Predicting Depression Level of Youth Smokers  
Using Machine Learning

Tobacco smoking is an alarming public health concern on a global scale due to its negative impact on the future generations wellbeing. This study aim to demonstrate the role of decision support system in predicting the depression level of youth using their smoking habits and related factors. In this work, we developed a hybrid machine learning model that consisted of clustering and classification. The idea of this model is to provide health care providers with a tool to predict the level of depression for youth smokers using a set of novel factors including: father’s job, number of Aarghile (Shisha) heads smoked, and other relevant factors. Our model illustrated a significant relationship between smoking and level of depression. Our model demonstrated a prediction accuracy of 94% when applied on a dataset consisting of 993 student smokers in Jordan. Age was found as the most influential attribute in predicting the depression level of youth smokers. Therefore, efficient solutions must be considered to find useful alternatives to smoking.

REFERENCES

[1] Demner-Fushman, D., Chapman, W., Mcdonald, C., "What can Natural Language Processing do for Clinical Decision Support?", Journal of Biomedical Informatics Volume 42 issue 5, pp.760-72, 2009.
[2] Karakülah, G., Koşaner, O., Birant, C., Berber,T., Karakülah, A., Karakulah, G., Suner, A., Dicle, O., "Computer Based Extraction Of Phenoptypic Features Of Human Congenital Anomalies From The Digital Literature With Natural Language Processing Techniques", Studies In Health Technology And Informatics, Volume 205, pp. 570-574, 2014.
[3] Jin, Y., McDonald, R., Lerman, K., Mandel, M., Carroll, S., Liberman M., F., Winters,, R., White, P., "Automated recognition of malignancy mentions in biomedical literature", BMC Bioinformatics,Volume 7: 492, 2006.
[4] Skounakis,M., Craven, M., Ray, S. "Hierarchical hidden Markov models for information extraction", in Proceedings of the 18th international joint conference on Artificial intelligence (IJCAI'03), pp. 427- 433, 2003.
[5] Poulymenopoulou, M., Malamateniou, F., Vassilacopoulos, G., "Machine Learning for Knowledge Extraction from PHR Big Data", Studies in health technology and informatics, Volume 202, pp.36-39,2014.
[6] Das, R., Turkoglub, I., Sengur, A., "Effective diagnosis of heart disease through neural networks ensembles", Expert Systems with Applications, Volume 36, pp. 7675-7680, 2009.
[7] Chien, C., Pottie, G., "A universal hybrid decision tree classifier design for human activity classification," in Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 1065-1068, 2012.
[8] Zuoa, W., Wanga, Z., Liua, T., Chenc, H., "Effective detection of Parkinson’s disease using an adaptive fuzzy k-nearest neighbor approach", Biomedical Signal Processing and Control, Elsevier, Volume 8, Issue 4, pp. 364-373, 2013.
[9] Jena, H., Wang, C., Jiangc, B., Chub, Y., Chen, M., "Application of classification techniques on development an early-warning systemfor chronic illnesses", Expert Systems with Applications, Volume 39, pp. 8852-8858, 2012.
[10] Garcia, H., Shihab, E.,"Characterizing and predicting blocking bugs in open source projects," in Proceedings of the 11th Working Conference on Mining Software Repositories (MSR'14), New York, NY, USA, pp. 72 - 81, 2014.
[11] Hassan, A., Zhang, K.," Using decision trees to predict the certification result of a build," In Proceedings of the 21st IEEE/ACM International Conference on Automated Software Engineering (ASE '06), pp. 189–198, 2006.
[12] Ahmad, P., Qamar, S.,Rizvi, S., "Techniques of Data Mining In Healthcare: A Review", International Journal of Computer Applications, Volume 120, pp. 38–50, 2015.
[13] Efron, B., " Estimating the error rate of a prediction rule: improvement on cross-validation ", Technical Journal of the American Statistical Association, vol. 78, no. 382, pp. 316–331, 1983.
[14] D. Mays, K. P. Tercyak, K. Rehberg, M.-K. Crane, and I. M. Lipkus, "Young adult waterpipe tobacco users’ perceived addictiveness of waterpipe tobacco," Tobacco Prevention & Cessation, vol. 3, no. December, 2017 2017.
[15] https://www.cs.waikato.ac.nz/ml/weka/
[16] M. Bkassiny, Y. Li ,SK. Jayaweera, “ A survey on machine-learning techniques in cognitive radios,” IEEE Communications Surveys & Tutorials, Vol. 15, No. 3, pp. 1136-59, 2013.
[17] F. Thung, S. Wang, D. Lo and L. Jiang, “An Empirical Study of Bugs in Machine Learning Systems,” IEEE 23rd International Symposium on Software Reliability Engineering, Dallas, pp. 271-280, 2012.
[18] J. S. Di Stefano and T. Menzies, “Machine learning for software engineering: case studies in software reuse, ”, 14th IEEE International Conference on Tools with Artificial Intelligence, pp. 246-251, 2002.
[19] K. A. Gunes, and L. Hongfang, “ Building effective defect-prediction models in practice,” IEEE Software, Vol. 22, No. 6, pp. 23-29 , 2005.
[20] Alzyoud, S., Kheirallah, K. A., Weglicki, L. S., Ward, K. D., Al-Khawaldeh, A., & Shotar, A. (2014). Tobacco smoking status and perception of health among a sample of Jordanian students. International journal of environmental research and public health, 11(7), 7022-7035
[21] Mohammad Kharabsheh, Omar Meqdadi, Mohammad Alabed, Sreenivas Veeranki, Ahmad Abbadi and Sukaina Alzyoud, “A Machine Learning Approach for Predicting Nicotine Dependence” International Journal of Advanced Computer Science and Applications(IJACSA), 10(3), 2019.
[22] Alaa Al-Nusirat, Feras Hanandeh, Mohammad Kamel Kharabsheh, Mahmoud Al-Ayyoub, Nahla Al-dhfairi: Dynamic Detection of Software Defects Using Supervised Learning Techniques. International Journal of Communication Networks and Information Security (IJCNIS) 11(1) (2019) 2017.
[23] Shihab, Emad, Akinori Ihara, Yasutaka Kamei, Walid M. Ibrahim, Masao Ohira, Bram Adams, Ahmed E. Hassan, and Ken-ichi Matsumoto. "Predicting Re-opened Bugs: A Case Study on the Eclipse Project", in Proceedings of the 17th Working Conference on Reverse Engineering, 2010.