BreathRight-AI: An Intelligent Breath Analyzer for Diabetic Risk Predicition, Monitoring, and Personalized Recommendations
Abstract
Diabetes mellitus remains a major global concern, with many cases undiagnosed due to costly and inaccessible diagnostic methods, especially in rural areas. This study developed and evaluated BreathRight-AI, a portable, non-invasive breath analyzer for detecting acetone in exhaled breath as a marker of diabetic risk. The device integrates an MQ-138 sensor with an ESP32 microcontroller to measure acetone, classify risk, and log data. Using a quantitative correlational design, thirty (30) diabetic and non-diabetic participants were purposively selected. Breath acetone levels (ppm) were compared with fasting blood sugar (mg/dL) using a glucometer. Results revealed a very strong correlation (r = 0.981, p < 0.00001), with each 1 ppm acetone increase corresponding to a 56 mg/dL rise in blood glucose. The prototype showed 95.6% classification accuracy, with better performance in low- and high-risk cases than borderline ones. Stability tests showed consistent results (SD = 0.073 ppm). Findings suggest that BreathRight-AI is a promising, user-friendly screening tool for early diabetes detection, though further calibration and large-scale clinical validation are needed.
Keywords: Diabetes, Breath Acetone, Non-invasive screening, MQ-138 sensor, Diabetic risk monitoring
References
Al-Jammas, H., et al. (2025). Internet of things enabled open source assisted real-time glucose monitoring system. Scientific Reports. https://www.nature.com/articles/s41598-024-56677-z
Al-Kateb, H., B. de Lacy Costello, and N. Ratcliffe. “Optimization of Fasting Duration for Breath-Based Diabetes Screening: A Metabolic Study.” Metabolomics, vol. 19, no. 3, 2023, p. 45. https://doi.org/10.1007/s11306-023-02008-8
Alkedeh, O., & Priefer, R. (2021). The ketogenic diet: Breath acetone sensing technology. Biosensors, 11(1), Article 26. https://doi.org/10.3390/bios11010026
Ansari, H. R., Mirzaei, Z., Kordrostami, Z., & Kraft, M. (2024). Deep-learning-based blood glucose detection device using acetone exhaled breath sensing features of α-Fe₂O₃-MWCNT nanocomposites. ACS Applied Materials & Interfaces, 16(36), 47973–47987. https://doi.org/10.1021/acsami.4c06855
ASEAN Endocrine Journal. (2019). Real-world diabetes monitoring and registries in Southeast Asia. ASEAN Federation of Endocrine Societies.
Baskoy, S., Akpinar, S., & Ozgurluk, Y. (2023). MXene-coated nylon mesh filters for high-efficiency aerosol removal. Separation and Purification Technology, 315, 123585. https://doi.org/10.1016/j.seppur.2023.123585
Bastide, G. M. G. B. H., A. L. Remund, D. N. Oosthuizen, N. Derron, P. A. Gerber, and I. C. Weber. “Handheld Device Quantifies Breath Acetone for Real-Life Metabolic Health Monitoring.” Sensors & Diagnostics, vol. 2, no. 6, 2023, pp. 918–28. https://doi.org/10.1039/D3SD00079F
Bhandari, P. (2023, June 21). Data collection | Definition, methods & examples. Scribbr. https://www.scribbr.com/methodology/data-collection/
Bosu, M. F., & MacDonell, S. G. (2021). Data quality in empirical software engineering: A targeted review. arXiv. https://arxiv.org/abs/2105.10895
Chen, L., & Wang, H. (2023). Optimizing breath sampling techniques for reproducible VOC analysis. Respiratory Physiology & Neurobiology, 307, 103976. https://doi.org/10.1016/j.resp.2022.103976
Chen, L., Zhang, W., & Hu, X. (2022). Performance of low-power UVCLED sterilization systems in portable biosensor applications. Sensors and Actuators B: Chemical, 359(12), 131627. https://doi.org/10.1016/j.snb.2022.131627
Cleveland Clinic. (2022, March 9). Type 1 Diabetes. Cleveland Clinic; Cleveland Clinic. https://my.clevelandclinic.org/health/diseases/21500-type-1-diabetes
Creswell, J. W., & Creswell, J. D. (2017). Research design: Qualitative, quantitative, and mixed methods approaches. Sage publications.
Cutiongco-de la Paz, E., Morales, M., Co, J., Natividad, F., Salonga, F., & De Roxas, R. (2024). Genetic variants associated with type 2 diabetes risk among Filipinos: A pilot study. Philippine Journal of Internal Medicine, 62(1), 15–23. https://pjim.org/article/view/2024-genetics-diabetes
Das, S., Pal, S., & Mitra, M. (2023). Metal oxide gas sensors to study acetone detection considering their potential in the diagnosis of diabetes: A review. Molecules, 28(1), 201. https://doi.org/10.3390/
Dela Cruz, M. T., Reyes, A. B., & Lim, S. C.(2023). Optimizing breath collection protocols for tropical environments. Environmental Research, 229, 115943. https://doi.org/10.1016/ j.envres.2023.115943
Department of Health. (2024). Diabetes program: National diabetes situation in the Philippines. Department of Health Philippines. https://doh.gov.ph/diabetes-program
Dixit, K., Fardindoost, S., Ravishankara, A., Tasnim, N., & Hoorfar, M. (2021). Exhaled breath analysis for diabetes diagnosis and monitoring: Relevance, challenges and possibilities. Biosensors, 11(12), Article 476. https://doi.org/10.3390/bios11120476
Donaldson, D. R., & Koepke, J. W. (2022). A focus groups study on data sharing and research data management. Scientific Data, 9(1), Article 345. https://doi.org/10.1038/s41597-022-01428-w
Drmosh, Q. A., and I. O. Alade. “Zinc Oxide-Based Acetone Gas Sensors for Breath Analysis: A Review.” Chemistry – An Asian Journal, vol. 16, no. 12, 2021, pp. 1519–38. https://doi.org/10.1002/asia.202100303
Duhaylungsod, L. A., Cagampang, A. A., & Fernandez, R. (2022). The effectiveness of collaborative telemedicine among diabetic patients in Koronadal City, South Cotabato. ResearchGate. https://www.researchgate.net/publication/359848250_The_Effectiveness_of_Collaborative_Telemedicine_among_Diabetic_Patients_in_Koronadal_City_South_Cotabato
Garcia, M. P., A. L. Tan, and J. C. Reyes. “Optimized Fasting Protocols for Breath-Based Diabetes Screening in Tropical Populations: A Multicenter Asian Study.” Diabetes Research and Clinical Practice, vol. 195, 2023, p. 110207. https://doi.org/10.1016/j.diabres.2022.110207
Hancock, G., et al. “The Correlation between Breath Acetone and Blood β-Hydroxybutyrate in Individuals with Type 1 Diabetes.” Journal of Breath Research, vol. 14, no. 4, 2020, p. 046006. https://doi.org/10.1088/1752-7163/abbf37
Glooko. (2023). Digital health platform for diabetes and related conditions. Glooko Inc. https://glooko.com
Huang, M., & Li, Y. (2024). Integration of UVC-assisted disinfection in semiconductor breath analyzers: Effects on sensor stability and biosafety. Journal of Biomedical Engineering and Technology, 11(2), 45–53. https://doi.org/10.3390/jbet1102045
IDF Diabetes Atlas. 10th ed., International Diabetes Federation, 2021. https://diabetesatlas.org10.1038/s41598-021-04072-3
Jadhav, S., Patil, R., & Kulkarni, S. (2023). Breath acetone as a non-invasive biomarker for diabetes monitoring. Biosensors, 13(1), 62. https://doi.org/10.3390/bios13010062
Jain, A., Verma, P., & Singh, R. (2024). Web-based health monitoring systems integrated with artificial intelligence: Design and scalability considerations. Journal of Medical Systems, 48(2), 1–12. https://doi.org/10.1007/s10916-024-01987-6
Jones, M. E., Carter, L. J., & Nguyen, T. (2025). Advances in breath-based diagnostics for metabolic disease detection. Journal of Breath Research, 19(1), 016001. https://doi.org/10.1088/1752-7163/ad1234
Kapur, P., et al. (2023). DiabeticSense: A non-invasive, multi-sensor, IoT-based diagnosing device for diabetes using breath analysis. Sensors. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10607308/
Kavya, C., Janis, R., Ezilarasi, P., & Kannan, S. R. (2025). Development of a non-invasive glucose monitoring system using acetone gas detection via exhaled breath analysis and MQ sensor integration. In Proceedings of the 2025 International Conference on Advanced Research in Electronics and Communication Systems (ICARECS-2025) (pp. 175–188). Atlantis Press. https://doi.org/10.2991/978-94-6463-754-0_16
Khan, Mohammad S., Suzanne Cuda, Genesio M. Karere, Laura A. Cox, and Andrew C. Bishop. “Breath Biomarkers of Insulin
Konda, A., Prakash, A., Moss, G. A., Schmoldt, M., Grant, G. D., & Guha, S. (2020). Aerosol filtration efficiency of common fabrics used in respiratory cloth masks. ACS Nano, 14(5), 6339–6347. https://doi.org/10.1021/acsnano.0c03252
Kumar, A., Singh, R., & Das, P. (2024). Contamination resistance and airflow optimization of hydrophobic nylon microfilters for medical sensing applications. IEEE Sensors Journal, 24(6), 5890–5898. https://doi.org/10.1109/JSEN.2024.3560123
Ku, Y., Lee, Y., & Hwang, J. (2019). Effect of filter media structure on the filtration performance of electrospun nanofibers. Journal of Aerosol Science, 137, 105438. https://doi.org/10.1016/j.jaerosci.2019.105438
Li, Wenqing, et al. “Exhaled Breath Acetone in Diabetic Patients and Healthy Individuals.” Frontiers in Endocrinology, vol. 6, 2015, p. 194. https://doi.org/10.3389/fendo.2015.00194
Machorro-Cano, Ignacio, et al. “Review of Cloud-Based Platforms for Health Monitoring.” Healthcare Technology Letters, vol. 10, no. 2, 2023, pp. 45–58. IET Digital Library, https://doi.org/10.1049/htl2.12075
Liu, T., & Lin, Z. (2021). Evaluation of droplet-blocking efficiency of nylon and polyester microfilter membranes in respiratory sensor systems. Applied Surface Science, 548(149264. https://doi.org/10.1016/j.apsusc.2021.149264
Marfatia, Y., et al. (2025). Innovations and applications of ketone body monitoring in diabetes. Trends in Analytical Chemistry. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11291811/
Memarzadeh, F. (2021). Ultraviolet germicidal irradiation: A powerful technology for infection control. Building and Environment, 197, 107852. https://doi.org/10.1016/j.buildenv.2021.107852
Moufti, M. A., Hamad, M., Shawa, A. A., Mardini, A., & Ghebeh, S. (2023). Efficacy and design requirements of UV light cabinets for disinfection of exchangeable non-sterilizable “dental objects.” Scientific Reports, 13(1), 19755. https://doi.org/10.1038/s41598-023-45481-w
Othmane, Amani, et al. AI-Based Prediction for Glucose Levels: A Comparative Study of Machine Learning and Deep Learning Approaches. Proceedings of the International Conference on Emerging Intelligent Systems for Sustainable Development (ICEIS 2024), Atlantis Press, 2024, pp. 231–245.
Paleczek, A., and A. Rydosz. “Review of the Algorithms Used in Exhaled Breath Analysis for the Detection of Diabetes.” Journal of Breath Research, vol. 16, no. 2, 2022, p. 026001. https://doi.org/10.1088/1752-7163/ac4916
Peverall, R., Hancock, G., & Ritchie, G. A. D. (2016). Breath analysis for clinical diagnosis and therapeutic monitoring. Analytical Chemistry, 88(9), 4264–4281. https://doi.org/10.1021/acs.analchem.5b04041
Philippine Statistics Authority. “Causes of Death in the Philippines (Preliminary): 2020.” 2021. https://psa.gov.ph
Rahman, M. M., Kabir, M. S., & Hasan, M. M. (2023). Breath-based biosensors for non-invasive diabetes monitoring: Current trends and future directions. Biosensors, 13(1), 62. https://doi.org/10.3390/bios13010062
Rydosz, A., Ł. Dołowy, and Ł. Komorowski. “Exhaled Acetone Dynamics during Controlled Glucose Ingestion in Type 1 Diabetics and Healthy Subjects.” Diabetes Technology & Therapeutics, vol. 24, no. 6, 2022, pp. 420–28. https://doi.org/10.1089/dia.2022.0078
Saasa, V., Beukes, M., Lemmer, Y., & Mwakikunga, B. (2019). Blood ketone bodies and breath acetone analysis and their correlations in Type 2 diabetes mellitus. Diagnostics, 9(4), 224. https://doi.org/10.3390/diagnostics9040224
Sakane, N., et al. (2025). Breath acetone correlates with capillary βhydroxybutyrate in patients with diabetic ketoacidosis. Journal of Diabetes Investigation. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12014577/
Shlomo, I. B., T. Fine, and A. Leshem. “Postprandial Breath Acetone as a Predictor of Hyperglycemia in Diabetes.” Scientific Reports, vol. 11, no. 1, 2021, p. 11223. https://doi.org/10.1038/s41598-021-90753-y
Suntrup, D. J., III, and T. V. Ratto. “Characterization of a HighResolution Breath Acetone Meter for Ketosis Monitoring.” PeerJ, vol. 8, 2020, p. e9969. https://doi.org/10.7717/peerj.9969
Sun Life Philippines. (2024). Diabetes in the Philippines: A nationwide survey on awareness, lifestyle, and impact. Sun Life Financial. https://sunlife.com.ph/diabetes-awareness-2024
Sun, M., Zhao, X., Yin, H., Wang, Z., Jiang, C., Liu, W., Chen, Z., Yuan, Y., Li, Y., & Wang, C. (2015). Study of breath acetone and its correlations with blood glucose and blood beta-hydroxybutyrate using an animal model with lab-developed type 1 diabetic rats. RSC Advances, 5(87), 71002–71010. https://doi.org/10.1039/c5ra07084h
Tumilba, L. A. C., Tan, K. E. M., & Macaraan, J. M. (2023). Epidemiology and gaps in diabetes care in the Philippines: A national perspective. BMJ Open Diabetes Research & Care, 11(1), e003388. https://pubmed.ncbi.nlm.nih.gov/38382166
Turner, Clare, et al. “The Use of Breath Acetone as a Biomarker for NonInvasive Diabetes Screening.” Biosensors and Bioelectronics, vols. 124–125, 2019, pp. 124–32. https://doi.org/10.1016/j.bios.2018.10.050
Uy, J., & Jimeno, C. (2021). Early-onset type 2 diabetes in the Philippines: Findings from the 8th National Nutrition and Health Survey. Journal of the ASEAN Federation of Endocrine Societies, 36(2), 122–130. https://asean-endocrinejournal.org/nnhealth-survey2021
Villareal, J., Jimeno, C., Baculi, J., Mercado-Asis, L., & Paterno, E. (2019). Prevalence of diabetes and associated risk factors among community health workers in the Philippines. Philippine Journal of Health Research and Development, 23(3), 45–52. https://pjhrd.upm.edu.ph/article/view/2019-diabetes-healthworkers
von Kalckreuth, N. (2025). Enhancing uploads of health data in the electronic health record—The role of framing and length of privacy information: A survey study in Germany. Digital Health, 11. https://doi.org/10.1177/20552076251351197
Wang, C., Mbi, A., & Shepherd, M. (2020). Correlation of breath acetone with blood glucose and ketone bodies in diabetes. Journal of Breath Research, 14(4), 046003. https://doi.org/10.1088/1752-7163/ab9f63
Wang, Z., & Wang, C. (2019). Is breath acetone a biomarker of diabetes? A historical review on breath acetone measurements. Journal of Breath Research, 7(3), 037109. https://doi.org/10.1088/1752-7155/7/3/037109
Wei, J., et al. “Detection of Acetone as a Gas Biomarker for Diabetes Based on Gas Sensor Technology.” arXiv, preprint, 2024. https://arxiv.org/abs/2406.00993
Wei, J., Liu, T., Huang, J., Li, X., Qi, Y., & Luo, G. (2023). Mixed potential type acetone sensor with ultralow detection limit for diabetic ketosis breath analysis. ACS Sensors, 9(1), 464–473. https://doi.org/10.1021/acssensors.3c02253
World Health Organization. (2020). 2008-2013 action plan for the global strategy for the prevention and control of noncommunicable diseases : prevent and control cardiovascular diseases, cancers, chronic respiratory diseases and diabetes. Who.int. https://doi.org/9789241597418
World Health Organization. Guide to Early Cancer Diagnosis. 2021. https://www.who.int/publications/i/item/97892415119402008-
Wu, Y., Zhou, Z., & Jiang, Y. (2019). Blood ketone bodies and breath acetone analysis and their correlations in type 2 diabetes mellitus. Journal of Diabetes Research, 2019, 1–9. https://doi.org/10.1155/2019/2018519
Yan, J., Pan, X., & Li, H. (2020). Non-fasting breath acetone detection for point-of-care diabetes screening. Biosensors and Bioelectronics, 150, 111919. https://doi.org/10.1016/j.bios.2019.111919
Sun, Y., Wu, Q., Liu, J., & Wang, Q. (2023). Effectiveness of ultraviolet-C disinfection systems for reduction of multi-drug resistant organism infections in healthcare settings: A systematic review and meta-analysis. Epidemiology and Infection, 151, e149. https://doi.org/10.1017/s0950268823001371
Yang, S., Zhang, C., Li, H., & Chen, D. (2023). Influence of nylon filter media on aerosol sampling efficiency and gas-phase adsorption. Environmental Research, 226, 115751. https://doi.org/10.1016/j.envres.2023.115751
Yoon, D., Park, J., & Lee, S. (2021). UVC-based sterilization of biosensor housings: Maintaining accuracy and long-term signal stability. Scientific Reports, 11(1), 16422. https://doi.org/10.1038/s41598021-95934-7
Yu, L., et al. (2025). A review of machine learning-assisted gas sensor systems for disease diagnosis. Biosensors and Bioelectronics. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12384702/
Zhang, Qingzhu, et al. “Exhaled Acetone Detection with Breath Analysis for Diabetes Diagnosis.” Sensors and Actuators B: Chemical, vol. 202, 2014, pp. 895–902. https://doi.org/10.1016/j.snb.2014.05.057 “Breath Acetone as a Biomarker of Blood Glucose Variability.” Journal of Breath Research, vol. 19, no. 2, 2025, p. 026012.
Zhao, Q., Chen, R., & Wang, D. (2023). Breath filtration performance of micron-scale nylon membranes in portable breath analysis devices. Journal of Breath Research, 17(3), 036012. https://doi.org/10.1088/1752-7163/acb301
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Nathan Wihlz Bestes, Alexa, Mizzy, Jerry, Zhykiah Winze
This work is licensed under a Creative Commons Attribution 4.0 International License.
