (2018). DIANNE: a modular framework for designing, training and deploying deep neural networks on heterogeneous distributed infrastructure. Journal of Systems and Software, 141, 52-65. https://doi.org/10.1016/j.jss.2018.03.032
12. DeLong, E. R., DeLong, D. M., & Clarke-Pearson, D. L. (1988). Comparing areas un-der two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics, 44, 837-845
13. Demler, O. V., Pencina, M. J., & D’Agostino, R. B. Sr. (2011). Equivalance of im-provement in area under ROC curve and linear discriminant analysis coefficient underassumption of normality. Statistics in Medicine, 30, 1410-1418.
14. Dreiseitl, S., & Ohno-Machado, L. (1999). Logistic regression and artificial neural network classification models: a methodology review. Journal of Biomedical Informatics, 35, 352-359;
15. Eftekhar, B., Mohammad, K., Ardebili, H. E., Ghodsi, M. , & Ketabchi, E. (2005). Comparison of artificial neural network and logistic regression models for prediction of mortality in head trauma based on initial clinical data. BMC Medical Informatics and Decision Making, 5, 3.
16. Esfandiari, K., Abdollahi, F.,& Talebi, H. A. (2017). Adaptive near-optimal neuro controller for continuous-time nonaffine nonlinear systems with constrained input. Neural Networks, 93,195-204.
17. Fan, Y., Huang, X., Wang, Z., & Li, Y. (2018). Global dissipativity and quasi-synchronization of asynchronous updating fractional-order memristor-based neural networks via interval matrix method. Journal of the Franklin Institute, 355(13), 5998-6025. https://doi.org/10.10Wj.jfranklin.2018.05.058
18. Garcia-Reiriz, A., Damiani, P. C., & Olivieri, A. C. (2007). Analysis of amoxicillin in human urine by photo-activated generation of fluorescence excitation-emission matrices and artificial neural networks combined with residual bilinearization. Analytica Chimica Acta, 588(2), 192-199. https://doi.org/10.1016/j.aca.2007.02.020
19. King, G., & Zeng, L. (2001). Logistic Regression in Rare Events Data. Political Analysis, 9, 137-163.
20. Graves, A., & Schmidhuber, J. (2005). Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Networks, 18(5-6), 602-610. https://doi.org/10.1016/j.neunet.2005.06.042
21. Hassanipour, S., Ghaem, H., Arab-Zozani, M., Seif, M. , Fararouei, M., Abdzadeh, E., & Paydar, S. (2019). Comparison of artificial neural network and logistic regression models for prediction of outcomes in trauma patients: A systematic review and meta-analysis. Injury, 50(2), 244-250. http://doi.org/10.1016/j.injury.2019.01.007
22. Haykin, S. (1999). Neural networks: a comprehensive foundation. Upper Saddle Rivero
23. Heinze, G., & Scemper, M. A. (2002). Solution to the problem of separation in logistic regression. Statistics in Medicine, 21(16), 2409-19. https://doi.org/10.1002/sim.1047
24. Han, C., Niu, Y., Pang, T., & Xia, Z. (2018). Intelligent anti-jamming communication based on the modified О-learning. Procedia Computer Science, 131, 1023-1031. https://ZZdoi.org/10.1016Zj.procs.2018.04.248
25. Hyvarinen, A., & Oja, E. (2000). Independent component analysis: algorithms and applications. Neural Networks, 13, 411-430. https://doi.org/10.10WS0893-6080(00)00026-5
26. Kulkarni, S. R., & Rajendran, B. (2018). Spiking neural networks for handwritten digit recognition— Supervised learning and network optimization. Neural Networks, 103, 118-127. https://doi.org/10.10Wj.neunet.2018.03.019
27. Lang, E., Pitts, L., Damron, S., & Rutledge, R. (1997). Outcome after severe head injury: an analysis of prediction based upon comparison of neural network versus logistic regression analysis. List of issues. Neurological Research,19(3), 274-80.
28. Lobo, J. L., Lana, I., Del Ser, J., Bilbao, M. N., & Kasabov, N. (2018). Evolving Spiking Neural Networks for online learning over drifting data streams. Neural Networks, 108, 1-19. https://ZZdoi.org/10.1016Zj.neunet.2018.07.014
29. Maddox, S. A., Watts, C. S., & Schafe, G. E. (2014). DNA methyltransferase activity is required for memory-related neural plasticity in the lateral amygdala. Neurobiology of Learning and Memory, 107, 93-100. https://ZZdoi.org/10.1016Zj.nlm.2013.11.008
30. Matsui, Y., Suto, Y., Shimura, S., Fukada, Y., Naito, Y., Yasuda, K., & Sasaki, S. (2005). Impact of papillary muscles approximation on the adequacy of mitral coaptation in functional mitral regurgitation due to dilated cardiomyopathy. Annals of Thoracic and Cardiovascular Surgery, 9, 164-171
31. Ottenbacher, K. J., Linn, R. T., Smith, P. M., Illig, S. B., Mancuso, M., & Granger, C. V. (2004). Comparison of logistic regression and neural network analysis applied to predicting living setting after hip fracture. Annals Epidemiology, 14(8),551-9.
32. Parisi, G. I., Kemker, R., Part, L. J., Kanan, C., &Wermtera, S. (2019). Continual lifelong learning with neural networks: A review. Neural Networks, 113, 54-71. https://doi.Org/10.1016/j.neunet.2019.01.012
33. Parsaeian, M., Mohammad, K., Mahmoudi, M, & Zeraati, H. (2012). Comparison of logistic regression and artificial neural network in low back pain prediction: second national health survey. Medical Journal of The Islamic Republic of Iran, 41(6), 86-92
34. Pasini, A., Lore, M., & Ameli, F. (2005). Neural network modelling for the analysis of forcings/temperatures relationships at different scales in the climate system. Ecological Modelling, 191,58-67.
35. Plis, S. M., Amin, M. F., Chekroud, A., Hjelm, D., Damaraju, E., Lee, H. J., Bustillo, J. R., Cho, K. H., Pearlson, G. D., & Calhoun, V. D. (2018). Reading the (functional) writing on the (structural) wall: Multimodal fusion of brain structure and function via a deep neural network based translation approach reveals novel impairments in schizophrenia. NeuroImage, 181, 734-747. https://doi.org/10.1016/j.neuroimage.2018.07.047
36. Sargent, D.J. (2001). Comparison of artificial neural networks with other statistical approaches: results from medical data sets. Cancer, 91(8), 1636-1642. 13.
37. Schaefer, R.L. (1983). Bias correction in maximum likelihood logistic regression. Statistics in Medicine, 2(1),71-78. https://doi.org/10.1002/sim.4780020108
38. Song, J. H., Venkatesh, S. S., Conant, E. A., Arger, P. H., & Sehgal, C. M. (2005). Comparative analysis of logistic regression and artificial neural network for computer-aided diagnosis of breast masses. Academic Radiology, 12(4), 487-495. http://doi.org/10.1016/j.acra.2004.12.016
39. Soltoggio, A., Stanley, K. O., & Risi, S. (2018). Born to learn: The inspiration, progress, and future of evolved plastic artificial neural networks. Neural Networks, 108, 48-67. https://doi.org/10.1016/j.neunet.2018.07.013
40. Tavanaei, A., Ghodrati, M., Kheradpisheh, S. R., Masquelier, T., & Maida, A. (2019). Deep learning in spiking neural networks. In Neural Networks, 111, 47-63. Elsevier Ltd. https://doi.org/10.1016/j.neunet.2018.12.002
41. Varikuti, D. P., Genon, S., Sotiras, A., Schwender, H., Hoffstaedter, F., Patil, K. R., Jockwitz, C., Caspers, S., Moebus, S., Amunts, K., Davatzikos, C., & Eickhoff, S. B. (2018). Evaluation of nonnegative matrix factorization of grey matter in age prediction. NeuroImage, 173, 394-410. https://doi.org/10.1016/j.neuroimage.2018.03.007
42. Vellappally, S., Al Kheraif, A. A., Anil, S., & Wahba, A. A. (2019). IoT medical tooth mounted sensor for monitoring teeth and food level using bacterial optimization along with adaptive deep learning neural network. Measurement: Journal of the International Measurement Confederation, 135, 672-677. https://doi.org/10.1016/j.measurement.2018.11.078
43. Wang, J., Ling, C., & Gao, J. (2017). CNNdel: Calling Structural Variations on Low Coverage Data Based on Convolutional Neural Networks. Journal of Biomedical Informatics, 6375059.
44. Waisman, A., La Greca, A., Mobbs, A. M., Scarafia, M. A., Santin Velazque, N. L., Neiman, G., Moro, L. N., Luzzani, C., Sevlever, G. E., Guberman, A. S., & Miriuka, S. G. (2019). Deep Learning Neural Networks Highly Predict Very Early Onset of Pluripotent Stem Cell Differentiation. Stem Cell Reports, 12(4), 845-859. https://doi.org/10.1016/j.stemcr.2019.02.004
45. Wideman, C. E., Jardine, K. H., & Winters, B. D. (2018). Involvement of classical neurotransmitter systems in memory reconsolidation: Focus on destabilization. Neurobiology of Learning and Memory, 156, 68-79. https://doi.org/10.1016/j.nlm.2018.11.001
46. Zhang, G., Eddy Patuwo, B., Y. Hu, M. (1998). Forecasting with artificial neural networks: The state of the art. International Journal of Forecasting, 14(1), 35-62. https://doi.org/10.1016/S0169-2070(97)00044-7
47. Zhang, Y., Ye, D., & Liu, Y. (2018). Robust locally linear embedding algorithm for machinery fault diagnosis. Neurocomputing, 273, 323-332. https://doi.org/10.1016/j.neucom.2017.07.048
48. Zurada, J., Malinowski, A., Cloete, A. (1994). Sensitivity analysis for minimization of input dimension for feedforward neural networks. Proceedings of the 2003 IEEE International Symposium on Circuits and Systems, 6, 447-50. https://doi.org/10.1109/ISCAS.1994.409622
Review
For citations:
Bazylev V.V., Karnakhin V.A. Comparison of the Possibilities of Logistic Regression and Artificial Neural Networks in Predicting the Results of Research on f Small Sample. Health, Food & Biotechnology. 2019;1(3):11-20. (In Russ.) https://doi.org/10.36107/hfb.2019.i3.s238
Views:
509
Email this article 