Project Report

On
“AI HEALTHCARE CHATBOT”

Submitted to
Savitribai Phule Pune University, Pune
In Partial Fulfillment of B.E. Computer Engineering
B.E. Semester I

Submitted by

Mr. Muhammed Umar Shaikh CO4054

Mr. Syed Mustafa Bilgrami CO4008
Mr. Hamza Asif Shaikh CO4053
Mr. Zaid Shakir Pathan CO4041
Mr. Siddique Ashpak Mujawar CO4036

Under the Guidance of

Prof. Jareena Shaikh

Department of Computer Engineering

KJEI’S Trinity College of Engineering and Research,
Pune-48
Academic Year 2024-25
 Department Of Computer Engineering

Certificate

This is to certify that the Course report entitled “AI HEALTHCARE CHAT-
BOT” being submitted by Muhammed Umar Shaikh,Syed Mustafa,Hamza Asif
Shaikh,Zaid Shakir Pathan,Siddique Ashpak Mujawar is a bona fide work car-
ried out under the supervision and guidance of Prof. Jareena Shaikh in fulfillment of
the requirement for the B.E. Computer Engineering course of Savitribai Phule Pune
University, Pune, for the academic year 2024-25.

Prof. Jareena Shaikh Dr. Geetika Narang

Guide, Computer Engineering Department HOD, Computer Engineering Department
Trinity College of Engineering and Research,
Pune

Date: Place:
Acknowledgement

We would like to extend our sincere appreciation to Prof. Jareena Shaikh of the
Computer Engineering Department for providing technical support, valuable guidance,
and constant encouragement throughout this project. Her insight and feedback have been
crucial in completing this stage of the project report.
We would also like to thank Dr. Geetika Narang, Head of the Computer Engineer-
ing Department, for her continued support.
Finally, we would like to express gratitude to all faculty members and friends from the
Computer Engineering Department for their suggestions and contributions to the success
of this report.

Name Roll No.

Mr. Muhammed Umar Shaikh [CO4054]
Mr. Syed Mustafa Bilgrami [CO4008]
Mr. Hamza Asif Shaikh [CO4053]
Mr. Zaid Shakir Pathan [CO4041]
Mr. Siddique Ashpak Mujawar [CO4036]
Abstract

This project introduces an AI-based healthcare chatbot designed to improve patient ac-
cess to healthcare services. The chatbot can assess symptoms, schedule appointments
with healthcare professionals, and offer mental health support. By leveraging Natural
Language Processing (NLP) and geolocation services, the chatbot provides relevant med-
ical advice and appointment options based on the user’s location.
The main objective is to ease the burden on healthcare facilities by providing ini-
tial medical guidance and facilitating patient management. This project addresses gaps
in healthcare delivery in underserved regions. The expected outcome is a functional,
user-friendly chatbot that bridges the gap between patients and healthcare professionals,
especially in remote areas.

Keywords: Artificial Intelligence, Healthcare, Chatbot, Natural Language Process-

ing, Appointment Scheduling
Contents

1 Introduction 9
1.1 Problem Statement . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
1.2 Objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
1.3 Scope of the Project . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
1.4 Motivation for the Project . . . . . . . . . . . . . . . . . . . . . . . . . . 10

2 Literature-Review 11
2.0.1 Scope of the Literature Review . . . . . . . . . . . . . . . . . . . 11

3 Requirements Analysis (Phase I) 12

3.1 User Requirements . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
3.2 Functional Requirements . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
3.3 Non-functional Requirements . . . . . . . . . . . . . . . . . . . . . . . . 13
3.4 System Requirements: Frontend, Backend, Database, Cloud . . . . . . . 13
3.4.1 Frontend . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
3.4.2 Backend . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
3.4.3 Database . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
3.4.4 Cloud Infrastructure . . . . . . . . . . . . . . . . . . . . . . . . . 14

4 Initial Design (Phase II) 15

4.1 Design Paradigm Chosen . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
4.2 System Architecture Overview . . . . . . . . . . . . . . . . . . . . . . . . 15
4.3 Initial UML Diagrams . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
4.3.1 Use Case Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . 17
4.3.2 Class Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
4.3.3 Activity Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
4.3.4 Sequence Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . 18

5 Project Timeline 20

6 Challenges Anticipated 22
6.1 Technical Challenges . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22
 6.2 Resource Challenges . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22
6.3 Project Scope Challenges . . . . . . . . . . . . . . . . . . . . . . . . . . . 23

7 Conclusion and Next Steps 24

7.1 Summary of Current Progress . . . . . . . . . . . . . . . . . . . . . . . . 24
7.2 Plan for Future Phases . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24

8 Conclusion 26
Table of Contents

No. Section Page

1 Introduction 7

1.1 Problem Statement 7

1.2 Objectives 7

1.3 Scope of the Project 7

1.4 Motivation for the Project 8

2 Literature Review 9

2.0.1 Scope of the Literature Review 9

3 Requirements Analysis (Phase I) 10

3.1 User Requirements 10

3.2 Functional Requirements 10

3.3 Non-functional Requirements 11

3.4 System Requirements: Frontend, Backend, 11

Database, Cloud

3.4.1 Frontend 11

3.4.2 Backend 11

3.4.3 Database 12

3.4.4 Cloud Infrastructure 12

No. Section Page

4 Initial Design (Phase II) 13

4.1 Design Paradigm Chosen 13

4.2 System Architecture Overview 13

4.3 Initial UML Diagrams 14

4.3.1 Use Case Diagram 15

4.3.2 Class Diagram 15

4.3.3 Activity Diagram 15

4.3.4 Sequence Diagram 16

5 Project Timeline 18

6 Challenges Anticipated 20

6.1 Technical Challenges 20

6.2 Resource Challenges 20

6.3 Project Scope Challenges 21

7 Conclusion and Next Steps 22

7.1 Summary of Current Progress 22

7.2 Plan for Future Phases 22

8 Conclusion 24
List of Diagrams

Fig. No. Name Page No.

4.3.1 Use Case Diagram 14

4.3.2 Class Diagram 14

4.3.3 Activity Diagram 14

4.3.4 Sequence Diagram 15

Chapter 1

Introduction

The AI Healthcare Chatbot project aims to address common healthcare challenges, espe-
cially in regions with limited access to doctors and healthcare professionals. The chatbot
will serve as a primary point of contact for patients, offering symptom checks, appoint-
ment booking, and mental health support.
The need for such a solution has become more evident with the rise of telemedicine
and the growing demand for instant, accessible healthcare. By leveraging AI and Natural
Language Processing (NLP), the chatbot provides users with quick access to medical
advice and healthcare services.

1.1 Problem Statement

Patients often face long waiting times, limited access to medical professionals, and a lack
of mental health support in underserved areas. The goal of this project is to create a
chatbot that can provide basic healthcare guidance, book appointments, and offer mental
health resources to reduce these barriers.

1.2 Objectives
- To create an AI-based chatbot that can assess patient symptoms and provide recom-
mendations. - To allow users to schedule medical appointments through a user-friendly
interface. - To provide mental health support by offering relevant resources. - To improve
healthcare access in remote or underserved regions.

1.3 Scope of the Project

The project will cover the development of a chatbot capable of handling healthcare-related
queries, scheduling appointments, and offering mental health guidance. The system will
be scalable to allow for additional features in the future, such as video consultations and
integration with wearable devices for health monitoring.

1.4 Motivation for the Project

The motivation for this project stems from the increasing demand for accessible health-
care, especially in underserved areas. Telemedicine has emerged as a critical tool for
bridging gaps in healthcare access. An AI-powered chatbot can complement traditional
healthcare systems by providing quick, automated assistance to users, helping them nav-
igate their medical concerns more efficiently.
Chapter 2

Literature-Review
Table 2.1: Summary of Reviewed Papers on Chatbot Technology and Healthcare

Paper Title Authors Key Contributions

An Overview of Chat- Eleni Adamopoulou, Explores chatbot history,
bot Technology Lefteris Moussiades classification, and design
challenges
AI-based Healthcare M.V. Patil, Sub- Provides medical advice and
Chatbot System hawna, Priya Shree, reduces doctor burden in
Puneet Singh underserved areas
Design and Develop- Rohit Tamrakar, Ni- Surveys chatbot design and
ment of CHATBOT: raj Wani applications; suggests inte-
A Review gration with CAD systems
AI Healthcare Chat- Niraj A. Wanjari, Assists in early diagnosis
bot Using NLP Roshan S. Ghosare, et and lowers healthcare costs
al.
Personal Healthcare R Jegadeesan, Dava Classifies disease severity
Chatbot for Medical Srinivas, et al. and offers treatment sugges-
Suggestions tions
AI-Based Healthcare Riddhi Shetty, Ankita Improves healthcare access,
Chatbot Bhosale, et al. especially during COVID-
19

2.0.1 Scope of the Literature Review

The reviewed papers highlight the growing importance of AI and NLP-based chatbots,
particularly in healthcare. These technologies improve patient interaction, facilitate ini-
tial diagnoses, and reduce healthcare costs, particularly in underserved regions. Addi-
tionally, chatbots play a role in diverse fields such as education, marketing, and CAD
systems, proving their broad applicability. Chatbots also improve healthcare accessibil-
ity, especially in times of crisis, such as during the COVID-19 pandemic.
Chapter 3

Requirements Analysis (Phase I)

3.1 User Requirements

The AI Healthcare Chatbot must meet the following user requirements:

• Allow users to input symptoms and receive healthcare advice.

• Enable users to book, modify, or cancel medical appointments.

• Provide users with mental health support and resources.

• Support multilingual functionality for users from different regions.

• Offer a user-friendly interface for ease of access via mobile and web platforms.

• Ensure data privacy and secure handling of medical information.

3.2 Functional Requirements

The system must fulfill the following functional requirements:

• Accept and process text and voice input from users for symptom checking.

• Provide real-time responses to symptom queries using an AI-based symptom

checker.

• Offer appointment booking with available doctors based on geolocation.

• Provide mental health resources, such as stress relief techniques and emotional
support.

• Store and manage user data securely, allowing users to view their appointment
history.
3.3 Non-functional Requirements
Non-functional requirements include:

• Performance: The chatbot should respond within 2-3 seconds of user input.

• Scalability: The system must be scalable to support multiple concurrent users.

• Security: Ensure HIPAA-compliant data security and encryption for medical

records.

• Availability: The system should be available 99.9% of the time, ensuring constant
access to users.

• Multilingual Support: The system should support multiple languages for user
inputs and responses.

• Reliability: The system must be robust, with minimal downtime, and ensure data
integrity.

3.4 System Requirements: Frontend, Backend,

Database, Cloud

3.4.1 Frontend
The frontend of the AI Healthcare Chatbot will be built using **ReactJS**. This frame-
work is chosen for its responsive design capabilities, making the system accessible on both
web and mobile platforms. Key aspects of the frontend include:

• User-friendly interface that supports both text and voice inputs.

• Display of real-time chatbot responses, appointment booking, and symptom check

results.

• Integration of geolocation services to suggest nearby healthcare professionals.

• Multilingual interface allowing users to choose their preferred language.

3.4.2 Backend
The backend of the system will be developed using **Flask (Python)**, which will handle
requests from the frontend, process user data, and interact with external services. Key
aspects of the backend include:
 • API handling for symptom checking, appointment scheduling, and mental health
support.

• Data processing for user queries and real-time response generation using NLP (Nat-
ural Language Processing).

• Secure handling of user data, ensuring encryption and data privacy.

• Interaction with external APIs (e.g., geolocation, medical databases).

3.4.3 Database
The system will use **MySQL** for managing and storing user data. Key aspects of the
database include:

• Storage of user information such as profiles, medical history, and appointments.

• Ensuring data integrity and secure access to sensitive information.

• Support for scalable, relational data storage to handle high volumes of data effi-
ciently.

• Daily backups to prevent data loss and ensure recovery in case of system failures.

3.4.4 Cloud Infrastructure

The system will be hosted on a cloud platform such as **Google Cloud** or **AWS
(Amazon Web Services)** to ensure scalability and reliability. Key aspects of the cloud
infrastructure include:

• Scalability to handle multiple users concurrently without performance degradation.

• Elastic load balancing to distribute user requests evenly across servers.

• Secure cloud storage with regular updates to meet data privacy requirements.

• Automated failover and disaster recovery to ensure high availability (99.9% uptime).
Chapter 4

Initial Design (Phase II)

4.1 Design Paradigm Chosen

For the development of the AI Healthcare Chatbot, the Agile methodology has been
chosen. Agile allows for iterative development, where features can be added incrementally.
This approach is ideal given the complexity of the project and the need for frequent
updates based on feedback. Key aspects of Agile methodology that benefit this project
include:

• Flexibility: Agile allows for changes and refinements as the chatbot evolves, ac-
commodating new features such as additional languages or extended mental health
support.

• Incremental Development: Features such as symptom checking, appointment book-

ing, and mental health support can be implemented in separate sprints, making it
easier to test and refine each component.

• Frequent Feedback: Stakeholders and end-users can provide feedback after each
sprint, ensuring that the chatbot meets user needs more effectively.

• Risk Mitigation: Agile’s iterative approach allows for early detection and mitigation
of potential risks, ensuring the project stays on track.

4.2 System Architecture Overview

The system architecture of the AI Healthcare Chatbot is composed of several intercon-
nected components that work together to provide the user with a seamless experience.
These components include:

• User Interface: The frontend interface that allows users to interact with the system
through a web or mobile platform, either by text or voice input.
 • Natural Language Processing (NLP) Engine: The component responsible for inter-
preting user input and generating appropriate responses.

• Symptom Checker: A backend module that processes user symptoms, searches the
medical database, and provides advice based on the information received.

• Appointment Scheduler: A component that allows users to book appointments with

healthcare professionals, leveraging geolocation to suggest nearby providers.

• Mental Health Support: Provides users with resources and advice for non-critical
mental health issues such as stress or anxiety.

• Backend Server: The core of the system where all data is processed and stored
securely, including user profiles, medical histories, and appointments.

• External APIs: APIs that provide external services such as geolocation for finding
nearby doctors and medical databases for symptom matching.

The diagram below represents the high-level architecture of the system:

Figure 4.1: System Architecture Overview

4.3 Initial UML Diagrams

To better understand the design of the AI Healthcare Chatbot, we will utilize **UML
diagrams** to represent the system’s structure and data flow. These diagrams help
visualize the relationships between various components of the system and how data moves
through the system.
4.3.1 Use Case Diagram
The Use Case diagram provides an overview of the interactions between users (patients,
doctors, and admins) and the system. This diagram identifies the main use cases such as
symptom checking, appointment scheduling, and mental health support.

Figure 4.2: Sequence Diagram for AI Healthcare Chatbot

4.3.2 Class Diagram

The Class Diagram provides a static view of the system, showing the structure of the AI
Healthcare Chatbot in terms of classes, attributes, and relationships between them. The
main classes include User, SymptomChecker, AppointmentScheduler, MentalHealthSup-
port, and more.

Figure 4.3: Sequence Diagram for AI Healthcare Chatbot

4.3.3 Activity Diagram

The Activity Diagram shows the workflow of the chatbot, focusing on how users interact
with the system. This diagram represents different actions such as symptom checking,
booking an appointment, or receiving mental health guidance.

Figure 4.4: Sequence Diagram for AI Healthcare Chatbot

4.3.4 Sequence Diagram

The Sequence Diagram represents the interaction between objects in the system over
time. It shows how the user interacts with the chatbot, from inputting symptoms to
receiving responses, and how backend components process these requests.
Figure 4.5: Sequence Diagram for AI Healthcare Chatbot
Chapter 5

Project Timeline

The project timeline for the AI Healthcare Chatbot is structured into several key phases,
beginning with initial research and review presentations, followed by design, development,
and deployment. Each phase is designed to ensure incremental progress and successful
completion of the project by June.
Phase 1: Initial Research and Documentation (July – November)
The project started in July with an initial focus on gathering resources, preparing pre-
sentations, and conducting a literature review. This phase included creating the project
proposal, identifying research papers for the literature review, and outlining the chatbot’s
objectives and scope.
Phase 2: Review Presentations (July – November)
To refine the project concept and receive feedback, a series of presentations were con-
ducted:
Review 1: covered the problem statement, project motivation, and objectives.
Review 2: added the literature review, feature set, and scope.
Review 3: introduced the requirement analysis.
Review 4: focused on UML diagrams, including use case, class, and activity diagrams.
These presentations were critical in shaping the project’s foundation and setting clear
requirements.
Phase 3: System Design and Prototype (December – January)
With a well-defined project scope, the next phase involves designing the system architec-
ture and creating a user interface prototype. During this phase, the team will develop the
UI/UX prototype, finalize the system’s architecture, and create a database schema. The
goal is to establish a comprehensive design document and initial prototype by January.
Phase 4: Development (February – March)
The development phase involves building both the backend and frontend of the chatbot,
implementing NLP for text processing, and integrating APIs for appointment scheduling
and geolocation. This phase will culminate in a minimum viable product (MVP) that
can demonstrate core chatbot functionality.
 Phase 5: Testing (April)
Following development, rigorous testing will be conducted to ensure the system’s stability,
usability, and performance. This phase includes functional testing, usability testing, and
performance testing. The goal is to identify and resolve any issues before deployment.
Phase 6: Deployment (May)
Once testing is complete, the chatbot will be deployed to a cloud platform. User docu-
mentation will be prepared to guide end-users in using the system effectively. This marks
the official launch of the AI Healthcare Chatbot.
Phase 7: Maintenance and Final Documentation (June)
In the final phase, the team will monitor the system’s performance, provide post-
deployment support, and complete the final project report. This phase ensures the
chatbot’s long-term reliability and the completion of all required documentation before
project submission.
This structured timeline allows for organized development, with ample time for research,
iterative testing, and deployment. Adjustments may be made based on feedback or
unforeseen challenges to ensure timely project completion.
Chapter 6

Challenges Anticipated

In the development of the AI Healthcare Chatbot, several challenges are anticipated.

These challenges can be grouped into three main categories: technical, resource-based,
and project scope-related. Addressing these challenges will be crucial for the successful
implementation of the project.

6.1 Technical Challenges

The technical challenges of this project relate primarily to the complexity of building a
reliable, efficient, and secure AI-powered chatbot. Specific challenges include:
• Natural Language Processing (NLP) Accuracy: Ensuring the chatbot accu-
rately interprets user inputs across a variety of languages and medical terminology
is challenging, especially when users use non-standard phrasing.

• Data Security and Privacy: As the chatbot will handle sensitive medical data,
strict compliance with healthcare data privacy regulations (e.g., HIPAA) is required.
This necessitates robust data encryption and security practices.

• System Scalability: The chatbot needs to handle a potentially high number of

simultaneous users without performance degradation, requiring scalable backend
infrastructure.

• Integration with External APIs: Integrating various APIs for geolocation,

symptom checking, and appointment scheduling can be complex and may result
in compatibility issues.

6.2 Resource Challenges

Resource constraints can limit the scope and efficiency of the project. The main resource
challenges anticipated include:
 • Access to Domain Experts: Developing a reliable medical chatbot requires input
from healthcare professionals to verify the medical accuracy of responses.

• Funding and Budget Constraints: Procuring high-quality datasets, maintain-

ing cloud resources, and ensuring continuous testing might stretch the project’s
budget.

• Human Resources: The project demands skilled personnel in AI, data security,
and software development, which may be challenging to secure within the project’s
timeline and budget.

• Training Data Acquisition: Obtaining and preprocessing sufficient high-quality

medical data for the chatbot’s NLP engine is both costly and time-intensive.

6.3 Project Scope Challenges

Defining a clear scope while ensuring that the chatbot meets all required functionalities
can be difficult. Specific scope-related challenges include:

• Feature Creep: As the project progresses, there may be a temptation to add more
features, which could lead to scope creep and delay the project timeline.

• Balancing Functionality with Usability: Ensuring the chatbot is user-friendly

while providing robust functionality can be challenging, as adding more features
may complicate the user interface.

• Ensuring Comprehensive Testing: The chatbot must be rigorously tested for

different scenarios to guarantee reliability, which can be difficult to achieve given
time and resource constraints.

• Adapting to User Feedback: During pilot testing, user feedback might necessi-
tate significant changes, which could affect both the project timeline and scope.

Addressing these challenges proactively will be key to the successful delivery of a reliable,
effective, and user-friendly AI healthcare chatbot. Continuous monitoring, feedback, and
iterative development will help mitigate these anticipated challenges.
Chapter 7

Conclusion and Next Steps

This section provides a summary of the project’s current progress and outlines the plan
for future phases. With a solid foundation established, the project is set to move into the
core development stages.

7.1 Summary of Current Progress

The AI Healthcare Chatbot project has successfully completed the initial research, plan-
ning, and design phases. Key milestones achieved so far include:
Research and Literature Review: Relevant research papers have been gathered, and a lit-
erature review has been completed to understand current advancements and limitations
in healthcare chatbots.
Project Definition and Scope: Through a series of presentations, the problem statement,
objectives, motivation, and project scope were clearly defined and refined based on feed-
back.
Requirement Analysis: An in-depth requirement analysis has been performed, establish-
ing the functional and non-functional requirements of the chatbot.
System Design: High-level design documents and initial UML diagrams (use case, class,
and activity diagrams) have been created to outline the chatbot’s architecture and inter-
action flow.
This progress establishes a strong groundwork for the development and testing phases
that follow.

7.2 Plan for Future Phases

The next steps in the project focus on the technical development, testing, and deployment
of the AI Healthcare Chatbot. The timeline for these phases is as follows:
Development Phase (February – March): The chatbot’s backend and fron-
tend will be developed, focusing on integrating Natural Language Processing (NLP)
capabilities for interpreting user inputs, along with API integrations for features like
appointment scheduling and geolocation. This phase aims to deliver a minimum viable
product (MVP) by the end of March.

Testing Phase (April): Following development, comprehensive testing will be

conducted, including functional, usability, and performance testing. Any issues identified
during this phase will be resolved to ensure the chatbot is robust and user-friendly.

Deployment Phase (May): The fully tested chatbot will be deployed to a cloud
platform, making it accessible to users. Documentation and a user guide will also be
prepared to assist users in navigating the system’s features.

Post-Deployment and Maintenance (June): After deployment, the system’s

performance will be closely monitored, and any post-launch issues will be addressed.
The final project report and documentation will be completed, ready for submission.
The project remains on track to meet all milestones within the designated timeline, with
an emphasis on iterative testing and refinement to ensure a reliable and efficient AI
healthcare chatbot by project completion.
Chapter 8

Conclusion

In conclusion, the AI Healthcare Chatbot project addresses critical challenges in health-

care accessibility, especially for underserved regions and individuals seeking quick, reliable
health information. By leveraging artificial intelligence and natural language process-
ing (NLP), the chatbot aims to provide users with symptom assessment, appointment
scheduling, and mental health support, thereby improving patient engagement and re-
ducing the workload on healthcare providers.
Throughout this project, significant progress has been made in defining the problem
statement, conducting an extensive literature review, and developing a comprehensive
system design. The initial phases included a detailed requirement analysis and the cre-
ation of foundational design documents, including UML diagrams to clarify the chatbot’s
structure and interactions. These preparatory stages have laid a solid groundwork for
the development and testing phases that follow.
As the project moves into the technical development phase, the focus will be on
building a functional prototype that meets the identified requirements and passes rigorous
testing. The final product will not only provide essential healthcare support but will also
demonstrate the potential of AI-based solutions to enhance healthcare delivery, especially
in areas with limited resources.
Overall, the AI Healthcare Chatbot project is expected to make a positive impact
by increasing healthcare accessibility, promoting mental wellness, and providing initial
support to patients. Upon successful completion, this project will showcase the practical
application of AI in healthcare, offering a scalable and valuable tool for both patients
and healthcare providers.
Bibliography

[1] Wanjari, N. A., Ghosare, R. S., Dhote, S. K., Meshram, A. P., & Bhandekar, R. (2022).
AI Healthcare Chatbot Using Natural Language Processing. International Research
Journal of Modernization in Engineering, Technology, and Science, 4(5), 1219-1222.
Retrieved from https://www.irjmets.com

[2] Tamrakar, R., & Wani, N. (2021). Design and Development of Chatbot: A Review.
Sardar Vallabhbhai National Institute of Technology, Surat, India. Retrieved from
https://www.researchgate.net/publication/351228837

[3] Shetty, R., Bhosale, A., Verma, P., & Phalke, A. (2022). AI Based Healthcare Chatbot.
Vasantdada Patil Pratishthan’s College of Engineering, Mumbai, India. Retrieved
from https://ssrn.com/abstract=4109100

[4] Adamopoulou, E., & Moussiades, L. (2020). An Overview of Chatbot Technology.

In AIAI 2020: Artificial Intelligence Applications and Innovations (Vol. 584, pp.
373–383). Springer. https://doi.org/10.1007/978-3-030-49186-4_31

[5] Patil, M.V., Subhawna, Shree, P., & Singh, P. (2021). AI based healthcare chat bot
system. International Journal of Scientific & Engineering Research, 12(7), 668-671.
Available at: https://www.researchgate.net/publication/362491736

[6] Jegadeesan, R., Srinivas, D., Umapathi, N., Ganesan, K., & Venkateswaran, N.
(2023). Personal Healthcare Chatbot for Medical Suggestions Using Artificial In-
telligence and Machine Learning. European Chemical Bulletin, 12(S3), 6004–6012.
https://doi.org/10.31838/ecb/2023.12.s3.670