MedAlert Synopsis

A Project Synopsis on
MedAlert
Submitted in Partial fulfillment of requirement for the award of
Diploma in
COMPUTER ENGINEERING
MAHARASHTRA STATE BOARD OF TECHNICAL EDUCATION

MUMBAI
At
Submitted by
Nikhil Rathod Vivek Raut
Aditya Tarwale Pawan Sontakke
Chetan Ahalle
Under the Guidance of
Prof. Nikhil Surkar

(Dept. CO, APN)
Department of Computer Engineering
Academic Year 2024-25
AGNIHOTRI POLYTECHNIC NAGTHANA ROAD, SINDI
(MEGHE), WARDHA
1. ABSTRACT:
MedAlert is a mobile app designed to improve medication adherence by providing timely
reminders and detailed medicine information. It features a chatbot for health-related
queries, enhancing user interaction. Built using Java and XML, it caters especially to the
elderly or those with complex medication routines, promoting better medication
management.
1.1 Keywords: Medication Management, Pill Reminder App, Medicine Schedule
Tracker, Android Healthcare App & Digital Health Assistant.
2. INTRODUCTION
Medication adherence is vital for managing chronic conditions like diabetes and
hypertension. MedAlert helps users stay on track with timely medication reminders and
provides a chatbot for key information like dosage, side effects, and interactions. This
tool supports better health management, especially for individuals with complex
regimens, promoting better adherence and overall well-being with minimal effort.
3. PROBLEM STATEMENT
 Many patients struggle with adhering to medication schedules, leading to adverse
health outcomes.
 The problem is particularly significant among elderly populations and individuals
with complex medication regimens.
 Traditional solutions, such as alarms, lack flexibility and user interaction.
 MedAlert offers a user-friendly and efficient solution to address this issue by:
o Leveraging modern mobile technology.
o Providing flexible, interactive features to improve medication adherence.
4. OBJECTIVES
 To search and Retrieve Detailed Medicine Information.
 To get Assistance Through a Chatbot for Health Tips.
 To set Reminders for Taking Medications on Time.
5. METHODOLOGY
5.1 Algorithms used
A. Input Medication Name and Time
 Algorithm Used: Input Validation and Storage Algorithm
o Input Validation: Ensure that the entered medication name and time are valid. This
can involve simple string validation (e.g., no special characters in the medicine name)
and time validation (valid hours, minutes, etc.).
o Storage: Once validated, the input data can be stored in a local or cloud database (e.g.,
Firebase).
o Techniques:
 Data validation (regex for input format)
 Data entry and storage (CRUD operations for database)
B. Set Up Reminder Notifications

 Algorithm Used: Scheduling Algorithm
o This involves setting up notifications to trigger at the specified times. Scheduling can
be managed using Android's built-in tools like AlarmManager or WorkManager.
o The algorithm schedules reminders based on the user’s input and repeats them at the
necessary intervals (e.g., daily or weekly reminders).
o Techniques:
 Time-based scheduling: Using time triggers to set when notifications should go
off.
 Repeating events: For daily or recurring notifications.
C. Trigger Notifications Based on the Schedule

 Algorithm Used: Notification Triggering Algorithm
o Once the schedule is set, the app will use the AlarmManager or WorkManager to
trigger notifications at the right times.
o WorkManager is particularly useful for background tasks that need to be managed
over time, even when the app isn’t actively running.
o Techniques:
 AlarmManager: Schedule exact-time notifications.
 WorkManager: Handle background notifications, especially for periodic tasks.
D. Allow Users to Interact with the Chatbot for Medicine-Related Queries

 Algorithm Used: Chatbot Interaction Algorithm
o Decision Tree Algorithm: A simple chatbot can be implemented using a decision tree,
where user inputs lead to pre-defined responses based on specific keywords.
o Natural Language Processing (NLP): For more advanced interactions, an NLP model
(such as one integrated with Dialogflow or another AI service) can process and
understand user queries about medicines.
o Techniques:
 Decision Tree/Rule-Based Chatbot: For basic queries and responses.
 NLP Algorithms: If using AI-powered responses, machine learning models are
applied to understand and process user inputs.
5.2 Technology
 Frontend (XML): XML is used to design the app's responsive and user-friendly UI,
ensuring consistent layouts for the search interface and chatbot.
 Backend (Java): Java handles the app's logic, database access, and chatbot responses,
ensuring modularity and scalability.
 Database (Firebase): Firebase stores user and medication data in real time, ensuring
secure, fast access and synchronization across devices.
 Notification Management (AlarmManager/WorkManager): AlarmManager sets
reminders, while WorkManager handles background tasks like cloud syncs, ensuring
notifications even when the app isn’t running.
 Chatbot (Decision-Tree/Dialogflow): The chatbot uses decision-tree logic for basic
queries or Dialogflow for advanced NLP, providing intelligent, conversational
responses.
5.3 Hardware Components
 Smartphone with Android OS.
5.4 Software Components
 Android Studio for App Development: Android Studio, the official IDE for
Android, is crucial for building MedAlert, offering tools for designing UI, writing
Java code, and testing across different devices. It supports plugins for features like
notifications and chatbots, ensuring the app follows Android design guidelines.
 Java Development Kit (JDK) for Programming: The JDK provides essential
libraries and tools for coding MedAlert in Java. Its features support core
functionalities such as reminders and data management, enabling modular and
scalable code for future updates.
 Firebase for Database Storage: Firebase handles real-time database management for
MedAlert, syncing user data and medication schedules securely. It supports push
notifications for reminders and authentication, making it ideal for an app focused on
timely medication alerts.
6 BLOCK DIAGRAM
Fig 6.1: Block Diagram

7 BENEFITS
 Convenience: A One-Stop Solution for Medicine Management MedAlert

consolidates medicine reminders and detailed medication information in one
platform, eliminating the need for multiple apps and simplifying medication
management for users.
 Timely Medication Reminders MedAlert customizes reminders to ensure users take
their medications on time, whether daily or as prescribed, reducing the risk of missed
doses and promoting better health, especially for those with complex regimens.
 Easy-to-Use Chatbot for Medicine Information The chatbot feature provides quick
access to essential medication details like dosage and side effects, helping users stay
informed without having to search online or consult a pharmacist for basic
information.
 Simple and Intuitive Interface MedAlert’s user-friendly design allows easy
navigation, ensuring that users can set reminders and manage medications with
minimal effort, making it accessible for users of all ages and tech skills.
8 DRAWBACK
Potential drawbacks of MedAlert:
• Dependency on internet for accessing medicine data
• Currently limited to smartphones.
9 FUTURE SCOPE
 Expanded Medicine Database: The app's medicine database will grow, connecting
to larger, verified sources to cover a wider range of drugs, including rare medications,
improving its usefulness for diverse users.
 Health Logs & Symptom Tracking: Users will be able to track health metrics and
symptoms, integrating with the chatbot for personalized advice and allowing them to
monitor how medications impact their health.
 Voice-Activated Reminders: Voice commands will be added for hands-free
interactions, making MedAlert more accessible, especially for elderly or disabled
users, and potentially integrating with smart home devices like Alexa.
 AI Health Predictions: MedAlert will use AI to predict health risks, offering
proactive suggestions based on user data, making it a tool for both monitoring and
preventing health issues.
10 CONCLUSION
MedAlert is a practical solution to enhance medication adherence, especially for people
with chronic conditions or elderly users. It’s an efficient, easy-to-use tool that leverages
technology to improve health outcomes through timely reminders and quick access to
medicine information. As mobile health applications become more prevalent, MedAlert
stands out with its integrated chatbot and user-focused features.
11 REFERENCES
[1] Joseph Weizenbaum, "ELIZA—A Computer Program for the Study of Natural
Language Communication Between Man and Machine," Communications of the ACM,
vol. 9, no. 1, pp. 36–45, January 1966.
[2] Richard Wallace, "The Anatomy of A.L.I.C.E.," 2009 AAAI Spring Symposium on
Emotion, Personality, and Social Behavior, Palo Alto, 2009.
[3] IBM, "Watson: A System Designed for Answering Questions in Open Domain," IBM
Journal of Research and Development, vol. 56, no. 3.4, pp. 1-14, 2012.
[4] Google Cloud, "Dialogflow: Enabling Conversational AI," Google Research White
Paper, Mountain View, 2016.
[5] Ada Health, "Adaptive AI in Medical Chatbots," Journal of Medical Systems, vol. 44,
no. 6, pp. 112-120, 2020.

MedAlert Synopsis

Uploaded by

Copyright:

Available Formats

MedAlert Synopsis

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

MedAlert Synopsis

Uploaded by

Copyright:

Available Formats

A Project Synopsis on

MAHARASHTRA STATE BOARD OF TECHNICAL EDUCATION

Under the Guidance of

Prof. Nikhil Surkar

B. Set Up Reminder Notifications

C. Trigger Notifications Based on the Schedule

D. Allow Users to Interact with the Chatbot for Medicine-Related Queries

5.4 Software Components

Fig 6.1: Block Diagram

 Convenience: A One-Stop Solution for Medicine Management MedAlert

You might also like

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.