Page 88 - The-5th-MCAIT2021-eProceeding

4. Discussion

Feature selection using filtration information gain ranking and combination with matrix correlation
successfully selects important features for all dataset thus improving model performance. The application of
SMOTE techniques improves the performance of the model and be able to predict both survival and mortality
classes efficiently. However, as the nature of the data should be very skewed, future research using outliers
behaviour detection should be investigated.

Acknowledgements

This research was supported by FTM1 of FTSM. We would like to thank our colleagues from IJN especially
PCI Team Clinical Research Department, who provided insight and expertise that greatly assisted the research,
as well as physial works while time-off for doing this project.

References

Canfield, J. & Totary-Jain, H. 2018. 40 years of percutaneous coronary intervention: History and future
directions. Journal of Personalized Medicine 8(4): 1–9. doi:10.3390/jpm8040033
Chawla, N. V., Bowyer, K. W., Hall, L. O. & Kegelmeyer, W. P. 2002. SMOTE: Synthetic minority over-
sampling technique. Journal of Artificial Intelligence Research 16(February 2017): 321–357.
doi:10.1613/jair.953
Department of Statistics Malaysia. 2019. Perangkaan Sebab Kematian Malaysia 2019. Jabatan Perangkaan
Malaysia 57: 1–441
Hsieh, M.-H., Lin, S.-Y., Lin, C.-L., Hsieh, M.-J., Hsu, W.-H., Ju, S.-W., Lin, C.-C., et al. 2019. A fitting
machine learning prediction model for short-term mortality following percutaneous catheterization
intervention: a nationwide population-based study. Annals of Translational Medicine 7(23): 732–732.
doi:10.21037/atm.2019.12.21
Gui, C. & Chan, V. 2017. Machine Learning in Medicine 76–78. Retrieved from http://www.uwomj.com/wp-
-content/uploads/2017/12/vol86no2_28.pdf
Mohamad, R. & Bee Wah, Y. 2019. Prediction of survival status of patients after Percutaneous coronary
intervention (PCI) using machine learning techniques. 6(1): 1–46. doi:10.1016/j.surfcoat.2019.125084

E- Proceedings of The 5th International Multi-Conference on Artificial Intelligence Technology (MCAIT 2021) [75]
Artificial Intelligence in the 4th Industrial Revolution