Comparing Random Forests Regression with Logistic Regression to Determine the Most Important Factors Affecting Congenital Malformations For Newborn Babies in Iraq

Authors

DOI:

https://doi.org/10.61841/rk3z0e42

Keywords:

Tree Regression, Random Forest, Binary Logistic regression, Congenital malformation, Mean Square Error

Abstract

A congenital malformation is a structural defect in one or more parts of the body from birth. The causes and sources of birth defects may be genetic or caused by a non-genetic event before birth. Some congenital malformations may be caused by taking drugs, or sometimes the causes are unknown. In recent years, the rate of congenital malformations among newborn children in Iraq has increased, and to identify this problem and identify the most important factors affecting it, a sample of children with congenital malformations was taken to the maternity hospitals of the Health Department of Baghdad/Rusafa and Karkh—Department of preterm infants of 2504 births. To identify the most important factors affecting the congenital malformations using artificial intelligence techniques and machine learning, including random forests regression and logistic regression decline, as these techniques are one of the most advanced techniques used in the case of big data , We concluded from this research, which aimed to find the best model for estimating the data of congenital anomalies in Iraq through the use of two types of machine learning models (artificial intelligence) and as these types are regression models at the same time, after estimating each model, we compared using the mean squares error criterion and it was the best A model is a random forest model regression. 

Downloads

Download data is not yet available.

References

1. Biondo, S.; Ramos, E.; Deiros, M.; Ragué, J. M.; De Oca, J.; Moreno, P.; Farran, L.; Jaurrieta, E. "Prognostic factors for mortality in left colonic peritonitis: A new scoring system." Journal of the American College of Surgeons. 191 (6): 635–42. (2000). doi:10.1016/S1072-7515(00)00758-4. PMID 11129812.

2. Boyd, C. R.; Tolson, M. A.; Copes, W. S. "Evaluating trauma care: The TRISS method. Trauma Score and the Injury Severity Score". The Journal of Trauma. 27 (4), (1987).: 370–378. doi:10.1097/00005373-198704000-00005. PMID 3106646

3. Breiman, L. Random Forests, Machine Learning, 2001, Volume 45, Issue 1, pp. 5–32.

4. Couronne, Raphael. Probst, Philipp.Boulesteix, Anne-Laure. Random forest versus logistic regression: a large-scale benchmark experiment. BMC Bioinformatics. 2018

5. G. Biau, Analysis of a Random Forest Model, J. Mach. Learn. Res. 98888 (2012) 1063–1095.

6. Goodfellow, Ian; Bengio, Yoshua; Courville, Aaron. Deep Learning. MIT Press. 2016

7. Hastie, T., Tibshirani, R., Friedman, J. The elements of statistical learning: data mining, inference, and prediction. Springer. 2009

8. Hosmer, D.W. "A comparison of goodness-of-fit tests for the logistic regression model" (1997). Stat Med. 16 (9): 965–980.

9. Kologlu, M.; Elker, D.; Altun, H.; Sayek, I. "Validation of MPI and PIA II in two different groups of patients with secondary peritonitis." Hepato-Gastroenterology. 48 (37), (2001): 147–51. PMID 11268952.

10. L. Breiman, Random forests, Mach. Learn. 45 (1) (2001) 5–32.

11. Le Gall, J. R.; Lemeshow, S.; Saulnier, F. "A new Simplified Acute Physiology Score (SAPS II) based on a European/North American multicenter study." JAMA. 270 (24): 2957–63. (1993). doi:10.1001/jama.1993.03510240069035. PMID 8254858.

12. Marshall, J. C.; Cook, D. J.; Christou, N. V.; Bernard, G. R.; Sprung, C. L.; Sibbald, W. J. "Multiple organ dysfunction score: A reliable descriptor of a complex clinical outcome." Critical Care Medicine. 23 (10): (1995). 1638–52. doi:10.1097/00003246-199510000-00007. PMID 7587228

13. Rokach, Lior. Maimon, Oded. Data Mining with Decision Trees: Theory and Applications. 2nd ed., World Scientific Publishing Co.

Downloads

Published

30.04.2020

How to Cite

Comparing Random Forests Regression with Logistic Regression to Determine the Most Important Factors Affecting Congenital Malformations For Newborn Babies in Iraq. (2020). International Journal of Psychosocial Rehabilitation, 24(2), 9081-9093. https://doi.org/10.61841/rk3z0e42