© 2024 IJNRD | Volume 9, Issue 3 March 2024| ISSN: 2456-4184 | IJNRD.

ORG

HEALTHCARE CHATBOT SYSTEM

Mark Lawrence MD Istiyak Mohd Aman

CSE CSE CSE
SHARDA UNIVERSITY SHARDA UNIVERSITY SHARDA UNIVERSITY
GREATER NOIDA, INDIA GREATER NOIDA, INDIA GREATER NOIDA, INDIA
2020493669.mark@ug.sharda.ac.in 2020560263.mdistiyak@ug.sharda.ac.in 2020457438.mohd@ug.sharda.ac.in

The project's core focus lies in developing an AI-powered healthcare

chatbot system, acknowledging its potential to revolutionize healthcare
Abstract—This paper presents the development and accessibility and delivery, echoing the sentiments of Muthukrishnan et
implementation of an AI-powered healthcare chatbot system al. [5]. This system aspires to provide users with a user-friendly
designed to offer efficient and personalized medical assistance. platform for seeking preliminary medical advice, symptom analysis,
Employing Python in PyCharm IDE and Flask framework, the and guidance, aligning with the findings of Zhang et al. [3]. Leveraging
system facilitates user login, symptom input, accurate disease AI algorithms and sophisticated natural language processing (NLP)
predictions, tailored solutions, and doctor recommendations. techniques, the chatbot can simulate human-like interactions, ensuring
Leveraging Pandas, NumPy, Sklearn, and gensim libraries, accurate responses and medical information, in line with the
machine learning algorithms drive disease prediction and solution methodologies outlined by Joel et al. [2].
recommendation functionalities. Evaluation results demonstrate
commendable accuracy in disease prediction and relevance in The significance of this project transcends conventional healthcare
solution provision. Ethical considerations, encompassing data paradigms, supported by the insights of Yamin et al. [1]. By
privacy and user trust, are meticulously addressed, marking a complementing traditional healthcare services, this chatbot system
significant advancement in enhancing healthcare accessibility and aims not only to enhance accessibility but also to empower users with
paving the way for future developments in AI-driven healthcare timely and reliable health information. The project envisages a future
services. where healthcare is more democratized, resonating with the aspirations
presented by Arpnikanondt et al. [4] and Muthukrishnan et al. [5],
Keywords:-Health care chatbot , python , Disease Prediction , where users can proactively engage with healthcare resources through
Personalized solution , Machine learning , user trust , pandas, sk- a conversational interface.
learn.
Despite their potential, as highlighted by Zhang et al. [3], healthcare
I. INTRODUCTION chatbots face significant hurdles in their widespread adoption.
The integration of artificial intelligence (AI) into healthcare services Ensuring the accuracy and reliability of medical information dispensed
has ushered in a new era of accessibility and convenience, aligning with by chatbots remains a primary concern, echoing the sentiments of
the findings of Yamin et al. [1] and Zhang et al. [3]. Healthcare Yamin et al. [1] and Joel et al. [2]. Additionally, safeguarding user
chatbots, as identified by Joel et al. [2], represent a groundbreaking privacy and maintaining data security in healthcare interactions is
innovation. These AI-driven conversational agents are designed to crucial but complex in a digital ecosystem, where sensitive health
engage with users, offering medical information, assistance, and information is exchanged, as acknowledged by Arpnikanondt et al. [4].
guidance. Their emergence addresses the pressing need for scalable and
user-centric healthcare solutions.
Furthermore, accurately interpreting and comprehending user queries,
In conventional healthcare systems, as highlighted by Arpnikanondt et especially those concerning intricate medical conditions, presents
al. [4], accessibility remains a significant hurdle. Long waiting times another layer of challenge, corroborated by Muthukrishnan et al. [5].
for appointments, geographical limitations, and resource constraints Overcoming these challenges necessitates the development of robust
often impede timely access to healthcare services. The advent of AI models, stringent ethical considerations, and continual
healthcare chatbots signifies a paradigm shift in healthcare delivery, enhancements in natural language understanding.
offering users immediate access to medical guidance and support
round-the-clock, irrespective of their location. Developing a healthcare chatbot system that navigates these obstacles
while ensuring the precision of medical information and preserving
user privacy stands as the primary goal of this project, aligning with
the objectives outlined by the aforementioned research papers.
IJNRD2403146 International Journal of Novel Research and Development (www.ijnrd.org) b403
c403
 © 2024 IJNRD | Volume 9, Issue 3 March 2024| ISSN: 2456-4184 | IJNRD.ORG

ensures the chatbot can access relevant user information (with consent)
and provide tailored advice based on individual medical histories [14].
II.MOTIVATION
In many healthcare systems, disparities exist in terms of accessibility,
especially for individuals residing in remote or underserved areas.
Long wait times for appointments, limited access to healthcare IV. OBJECTIVE OF THE PROJECT
professionals, and geographical barriers can hinder individuals from The primary objective is to create an interactive chatbot capable of
seeking timely medical advice [6]. This creates a gap in healthcare engaging users in natural language conversations. The chatbot should
accessibility, leaving many without the guidance and support they understand user queries, provide accurate medical information, and
require [7]. offer preliminary guidance based on symptoms or health concerns.The
Moreover, in an era where information is readily available, there's a project aims to ensure the accuracy and reliability of medical
growing demand among users for immediate access to medical information provided by the chatbot. This includes implementing
information. Patients seek to understand their symptoms, explore robust algorithms and utilizing reliable medical databases to offer
potential causes, and seek preliminary guidance before consulting precise advice and information [10].
healthcare professionals [8]. However, the lack of accessible platforms A key objective is to enhance accessibility to healthcare information
for such information often leads individuals to unreliable sources, and support. The chatbot should provide round-the-clock assistance,
resulting in misconceptions and delayed medical attention. offering immediate access to medical guidance irrespective of
The emergence of AI-driven healthcare chatbots presents an geographical constraints.Ensuring user privacy and data security is
opportunity to bridge these gaps. By leveraging advancements in AI, paramount [11]. The project aims to implement stringent security
natural language processing, and machine learning, these chatbots can measures, comply with healthcare regulations, and prioritize user
engage with users in conversational formats, providing accurate, confidentiality in handling sensitive health information.
personalized medical information and preliminary guidance [9]. This
technology offers the promise of democratizing health care V. LITERATURE REVIEW
information, empowering users with immediate access to reliable The development of healthcare chatbot systems has gained significant
medical advice, irrespective of their geographical location or time attention in recent years due to their potential to revolutionize patient
constraints. care, improve accessibility, and streamline healthcare services. This
section presents a comprehensive review of the existing literature
III. LIMITATION AND CHALLENGES pertaining to healthcare chatbot systems, focusing on their
applications, functionalities, challenges, and the current state of
A. Problem statement research in the field.
The central challenge addressed by this project revolves around Patil et al. proposed a system the healthcare chatbot system that was
enhancing healthcare accessibility and providing reliable medical aimed at assisting individuals who were unable to secure appointments
guidance through an AI-driven chatbot interface. The goal is to create or access medical information from doctors, particularly in government
a user-friendly platform that not only disseminates accurate medical hospitals and rural areas. Chatbots were utilized to aid them in
information but also engages users in natural language conversations, addressing their concerns [15]. L. Athota et al. proposed that artificial
simulating interactions with healthcare professionals. intelligence to create a medical chatbot that can diagnose conditions
and provide basic details about them, negating the need for patients to
B. Challenges see a doctor. The goal of using medical chatbots was to save healthcare
1. Accuracy and Reliability: costs while improving access to medical information [16]. L. and Liu
Ensuring the accuracy and reliability of medical information provided et al. proposed a system in which the chatbot framework utilized a
by the chatbot remains a primary concern [10]. The system must be hybrid model comprising a text similarity model and a knowledge
equipped to offer precise medical advice based on user input, graph. We developed HHH, an online question-and-answer (QA)
encompassing a wide array of symptoms and medical conditions. Healthcare Helper system, to address difficult medical queries based
2. Privacy and Data Security: on our chatbot foundation [17]. Hossain et al.proposed a system to
Safeguarding user privacy and maintaining data security in healthcare create, develop, and assess the "MR.Dr." health assistant chatbot
interactions are critical. Dealing with sensitive health information application, allowing users to ask any private healthcare-related
requires stringent measures to ensure compliance with healthcare question without having to visit the hospital in person [18]. N. V.
regulations and standards while preserving user confidentiality [11]. Shinde et al. proposed that in order to shorten the process's duration
and expense, this effort addressed the user's symptoms and offered
3. Understanding Natural Language: recommendations for treatment in accordance with them [19]. The
Interpreting user queries accurately, especially when they describe main objective of the project by T. and Kalakota et al. is to cover
complex or diverse symptoms, which remains a challenge. The chatbot administrative tasks, patient participation and adherence, and diagnosis
needs to comprehend various linguistic nuances and provide and treatment suggestions [20].Denecke et al. proposed a system that
contextually relevant responses [12]. used artificial intelligence to analyze natural language, simulate human
speech, and provide relevant recommendations based on a user's
4. Continuous Learning and Adaptation: utterances and mental states [21]. The main objective of the project by
Health care is an evolving field with constant updates and H.S.J. and Achananuparp et al, AI was perceived as promising but
advancements [13]. The chatbot system must be adaptive, continuously faced challenges in healthcare adoption. Greater data security,
learning from new data, medical literature, and user interactions to regulatory compliance, and improved user trust were needed for wider
provide up-to-date and accurate information. AI utilization in healthcare [22]. The main objective of the project by
Biju et al, the consumers were provided with precise and accurate
illness predictions based on their symptoms. A decision tree was used
5. Integration with Health Care Systems: in creating the chatbot to simulate disease scenarios [23]. B.R. and
Seamless integration with existing health care systems, such as Murthy et al. proposed a system that which Conversational virtual
electronic health records (EHRs) or hospital databases, is crucial. This assistants, or chatbots, conducted user interactions automatically.
IJNRD2403146 International Journal of Novel Research and Development (www.ijnrd.org) b404
c404
 © 2024 IJNRD | Volume 9, Issue 3 March 2024| ISSN: 2456-4184 | IJNRD.ORG

Artificial intelligence-powered chatbots used machine-learning

techniques to comprehend natural language. d.Language Modeling and Understanding User Intent:
Use statistical techniques or neural networks to build models that
VI. EXISTING SYSTEM predict the next word or phrase in a sequence, aiding in the completion
The current healthcare chatbot system stands as an interactive and user- or correction of user queries.Understand and classify user intents to
centric platform, designed to provide accessible medical guidance. provide appropriate responses or actions.
Operating through an intuitive interface, users engage with the system
by inputting diverse health-related queries, symptoms, or concerns in a e.Continuous Learning and Model Adaptation:
conversational format. Integral to its functioning are advanced Natural Allow the NLP system to learn from user interactions, improving its
Language Processing (NLP) techniques that enable a comprehensive understanding and responses over time. Update and adapt NLP models
analysis of user inputs [25]. This includes intricate processes such as based on new data or changes in language usage patterns [30].
tokenization, entity recognition, and semantic analysis, facilitating the
extraction of relevant information necessary for informed responses. 3. Machine Learning Algorithms:
Decision Trees and Support Vector Machines (SVM) are implemented
The system's response generation heavily relies on predefined rules, within the chatbot for disease prediction, symptom analysis, and
pattern matching, and structured knowledge repositories. Through this personalized recommendations [32].
mechanism, the system delivers preliminary disease predictions by
correlating user-entered symptoms with known medical conditions. a.Decision Trees and SVM Implementation:
However, despite these capabilities, the system faces inherent Construct a decision tree model to classify symptoms or inputs,
limitations in its functionalities. Primarily, it operates within a realm of splitting data based on features to predict diseases or suggest suitable
static responses, lacking the dynamic adaptability needed to evolve in actions.Utilize SVM for classification tasks, mapping data into a
real-time with user interactions [26]. Moreover, its contextual higher-dimensional space to find optimal decision boundaries between
understanding remains limited, inhibiting its ability to respond classes [33].
contextually to diverse and evolving user needs.
b.Model Development and Optimization:
Though the system incorporates basic user feedback mechanisms to Build robust machine learning models using collected and
refine responses over time, its reliance on structured data sources poses preprocessed data, incorporating algorithms like Decision Trees, SVM,
notable constraints. This reliance potentially hampers its interpretative or ensemble methods for disease prediction and
capabilities when encountering unstructured or varied user queries, recommendation.Optimize model performance by tuning
limiting the depth and accuracy of its assistance [27]. Furthermore, hyperparameters, enhancing accuracy, reducing overfitting, and
while proficient in offering initial disease predictions, the system lacks improving generalization [32].
the ability to engage in nuanced and contextually rich conversations
that might significantly enhance user experience and aid in more c.Feature Selection and Importance:
precise medical assistance [28]. Identify and select the most relevant features contributing to disease
prediction or user recommendation.Analyze the importance of various
features in decision-making within the models.
VII. PROPOSED SYSTEM
1. Data Collection and Preprocessing:
4. Chatbot Functionality:
Describe the process of collecting the data used to train and validate
the chatbot system. This may include data sets containing medical
a.User Interaction and Input Processing:
information, symptom databases, or relevant healthcare literature.
Develop an intuitive and user-friendly interface allowing users to input
Explain the preprocessing steps involved, such as data cleaning,
symptoms, medical history, or specific health queries.Implement NLU
normalization, and feature extraction from textual data [29].
techniques to comprehend and interpret user inputs, extracting relevant
information effectively [31].
2. Natural Language Processing (NLP) Integration:
NLP techniques, including text processing, entity recognition, and
b.Contextual Understanding and Memory:
sentiment analysis, are integrated into the chatbot system [30]. These
Enable the chatbot to maintain context during conversations,
facilitate the understanding and interpretation of user queries.
remembering previous user inputs to ensure continuity and relevance
in responses. Leverage context awareness to tailor responses based on
a.Tokenization and Parsing:
the ongoing conversation, ensuring coherence and personalized
Tokenization: Break down user input into tokens (words, phrases,
interaction [34].
symbols) to understand the structure of the text [31].
Parsing: Analyze the grammatical structure of sentences to extract
c.Response Generation and Personalization:
relationships between words.
Employ NLP models to generate responses that are contextually
relevant, accurate, and understandable to the user.Customize responses
b.Entity Recognition and Named Entity Recognition (NER):
based on user-specific data, such as medical history or preferences, for
Entity Recognition: Identify entities within the text such as names,
a more personalized and user-centric experience.
dates, locations, and medical terms.
Named Entity Recognition (NER): Extract specific entities from text
5. Healthcare Professional Support:
for better understanding and contextual analysis.
Develop a backend system that supports healthcare professionals by
providing quick access to updated medical literature, drug interactions,
c.Semantic Understanding and Contextual Analysis:
and treatment guidelines.Ensure seamless integration with existing
Semantic Understanding: Comprehend the meaning of words in
healthcare systems to facilitate efficient data exchange and provide
context, deciphering intent beyond literal interpretation.
comprehensive support to healthcare professionals.
Contextual Analysis: Analyze the context of queries to provide more
accurate and relevant responses.
IJNRD2403146 International Journal of Novel Research and Development (www.ijnrd.org) b405
c405
 © 2024 IJNRD | Volume 9, Issue 3 March 2024| ISSN: 2456-4184 | IJNRD.ORG

6. Data Gathering and Analysis for Doctor Tracking:

Implement mechanisms to track and analyze doctor suggestions made X.CONCLUSION AND FUTURE WORKS
by the chatbot to users.Conduct thorough evaluations of suggested
doctors, analyzing user feedback and success rates to refine and In conclusion, the current healthcare chatbot system, while making
optimize the doctor recommendation system [35]. strides in providing accessible medical guidance, exhibits certain
limitations. The reliance on static responses and structured data sources
7. Data Analysis for Area Analysis: constrains its adaptability and contextual understanding, hindering its
Utilize geographic data to analyze healthcare access patterns, identify potential for nuanced interactions. However, the system's utilization of
underserved areas, and understand regional health trends.Derive advanced Natural Language Processing (NLP) techniques showcases a
insights to support public health initiatives and policy-making, foundation ripe for enhancement. The integration of user feedback
recommending measures to address healthcare accessibility gaps. mechanisms reflects a commitment to iterative improvement, setting
the stage for future developments. As technology continues to evolve,
VIII.DESIGN addressing these limitations becomes imperative to create a more
responsive, context-aware, and user-centric healthcare chatbot.
Use case Diagram
To propel the healthcare chatbot system into a more advanced and
One kind of behavioral diagram in the Unified Modeling Language adaptable tool, several avenues for future work emerge. Firstly, the
(UML) is a use case diagram. Its objective is to provide a graphical integration of dynamic learning mechanisms, including machine
summary of the functionality that a system offers in terms of actors, learning algorithms capable of continuous improvement, is paramount.
use cases (representations of their goals), and any interdependence This would empower the chatbot to evolve with user interactions,
among those use cases. A use case diagram's primary goal is to display refining its responses based on real-time feedback and emerging
which actors receive which system functionality.The roles of the actors medical insights. Additionally, diversifying data sources to include
in the system can be illustrated. unstructured information and real-time databases would broaden the
system's knowledge base, enhancing its capacity to handle varied and
evolving user queries.

Future iterations should also focus on advancing the system's

conversational abilities. Implementing more sophisticated contextual
understanding mechanisms and sentiment analysis would enable the
chatbot to engage in nuanced discussions, leading to a more
comprehensive user experience. Further enhancements in disease
prediction accuracy and tailored recommendations can be achieved
through the integration of more advanced machine-learning models
and ensemble techniques.
Moreover, a user-centric approach should guide the development of
features like personalized health recommendations and proactive
health monitoring. Integration with wearable devices and health
trackers could contribute to a more holistic and personalized user
experience, allowing the chatbot to offer proactive health advice based
on individual health metrics.

XI.REFERENCES
IX.RESULTS
[1].Yamin, F. M., Yusof, N. M., et al. (2019). "A Review of Chatbot in
The comprehensive evaluation of the healthcare chatbot system Healthcare: Promises and Challenges." 2019 IEEE Conference on
provided multifaceted insights into its functionality and user reception. Open Systems (ICOS).
The system demonstrated commendable disease prediction accuracy, [2].Joel, J. I., Premalatha, K., et al. (2021). "Design and
boasting an overall precision rate of 78%, affirming its ability to Implementation of a Health Care Chatbot with Deep Learning
accurately diagnose ailments based on user-input symptoms. Parallelly, Techniques." 2021 International Conference on Communication and
user feedback surveys unveiled a positive user satisfaction rate of 85%, Signal Processing (ICCSP).
indicating users' contentment with the system's responsiveness and [3].Zhang, Y., Wang, G., et al. (2018). "An intelligent healthcare
assistance. However, nuanced challenges surfaced during evaluations, chatbot system." 2018 IEEE 8th Annual International Conference on
particularly in sustaining conversational context across multi-turn CYBER Technology in Automation, Control, and Intelligent Systems
interactions, leading to occasional misinterpretations and incomplete (CYBER).
responses. Moreover, the system's reliance on structured data sources [4].Arpnikanondt, C., Kerdprasop, N., et al. (2020). "Development of
posed constraints when handling unstructured queries, revealing an a Rule-Based Chatbot System for Healthcare Information Retrieval."
area for improvement in contextual understanding. While the system 2020 4th International Conference on Information Science and
displayed competitiveness against industry benchmarks in disease Systems (ICISS).
prediction, there remains a noteworthy scope for refining contextual [5].Muthukrishnan, K., Poongodi, P., et al. (2021). "Health Chatbots
comprehension and augmenting user engagement. These findings for Patient Communication: A Study of Intent Recognition
delineate the system's strengths while highlighting pivotal areas for Performance and Knowledge Retention." 2021 IEEE International
enhancement, emphasizing the imperative for future refinements aimed Conference on Healthcare Informatics (ICHI).
at bolstering adaptability, augmenting contextual comprehension, and [6].Levesque, J.F., Harris, M.F. and Russell, G., 2013. Patient-centred
delivering more tailored and effective healthcare guidance. access to health care: conceptualising access at the interface of health

IJNRD2403146 International Journal of Novel Research and Development (www.ijnrd.org) b406

c406
 © 2024 IJNRD | Volume 9, Issue 3 March 2024| ISSN: 2456-4184 | IJNRD.ORG

systems and populations. International journal for equity in health, 12, [24].Kavitha, B.R. and Murthy, C.R., 2019. Chatbot for healthcare
pp.1-9. system using Artificial Intelligence. Int J Adv Res Ideas Innov Technol,
[7].van Gaans, D. and Dent, E., 2018. Issues of accessibility to health 5, pp.1304-1307.
services by older Australians: a review. Public health reviews, 39(1), [25].Cruz, S.E.M., 2021. Chatbot assistant for diabetic patients
pp.1-16. (Doctoral dissertation).
[8].Fiksdal, A.S., Kumbamu, A., Jadhav, A.S., Cocos, C., Nelsen, L.A., [26].Maity, N.G. and Das, S., 2017, March. Machine learning for
Pathak, J. and McCormick, J.B., 2014. Evaluating the process of online improved diagnosis and prognosis in healthcare. In 2017 IEEE
health information searching: a qualitative approach to exploring aerospace conference (pp. 1-9). IEEE.
consumer perspectives. Journal of medical Internet research, 16(10), [27].Sagar, R.H., Ashraf, T., Sharma, A., Goud, K.S.R., Sahana, S. and
p.e224. Sagar, A.K., 2021. Revolution of AI-enabled health care chat-bot
[9].Chen, M. and Decary, M., 2020, January. Artificial intelligence in system for patient assistance. In Applications of Artificial Intelligence
healthcare: An essential guide for health leaders. In Healthcare and Machine Learning: Select Proceedings of ICAAAIML 2020 (pp.
management forum (Vol. 33, No. 1, pp. 10-18). Sage CA: Los Angeles, 229-249). Springer Singapore.
CA: SAGE Publications. [28].Nadarzynski, T., Miles, O., Cowie, A. and Ridge, D., 2019.
[10].Xu, L., Sanders, L., Li, K. and Chow, J.C., 2021. Chatbot for Acceptability of artificial intelligence (AI)-led chatbot services in
health care and oncology applications using artificial intelligence and healthcare: A mixed-methods study. Digital health, 5,
machine learning: systematic review. JMIR cancer, 7(4), p.e27850. p.2055207619871808.
[11].Fernández-Alemán, J.L., Señor, I.C., Lozoya, P.Á.O. and Toval, [29].Lee, H., Kang, J. and Yeo, J., 2021. Medical specialty
A., 2013. Security and privacy in electronic health records: A recommendations by an artificial intelligence chatbot on a smartphone:
systematic literature review. Journal of biomedical informatics, 46(3), development and deployment. Journal of medical Internet research,
pp.541-562. 23(5), p.e27460.
[12].Khadija, A., Zahra, F.F. and Naceur, A., 2021. AI-powered health [30].Ayanouz, S., Abdelhakim, B.A. and Benhmed, M., 2020, March.
chatbots: toward a general architecture. Procedia Computer Science, A smart chatbot architecture based NLP and machine learning for
191, pp.355-360. health care assistance. In Proceedings of the 3rd international
[13].Junaid, S.B., Imam, A.A., Balogun, A.O., De Silva, L.C., Surakat, conference on networking, information systems & security (pp. 1-6).
Y.A., Kumar, G., Abdulkarim, M., Shuaibu, A.N., Garba, A., Sahalu, [31].Bhirud, N., Tataale, S., Randive, S. and Nahar, S., 2019. A
Y. and Mohammed, A., 2022, October. Recent advancements in literature review on chatbots in healthcare domain. International
emerging technologies for healthcare management systems: A survey. journal of scientific & technology research, 8(7), pp.225-231.
In Healthcare (Vol. 10, No. 10, p. 1940). MDPI. [32].Matthew, R., Agustriawan, D., Bani, M.D., Sadrawi, M.,
[14].Chung, K. and Park, R.C., 2019. Chatbot-based heathcare service Ratnasari, N.R.P., Firmansyah, M. and Parikesit, A.A., 2022, October.
with a knowledge base for cloud computing. Cluster Computing, 22, The Development of A Medical Chatbot Using The SVM Algorithm.
pp.1925-1937. In 2022 4th International Conference on Cybernetics and Intelligent
[15].Patil, M.V., Shree, P. and Singh, P., 2021. AI based healthcare System (ICORIS) (pp. 1-6). IEEE.
chat bot system. International Journal of Scientific & Engineering [33].Rahman, M.M., Amin, R., Liton, M.N.K. and Hossain, N., 2019,
Research, 12(7). December. Disha: an implementation of machine learning based
[16].L. Athota, V. K. Shukla, N. Pandey and A. Rana, "Chatbot for Bangla healthcare chatbot. In 2019 22nd International Conference on
Healthcare System Using Artificial Intelligence," 2020 8th Computer and Information Technology (ICCIT) (pp. 1-6). IEEE.
International Conference on Reliability, Infocom Technologies and [34].Kandpal, P., Jasnani, K., Raut, R. and Bhorge, S., 2020, July.
Optimization (Trends and Future Directions) (ICRITO), Noida, India, Contextual chatbot for healthcare purposes (using deep learning). In
2020, pp. 619-622, doi: 10.1109/ICRITO48877.2020.9197833. 2020 Fourth World Conference on Smart Trends in Systems, Security
[17].Bao, Q., Ni, L. and Liu, J., 2020, February. HHH: an online and Sustainability (WorldS4) (pp. 625-634). IEEE.
medical chatbot system based on knowledge graph and hierarchical bi- [35].Sheth, A., Yip, H.Y. and Shekarpour, S., 2019. Extending patient-
directional attention. In Proceedings of the Australasian computer chatbot experience with internet-of-things and background knowledge:
science week multiconference (pp. 1-10). case studies with healthcare applications. IEEE intelligent systems,
[18].Hossain, M.M., Pillai, S.K., Dansy, S.E., Bilong, A.A. and 34(4), pp.24-30.
Panessai, I.Y., 2021. Mr. Dr. Health-Assistant Chatbot. International
Journal of Artificial Intelligence, 8(2), pp.58-73.
[19].N. V. Shinde, A. Akhade, P. Bagad, H. Bhavsar, S. K. Wagh and
A. Kamble, "Healthcare Chatbot System using Artificial Intelligence,"
2021 5th International Conference on Trends in Electronics and
Informatics (ICOEI), Tirunelveli, India, 2021, pp. 1-8, doi:
10.1109/ICOEI51242.2021.9452902.
[20].Davenport, T. and Kalakota, R., 2019. The potential for artificial
intelligence in healthcare. Future healthcare journal, 6(2), p.94.
[21].Denecke, K., Abd-Alrazaq, A. and Househ, M., 2021. Artificial
intelligence for chatbots in mental health: opportunities and challenges.
Multiple perspectives on artificial intelligence in healthcare:
Opportunities and challenges, pp.115-128.
[22].Chew, H.S.J. and Achananuparp, P., 2022. Perceptions and needs
of artificial intelligence in health care to increase adoption: scoping
review. Journal of medical Internet research, 24(1), p.e32939.
[23].Biju, A., Menon, N.S., Joseph, S.L., Lopez, D. and PJ, S., 2021.
Medical Chatbot (Medibot). International Journal, 10(3).

IJNRD2403146 International Journal of Novel Research and Development (www.ijnrd.org) b407

c407