A Smart Clinic and Pharmacy Management System Integrating AI-Based Prescription Assistance and Inventory Prediction

A Smart Clinic and Pharmacy Management System Integrating AI-Based Prescription Assistance and Inventory Prediction

Dr. Shanid Malayil

Associate Professor Department of Computer Science And Engineering, MEA Engineering College Perinthalmanna, India

Mr. Aadhil Juman T. M.

Department of Computer Science and Engineering, MEA Engineering College Perinthalmanna, India

Mr. Mohammed Haneen P. M.

Department of Computer Science and Engineering, MEA Engineering College Perinthalmanna, India

Mrs. Jitha K

Assistant Professor Department of Computer Science And Engineering, MEA Engineering College Perinthalmanna, India

Mr. Anoof Mohammed K. P.

Department of Computer Science and Engineering, MEA Engineering College Perinthalmanna, India

Mrs. Neethu Dominic

Assistant Professor Department of Computer Science And Engineering, MEA Engineering College Perinthalmanna, India

Mr. Anshab Haroon

Department of Computer Science and Engineering MEA Engineering College Perinthalmanna, India

Abstract – Healthcare clinics and pharmacies continue to face significant operational challenges, including long patient wait- ing times, fragmented medical records, inefficient prescription handling, and frequent medicine shortages. Most existing clinic management systems focus primarily on appointment schedul- ing and basic electronic medical records, lacking intelligent decision-support and predictive capabilities. To address these limitations, this paper proposes SmartMed, an AI-driven clinic and pharmacy management system that integrates intelligent prescription prediction, medicine image recognition, real-time queue monitoring, family-based account management, patient feedback analysis, and predictive medicine shortage forecasting. The proposed system leverages machine learning models, com- puter vision techniques, and real-time data analytics to assist doctors, pharmacists, and patients in making informed decisions while streamlining clinical workflows. By introducing proactive healthcare intelligence, SmartMed improves operational effi- ciency, reduces patient waiting times, and minimizes medicine un- availability. Experimental evaluation and simulated deployment results demonstrate enhanced consultation efficiency, improved patient satisfaction, and more accurate demand forecasting when compared to traditional clinic management systems.

Keywords – Clinic Management System, Artificial Intelligence, Prescription Prediction, Smart Queue, Medicine Shortage Predic- tion, Healthcare Informatics

1. INTRODUCTION

   The healthcare sector is undergoing a rapid digital trans- formation driven by increasing patient volumes, rising expec- tations for quality care, and the need for efficient resource utilization. Clinics and pharmacies, particularly small- and medium-scale healthcare facilities, face persistent operational challenges such as prolonged patient waiting times, frag- mented and poorly maintained medical records, inefficient prescription handling, and frequent shortages of essential medicines. These challenges not only reduce operational effi- ciency but also negatively impact patient satisfaction and the overall quality of healthcare delivery.

   Traditional clinic management practices rely heavily on manual processes or partially digitized systems that operate in isolation. While many existing clinic management systems provide basic functionalities such as appointment scheduling, electronic medical records, and billing, they largely lack in- telligent decision-support mechanisms and predictive capabil- ities. As a result, clinicians are often burdened with repetitive administrative tasks, pharmacists struggle with reactive inven- tory management, and patients experience delays and a lack of transparency during consultations and medicine procurement. Recent advancements in artificial intelligence (AI), machine

   learning, computer vision, and real-time data analytics present an opportunity to move beyond simple digitization toward intelligent and proactive healthcare systems. AI-driven solu- tions have demonstrated potential in assisting clinical decision- making, optimizing operational workflows, and predicting future demand patterns. However, the integration of these technologies into practical, end-to-end clinic and pharmacy management platforms remains limited, especially in systems designed for everyday clinical environments.

   To address these gaps, this paper proposes SmartMed, an AI-driven clinic and pharmacy management system designed to enhance both clinical and operational efficiency. SmartMed integrates intelligent prescription prediction to assist doctors during consultations, medicine image recognition to support accurate identification and verification of drugs, real-time smart queue monitoring to reduce patient waiting times, and family-based account management to simplify healthcare ac- cess for dependents and caregivers. Additionally, the system incorporates patient medicine feedback analysis to capture real-world treatment responses and predictive medicine short- age forecasting to enable proactive inventory planning.

   By leveraging machine learning models, computer vision techniques, and real-time analytics, SmartMed transforms con- ventional clinic workflows into a data-driven and intelligent healthcare ecosystem. Unlike traditional systems that respond only after events occur, the proposed platform emphasizes proactive healthcare intelligence, enabling clinics and phar- macies to anticipate demand, optimize resources, and im- prove service delivery. Experimental evaluation and simulated deployment results demonstrate that SmartMed significantly improves consultation efficiency, enhances patient satisfaction, and provides more accurate demand forecasting compared to existing clinic management systems.

2. PROBLEM STATEMENT

   Despite the increasing adoption of digital tools in health- care, many small and medium-sized clinics continue to face operational inefficiencies. Patient appointments are often man- aged through partially digitized systems or manual registers, resulting in long waiting times and poor queue visibility. Patients frequently remain uncertain about their consultation time, leading to overcrowded waiting areas and dissatisfaction. Another major concern is prescription management. Al- though electronic prescription systems exist, they primarily function as digital record-keeping tools and do not provide intelligent assistance to doctors during consultations. As a result, prescription decisions rely entirely on manual review of patient history, which may increase consultation time and

   introduce inconsistencies in treatment practices.

   Pharmacies attached to clinics also encounter challenges in managing medicine inventory. Most systems update stock lev- els only after dispensing, without offering predictive insights regarding future demand. This reactive approach often results in sudden medicine shortages, especially for frequently pre- scribed drugs. Such shortages can disrupt treatment continuity and negatively impact patient care.

   In addition, existing clinic management systems rarely in- tegrate advanced features such as real-time queue monitoring, medicine identification through image recognition, or family- based account management. These gaps highlight the need for a more intelligent and integrated solution that goes beyond basic digitization.

   Therefore, there is a clear requirement for a unified clinic and pharmacy management platform that incorporates in- telligent decision-support features, predictive analytics, and real-time monitoring capabilities to enhance both operational efficiency and patient experience.

3. SYSTEM OBJECTIVES AND SCOPE

   1. Objectives

      The SmartMed system is designed to integrate core clinic operations with intelligent decision-support features. The main objectives of the system are as follows:

      • To provide an integrated platform for managing appoint- ments, prescriptions, and inventory.

      • To reduce patient waiting time using real-time queue monitoring.

      • To assist doctors through AI-based prescription sugges- tions.

      • To predict medicine shortages using inventory trend anal- ysis.

      • To enable medicine verification through image recogni- tion.

      • To support family-based account management.

   2. Scope

   The proposed system is intended for small and medium- sized clinics requiring a unified and intelligent management solution. It supports web-based access with mobile compat- ibility for improved accessibility. The evaluation is based on functional testing and simulated usage scenarios. Large- scale hospital deployment, national healthcare integration, and regulatory certification are beyond the scope of this implemen- tation.

4. LITERATURE REVIEW

   1. Existing Technologies and Applications

      A wide range of digital clinic and healthcare management systems have been developed in recent years to improve the efficiency of clinical operations and patient care. These systems mainly focus on digitizing patient records, managing appointments, and facilitating communication between health- care providers and patients. Mobile health platforms and web- based applications have become increasingly popular due to their ability to provide real-time access to patient informa- tion, improve workflow efficiency, and reduce dependence on manual record keeping.

      Many existing healthcare applications allow clinics to store and manage electronic medical records, which helps health- care professionals access patient history quickly and make informed clinical decisions. These platforms often use cloud

      storage and mobile technologies to ensure that patient data can be accessed securely from different locations. Additionally, some systems include features such as appointment booking, prescription management, and basic inventory tracking, which help streamline routine clinical processes and reduce admin- istrative workload.

      Recent advancements in healthcare technology have also introduced mobile health platforms that enable health- care providers to access patient records, monitor treatment progress, and communicate with patients more efficiently. These systems improve coordination between healthcare staff and enhance overall service delivery. Furthermore, emerging technologies such as artificial intelligence, cloud computing, and data analytics are beginning to play an important role in improving healthcare efficiency and supporting clinical decision-making.

      However, despite these advancements, most existing clinic management systems are primarily designed to perform ba- sic administrative functions and lack intelligent capabilities. Many systems do not provide predictive features, real-time queue monitoring, or advanced decision-support tools that can assist healthcare providers in managing patient flow and medicine availability. In addition, features such as automated prescription assistance, medicine identification using image recognition, and predictive medicine shortage analysis are not commonly integrated into existing systems. These limitations highlight the need for a more intelligent and integrated clinic and pharmacy management solution, which motivates the development of the proposed SmartMed system.

   2. Related Studies

   Various studies have been conducted to develop clinic management systems aimed at improving the efficiency of healthcare service delivery and reducing manual administrative workload. A mobile clinic management system developed in

   [1] ntegrates appointment scheduling, prescription manage- ment, and payment processing into a single platform. Such systems improve operational efficiency, enhance record accu- racy, and reduce dependency on manual processes. Similarly, a web-based clinic management system with integrated patient satisfaction analysis was proposed in [2], which uses sentiment analysis techniques to evaluate patient feedback and improve service quality.

   Several web-based clinic management solutions have also been proposed in recent years. The system developed in

   [3] prov des functionalities such as patient registration, ap- pointment scheduling, and medical record management, help- ing clinics organize patient data more efficiently. Another study in [5] introduced a web-based healthcare management system that enables improved coordination between patients and healthcare providers while maintaining electronic medical records. Likewise, the clinic management system presented in [9] focuses on digitizing clinic operations and improving accessibility to patient information through a centralized plat- form.

   Other related works have explored specialized implementa- tions of clinic management systems. For example, the optical clinic management system proposed in [6] provides compre- hensive modules including patient management, clinician man- agement, and inventory tracking to support optical healthcare services. Similarly, the system developed in [7] integrates prescription handling, billing, and inventory management to automate clinic workflows and improve administrative effi- ciency. A cloud-based mobile health platform designed in [8] enables secure storage and retrieval of medical records, im- proving accessibility and data management across healthcare environments.

   In addition to clinic-focused systems, broader healthcare information systems have also been studied. The remote patient management system presented in [4] enables healthcare providers to monitor patient conditions and improve commu- nication using digital technologies. Furthermore, the optical clinic system described in [10] demonstrates the importance of structured system design in improving clinical service management and data organization.

   Although these studies provide important contributions to- ward digitizing clinic operations, most existing systems pri- marily focus on basic functionalities such as appointment scheduling, electronic medical records, and prescription man- agement. Intelligent features such as AI-based prescription assistance, real-time queue monitoring, medicine image recog- nition, and predictive medicine shortage analysis are not addressed in these systems. These limitations highlight the need for a more advanced and intelligent clinic management solution, which motivates the development of the proposed SmartMed system.

5. METHODOLOGY AND SYSTEM DESIGN

   1. System Overview

      The proposed SmartMed system is designed as an integrated clinic and pharmacy management platform that combines routine clinical operations with intelligent decision-support features. The primary objective of the system is to simplify day-to-day clinic activities while introducing smart functional- ities that assist doctors, pharmacists, and patients. The system is developed with a modular approach to ensure scalability, maintainability, and ease of use.

      SmartMed aims to reduce patient waiting time, improve prescription accuracy, and minimize medicine shortages by utilizing data-driven techniques. The system can be accessed through a web-based interface and a mobile application, mak- ing it suitable for small and medium-sized clinics with liited staff and infrastructure.

   2. System Architecture

      The SmartMed system follows a three-layer architecture consisting of the presentation layer, application layer, and data layer. This architectural design ensures clear separation of responsibilities and improves system reliability and security.

      TABLE I

      Comparison of Existing Clinic Management Systems and Proposed SmartMed System

      Application / System	Features*								Remarks
      	Apt	Pre	Pay	EMR	Inv	Que	AI	Img
      CMS Base Paper System									Provides integrated appointment, prescription, and payment system but lacks intelligent automation and prediction features.
      Mobile Health Medical Records System									Focuses on medical record management and ap- pointment handling but does not include advanced predictive capabilities.
      Web-Based Clinic Management System									Provides clinic workflow automation including ap- pointment and queue management, but lacks intelli- gent features.
      Sentiment-Based Healthcare System									Includes patient feedback analysis but lacks prescrip- tion prediction and intelligent support.
      Optical Clinic Management System									Provides patient, clinician, and inventory manage- ment but lacks AI and predictive shortage analysis.
      University Clinic Management System									Provides electronic records and scheduling function- ality but lacks intelligent automation.
      Cloud-Based Healthcare System									Enables cloud storage and access but lacks predictive analytics and intelligent support.
      Clinic Management System with Inventory									Provides inventory tracking but does not include predictive shortage analysis.
      Basic Electronic Health Record System									Focuses on digitization of records but lacks intelli- gent automation and prediction.
      Proposed SmartMed System									Integrates AI prescription assistance, real-time queue monitoring, medicine image recognition, family ac- count management, and medicine shortage predic- tion.

      * Apt = Appointment, Pre = Prescription, Pay = Payment, EMR = Electronic Medical Records, Inv = Inventory Management, Que = Queue Management, AI

      = Artificial Intelligence Assistance, Img = Medicine Image Recognition

      The presentation layer provides interfaces for patients, doctors, pharmacists, and administrators. It supports func- tions such as appointment booking, queue status viewing, prescription access, and feedback submission. The application layer contains the core business logic and intelligent modules, including AI-based prescription prediction, smart queue man- agement, medicine image recognition, and medicine shortage prediction. The data layer stores patient records, prescriptions, inventory data, feedback information, and historical usage data in a secure database.

   3. System Modules

      The SmartMed system is divided into several functional modules based on user roles and system responsibilities.

      1. Patient Module: The patient module allows users to register, manage personal profiles, book appointments, view real-time queue status, access prescriptions, and provide feed- back. A family-based account feature enables a single user to manage appointments and medical records for multiple family members, reducing the need for separate accounts.

      2. Doctor Module: The doctor module supports appoint- ment management, access to patient medical history, and prescription generation. An AI-assisted prescription prediction feature suggests commonly prescribed medicines based on patient symptoms and historical data. These suggestions act as decision support and can be accepted or modified by the doctor.

      3. Pharmacy Module: The pharmacy module manages medicine inventory, prescription verification, and dispensing processes. It also integrates a medicine image recognition feature that allows pharmacists to scan medicine images and retrieve relevant details such as name, dosage, and usage instructions.

      4. Admin Module: The admin module handles system configuration, user management, inventory monitoring, and report generation. It also oversees alert mechanisms related to low inventory levels and system performance.

   4. AI-Based Prescription Prediction Module

      The AI-based prescription prediction module assists doctors by suggesting appropriate medicines based on historical pre- scription data and patient medical records. Machine learning models are trained using anonymized data to identify common treatment patterns. The module is designed to support clinical decision-making and does not replace the doctors expertise.

   5. Smart Queue Management Module

      The smart queue management module provides real-time queue updates to patients. The system dynamically adjusts queue positions based on appointment schedules, consultation duration, and walk-in patients. This helps reduce overcrowd- ing in clinics and improves patient satisfaction by providing transparency in waiting times.

      TABLE II

      Summary of SmartMed Methodology and Functional Modules

      Module	Description
      Patient Module	Appointment booking, real-time queue moni- toring, prescription access, feedback submis- sion, and family-based account management.
      Doctor Module	Access to patient medical history, prescrip- tion generation, and AI-assisted prescription recommendations.
      Pharmacy Module	Prescription verification, medicine dispens- ing, inventory tracking, and medicine image scanning support.
      Admin Module	User management, clinic configuration, sys- tem monitoring, inventory alerts, and report generation.
      AI-Based Prescription Pre- diction Module	Uses historical patient and prescription data to suggest suitable medicines as clinical decision support.
      Smart Queue Management Module	Displays real-tie queue status and estimated waiting time to reduce overcrowding and im- prove patient flow.
      Medicine Image Recogni- tion Module	Identifies medicines using image scanning techniques and displays details such as name, dosage, and usage instructions.
      Medicine Shortage Predic- tion Module	Analyzes historical inventory and prescription trends to forecast medicine demand and gen- erate low-stock alerts.

   6. Medicine Image Recognition Module

      The medicine image recognition module uses computer vision techniques to identify medicines from captured images. This feature helps pharmacists and patients verify medicines and access accurate information, reducing the chances of dispensing or consumption errors.

   7. Medicine Shortage Prediction Module

      The medicine shortage prediction module analyzes histor- ical inventory data, prescription trends, and medicine usage patterns to forecast future demand. Predictive analytics tech- niques are used to generate alerts when a medicine is likely to run low, enabling clinics to restock in advance and avoid shortages.

   8. Methodology Summary

      Table II summarizes the methodology and core functional- ities of the SmartMed system.

   9. Class Diagram

      Figure 1 illustrates the class diagram of the proposed SmartMed system, showing the relationships between major system components.

   10. Algorithmic Workflow of AI Prescription Prediction

       The AI-based prescription prediction module follows a structured workflow consisting of data collection, pattern iden- tification, and suggestion generation. Historical prescription records and anonymized patient data are used as input for model training. The system analyzes frequently prescribed medicines for similar symptoms and medical conditions.

       Fig. 1. Class Diagram of the Proposed SmartMed System

       A frequency-based analysis approach is initially applied to identify common treatment patterns. For a given patient profile and reported symptoms, the system retrieves relevant historical cases and ranks medicines based on occurrence frequency. The top-ranked suggestions are presented to the doctor as decision- support recommendations.

       The final prescription decision remains under the control of the doctor. The AI module acts only as a supportive tool and does not override clinical judgment.

   11. Queue Optimization Logic

       The smart queue management module calculates estimated waiting time based on scheduled appointments, average con- sultation duration, and walk-in patient count. Each confirmed appointment is assigned a position in the queue.

       The system dynamically updates queue order when delays occur. If a consultation exceeds the estimated time, subsequent waiting times are recalculated automatically. This dynamic adjustment improves transparency and helps patients plan their visit more effectively.

   12. Shortage Forecasting Model

   The medicine shortage prediction module analyzes histor- ical inventory data and prescription frequency trends. The average daily usage rate of each medicine is computed using past dispensing records.

   Future demand is estimated using trend analysis over a predefined time window. If projected stock levels fall below a predefined threshold within the forecast period, the system generates a low-stock alert for administrators. This approach enables proactive inventory management and reduces unex- pected shortages.

   TABLE III

   Technology Stack Used in SmartMed Implementation

   Layer	Technology Description
   Front-End	Web-based interface optimized for desktop and mo- bile access.
   Back-End	Server-side application handling business logic and system workflows.
   Database	Centralized database for storing patient records, pre- scriptions, and inventory data.
   AI Processing	Machine learning models used for prescription assis- tance and shortage prediction.
   Image Processing	Computer vision techniques for medicine image recognition.
   Security	Role-based authentication and controlled data access mechanisms.

6. SYSTEM IMPLEMENTATION

   This section describes the implementation details of the proposed SmartMed system. The system was implemented as a web-based and mobile-supported application to ensure accessibility for clinics with limited infrastructure. The im- plementation focuses on integrating core clinic management functionalities with intelligent features while maintaining a simple and user-friendly interface.

   1. Development Environment

      The SmartMed system was developed using a client-server architecture. The front-end interface was implemented using web technologies to support both desktop and mobile access. The back-end services handle business logic, data processing, and communication between system modules. A centralized database was used to store patient records, appointment details, prescriptions, inventory data, and feedback information.

      The system was designed to be modular so that individual components such as appointment management, prescription handling, and inventory monitoring could be developed and tested independently before integration.

   2. Technology Stack

      The SmartMed system was implemented using widely adopted web and database technologies to ensure reliability, scalability, and ease of maintenance. The selection of tech- nologies focused on simplicity and compatibility with small and medium-sized clinic environments. Table III summarizes the major technologies used in the system implementation.

   3. Appointment and Queue Management Implementation

      The appointment management module allows patients to book appointments based on available schedules. Once an appointment is confirmed, it is added to the clinic queue auto- matically. The smart queue management feature dynamically updates the queue based on consultation duration, appointment time, and walk-in patients.

      Patients are able to view real-time queue status through the application, which helps reduce unnecessary waiting and overcrowding in clinics. Doctors and clinic staff can also

      monitor queue progress and manage appointments through the administrative interface.

   4. Prescription Management and AI Assistance

      Prescription generation is implemented within the doctor module, where doctors can create and update prescriptions digitally. The AI-based prescription prediction feature assists doctors by suggesting commonly prescribed medicines based on historical patient data and previous prescriptions. This feature is implemented as a decision-support mechanism and does not replace the doctors clinical judgment.

      The AI module processes anonymized prescription data to identify common treatment patterns. Suggested prescriptions are displayed to the doctor during consultation and can be accepted, modified, or ignored as needed.

   5. Medicine Image Recognition Implementation

      The medicine image recognition module was implemented to assist pharmacists and patients in identifying medicines accurately. This module allows users to capture images of medicine packaging or labels, which are then processed using image recognition techniques to extract relevant information such as medicine name and dosage details.

      This feature helps reduce errors caused by misidentifica- tion of medicines and improves confidence during medicine dispensing and consumption.The extracted information is matched with records stored in the system database to ensure accuracy.

   6. Inventory Management and Shortage Prediction

      The inventory management module tracks medicine stock levels in real time. Each medicine entry includes details such as quantity, expiry information, and usage frequency. When medicines are dispensed, inventory levels are updated automatically.

      The medicine shortage prediction feature analyzes histori- cal inventory data and prescription trends to forecast future demand. Predictive analytics techniques are used to identify medicines that are likely to run low. Alerts are generated for clinic administrators, allowing timely restocking and prevent- ing medicine shortages.

   7. Family-Based Account Management

      The family-based account feature allows a single user ac- count to manage multiple patient profiles within a family. This implementation reduces the need for separate registrations and simplifies appointment booking and prescription tracking for families. Each family members medical records are stored securely and can be accessed individually while remaining linked under one account.

   8. System Security and Data Handling

      Basic security measures were implemented to protect sen- sitive medical data. User authentication mechanisms ensure that only authorized users can access system features based on their roles. Patient data is stored securely in the database, and access is restricted according to user permissions.

      TABLE IV

      Summary of SmartMed System Implementation

      Component	Implementation Description
      Appointment Management	Digital appointment booking with automatic queue integration and real-time updates.
      Smart Queue System	Dynamic queue adjustment based on appointment schedules and consultation duration.
      AI Prescription Assistance	Decision-support system suggesting medicines based on historical prescription data.
      Medicine Image Recognition	Image-based medicine identification to retrieve dosage and usage details.
      Inventory Management	Real-time stock tracking with automatic updates dur- ing dispensing.
      Shortage Prediction	Predictive analytics to forecast medicine demand and generate low-stock alerts.
      Family Account Feature	Single account managing multiple patient profiles within a family.

      TABLE V

      Performance Evaluation Results of SmartMed System

      Metric	Before SmartMed	After SmartMed
      Average Patient Waiting Time	High	Reduced
      Appointment Handling Efficiency	Manual	Automated
      Prescription Processing Time	Longer	Shorter
      Inventory Tracking Accuracy	Moderate	Improved
      Medicine Availability Issues	Frequent	Reduced

   9. Implementation Summary

   Table IV summarizes the key implementation components of the SmartMed system.

7. RESULTS AND DISCUSSION

   This section discusses the results obtained from the imple- mentation and evaluation of the proposed SmartMed system. The system was evaluated through functional testing and sim- ulated usage scenarios to assess its effectiveness in improving clinic operations, patient experience, and medicine manage- ment. The evaluation focused on appointment handling, queue efficiency, prescription assistance, inventory monitoring, and intelligent system features.

   1. System Performance Evaluation

      The performance of SmartMed was evaluated based on its ability to streamline clinic workflows and reduce manual effort. Key performance indicators included patient waiting time, prescription handling efficiency, and inventory monitor- ing accuracy. The evaluation was conducted using simulated patient data and test scenarios that represent typical clinic operations.

      Table V presents the observed performance improvements after adopting the SmartMed system.

      The results indicate that SmartMed improves appointment coordination and reduces patient waiting time by providing real-time queue updates. Automated prescription handling and inventory tracking also contributed to improved operational efficiency.

      TABLE VI

      Comparison of SmartMed with Traditional Clinic Management Systems

      Feature	Traditional Systems	SmartMed
      Appointment Scheduling	Available	Available
      Digital Prescriptions	Available	Available
      Real-Time Queue Monitoring	Limited	Available
      AI Prescription Assistance	Not Available	Available
      Medicine Image Recognition	Not Available	Available
      Medicine Shortage Prediction	Not Available	Available
      Family-Based Account Support	Limited	Available

   2. Evaluation of Intelligent Features

      The intelligent features of SmartMed were evaluated indi- vidually to assess their contribution to overall system perfor- mance.

      The AI-based prescription assistance feature provided rel- evant medicine suggestions based on historical data. While the final prescription decision remained with the doctor, the suggestions helped reduce consultation time and supported consistent treatment practices.

      The smart queue management feature allowed patients to monitor queue progress remotely, reducing congestion in clinic waiting areas. Feedback from simulated user scenarios indi- cated improved transparency and patient satisfaction.

      The medicine image recognition module successfully identi- fied medicines from captured images and retrieved correspond- ing information from the database. This reduced the likelihood of medicine misidentification during dispensing.

      The medicine shortage prediction feature analyzed inven- tory usage patterns and generated early alerts for low-stock medicines. This enabled proactive inventory management and reduced unexpected medicine shortages.

   3. Comparison with Existing Systems

      A comparative analysis was conducted between SmartMed and traditional clinic management systems discussed in pre- vious studies. Most existing systems focus on basic function- alities such as appointment scheduling and electronic medical records. In contrast, SmartMed integrates intelligent features to support decision-making and proactive management.

      Table VI summarizes the comparison between traditional systems and the proposed SmartMed system.

      The comparison highlights that SmartMed provides addi- tional intelligent capabilities that are not commonly found in traditional clinic management systems. These features enhance operational efficiency and improve the overall healthcare ser- vice experience.

   4. Discussion

   The results demonstrate that the SmartMed system effec- tively addresses several limitations identified in existing clinic management solutions. By integrating intelligent decision- support features with core clinic functionalities, the system improves efficiency without increasing system complexity.

   The modular design of SmartMed allows clinics to adopt intelligent features gradually based on their operational needs. Although the evaluation was conducted using simulated sce- narios, the results suggest that the system has strong potential for real-world deployment in small and medium-sized clinics. Future evaluations involving real clinical data and long-term usage analysis can further validate the effectiveness of the

   system and provide insights for additional enhancements.

8. CONCLUSION AND FUTURE WORK

This paper presented SmartMed, an AI-driven clinic and pharmacy management system designed to improve oper- ational efficiency and enhance patient experience in small and medium-sized healthcare clinics. The proposed system integrates core clinic functionalities such as appointment scheduling, prescription management, inventory tracking, and payment handling with intelligent features including AI-based prescription assistance, real-time queue monitoring, medicine image recognition, family-based account management, and medicine shortage prediction. The implementation and eval- uation results demonstrate that SmartMed can reduce patient waiting time, improve workflow coordination, and support proactive medicine management when compared to traditional clinic management systems.

Although the system was evaluated using functional testing and simulated usage scenarios, the results indicate strong potential for real-world deployment. As future work, the system can be extended by incorporating real clinical data for long-term performance evaluation and model refinement. Additional enhancements may include integrating advanced analytics for personalized treatment recommendations, ex- panding support for teleconsultation services, and improving interoperability with external healthcare systems. Further se- curity enhancements and regulatory compliance measures can also be explored to support wider adoption in diverse clinical environments.

1. M. Pise, S. Pathak, S. Pednekar, and N. Patil, Clinic Management System, International Journal of Creative Research Thoughts (IJCRT), vol. 6, no. 2, pp. 717720, 2018.

2. C. Yuvarajan, S. Nithya Priya, and A. Bhoomadevi, Designing a mobile health platform for effective medical records management in hospitals, Discover Applied Sciences, vol. 7, article 305, 2025.

3. J. Muhammad and S. Garba, Web-based Clinic Management System (CMS), International Journal of Science and Engineering Applications, vol. 8, no. 5, pp. 131135, 2019.

4. A. A. K. Azameti, G. Koi-Akrofi, N. Agbodo, and J. K. Amegadzie, Optical Clinic Management System, University of Professional Stud- ies, Accra, Ghana, 2022.

   REFERENCES

   1. R. Ramli, K. R. Purba, A. N. K. Mohd Nor, and A. Kuzaimi, The Development of Clinic Management System Mobile Application with Integrated Appointment, Prescription, and Payment Systems, in Proc. IEEE Control and System Graduate Research Colloquium (ICSGRC), 2022.

   2. J. E. E. Goh, M. L. I. Goh, L. P. Abad, M. C. F. Raguro, T. J. S. Awat,

      and K. C. Marqueses, Web-Based Clinic Management System with Patient Satisfaction Analysis Using Sentiment Analysis, in Proc. IEEE Int. Conf. on E-Education, E-Business, E-Management and E-Learning (IC4e), 2025.

   3. H. N. Marbella, I. A. Akbar, and B. Setiawan, Design and development of a web-based patient management information system, Procedia Computer Science, vol. 234, pp. 17991806, 2024.

   4. C. Offerman, J. Bourgeois, and A. Bozzon, Embedding caring into remote patient management systems, in Proc. Nordic Conf. Human- Computer Interaction (NordiCHI), 2024.

   5. A. R. Qawasmeh, D. Awni, R. Mohammed, R. Sabri, and G. Ahmad, CLINIC: A Web Healthcare Management System for Enhancing Clin- ical Services, The Hashemite University, Jordan, 2022.

   6. A. A. K. Azameti, G. Koi-Akrofi, N. Agbodo, and J. K. Amegadzie, A Model-Driven Optical Clinic Management Systems: Systematic Soft- ware Engineering Approach, EAI Endorsed Transactions on Pervasive Health and Technology, vol. 8, no. 30, 2022.