volume | PIER Journals

Abstract

This study introduces a machine learning (ML)-based method for point-of-care (POC) colorimetric testing of total antioxidant concentration (TAC) in saliva, an important biomarker for health monitoring. The approach leverages ML to accurately classify color intensity in the POC test. Saliva samples were collected and imaged at specific intervals during the colorimetric reaction, generating a dataset representative of various antioxidant levels. Four classifiers (Convolutional Neural Network, Support Vector Machine, K-Nearest Neighbors, and Single-layer Feed-Forward Neural Network) were evaluated on distinct datasets, with Convolutional Neural Network (CNN) consistently achieving superior performance. To enhance classification accuracy, stacking-based ensemble learning was applied, combining CNN predictions with a Support Vector Machine (SVM) meta-classifier, achieving up to 92% accuracy. Additionally, YOLOv4-tiny was utilized for object detection to isolate regions of interest in the images, creating a refined dataset that a CNN model is then classified with ca. 98% accuracy. This YOLOv4-CNN approach not only improved accuracy but also simplified the model architecture. The integrated object detection and CNN models were deployed on an Android application, enabling real-time TAC analysis on a smartphone with 98% accuracy and a fast readout time of 2 minutes. This method offers a robust, efficient, and accessible solution for POC antioxidant testing.

1. Ragusa, Edoardo, Valentina Mastronardi, Deborah Pedone, Mauro Moglianetti, Pier Paolo Pompa, Rodolfo Zunino, and Paolo Gastaldo, "Random weights neural network for low-cost readout of colorimetric reactions: Accurate detection of antioxidant levels," International Conference on System-Integrated Intelligence, 95-104, 2022.

2. Yager, Paul, Thayne Edwards, Elain Fu, Kristen Helton, Kjell Nelson, Milton R. Tam, and Bernhard H. Weigl, "Microfluidic diagnostic technologies for global public health," Nature, Vol. 442, No. 7101, 412-418, 2006. Google Scholar

3. Tania, Marzia Hoque, Khin T. Lwin, Antesar M. Shabut, Mohammad Najlah, Jeannette Chin, and Mohammed Alamgir Hossain, "Intelligent image-based colourimetric tests using machine learning framework for lateral flow assays," Expert Systems with Applications, Vol. 139, 112843, 2020. Google Scholar

4. Zhu, Hongying, Ikbal Sencan, Justin Wong, Stoyan Dimitrov, Derek Tseng, Keita Nagashima, and Aydogan Ozcan, "Cost-effective and rapid blood analysis on a cell-phone," Lab on a Chip, Vol. 13, No. 7, 1282-1288, 2013. Google Scholar

5. Coskun, Ahmet F., Justin Wong, Delaram Khodadadi, Richie Nagi, Andrew Tey, and Aydogan Ozcan, "A personalized food allergen testing platform on a cellphone," Lab on a Chip, Vol. 13, No. 4, 636-640, 2013. Google Scholar

6. Coskun, Ahmet F., Richie Nagi, Kayvon Sadeghi, Stephen Phillips, and Aydogan Ozcan, "Albumin testing in urine using a smart-phone," Lab on a Chip, Vol. 13, No. 21, 4231-4238, 2013. Google Scholar

7. Mutlu, Ali Y., Volkan Kılıç, Gizem Kocakuşak Özdemir, Abdullah Bayram, Nesrin Horzum, and Mehmet E. Solmaz, "Smartphone-based colorimetric detection via machine learning," Analyst, Vol. 142, No. 13, 2434-2441, 2017. Google Scholar

8. Kohen, Ron and Abraham Nyska, "Invited review: Oxidation of biological systems: Oxidative stress phenomena, antioxidants, redox reactions, and methods for their quantification," Toxicologic Pathology, Vol. 30, No. 6, 620-650, 2002. Google Scholar

9. Mastalerz-Migas, A., A. Steciwko, M .Pokorski, I. Pirogowicz, J. Drobnik, A. Bunio, A. Muszyńska, and A. Jasińska, "What influences the level of oxidative stress as measured by 8-hydroxy-2'-deoxyguanosine in patients on hemodialysis?," Journal of Physiology and Pharmacology: An Official Journal of the Polish Physiological Society, Vol. 57, 199-205, 2006. Google Scholar

10. Buczko, P., A. Zalewska, and I. Szarmach, "Saliva and oxidative stress in oral cavity and in some systemic disorders," Journal of Physiology and Pharmacology, Vol. 66, 1-7, 2015. Google Scholar

11. Popolo, Ada, G. Autore, A. Pinto, and S. Marzocco, "Oxidative stress in patients with cardiovascular disease and chronic renal failure," Free Radical Research, Vol. 47, No. 5, 346-356, 2013. Google Scholar

12. Mangge, Harald, Kathrin Becker, Dietmar Fuchs, and Johanna M. Gostner, "Antioxidants, inflammation and cardiovascular disease," World Journal of Cardiology, Vol. 6, No. 6, 462-477, 2014. Google Scholar

13. Fusco, Domenico, Giuseppe Colloca, Maria Rita Lo Monaco, and Matteo Cesari, "Effects of antioxidant supplementation on the aging process," Clinical Interventions in Aging, Vol. 2, No. 3, 377-387, 2007. Google Scholar

14. Bjørklund, Geir, Mariia Shanaida, Roman Lysiuk, Halyna Antonyak, Ivan Klishch, Volodymyr Shanaida, and Massimiliano Peana, "Selenium: An antioxidant with a critical role in anti-aging," Molecules, Vol. 27, No. 19, 6613, 2022. Google Scholar

15. Reuter, Simone, Subash C. Gupta, Madan M. Chaturvedi, and Bharat B. Aggarwal, "Oxidative stress, inflammation, and cancer: How are they linked?," Free Radical Biology and Medicine, Vol. 49, No. 11, 1603-1616, 2010. Google Scholar

16. Bahar, Gideon, Raphael Feinmesser, Thomas Shpitzer, Aaron Popovtzer, and Rafael M. Nagler, "Salivary analysis in oral cancer patients: DNA and protein oxidation, reactive nitrogen species, and antioxidant profile," Cancer, Vol. 109, No. 1, 54-59, 2007. Google Scholar

17. Tulunoglu, Ö., S. Demirtas, and I. Tulunoglu, "Total antioxidant levels of saliva in children related to caries, age, and gender," International Journal of Paediatric Dentistry, Vol. 16, No. 3, 186-191, 2006. Google Scholar

18. Pedone, Deborah, Mauro Moglianetti, Mariagrazia Lettieri, Giovanna Marrazza, and Pier Paolo Pompa, "Platinum nanozyme-enabled colorimetric determination of total antioxidant level in saliva," Analytical Chemistry, Vol. 92, No. 13, 8660-8664, 2020. Google Scholar

19. Sateanchok, Suphasinee, Sunanta Wangkarn, Chalermpong Saenjum, and Kate Grudpan, "A cost-effective assay for antioxidant using simple cotton thread combining paper based device with mobile phone detection," Talanta, Vol. 177, 171-175, 2018. Google Scholar

20. Frankel, Edwin N., "Antioxidants in lipid foods and their impact on food quality," Food Chemistry, Vol. 57, No. 1, 51-55, 1996. Google Scholar

21. Scarsi, Anna, Deborah Pedone, and Pier Paolo Pompa, "A multi-line platinum nanozyme-based lateral flow device for the colorimetric evaluation of total antioxidant capacity in different matrices," Nanoscale Advances, Vol. 5, No. 8, 2167-2174, 2023. Google Scholar

22. Puangbanlang, Chanoknan, Kitima Sirivibulkovit, Duangjai Nacapricha, and Yupaporn Sameenoi, "A paper-based device for simultaneous determination of antioxidant activity and total phenolic content in food samples," Talanta, Vol. 198, 542-549, 2019. Google Scholar

23. Choices, N., "Colour vision deficiency (colour blindness)," [Online; Accessed: Sep. 1, 2024] nhs.uk, 2016.

24. Awareness, C. B., "Colour blindness," [Online; Accessed: Nov. 1, 2024], 2018.

25. Liu, Weiran, Shixian Liu, Kexin Fan, Zijian Li, Zijun Guo, Davy Cheng, and Guozhen Liu, "Machine-learning-based colorimetric sensor on smartphone for salivary uric acid detection," IEEE Sensors Journal, Vol. 24, No. 20, 32991-33000, 2024. Google Scholar

26. Taccioli, Tommaso, Edoardo Ragusa, Tania Pomili, Paolo Gastaldo, and Pier Paolo Pompa, "Semi-quantitative determination of thiocyanate in saliva through colorimetric assays: Design of CNN architecture via input-aware NAS," IEEE Sensors Journal, Vol. 23, No. 23, 29869-29876, 2023. Google Scholar

27. Mercan, Öykü Berfin, Volkan Kılıç, and Mustafa Şen, "Machine learning-based colorimetric determination of glucose in artificial saliva with different reagents using a smartphone coupled μPAD," Sensors and Actuators B: Chemical, Vol. 329, 129037, 2021. Google Scholar

28. Fan, Kexin, Weiran Liu, Yuchen Miao, Zhen Li, and Guozhen Liu, "Engineering strategies for advancing optical signal outputs in smartphone-enabled point-of-care diagnostics," Advanced Intelligent Systems, Vol. 5, No. 6, 2200285, 2023. Google Scholar

29. Jia, Ming-Yan, Qiong-Shui Wu, Hui Li, Yu Zhang, Ya-Feng Guan, and Liang Feng, "The calibration of cellphone camera-based colorimetric sensor array and its application in the determination of glucose in urine," Biosensors and Bioelectronics, Vol. 74, 1029-1037, 2015. Google Scholar

30. Lopez-Ruiz, Nuria, Vincenzo F. Curto, Miguel M. Erenas, Fernando Benito-Lopez, Dermot Diamond, Alberto J. Palma, and Luis F. Capitan-Vallvey, "Smartphone-based simultaneous pH and nitrite colorimetric determination for paper microfluidic devices," Analytical Chemistry, Vol. 86, No. 19, 9554-9562, 2014. Google Scholar

31. Jung, Youngkee, Jinhee Kim, Olumide Awofeso, Huisung Kim, Fred Regnier, and Euiwon Bae, "Smartphone-based colorimetric analysis for detection of saliva alcohol concentration," Applied Optics, Vol. 54, No. 31, 9183-9189, 2015. Google Scholar

32. Shen, Li, Joshua A. Hagen, and Ian Papautsky, "Point-of-care colorimetric detection with a smartphone," Lab on a Chip, Vol. 12, No. 21, 4240-4243, 2012. Google Scholar

33. Fisher, Rachel, Karen Anderson, and Jennifer Blain Christen, "Using machine learning to objectively determine colorimetric assay results from cell phone photos taken under ambient lighting," 2021 IEEE International Midwest Symposium on Circuits and Systems (MWSCAS), 467-470, Lansing, MI, USA, 2021.

34. Geng, Zhaoxin, Yanrui Miao, Guling Zhang, and Xiao Liang, "Colorimetric biosensor based on smartphone: State-of-art," Sensors and Actuators A: Physical, Vol. 349, 114056, 2023. Google Scholar

35. Bhatt, Sunita, Sunil Kumar, Mitesh Kumar Gupta, Sudip Kumar Datta, and Satish Kumar Dubey, "Colorimetry-based and smartphone-assisted machine-learning model for quantification of urinary albumin," Measurement Science and Technology, Vol. 35, No. 1, 015030, 2023. Google Scholar

36. Sajed, Samira, Mohammadreza Kolahdouz, Mohammad Amin Sadeghi, and Seyedeh Fatemeh Razavi, "High-performance estimation of lead ion concentration using smartphone-based colorimetric analysis and a machine learning approach," ACS Omega, Vol. 5, No. 42, 27675-27684, 2020. Google Scholar

37. Ashraf, Shahzad and Tauqeer Ahmed, "Sagacious intrusion detection strategy in sensor network," 2020 International Conference on UK-China Emerging Technologies (UCET), 1-4, Glasgow, UK, 2020.

38. STMicroelectronics "STM32-bit Arm Cortex MCUs," [Online; Accessed: Nov. 20, 2024] https://www.st.com/en/microcontrollers-microprocessors/stm32-32-bit-arm-cortex-mcus.html, 2022.

39. Cui, Feiyun, Yun Yue, Yi Zhang, Ziming Zhang, and H. Susan Zhou, "Advancing biosensors with machine learning," ACS sensors, Vol. 5 , No. 11, 3346-3364, 2020.
doi:10.1021/acssensors.0c01424 Google Scholar

40. Kadian, Sachin, Pratima Kumari, Shubhangi Shukla, and Roger Narayan, "Recent advancements in machine learning enabled portable and wearable biosensors," Talanta Open, Vol. 8, 100267, 2023. Google Scholar

41. Amin, Youssef, Christian Gianoglio, and Maurizio Valle, "Embedded real-time objects’ hardness classification for robotic grippers," Future Generation Computer Systems, Vol. 148, 211-224, 2023. Google Scholar

42. Athira, M. V. and Diliya M. Khan, "Recent trends on object detection and image classification: A review," 2020 International Conference on Computational Performance Evaluation (ComPE), 427-435, Shillong, India, 2020.

43. Tania, Marzia Hoque, Khin T. Lwin, Antesar M. Shabut, Kamal J. Abu-Hassan, M. Shamim Kaiser, and M. Alamgir Hossain, "Assay type detection using advanced machine learning algorithms," 2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA), 1-8, Island of Ulkulhas, Maldives, 2019.

44. Chen, Xue-Wen and Xiaotong Lin, "Big data deep learning: Challenges and perspectives," IEEE Access, Vol. 2, 514-525, 2014. Google Scholar

45. Ballard, Zachary S., Hyou-Arm Joung, Artem Goncharov, Jesse Liang, Karina Nugroho, Dino Di Carlo, Omai B. Garner, and Aydogan Ozcan, "Deep learning-enabled point-of-care sensing using multiplexed paper-based sensors," NPJ Digital Medicine, Vol. 3, No. 1, 66, 2020. Google Scholar

46. Luo, Yi, Hyou-Arm Joung, Sarah Esparza, Jingyou Rao, Omai Garner, and Aydogan Ozcan, "Quantitative particle agglutination assay for point-of-care testing using mobile holographic imaging and deep learning," Lab on a Chip, Vol. 21, No. 18, 3550-3558, 2021. Google Scholar

47. Joung, Hyou-Arm, Zachary S. Ballard, Jing Wu, Derek K. Tseng, Hailemariam Teshome, Linghao Zhang, Elizabeth J. Horn, Paul M. Arnaboldi, Raymond J. Dattwyler, Omai B. Garner, Dino Di Carlo, and Aydogan Ozcan, "Point-of-care serodiagnostic test for early-stage Lyme disease using a multiplexed paper-based immunoassay and machine learning," ACS Nano, Vol. 14, No. 1, 229-240, 2019. Google Scholar

48. Amin, Youssef, Christian Gianoglio, and Maurizio Valle, "Towards a trade-off between accuracy and computational cost for embedded systems: A tactile sensing system for object classification," International Conference on System-Integrated Intelligence, 148-159, 2022.

49. Kim, Huisung, Olumide Awofeso, SoMi Choi, Youngkee Jung, and Euiwon Bae, "Colorimetric analysis of saliva-alcohol test strips by smartphone-based instruments using machine-learning algorithms," Applied Optics, Vol. 56, No. 1, 84-92, 2016. Google Scholar

50. Khanal, Bidur, Pravin Pokhrel, Bishesh Khanal, and Basant Giri, "Machine-learning-assisted analysis of colorimetric assays on paper analytical devices," ACS Omega, Vol. 6, No. 49, 33837-33845, 2021. Google Scholar

51. Feng, Fan, Zeping Ou, Fangdou Zhang, Jinxing Chen, Jiankun Huang, Jingxiang Wang, Haiqiang Zuo, and Jingbin Zeng, "Artificial intelligence-assisted colorimetry for urine glucose detection towards enhanced sensitivity, accuracy, resolution, and anti-illuminating capability," Nano Research, Vol. 16, No. 10, 12084-12091, 2023. Google Scholar

52. Duan, Sixuan, Tianyu Cai, Jia Zhu, Xi Yang, Eng Gee Lim, Kaizhu Huang, Kai Hoettges, Quan Zhang, Hao Fu, Qiang Guo, et al., "Deep learning-assisted ultra-accurate smartphone testing of paper-based colorimetric ELISA assays," Analytica Chimica Acta, Vol. 1248, 340868, 2023. Google Scholar

53. Ragusa, Edoardo, Rodolfo Zunino, Valentina Mastronardi, Mauro Moglianetti, Pier P. Pompa, and Paolo Gastaldo, "Design of a quantitative readout in a point-of-care device for cisplatin detection," IEEE Sensors Letters, Vol. 6, No. 11, 1-4, 2022. Google Scholar

54. Liu, Xing, Qi Wang, Yu Zhang, Lichun Zhang, Yingying Su, and Yi Lv, "Colorimetric detection of glutathione in human blood serum based on the reduction of oxidized TMB," New Journal of Chemistry, Vol. 37, No. 7, 2174-2178, 2013. Google Scholar

55. Josephy, P. David, Tohomas Eling, and Ronald P. Mason, "The horseradish peroxidase-catalyzed oxidation of 3, 5, 3', 5'-tetramethylbenzidine. Free radical and charge-transfer complex intermediates," Journal of Biological Chemistry, Vol. 257, No. 7, 3669-3675, 1982. Google Scholar

56. Lin, Shan, Danmin Zheng, Ailing Li, and Yuwu Chi, "Black oxidized 3, 3′, 5, 5′-tetramethylbenzidine nanowires (oxTMB NWs) for enhancing Pt nanoparticle-based strip immunosensing," Analytical and Bioanalytical Chemistry, Vol. 411, 4063-4071, 2019. Google Scholar

57. Sakr, Fouad, Francesco Bellotti, Riccardo Berta, and Alessandro De Gloria, "Machine learning on mainstream microcontrollers," Sensors, Vol. 20, No. 9, 2638, 2020.
doi:10.3390/s20092638 Google Scholar

58. Elngar, Ahmed A., Mohamed Arafa, Amar Fathy, Basma Moustafa, Omar Mahmoud, Mohamed Shaban, and Nehal Fawzy, "Image classification based on CNN: A survey," Journal of Cybersecurity and Information Management, Vol. 6, No. 1, 18-50, 2021.
doi:10.54216/JCIM.060102 Google Scholar

59. Tzutalin "Labelimg: A graphical image annotation tool and label object bounding boxes in images," https://github.com/ HumanSignal/labelImg, 2015.

Dr. Youssef Amin

Dr. Paola Cecere

Dr. Tania Pomili

Prof. Pier Paolo Pompa