Abstract

Nicotine consumption is a condition that negatively affects the health of millions of people worldwide each year and leads to severe addiction problems. This study aims to develop and evaluate a machine-learning model for predicting nicotine consumption patterns and quitting times. By analyzing factors influencing nicotine use, the research seeks to identify the most appropriate time intervals for intervention before the transition to addiction. Moreover, the interactions between nicotine addiction and the use of psychotropic narcotic drugs have been examined in depth. The results show that nicotine addiction increases the risk of developing narcotic drug dependence, highlighting the importance of early intervention strategies. In analyses using machine learning models, the highest performance was achieved by Support Vector Machines with an accuracy of 94.07% and an F1 score of 91.24%. These findings have the potential to assist healthcare professionals in managing prescription processes more consciously and preventing addictive behaviors. The study provides significant scientific and practical contributions to better understanding the connections between nicotine and narcotic addictions and developing more effective intervention strategies in healthcare services.

References

[1] Kim, M., Yang, J., Ahn, W. Y., & Choi, H. J. Machine learning analysis to identify digital behavioral phenotypes for engagement and health outcome efficacy of a mHealth intervention for obesity: Randomized controlled trial. Journal of Medical Internet Research, 2021; 23(6), e27218.

[2] Sağlam, L. Clinical evaluation of nicotine dependence. Güncel Göğüs Hastalıkları Serisi, 2017; 4(1), 78-89.

[3] Şengül, A. C. Drug misuse and drug addiction. Turkiye Klinikleri Neurology-Special Topics, 2010; 3(1), 199-203.

[4] Armbruster, W. S., Di Stilio, V. S., Tuxill, J. D., Flores, T. C., & Runk, J. L. Covariance and decoupling of floral and vegetative traits in nine Neotropical plants: A re-evaluation of Berg’s correlation-Pleiades concept. American Journal of Botany, 1999; 86(1), 39–55.

[5] Karakülah, K., Şengül, C., & Balcı Şengül, C. Genetics of smoking addiction. Psikiyatride Güncel Yaklaşımlar - Current Approaches in Psychiatry, 2014; 6(3), 284-293.

[6] Uysal, M. A. How does nicotine take you captive? Neurobiology of tobacco addiction. Güncel Göğüs Hastalıkları Serisi, 2016; 4(1), 37-43.

[7] Goh, Y. S., Ow Yong, J. Q. Y., Chee, B. Q. H., Kuek, J. H. L., & Ho, C. S. H. Machine learning in health promotion and behavioral change: Scoping review. Journal of Medical Internet Research, 2022; 24(6), e35831.

[8] Obey, K. (24.09.2024). Drug consumption prediction. Kaggle. https://www.kaggle.com/code/obeykhadija/drug-consumption-prediction#Feature-Engineering

[9] Glasner-Edwards, S., Mooney, L. J., Marinelli-Casey, P., Hillhouse, M., Ang, A., & Rawson, R. Risk factors for suicide attempts in methamphetamine-dependent patients. The American Journal on Addictions, 2008; 17(1), 24-27.

[10] Nordahl, T. E., Salo, R., & Leamon, M. Neuropsychological effects of chronic methamphetamine use on neurotransmitters and cognition: A review. The Journal of Neuropsychiatry and Clinical Neurosciences, 2023; 15(3), 317-325.

[11] Hernández-Llanes, N. F., Sánchez-Domínguez, R., Pérez-Zapata, S., Fernández-Domínguez, E., & González-Rosales, F. Machine learning analysis to identify factors associated with requesting tobacco cessation services among users of an online self-diagnostic questionnaire in Mexico. Research Square. 2023.

[12] Almahmood, M., Najadat, H., Alzubi, D., Abualigah, L., Zitar, R. A., Abualigah, S., & AL-Saqqar, F. Predictive model of psychoactive drugs consumption using classification machine learning algorithms. Applied and Computational Engineering, 2023; 8(1), 853–858.

[13] Liu, J., Rensch, J., Wang, J., Jin, X., Vansickel, A., Edmiston, J., & Sarkar, M. Nicotine pharmacokinetics and subjective responses after using nicotine pouches with different nicotine levels compared to combustible cigarettes and moist smokeless tobacco in adult tobacco users. Psychopharmacology, 2022; 239(9), 2863–2873.

[14] Suma, S. N., Nataraja, P., & Sharma, M. K. Internet addiction predictor: Applying machine learning in psychology. In N. N. Chiplunkar & T. Fukao (Eds.), Advances in Artificial Intelligence and Data Engineering. AIDE 2019. Advances in Intelligent Systems and Computing Vol. 1133. 2021, pp. 399-409.

[15] Bozkurt, N., & Bozkurt, A. İ. Assessment of the Fagerström Test for Nicotine Dependence (FTND) used in the determination of nicotine dependence and developing a new test for nicotine dependence. Pamukkale University Faculty of Medicine, Department of Chest Diseases, Denizli; Pamukkale University Faculty of Medicine, Department of Public Health, Denizli. 2016.

[16] Wang, P., Abdin, E., Asharani, P., Seet, V., Devi, F., Roystonn, K., Lee, Y. Y., Cetty, L., Teh, W. L., Verma, S., & others. Nicotine dependence in patients with major depressive disorder and psychotic disorders and its relationship with quality of life. International Journal of Environmental Research and Public Health, 2021; 18(24), 13035.

[17] Leys, C., Ley, C., Klein, O., Bernard, P., & Licata, L. Detecting outliers: Do not use standard deviation around the mean, use absolute deviation around the median. Journal of Experimental Social Psychology, 2013; 49(4), 764-766.

[18] Smith, J., & Johnson, A. Evaluating the role of precision in machine learning models for medical diagnosis. Journal of Medical Systems, 2020; 44(8), 1-10.

[19] Pala, M. A., & Yıldız, M. Z. (2024). Improving cellular analysis throughput of lens-free holographic microscopy with circular Hough transform and convolutional neural networks. Optics & Laser Technology, 176, 110920.

[20] Akgul, A., Karaca, Y., Pala, M. A., Çimen, M. E., Boz, A. F., & Yildiz, M. Z. (2024). Chaos theory, advanced metaheuristic algorithms and their newfangled deep learning architecture optimization applications: a review. Fractals, 32(03), 2430001.