Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{204452,
        author = {Subinraj S and Muhammed Sabith J N and Adith S Nair and Jiyana Maria Foustin and Ms. Vijaya Lekshmi S V},
        title = {Pill Track: A Voice-Enabled AI-Based System for Pill Identification and Elderly Healthcare Management},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {no},
        pages = {108-113},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204452},
        abstract = {Medication adherence is a critical challenge in elderly healthcare, where incorrect dosage or wrong pill intake can lead to serious health complications. Existing medication re-minder systems primarily provide alerts but fail to verify whether the correct medicine is actually taken, creating risks of medication errors and reduced treatment effectiveness. To address these challenges, this paper presents Pill Track, an integrated and intelligent medication management system designed specifically for elderly care. The proposed system combines a cross-platform mobile application, artificial intelligence-based pill identification, and a Raspberry Pi-based hardware verification unit. The AI module utilizes a multi-stage pipeline consisting of YOLOv8 for real-time pill detection, Convolutional Neural Networks (CNN) for classification, and EasyOCR for imprint recognition, enabling accurate and reliable pill verification. In addition, the system incorporates automated medication reminders, push notifications, and voice-based alert calls using Twilio, along with caregiver monitoring and secure cloud-based Electronic Health Record (EHR) storage. Experimental evaluation demonstrates that the proposed system achieves a pill detection accuracy of 94.3 percent while maintaining efficient real-time performance. The system aims to reduce medication errors, improve adherence, and promote safe and independent healthcare management for elderly users.},
        keywords = {Pill Identification, YOLOv8, CNN, EasyOCR, Raspberry Pi, Medication Reminder, Elderly Healthcare, EHR},
        month = {June},
        }