Aykut EKEN, Şevket ÇALIŞKAN, Soner ÇİVİLİBAL, Pınar Deniz TOSUN

Sigara Kullanma Durumunun Çoklu Fizyolojik Ölçümler Ve Makine Öğrenmesi Teknikleri Kullanılarak Tahmini

Sigara kullanımı toplumlarda gerek sağlık gerek ekonomik açıdan ciddi kayıplara sebep olmaktadır. Kullanım seviyesinin ölçümünde bir altın standart bulunmamasına rağmen, Fagerstörm Nikotin Bağımlılık Testi (Fagerstörm Test for Nicotine Dependency – FTND) ve HONC (Hooked on Nicotine Checklist) gibi geleneksel testler ve çeşitli nörogörüntüleme yaklaşımları kişinin sigara içme durumunun seviyesi hakkında bir bilgi vermektedir. Bu çalışmada, objektif bir veri olan fizyolojik parametrelerin subjektif bir veri olan bağımlılık testlerinin yerine kullanım seviye tespitinde yeni bir yaklaşım olarak kullanılabileceğini göstermek amaçlanmıştır. Bu amaçla çeşitli seviyelerdeki sigara kullanıcılarından fizyolojik sinyaller (elektrokardiyogram (EKG), Solunum ve Fotopletismografi) toplanmıştır. Bu sinyallerden elde edilen çeşitli öz niteliklerden makine öğrenmesi yaklaşımları kullanılarak katılımcılar düşük seviye veya yüksek seviye olarak tahmin edilmeye çalışılmıştır. Çalışma için önceden FTND bağımlılık testine giren değişik kullanım seviyelerinde 95 katılımcı alınıp bu kişilerden sırasıyla 50 saniyelik EKG, solunum ve fotopletismografi sinyalleri alınmıştır. Öznitelik çıkarımından sonra, parametre optimizasyonu ve sınıflandırma içeren 10 kat içiçe çapraz geçerlilik gerçekleştirilmiştir. Yapılan sınıflandırma sonucunda destek vektör makinesi kullanılarak %93, diskriminant analizi kullanılarak ise %91 doğruluk başarımı elde edilmiştir. Bu sonuçlar, yukarıda belirtilen fizyolojik parametrelerin makine öğrenmesi algoritmaları aracılığı ile sigara kullanım durumunun tespitinde kullanılabileceğini göstermektedir.

Anahtar Kelimeler:

Sigara Kullanımı, Fotopletismografi, EKG, Solunum, Makine Öğrenmesi, Sınıflandırma

Prediction of smoking status by using multi-physiological measures and machine learning techniques

Smoking causes severe economic and health losses in communities. Despite the lack of a gold standard for the measurement of usage level, conventional tests such as Fagerstörm Test for Nicotine Dependency (FTND), Hooked on Nicotine Checklist (HONC) and various neuroimaging approaches provide information about the level of smoking status. In this study, usage of objective physiological parameters was proposed as a new approach to detect level of status instead of subjective status tests. In order to achieve this physiological signals (i.e.., electrocardiogram (ECG), respiration and photoplestimography) were acquired from participants from different smoking status levels. Participants’ smoking status levels were predicted as high dependent and low dependent from features extracted from these physiological signals using machine learning approaches. For this study, 95 university students with different levels of smoking status were recruited according to FTND test results and ECG, respiration and photopletismography signals were acquired respectively for 50 seconds to provide data for machine learning models. After feature extraction, a 10 fold nested- cross validation that includes hyperparameter optimization and classification was performed. According to the classification results, 93 % accuracy and 91 % accuracy were found by using Support Vector Machine and Discriminant Analysis respectively. These results revealed that physiological parameters might be used to predict smoking status via machine learning algorithms.

Keywords:

smoking status, photopletsmography, ECG, respiration, machine learning, classification,

PDF

___

[1] West, R. 2017. Tobacco smoking: Health impact, prevalence, correlates and interventions, Cilt. 32 s. 1018-1036. 10.1080/08870446.2017.1325890
[2] WHO, WHO report on the global tobacco epidemic, 2013. Enforcing bans on tobacco advertising, promotion and sponsorship. Geneva: World Health Organization (in English), 2013, p. 202 pp.
[3] Services, U. D. o. H. a. H., in The Health Consequences of Smoking: A Report of the Surgeon General, (Reports of the Surgeon General. Atlanta (GA), 2004, p. 62.
[4] West, R. 2009. The multiple facets of cigarette addiction and what they mean for encouraging and helping smokers to stop, Cilt. 6 s. 277-83.
[5] Heatherton, T. F., Kozlowski, L. T., Frecker, R. C. and Fagerstrom, K.-O. 1991. The Fagerström Test for Nicotine Dependence: a revision of the Fagerstrom Tolerance Questionnaire, Cilt. 86 s. 1119-1127. 10.1111/j.1360-0443.1991.tb01879.x
[6] DiFranza, J. R., Savageau, J. A., Fletcher, K., Ockene, J. K., Rigotti, N. A., McNeill, A. D., Coleman, M. and Wood, C. 2002. Measuring the loss of autonomy over nicotine use in adolescents: the DANDY (Development and Assessment of Nicotine Dependence in Youths) study, Cilt. 156 s. 397-403.
[7] Brody, A. L., Mandelkern, M. A., Jarvik, M. E., Lee, G. S., Smith, E. C., Huang, J. C., Bota, R. G., Bartzokis, G. and London, E. D. 2004. Differences between smokers and nonsmokers in regional gray matter volumes and densities, Cilt. 55 s. 77-84. 10.1016/s0006-3223(03)00610-3
[8] Gallinat, J., Meisenzahl, E., Jacobsen, L. K., Kalus, P., Bierbrauer, J., Kienast, T., Witthaus, H., Leopold, K., Seifert, F., Schubert, F. and Staedtgen, M. 2006. Smoking and structural brain deficits: a volumetric MR investigation, Cilt. 24 s. 1744-50. 10.1111/j.1460-9568.2006.05050.x
[9] Paul, R. H., Grieve, S. M., Niaura, R., David, S. P., Laidlaw, D. H., Cohen, R., Sweet, L., Taylor, G., Clark, R. C., Pogun, S. and Gordon, E. 2008. Chronic cigarette smoking and the microstructural integrity of white matter in healthy adults: a diffusion tensor imaging study, Cilt. 10 s. 137-47. 10.1080/14622200701767829
[10] Domino, E. F. 2008. Tobacco smoking and MRI/MRS brain abnormalities compared to nonsmokers, Cilt. 32 s. 1778-81. 10.1016/j.pnpbp.2008.09.004
[11] Ding, X., Yang, Y., Stein, E. A. and Ross, T. J. 2015. Multivariate classification of smokers and nonsmokers using SVM-RFE on structural MRI images, Cilt. 36 s. 4869-4879. 10.1002/hbm.22956
[12] Pariyadath, V., Stein, E. A. and Ross, T. J. 2014. Machine learning classification of resting state functional connectivity predicts smoking status, Cilt. 8 s. 425. 10.3389/fnhum.2014.00425
[13] Wetherill, R. R., Rao, H., Hager, N., Wang, J., Franklin, T. R. and Fan, Y. 2019. Classifying and characterizing nicotine use disorder with high accuracy using machine learning and resting-state fMRI, Cilt. 24 s. 811-821. 10.1111/adb.12644
[14] Mamoshina, P., Kochetov, K., Cortese, F., Kovalchuk, A., Aliper, A., Putin, E., Scheibye-Knudsen, M., Cantor, C. R., Skjodt, N. M., Kovalchuk, O. and Zhavoronkov, A. 2019. Blood Biochemistry Analysis to Detect Smoking Status and Quantify Accelerated Aging in Smokers, Cilt. 9 s. 142. 10.1038/s41598-018-35704-w
[15] Frank, C., Habach, A., Seetan, R. and Wahbeh, A., Predicting Smoking Status Using Machine Learning Algorithms and Statistical Analysis. 2018, pp. 184-189.
[16] Savova, G. K., Ogren, P. V., Duffy, P. H., Buntrock, J. D. and Chute, C. G. 2008. Mayo clinic NLP system for patient smoking status identification, Cilt. 15 s. 25-8. 10.1197/jamia.M2437
[17] McCormick, P. J., Elhadad, N. and Stetson, P. D. 2008. Use of semantic features to classify patient smoking status, Cilt. 2008 s. 450-454.
[18] Poredos, P., Orehek, M. and Tratnik, E. 1999. Smoking is associated with dose-related increase of intima-media thickness and endothelial dysfunction, Cilt. 50 s. 201-8. 10.1177/000331979905000304
[19] Rabe, K. F., Hurd, S., Anzueto, A., Barnes, P. J., Buist, S. A., Calverley, P., Fukuchi, Y., Jenkins, C., Rodriguez-Roisin, R., van Weel, C., Zielinski, J. and Global Initiative for Chronic Obstructive Lung, D. 2007. Global strategy for the diagnosis, management, and prevention of chronic obstructive pulmonary disease: GOLD executive summary, Cilt. 176 s. 532-55. 10.1164/rccm.200703-456SO
[20] Devi, M. R., Arvind, T. and Kumar, P. S. 2013. ECG Changes in Smokers and Non Smokers-A Comparative Study, Cilt. 7 s. 824-6. 10.7860/JCDR/2013/5180.2950
[21] Ramakrishnan, S., Bhatt, K., Dubey, A. K., Roy, A., Singh, S., Naik, N., Seth, S. and Bhargava, B. 2013. Acute electrocardiographic changes during smoking: an observational study, Cilt. 3 s. 10.1136/bmjopen-2012-002486
[22] Bodin, F., McIntyre, K. M., Schwartz, J. E., McKinley, P. S., Cardetti, C., Shapiro, P. A., Gorenstein, E. and Sloan, R. P. 2017. The Association of Cigarette Smoking With High-Frequency Heart Rate Variability: An Ecological Momentary Assessment Study, Cilt. 79 s. 1045-1050. 10.1097/PSY.0000000000000507
[23] Glass, K. L., Dillard, T. A., Phillips, Y. Y., Torrington, K. G. and Thompson, J. C. 1996. Pulse oximetry correction for smoking exposure, Cilt. 161 s. 273-6.
[24] Irizar-Aramburu, M. I., Martinez-Eizaguirre, J. M., Pacheco-Bravo, P., Diaz-Atienza, M., Aguirre-Arratibel, I., Pena-Pena, M. I., Alba-Latorre, M. and Galparsoro-Goikoetxea, M. 2013. Effectiveness of spirometry as a motivational tool for smoking cessation: a clinical trial, the ESPIMOAT study, Cilt. 14 s. 185. 10.1186/1471-2296-14-185
[25] Akbarzadeh, M. A., Yazdani, S., Ghaidari, M. E., Asadpour-Piranfar, M., Bahrololoumi-Bafruee, N., Golabchi, A. and Azhari, A. 2014. Acute effects of smoking on QT dispersion in healthy males, Cilt. 10 s. 89-93.
[26] Chatterjee, S., Kumar, S., Dey, S. K. and Chatterjee, P. 1989. Chronic effect of smoking on the electrocardiogram, Cilt. 30 s. 827-39.
[27] Özdal, M., Pancar, Z., Çınar, V., Bilgiç, M., 2017. Effect of Smoking on Oxygen Saturation in Healthy Sedentary Men and Women, Cilt. 4 s. 178-182.
[28] Tantisuwat, A. and Thaveeratitham, P. 2014. Effects of smoking on chest expansion, lung function, and respiratory muscle strength of youths, Cilt. 26 s. 167-70. 10.1589/jpts.26.167
[29] Hampel, F. R. 1971. A general qualitative definition of robustness, Cilt. s. 1887-1896.
[30] Hampel, F. R. 1974. The influence curve and its role in robust estimation, Cilt. 69 s. 383-393.
[31] Tibshirani, R. 1996. Regression Shrinkage and Selection via the Lasso, Cilt. 58 s. 267-288.
[32] Zou, H. and Hastie, T. 2005. Regularization and Variable Selection via the Elastic Net, Cilt. 67 s. 301-320. [33] Vapnik, V. N. 1995. The Nature of Statistical Learning, Cilt. s.
[34] Ge, D., Srinivasan, N. and Krishnan, S. M. 2002. Cardiac arrhythmia classification using autoregressive modeling, Cilt. 1 s. 5-5. 10.1186/1475-925X-1-5
[35] Padmavathi, K. and Ramakrishna, K. S. 2015. Classification of ECG Signal during Atrial Fibrillation Using Autoregressive Modeling, Cilt. 46 s. 53-59. https://doi.org/10.1016/j.procs.2015.01.053
[36] Xi, Q., Sahakian, A. V. and Swiryn, S. 2003. The effect of QRS cancellation on atrial fibrillatory wave signal characteristics in the surface electrocardiogram, Cilt. 36 s. 243-9. 10.1016/s0022-0736(03)00046-3
[37] Vidaurre, D., Bielza, C. and Larrañaga, P. 2013. Classification of neural signals from sparse autoregressive features, Cilt. 111 s. 21-26. https://doi.org/10.1016/j.neucom.2012.12.013
[38] Anderson, C. W., Stolz, E. A. and Shamsunder, S. 1998. Multivariate autoregressive models for classification of spontaneous electroencephalographic signals during mental tasks, Cilt. 45 s. 277-86. 10.1109/10.661153
[39] Xin, Y., Kong, L., Liu, Z., Wang, C., Zhu, H., Gao, M., Zhao, C. and Xu, X. 2018. Multimodal Feature-Level Fusion for Biometrics Identification System on IoMT Platform, Cilt. 6 s. 21418-21426. 10.1109/ACCESS.2018.2815540
[40] Beltz, A. M., Berenbaum, S. A. and Wilson, S. J. 2015. Sex differences in resting state brain function of cigarette smokers and links to nicotine dependence, Cilt. 23 s. 247-254. 10.1037/pha0000033