CORTISOL HORMONE AND STRESS LEVELS: COLORIMETRIC ASSESSMENT WITH ARTIFICIAL INTELLIGENCE SUPPORTED IMAGE PROCESSING METHOD

Abstract

This study presents a new method for determining cortisol hormone levels, a key biomarker of stress, using microfluidic pads to collect sweat samples. The pads facilitate the colorimetric detection of cortisol levels via the blue tetrazolium method. The resulting color change is analytically assessed using Convolutional Neural Networks (CNN), Decision Trees, and Vector Regression, alongside advanced image processing techniques. The developed algorithm is robust, providing reliable results despite hardware variations and color distortion, enhancing the system's applicability and generalizability across different environments. Validation studies conducted with ELISA and a colorimeter revealed that the system achieved an accuracy of 84.2% in determining users' cortisol levels. Additionally, psychosocial stress levels were assessed using the Copenhagen Psychosocial Risk Assessment and the Perceived Stress Scale tests during the collection of sweat samples from 20 participants. The results demonstrated a significant correlation between cortisol levels and stress, confirming the method's reliability and effectiveness in various applications.

Keywords

• Computer vision
• Convolutional neural networks
• Cortisol hormone
• Occupational stress
• Psychosocial risk assessment

Supporting Institution

Istanbul University BAP

Project Number

FYL-2022-38254. Project No: 38254

Ethical Statement

This study is supported within the scope of ISTANBUL University BAP Postgraduate Thesis Project numbered FYL-2022-38254. Project No: 38254

References

1. H. Kepir, “İş Kazalarında İnsan Faktörü ve Eğitimi,” in Çeşitli Boyutları ve Çözüm Önerileri ile İş Kazaları Seminer Bildirileri, MPM Yayınları No: 284, Ankara, 1983, pp. 96-104.
2. A. Çelikkol, İş Kazalarında Ruhsal Etmenler, Doçentlik Tezi, Ege Üniversitesi Tıp Fakültesi, İzmir, 1977, p. 28.
3. C. L. Cooper, C. P. Cooper, P. J. Dewe, P. J. Dewe, M. P. O'Driscoll, and M. P. O'Driscoll, Organizational Stress: A Review and Critique of Theory, Research, and Applications, 2001.
4. J. Gaab, N. Rohleder, U. M. Nater, and U. Ehlert, “Psychological determinants of the cortisol stress response: the role of anticipatory cognitive appraisal,” Psychoneuroendocrinology, vol. 30, no. 6, pp. 599-610, 2005.
5. P. Gupta and B. Gupta, “Applications of OpenCV in computer vision: A review,” International Journal of Computer Vision and Signal Processing, vol. 10, no. 12, pp. 12-28, 2020.
6. I. Kandel, M. Castelli, and L. Manzoni, “Brightness as an augmentation technique for image classification,” Emerging Science Journal, vol. 6, no. 4, pp. 881-892, 2022.
7. R. K. Nath, H. Thapliyal, and A. Caban-Holt, “Machine learning-based stress monitoring in older adults using wearable sensors and cortisol as stress biomarker,” Journal of Signal Processing Systems, pp. 1-13, 2022.
8. M. Qi, S. Cui, X. Chang, Y. Xu, H. Meng, Y. Wang, and T. Yin, “Multi-region nonuniform brightness correction algorithm based on L-channel gamma transform,” Security and Communication Networks, vol. 2022, 2022.

9. I. Kandel, M. Castelli, and L. Manzoni, “Brightness as an augmentation technique for image classification,” Emerging Science Journal, vol. 6, no. 4, pp. 881-892, 2022.
10. F. Gasparini and R. Schettini, “Color balancing of digital photos using simple image statistics,” Pattern Recognition, vol. 37, no. 6, pp. 1201-1217, 2004.
11. M. Buzzelli, S. Zini, S. Bianco, G. Ciocca, R. Schettini, and M. K. Tchobanou, “Otomatik beyaz dengesi veri kümeleri ve yöntemlerindeki sapmaların analizi,” Renk Araştırması ve Uygulaması, vol. 48, no. 1, pp. 40-62, 2023.
12. R. F. Rachmadi and I. Purnama, “Vehicle color recognition using convolutional neural network,” arXiv preprint arXiv:1510.07391, 2015.
13. N. Maitlo, N. Noonari, S. A. Ghanghro, S. Duraisamy, and F. Ahmed, “Color Recognition in Challenging Lighting Environments: CNN Approach,” in 2024 IEEE 9th International Conference for Convergence in Technology (I2CT), pp. 1-7, 2024.
14. M. Nafzi, M. Brauckmann, and T. Glasmachers, “Vehicle shape and color classification using convolutional neural network,” arXiv preprint arXiv:1905.08612, 2019.
15. N. A. Mohammed, M. H. Abed, and A. T. Albu-Salih, “Convolutional neural network for color images classification,” Bulletin of Electrical Engineering and Informatics, vol. 11, no. 3, pp. 1343-1349, 2022.
16. L. Breiman, J. Friedman, R. A. Olshen, and C. J. Stone, Classification and Regression Trees, Wadsworth & Brooks/Cole Advanced Books & Software, 1986.
17. J. Bergstra and Y. Bengio, “Random Search for Hyper-Parameter Optimization,” Journal of Machine Learning Research, vol. 13, pp. 281-305, 2012.
18. T. Chai and R. R. Draxler, “Root Mean Square Error (RMSE) or Mean Absolute Error (MAE) for assessing model performance?,” Geoscientific Model Development, vol. 7, no. 3, pp. 1247-1250, 2014.
19. C. Şahan, Kopenhag Psikososyal Risk Değerlendirme Ölçeği'nin Türkçe'ye uyarlanması, Yüksek Lisans Tezi, Dokuz Eylül Üniversitesi Sağlık Bilimleri Enstitüsü, 2016.
20. M. Eskin, H. Harlak, F. Demirkıran, and Ç. Dereboy, “Algılanan stres ölçeğinin Türkçeye uyarlanması: güvenirlik ve geçerlik analizi,” New/Yeni Symposium Journal, vol. 51, no. 3, pp. 132-140, 2013.
21. A. Çelikkol, İş Kazalarında Ruhsal Etmenler, Doçentlik Tezi, Ege Üniversitesi Tıp Fakültesi, İzmir, 1977, p. 28.
22. M. Cufta, “Stres ve dini inanç,” Pamukkale Üniversitesi İlahiyat Fakültesi Dergisi, vol. 3, no. 5, pp. 50-70, 2016.
23. İ. Durak, H. Özbek, M. Karaayvaz, and H. S. Öztürk, “Cisplatin induces acute renal failure by impairing antioxidant system in guinea pigs: effects of antioxidant supplementation on the cisplatin nephrotoxicity,” Drug and Chemical Toxicology, vol. 25, no. 1, pp. 1-8, 2002.
24. J. C. Quick and C. L. Cooper, Gerilme ve Gerinim, 2nd ed., Sağlık Basın, Oxford, İngiltere, p. 75, 2003.
25. C. Spiers, Accuracy Clarity Value Tolley’s Managing Stress In The Workplace, Reed Elsevier, USA, 2003.
26. E. Tu, P. Pearlmutter, M. Tiangco, G. Derose, L. Begdache, and A. Koh, “Comparison of colorimetric analyses to determine cortisol in human sweat,” ACS Omega, vol. 5, no. 14, pp. 8211-8218, 2020.
27. J. Kim, A. S. Campbell, B. E.-F. de Ávila, and J. Wang, “A portable 3D microfluidic origami biosensor for cortisol detection in human sweat,” Analytical Chemistry, vol. 96, no. 2, pp. 482-488, 2024.
28. L. Fiore et al., “Microfluidic paper-based wearable electrochemical biosensor for reliable cortisol detection in sweat,” Sensors and Actuators B: Chemical, vol. 379, p. 133258, 2023.
29. D. Nordholm et al., “A longitudinal study on physiological stress in individuals at ultra high-risk of psychosis,” Schizophrenia Research, vol. 254, pp. 218-226, 2023.
30. H. Janssens et al., “Hair cortisol in relation to job stress and depressive symptoms,” Occupational Medicine, vol. 67, no. 2, pp. 114-120, 2017.
31. A. T. T. Pham et al., “Optical-based biosensors and their portable healthcare devices for detecting and monitoring biomarkers in body fluids,” Diagnostics, vol. 11, no. 7, p. 1285, 2021.
32. M. Yang et al., “Advances in Non-Electrochemical Sensing of Human Sweat Biomarkers: From Sweat Sampling to Signal Reading,” Biosensors, vol. 14, no. 1, p. 17, 2023.
33. Gaab, J., Rohleder, N., Nater, U. M., & Ehlert, U. (2005). Psychological determinants of the cortisol stress response: the role of anticipatory cognitive appraisal. Psychoneuroendocrinology, 30(6), 599-610.
34. Law, R., & Clow, A. (2020). Stress, the cortisol awakening response and cognitive function. International review of neurobiology, 150, 187-217.
35. Knezevic, E., Nenic, K., Milanovic, V., & Knezevic, N. N. (2023). The Role of Cortisol in Chronic Stress, Neurodegenerative Diseases, and Psychological Disorders. Cells, 12(23), 2726.
36. Gaab, J., Rohleder, N., Nater, U. M., & Ehlert, U. (2005). Psychological determinants of the cortisol stress response: the role of anticipatory cognitive appraisal. Psychoneuroendocrinology, 30(6), 599-610.
37. McEwen, B. S., & Wingfield, J. C. (2003). The concept of allostasis in biology and biomedicine. Hormones and Behavior, 43(1), 2-15. https://doi.org/10.1016/S0018-506X(02)00024-7
38. Matousek, R. H., Dobkin, P. L., & Pruessner, J. (2010). Cortisol as a marker for improvement in mindfulness-based stress reduction. Complementary therapies in clinical practice, 16(1), 13-19.
39. Hogenelst, K., Soeter, M., & Kallen, V. (2019). Ambulatory measurement of cortisol: Where do we stand, and which way to follow?. Sensing and Bio-Sensing Research, 22, 100249.
40. Chen, C., Wang, J., & Liu, G. (2017). Recent advances in electrochemical sensors for detecting cortisol. Biosensors and Bioelectronics, 96, 217-227. https://doi.org/10.1016/j.bios.2017.05.018
41. Kaushik, A., Vasudev, A., Arya, S. K., Pasha, S. K., & Bhansali, S. (2014). Recent advances in cortisol sensing technologies for point-of-care application. Biosensors and Bioelectronics, 53, 499-512
42. Gatti, R., Antonelli, G., Prearo, M., Spinella, P., Cappellin, E., & Elio, F. (2009). Cortisol assays and diagnostic laboratory procedures in human biological fluids. Clinical biochemistry, 42(12), 1205-1217.
43. Tu, E., Pearlmutter, P., Tiangco, M., Derose, G., Begdache, L., & Koh, A. (2020). Comparison of colorimetric analyses to determine cortisol in human sweat. ACS omega, 5(14), 8211-8218.
44. Cingöz, E. (2022). *Mikroakışkan tabaka aracılığıyla kortizol hormonu düzeyinin belirlenmesine yönelik giyilebilir cihaz üzerine çalışmalar / Studies on a wearable device for determining cortisol hormone level through microfluidic layer* (Yüksek lisans tezi). İstanbul Üniversitesi, Fen Bilimleri Enstitüsü, Moleküler Biyoloji ve Genetik Ana Bilim Dalı, Moleküler Biyoloji-Genetik ve Biyoteknoloji Bilim Dalı.
45. Nath, R. K., Thapliyal, H., & Caban-Holt, A. (2022). Machine learning based stress monitoring in older adults using wearable sensors and cortisol as stress biomarker. Journal of Signal Processing Systems, 1-13.
46. Nath, R. K., & Thapliyal, H. (2021). Smart wristband-based stress detection framework for older adults with cortisol as stress biomarker. IEEE Transactions on Consumer Electronics, 67(1), 30-39.
47. W. Liao, W. Zhang, Z. Zhu, and Q. Ji, “A real-time human stress monitoring system using dynamic Bayesian network,” in Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. (CVPR) Workshops, San Diego, CA, USA, 2005, p. 70.
48. J. J. Shaughnessy, E. B. Zechmeister, and J. S. Zechmeister, Research Methods in Psychology. Boston, MA, USA: McGraw-Hill, 2000.
49. N. Charness, R. Best, and J. Evans, “Supportive home health care technology for older adults: Attitudes and implementation,” Gerontechnol. Int. J. Fundam. Aspects Technol. Serve Ageing Soc., vol. 15, no. 4, pp. 233–242, 2016.
50. Pandit, P., Crewther, B., Cook, C., Punyadeera, C., & Pandey, A. K. (2024). Sensing methods for stress biomarker detection in human saliva: a new frontier for wearable electronics and biosensing. Materials Advances, 5(13), 5339-5350.
51. Ahmed, T., Powner, M. B., Qassem, M., & Kyriacou, P. A. (2024). Colorimetric Determination of Salivary Cortisol Levels in Artificial Saliva for the Development of a Portable Colorimetric Sensor (Salitrack). Sci, 6(2), 20.