International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | An Intelligent Medication Reminder and Patient Compliance Monitoring Framework Using Cohort-Based Anomaly Detection |
|---|---|
| ABSTRACT | Non-adherence to prescribed medication remains one of the most persistent and economically significant problems in chronic-disease management, contributing to avoidable hospitalisations, therapeutic failure, and elevated healthcare expenditure. Although digital reminder applications are widely available, most operate as passive notification tools that neither verify intake nor reason about the longitudinal regularity of a patient's dosing behaviour. This paper presents a lightweight, fully self-hosted framework that unifies timezone-aware dose scheduling, multi-channel reminder delivery, and unsupervised compliance analytics within a single deployable system. The platform is implemented using a three-tier architecture in which a React single-page interface communicates with an asynchronous Python service layer that persists structured intake events through an object-relational mapping layer backed by an embedded relational database. A background scheduler periodically evaluates due-dose windows against the patient's local civil time and dispatches deduplicated reminders through electronic mail-to-SMS carrier gateways, a programmable telephony provider, or in-browser notifications. Compliance is quantified from logged intake events, and an Isolation Forest model identifies medications whose timing variance and missed-dose ratio deviate from the patient's own behavioural cohort, with a deterministic rule-based estimator providing graceful degradation when machine-learning dependencies are unavailable. Experimental evaluation on synthetically generated dosing histories demonstrates sub-100-millisecond median interface latency and an anomaly-detection F1 score that improves from 0.69 to 0.94 as logging history accumulates. The proposed approach offers a privacy-preserving, infrastructure-light alternative to cloud-dependent adherence platforms. |
| AUTHOR | VADDI SATYA GANESH, K. LAKSHMI SAI SRI PG Scholar, Department of Computer Science, S.V.K.P & Dr. K.S. Raju Arts and Science College (Autonomous), Penugonda, Affiliated to Adikavi Nannaya University, Andhra Pradesh, India Associate Professor, Department 0f Master of Computer Applications, S.V.K. P & Dr. K. S. Raju Arts and Science College (Autonomous), Penugonda, Affiliated to Adikavi Nannaya University, Andhra Pradesh, India |
| VOLUME | 185 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1406060 |
| pdf/60_An Intelligent Medication Reminder and Patient Compliance Monitoring Framework Using Cohort-Based Anomaly Detection.pdf | |
| KEYWORDS | |
| References | [1] World Health Organization, Adherence to Long-Term Therapies: Evidence for Action. Geneva, Switzerland: WHO Press, 2003. [2] M. T. Brown and J. K. Bussell, “Medication adherence: WHO cares?,” Mayo Clinic Proceedings, vol. 86, no. 4, pp. 304–314, 2011. [3] B. Vrijens et al., “A new taxonomy for describing and defining adherence to medications,” British Journal of Clinical Pharmacology, vol. 73, no. 5, pp. 691–705, 2012. [4] S. R. Majeed et al., “Effectiveness of mobile phone reminders on medication adherence: a systematic review,” Journal of Medical Internet Research, vol. 22, no. 9, e17776, 2020. [5] A. K. Pandey and R. Sharma, “Smartphone-based reminder systems for chronic disease management,” IEEE Access, vol. 9, pp. 112045–112060, 2021. [6] C. R. Hayes et al., “Electronic monitoring of medication adherence using smart packaging,” IEEE Sensors Journal, vol. 20, no. 14, pp. 8123–8132, 2020. [7] P. Kumar and S. Banerjee, “Wearable sensor-driven intake detection for adherence support,” in Proc. IEEE Int. Conf. on Healthcare Informatics, 2021, pp. 245–252. [8] L. Zhang, Y. Chen, and H. Liu, “Vision-based medication intake verification using deep learning,” IEEE J. Biomed. Health Informatics, vol. 25, no. 6, pp. 2210–2219, 2021. [9] D. Patel et al., “Machine learning for prediction of medication non-adherence,” npj Digital Medicine, vol. 4, art. 110, 2021. [10] R. Gupta and M. Iyer, “Risk stratification of medication non-adherence using ensemble classifiers,” IEEE Access, vol. 10, pp. 33210–33223, 2022. [11] S. Ahmed and K. Rao, “Recurrent neural networks for forecasting missed medication doses,” in Proc. IEEE EMBC, 2022, pp. 1788–1792. [12] F. T. Liu, K. M. Ting, and Z.-H. Zhou, “Isolationforest,” in Proc. IEEE Int. Conf. on Data Mining, 2008, pp. 413–422. [13] V. Chandola, A. Banerjee, and V. Kumar, “Anomaly detection: a survey,” ACM Computing Surveys, vol. 41, no. 3, pp. 1–58, 2009. [14] J. M. Silva and A. Costa, “Lightweight REST architectures for digital health applications,” IEEE Software, vol. 39, no. 2, pp. 64–71, 2022. [15] N. Roberts and T. Williams, “Component-based front-end design for clinical dashboards,” IEEE Computer, vol. 54, no. 8, pp. 40–48, 2021. [16] H. Park and J. Lee, “Timezone-aware scheduling for distributed reminder services,” IEEE Trans. Services Computing, vol. 16, no. 1, pp. 220–231, 2023. [17] A. Fernandez et al., “Privacy-preserving self-hosted health platforms: a comparative study,” IEEE Security & Privacy, vol. 21, no. 4, pp. 55–64, 2023. |
