BioSentry: Real-Time Adverse Drug Reaction Monitoring and Detection

This paper introduced BioSentry, an AI and IoT-based framework for real-time monitoring and early warning of adverse drug reactions (ADRs) during medication regimens. By incorporating wearable physiological sensors, visual symptom analysis through camera-based systems, and multimodal machine learning models, the proposed framework overcomes some of the current limitations of traditional pharmacovigilance systems, which are mainly dependent on retrospective reporting or individual data sources. The addition of user security management, event triggered monitoring based on medication consumption, personalized baseline establishment, and alert mechanisms also improves the proposed system’s applicability for clinical use and regulatory purposes.             By virtue of its modularity, hybrid edge-cloud approach, and privacy-focused design, the framework exhibits potential for large-scale, cost-effective implementation within the hospital setting as well as the home care setting. The design analysis above underscored how lessons learned from previous research in ADR analysis, IoT healthcare systems, and clinical decision support systems had influenced the proposed approach while also justifying a need for a more proactive, patient-focused drug safety monitoring approach. There are a number of avenues for future research. Large scale clinical validation studies are needed to evaluate the accuracy of detection, false positives, latency, and user acceptance. The sensing layer can be augmented by incorporating additional biomedical sensors such as electrocardiogram (ECG), continuous blood pressure measurement, respiratory rate measurement, and motion sensors. In the coming versions of the mobile app, the system may include an interaction module based on voice interaction, enabling patients to enter their symptoms, confirm drug consumption, or answer automated health surveys. Speech recognition and natural language processing algorithms would further enhance multimodal data entry for ADR monitoring. Other areas of research will also include on-device inference and federated learning approaches to enhance robustness against connectivity constraints and improve data privacy. Breakthroughs in computer vision models would also allow for more accurate identification of subtle dermatological and neurological symptoms in different lighting conditions. Lastly, better integration with electronic health records and pharmacovigilance systems would enable automated reporting to health authorities and large-scale drug safety analysis. Taken together, these developments would make the proposed system a promising step towards intelligent, continuous, and personalized ADR monitoring in real-world healthcare settings.

1.  Wang, X., Wang, X., & Zhang, S. (2022). Adverse drug reaction detection from social media based on quantum bi-lstm with attention. IEEE Access, 11, 16194-16202. 2.   Amit, D., & Rataboli, P. V. (2008). Adverse drug reaction (ADR) notification drop box: an easy way to report ADRs. British journal of clinical pharmacology, 66(5), 723. 3  Li, Z., Lin, H., & Zheng, W. (2020). An effective emotional expression and knowledge-enhanced method for detecting adverse drug reactions. IEEE Access, 8, 87083-87093. 4.  Jara, A. J., Belchi, F. J., Alcolea, A. F., Santa, J., Zamora-Izquierdo, M. A., & Gómez-Skarmeta, A. F. (2010, March). A Pharmaceutical Intelligent Information System to detect allergies and Adverse Drugs Reactions based on internet of things. In 2010 8th IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOM Workshops) (pp. 809-812). IEEE. 5.  ChandraUmakantham, O., Srinivasan, S., & Pathak, V. (2024). Detecting Side Effects of Adverse Drug Reactions Through Drug-Drug Interactions Using Graph Neural Networks and Self-Supervised Learning. IEEE Access, 12, 93823-93840. 6.  Lee, E. K., Wu, T. L., Senior, T., & Jose, J. (2014, November). Medical alert management: a real-time adaptive decision support tool to reduce alert fatigue. In AMIA Annual Symposium Proceedings (Vol. 2014, p. 845). 7.  Sun, L., Sun, S., Wang, T., Li, J., & Lin, J. (2018). Parallel ADR detection based on spark and BCPNN. Tsinghua Science and Technology, 24(2), 195-206. 8.  Wei, J., Lu, Z., Qiu, K., Li, P., & Sun, H. (2020). Predicting drug risk level from adverse drug reactions using SMOTE and machine learning approaches. IEEE Access, 8, 185761-185775. 9.  Aditya, T. R., Pai, S. S., Bhat, K., Manjunath, P., & Jagadamba, G. (2020, July). Real time patient activity monitoring and alert system. In 2020 International Conference on Electronics and Sustainable Communication Systems (ICESC) (pp. 708-712). IEEE. 10.  Sweidan, A. H., El-Bendary, N., & Al-Feel, H. (2021). Sentence-level aspect-based sentiment analysis for classifying adverse drug reactions (ADRs) using hybrid ontology-XLNet transfer learning. IEEE Access, 9, 90828-90846.