Design and Statistical Evaluation of an AI-Enabled IoT-Based Non-Invasive Biosensing System for Diabetes Risk Screening

Prachi C.  Kamble; Lakshamappa Ragha; Yogesh Pingle

doi:10.35882/jeeemi.v8i2.1541

Prachi C. Kamble Department of Electronics Engineering, Terna Engineering College, University of Mumbai, Maharashtra, India https://orcid.org/0009-0000-9045-162X
Lakshamappa Ragha Department of Electronics Engineering, Terna Engineering College, University of Mumbai, Maharashtra, India https://orcid.org/0009-0000-7574-0140
Yogesh Pingle Department of Computer Science & Engineering (Data Science), Vidyavardhini’s College of Engineering & Technology, University of Mumbai, Maharashtra, India https://orcid.org/0000-0003-2124-885X

DOI: https://doi.org/10.35882/jeeemi.v8i2.1541

Keywords: Diabetes Risk Screening, Non-Invasive Biosensing, Internet of Things, Ensemble Machine Learning, Wearable Healthcare Systems, Breath Acetone Sensing

Abstract

Early identification of diabetes risk remains a significant challenge due to the invasive nature, recurring cost, and limited accessibility of conventional biochemical diagnostic tests. These limitations restrict continuous monitoring and hinder large-scale population screening, particularly in remote and resource-limited settings. The aim of this study is to design and statistically evaluate an AI-enabled IoT-based non-invasive biosensing system for diabetes risk screening, focusing on system-level engineering design, data integration, and performance validation rather than clinical diagnosis. In this study, the term “non-invasive” refers exclusively to externally measurable surface-level physiological and breath-based signals that do not require skin penetration, blood sampling, or subdermal sensor implantation. The main contributions of this work include the development of a wearable IoT-based non-invasive biosensing framework, integration of multi-modal physiological and breath-based biomarkers for risk assessment, implementation of an ensemble machine learning model for diabetes risk classification, and comprehensive statistical validation using agreement, reliability, and calibration metrics. The proposed DiaAssist system acquires physiological parameters such as heart rate, blood pressure, oxygen saturation, body temperature, physical activity indicators, and breath volatile organic compound acetone through a wearable IoT platform with edge-level preprocessing. Fused physiological and demographic features are processed using an ensemble learning framework to generate individualized diabetes risk scores. Performance evaluation was conducted on a single-center observational dataset comprising 625 records using paired statistical tests, agreement analysis, and calibration assessment. The optimized model achieved an accuracy of 99.7%, an area under the receiver operating characteristic curve of 1.000, a Cohen’s Kappa coefficient of 0.993, a Matthews correlation coefficient of 0.993, and a Brier score of 0.045, demonstrating strong classification reliability and probabilistic calibration. The results confirm that combining IoT-based non-invasive biosensing with ensemble machine learning enables accurate and reliable screening for diabetes risk. The proposed system provides a scalable, cost-effective, and engineering-oriented solution suitable for remote monitoring and preventive healthcare applications

Downloads

Download data is not yet available.

References

G. A. Roth et al., “Global Burden of Cardiovascular Diseases and Risk Factors, 1990–2019,” J. Am. Coll. Cardiol., vol. 76, no. 25, pp. 2982–3021, Dec. 2020, doi: 10.1016/j.jacc.2020.11.010.

Md. J. Hossain, Md. Al‐Mamun, and Md. R. Islam, “Diabetes mellitus, the fastest growing global public health concern: Early detection should be focused,” Health Sci. Rep., vol. 7, no. 3, Mar. 2024, doi: 10.1002/hsr2.2004.

S. Zhang et al., “Wearable non-invasive glucose sensors based on metallic nanomaterials,” Mater. Today Bio, vol. 20, p. 100638, Jun. 2023, doi: 10.1016/j.mtbio.2023.100638.

U. M. Butt, S. Letchmunan, M. Ali, F. H. Hassan, A. Baqir, and H. H. R. Sherazi, “Machine Learning Based Diabetes Classification and Prediction for Healthcare Applications,” J. Healthc. Eng., vol. 2021, pp. 1–17, Sep. 2021, doi: 10.1155/2021/9930985.

M. R. Jadhav, P. R. Wankhede, S. Srivastava, H. N. Bhargaw, and S. Singh, “Breath-based biosensors and system development for noninvasive detection of diabetes: A review,” Diabetes & Metabolic Syndrome: Clinical Research & Reviews, vol. 18, no. 1, p. 102931, Jan. 2024, doi: 10.1016/j.dsx.2023.102931.

S. Checker, A. B. Yadav, G. V. Sivnath Reddy, and R. Checker, “Advances in Volatile Organic Compounds-Based Biomarker Detection Using Nanomaterial-Integrated Sensor Platforms for Cancer Diagnosis,” ACS Appl. Electron. Mater., Mar. 2026, doi: 10.1021/acsaelm.5c02148.

R. Kapur et al., “GlucoBreath: An IoT, ML, and Breath-Based Non-Invasive Glucose Meter,” IEEE Access, vol. 12, pp. 59346–59360, 2024, doi: 10.1109/ACCESS.2024.3392015.

Muthupandi G, Vikram R, and P. Vidhya Lakshmi, “IoT Wearables for Continuous Health Monitoring,” in Artificial intelligence and IoT in Predictive Healthcare, Deep Science Publishing, 2025. doi: 10.70593/978-93-7185-397-2_2.

C. A. Patil, A. S. Parab, A. S. Tawade, Y. Pingle, and S. Raul, “IoT based Counter System for Press Fit Machines,” in 2024 11th International Conference on Computing for Sustainable Global Development (INDIACom), IEEE, Feb. 2024, pp. 64–69. doi: 10.23919/INDIACom61295.2024.10498630.

D. Verma et al., “Internet of things (IoT) in nano-integrated wearable biosensor devices for healthcare applications,” Biosens. Bioelectron. X, vol. 11, p. 100153, Sep. 2022, doi: 10.1016/j.biosx.2022.100153.

D. V. K. and T. K. Ramesh, “Optimized stacking ensemble models for the prediction of diabetic progression,” Multimed. Tools Appl., vol. 82, no. 27, pp. 42901–42925, Nov. 2023, doi: 10.1007/s11042-023-14858-4.

K. Oliullah, M. H. Rasel, Md. M. Islam, Md. R. Islam, Md. A. H. Wadud, and Md. Whaiduzzaman, “A stacked ensemble machine learning approach for the prediction of diabetes,” J. Diabetes Metab. Disord., vol. 23, no. 1, pp. 603–617, Nov. 2023, doi: 10.1007/s40200-023-01321-2.

B. Amma N.G., “En-RfRsK: An ensemble machine learning technique for prognostication of diabetes mellitus,” Egyptian Informatics Journal, vol. 25, p. 100441, Mar. 2024, doi: 10.1016/j.eij.2024.100441.

S. Kumari, D. Kumar, and M. Mittal, “An ensemble approach for classification and prediction of diabetes mellitus using soft voting classifier,” International Journal of Cognitive Computing in Engineering, vol. 2, pp. 40–46, Jun. 2021, doi: 10.1016/j.ijcce.2021.01.001.

H. Habehh and S. Gohel, “Machine Learning in Healthcare,” Curr. Genomics, vol. 22, no. 4, pp. 291–300, Dec. 2021, doi: 10.2174/1389202922666210705124359.

M. Scholz and T. Wimmer, “A comparison of classification methods across different data complexity scenarios and datasets,” Expert Syst. Appl., vol. 168, p. 114217, Apr. 2021, doi: 10.1016/j.eswa.2020.114217.

K. Denecke, R. May, and O. Rivera-Romero, “Transformer Models in Healthcare: A Survey and Thematic Analysis of Potentials, Shortcomings and Risks,” J. Med. Syst., vol. 48, no. 1, p. 23, Feb. 2024, doi: 10.1007/s10916-024-02043-5.

N. A. ElSayed et al., “2. Classification and Diagnosis of Diabetes: Standards of Care in Diabetes—2023,” Diabetes Care, vol. 46, no. Supplement_1, pp. S19–S40, Jan. 2023, doi: 10.2337/dc23-S002.

Y. Liu and B. Wang, “Advanced applications in chronic disease monitoring using IoT mobile sensing device data, machine learning algorithms and frame theory: a systematic review,” Front. Public Health, vol. 13, Feb. 2025, doi: 10.3389/fpubh.2025.1510456.

V. Nguyen, P. Ara, D. Simmons, and U. L. Osuagwu, “The Role of Digital Health Technology Interventions in the Prevention of Type 2 Diabetes Mellitus: A Systematic Review,” Clin. Med. Insights Endocrinol. Diabetes, vol. 17, Jan. 2024, doi: 10.1177/11795514241246419.

C. J. Kelly, A. Karthikesalingam, M. Suleyman, G. Corrado, and D. King, “Key challenges for delivering clinical impact with artificial intelligence,” BMC Med., vol. 17, no. 1, p. 195, Dec. 2019, doi: 10.1186/s12916-019-1426-2.

J. S. Varghese, E. N. Peterson, M. K. Ali, and N. Tandon, “Advancing diabetes surveillance ecosystems: a case study of India,” Lancet Diabetes Endocrinol., vol. 12, no. 7, pp. 493–502, Jul. 2024, doi: 10.1016/S2213-8587(24)00124-4.

Y. Muramatsu, S. Watanabe, M. Osada, K. Tajima, A. Karashima, and Y. Y. Maruo, “Small Acetone Sensor with a Porous Colorimetric Chip for Breath Acetone Detection Using the Flow–Stop Method,” Chemosensors, vol. 13, no. 4, p. 136, Apr. 2025, doi: 10.3390/chemosensors13040136.

A. Thati, A. Biswas, S. R. Chowdhury, and T. K. Sau, “Breath Acetone-Based Non-Invasive Detection of Blood Glucose Levels,” International Journal on Smart Sensing and Intelligent Systems, vol. 8, no. 2, pp. 1244–1260, Jan. 2015, doi: 10.21307/ijssis-2017-805.

Z. Zhou et al., “Digital Health Platform for Improving the Effect of the Active Health Management of Chronic Diseases in the Community: Mixed Methods Exploratory Study,” J. Med. Internet Res., vol. 26, p. e50959, Nov. 2024, doi: 10.2196/50959.

K. Fan and Y. Zhao, “Mobile health technology: a novel tool in chronic disease management,” Intelligent Medicine, vol. 2, no. 1, pp. 41–47, Feb. 2022, doi: 10.1016/j.imed.2021.06.003.

Y.-T. Chang, Y.-Z. Tu, H.-Y. Chiou, K. Lai, and N. C. Yu, “Real-world Benefits of Diabetes Management App Use and Self-monitoring of Blood Glucose on Glycemic Control: Retrospective Analyses,” JMIR Mhealth Uhealth, vol. 10, no. 6, p. e31764, Jun. 2022, doi: 10.2196/31764.

Z. Guan et al., “Artificial intelligence in diabetes management: Advancements, opportunities, and challenges,” Cell Rep. Med., vol. 4, no. 10, p. 101213, Oct. 2023, doi: 10.1016/j.xcrm.2023.101213.

R. Hirani et al., “Artificial Intelligence and Healthcare: A Journey through History, Present Innovations, and Future Possibilities,” ., vol. 14, no. 5, p. 557, Apr. 2024, doi: 10.3390/life14050557.

A. Shrivastava et al., “Leveraging XGBoost for Predictive Analytics in Healthcare: Enhancing Disease Diagnosis,” in 2024 7th International Conference on Contemporary Computing and Informatics (IC3I), IEEE, Sep. 2024, pp. 1666–1672. doi: 10.1109/IC3I61595.2024.10829136.

J. J. Khanam and S. Y. Foo, “A comparison of machine learning algorithms for diabetes prediction,” ICT Express, vol. 7, no. 4, pp. 432–439, Dec. 2021, doi: 10.1016/j.icte.2021.02.004.

D. Sisodia and D. S. Sisodia, “Prediction of Diabetes using Classification Algorithms,” Procedia Comput. Sci., vol. 132, pp. 1578–1585, 2018, doi: 10.1016/j.procs.2018.05.122.

M. Salmi, D. Atif, D. Oliva, A. Abraham, and S. Ventura, “Handling imbalanced medical datasets: review of a decade of research,” Artif. Intell. Rev., vol. 57, no. 10, p. 273, Sep. 2024, doi: 10.1007/s10462-024-10884-2.

R. J. Chen, M. Y. Lu, T. Y. Chen, D. F. K. Williamson, and F. Mahmood, “Synthetic data in machine learning for medicine and healthcare,” Nat. Biomed. Eng., vol. 5, no. 6, pp. 493–497, Jun. 2021, doi: 10.1038/s41551-021-00751-8.

S. Padhy, S. Dash, S. Routray, S. Ahmad, J. Nazeer, and A. Alam, “IoT-Based Hybrid Ensemble Machine Learning Model for Efficient Diabetes Mellitus Prediction,” Comput. Intell. Neurosci., vol. 2022, pp. 1–11, May 2022, doi: 10.1155/2022/2389636.

Y. Ghazizadeh, “Machine learning-based diabetes prediction: A comprehensive study on predictive modeling and risk assessment,” Journal of Clinical Images and Medical Case Reports, vol. 6, no. 5, May 2025, doi: 10.52768/2766-7820/3578.

Y. A. Fahim, I. W. Hasani, S. Kabba, and W. M. Ragab, “Artificial intelligence in healthcare and medicine: clinical applications, therapeutic advances, and future perspectives,” Eur. J. Med. Res., vol. 30, no. 1, p. 848, Sep. 2025, doi: 10.1186/s40001-025-03196-w.

B. Chen, Y. Wang, X. Xie, B. Fan, W. Zhang, and G. Sun, “Trends in AI-based diagnosis and intervention of metabolic diseases: a bibliometric analysis of the literature from 2000 to 2024,” Front. Med. (Lausanne)., vol. 12, Dec. 2025, doi: 10.3389/fmed.2025.1698366.

A. I. Stoumpos, F. Kitsios, and M. A. Talias, “Digital Transformation in Healthcare: Technology Acceptance and Its Applications,” Int. J. Environ. Res. Public Health, vol. 20, no. 4, p. 3407, Feb. 2023, doi: 10.3390/ijerph20043407.

Y. P. Pingle and L. K. Ragha, “Statistical assessment of Indian classical music’s role in diabetes, thyroid, hypertension management,” International Journal of Information Technology, vol. 17, no. 1, pp. 423–429, Jan. 2025, doi: 10.1007/s41870-024-02227-9.

E. Maimaitijiang, M. Aihaiti, and Y. Mamatjan, “An Explainable AI Framework for Online Diabetes Risk Prediction with a Personalized Chatbot Assistant,” Electronics (Basel)., vol. 14, no. 18, p. 3738, Sep. 2025, doi: 10.3390/electronics14183738.

A. F. Scheideman et al., “Machine Learning to Diagnose Complications of Diabetes,” J. Diabetes Sci. Technol., vol. 19, no. 6, pp. 1650–1670, Nov. 2025, doi: 10.1177/19322968251365245.

T. Liu et al., “Emerging Wearable Acoustic Sensing Technologies,” Advanced Science, vol. 12, no. 6, Feb. 2025, doi: 10.1002/advs.202408653.

Y.-T. Chang, Y.-Z. Tu, H.-Y. Chiou, K. Lai, and N. C. Yu, “Real-world Benefits of Diabetes Management App Use and Self-monitoring of Blood Glucose on Glycemic Control: Retrospective Analyses,” JMIR Mhealth Uhealth, vol. 10, no. 6, p. e31764, Jun. 2022, doi: 10.2196/31764.

Z. Guan et al., “Artificial intelligence in diabetes management: Advancements, opportunities, and challenges,” Cell Rep. Med., vol. 4, no. 10, p. 101213, Oct. 2023, doi: 10.1016/j.xcrm.2023.101213.

I. Kavakiotis, O. Tsave, A. Salifoglou, N. Maglaveras, I. Vlahavas, and I. Chouvarda, “Machine Learning and Data Mining Methods in Diabetes Research,” Comput. Struct. Biotechnol. J., vol. 15, pp. 104–116, 2017, doi: 10.1016/j.csbj.2016.12.005.