Intelligent Healthcare: Using NLP and ML to Power

Chatbots for Improved Assistance

Rajasrikar Punugoti Ronak Duggar Risha Ranganath Dhargalkar
Senior Director Department of Research & Innovation Department of CS
Broadridge Financial Solutions Inc. AVN Innovations Govt. College of Arts, Science & Commerce
2023 International Conference on IoT, Communication and Automation Technology (ICICAT) | 979-8-3503-0282-0/23/$31.00 ©2023 IEEE | DOI: 10.1109/ICICAT57735.2023.10263708

NY, US Ajmer, India Sanquelim, Goa, India

[email protected] [email protected] [email protected]

Neha Bhati
Department of Research & Development
AVN Innovations
Ajmer, India
[email protected]

Abstract— This research examines the fundamental reasons systematic software of a chatbot is still one of the toughest
chatbots exist, their functions, and their challenges. The challenges in forming a chatbot [7]. Communication is a two-
applicability and consistency of the analysis are improved by the way thing. Therefore, an AI-based machine cannot completely
utilization of quantitative data that is gathered in real-time. The interpret the natural communication process of human beings
research also compares past techniques of creating chatbots with as there is no singular pattern of it [8]. The work critically
modern ones, highlighting how far chatbots have progressed addresses this and the probable possibilities of making a
from being able to merely engage in scripted scenarios to the successful chatbot using the NLP design.
advanced skills they have today thanks to end-to-end neural
networks. Microsoft Research carried out the research and Besides, the NLP has multiple stages that must be fulfilled
published it in the journal Science. The first paragraph of this completely [9]. Natural language understanding (NLU) and
essay presents a detailed examination of chatbots' roles, natural language generation (NLG) are also critical and
significance, and potential. This research sheds new insight into challenging to implement in the AI function of the chatbot
the concept of chatbots by investigating their development and [10]. There are five stages of analysis within the NLU pattern.
many uses in greater detail than previously. They include Lexical analysis, Syntactic analysis (parsing),
Semantic analysis, Discourse integration, and Pragmatic
Keywords— Chatbot, Natural Language Processing (NLP),
analysis [11]. Therefore, the study's key analysis process and
Intelligence, Machine Learning, Conversational Agents, Modelling
the challenges' explanation are fully explored.
of Conversations, Neural Machine Translation.
All the researchers are from technology, science and
I. INTRODUCTION digital development. Their areas of interest are using science
Several types of chatbots in the market are quite popular in and technology for modernized development. Different fields
the health service industry [1]. These chatbots are identified in of technology have been modified with the usage of chatbots.
this work and critically explained as well. For example, to treat From applications to individual websites, large companies to
insomnia, a chatbot called Casper or Insomnobot: 3000 has SMEs, all use chatbots for effective communication,
been structured [2-3]. Furthermore, the study has further marketing and brand promotion [12]. Especially in the
highlighted a chatbot's different roles and functions. A healthcare system, a chatbot is available for all and flexible
successful chatbot has the best engine for natural language with the time. Chatbots' flexible and efficient usage can
processing (NLP) [4]. Communication or chatter is the key control medical disasters and reach patients in need at their
purpose of creating a box. The chatbots are loaded with
flexibility, at their home and whenever they need proper
information. However, they can communicate or respond to a
human being only if they can read and access all the words or health-related advice [13]. Therefore, this is highly impactful
pronunciations coming out of a human being. The natural in the development of scientific growth. However, the chatbot,
language and the natural pronunciation process with human even though being in the market for a long time, cannot
beings vary from person to person. Programmers must completely satisfy the demand in the healthcare industry due
understand the difference between structured and unstructured to the lack of proper functioning in NLP. Therefore, the
conversations to address this gap [5]. The work has critically researchers are focusing on this topic to attract the attention of
highlighted these aspects. Using figures such as the artificial young scientists and technology developers to enhance the
intelligence concept is highly apt to provide a clear structure of system of chatbots and to develop the NLP and NLU functions
the AI and the construction of chatbots. The work thus of chatbots with ML and AI implementation [14].
provides satisfactory growth in its structure.
The key objectives of the paper are:
The key challenge that this work deals with is the challenge • To assess the key significance of Chatbot in
of using natural language processing in a chatbot [6]. For understanding the communication medium
example, using NLP and properly implementing this within the

Authorized licensed use limited to: HKBK College of Engineering. Downloaded on October 09,2024 at 05:04:16 UTC from IEEE Xplore. Restrictions apply.
 • To perform as an effective communication solution and providing patient assistance can save healthcare
to the health care assistant. expenditures. Healthcare staff can do more complex tasks and
• To identify the key needs to make an intelligent offer higher-value services.
chatbot using NLP and Machine Learning (ML) Finally, chatbots collect health history, symptoms, and
algorithms. concerns. These data can improve patient care and treatment
• The introduction has been precise, and the objectives regimens. Chatbots improve healthcare efficiency,
are not separately highlighted. However, it is clear accessibility, and quality. Chatbots provide fast, accurate
from the content that the key objectives are health information and tools to improve patient outcomes and
interwoven within the written content. satisfaction [16-19].
With 11 extremely reliable sources, this study critically A. Proposed Mode
analyses pertinent literature on chatbots and natural language
processing (NLP). It emphasizes important problems The proposed model for using NLP and ML to power
integrating NLP and NLU into chatbot machine learning chatbots for improved assistance in healthcare involves
algorithms. The research examines the value of collecting healthcare data, preprocessing it, training an NLP
communicational programming and chatbots' function in model to extract insights, using these insights to train an ML
understanding human speech. The study suggests employing model, developing a chatbot application, and evaluating and
developed patterns like echoes for efficient NLP-based improving the performance of the chatbot and underlying
chatbots to mitigate communication issues with chatbots. The models based on feedback.
research significantly advances the fields of NLP and 1) Pseudocode
chatbots. 1. Let 𝐷 be the set of all healthcare data. The data can
II. CHATBOTS FOR HEALTHCARE ASSISTANCE include medical literature, patient records, and other
relevant information.
Chatbots aid patients. They handle appointment 𝐷 = {𝑑1, 𝑑2, … , 𝑑𝑛}
scheduling, patient education, symptom evaluation,
medication reminders, post-operative care, mental health help, 2. Let 𝑃 be the set of preprocessed data. Preprocessing
and emergency response. Chatbots let patients plan and can involve text normalization, tokenization, and
reschedule healthcare appointments without holding or using 𝑃 = 𝑝𝑟𝑒𝑝𝑟𝑜𝑐𝑒𝑠𝑠𝑑𝑎𝑡𝑎(𝐷)
sophisticated phone systems. Chatbots can explain health
conditions, medications, and treatments in a conversational 3. Let 𝑁𝐿𝑃 be the 𝑁𝐿𝑃 model, which can extract useful
and easy-to-understand manner, improving patient awareness information and insights from the preprocessed data.
and adherence. 𝑁𝐿𝑃 techniques can include named entity
recognition, sentiment analysis, and topic modeling.
Artificial intelligence's use in digital enhancement and
technological growth was initiated long ago. However, since 𝑁𝐿𝑃 = 𝑡𝑟𝑎𝑖𝑛𝑛𝑙𝑝_ 𝑚𝑜𝑑𝑒𝑙(𝑃)
the inception of AI, scientists have been trying to make the 𝑒𝑥𝑡𝑟𝑎𝑐𝑡𝑒𝑑𝑖𝑛𝑓𝑜𝑟𝑚𝑎𝑡𝑖𝑜𝑖𝑛 = 𝑎𝑝𝑝𝑙𝑦𝑛𝑙𝑝_𝑚𝑜𝑑𝑒𝑙(𝑁𝐿𝑃,𝑃)
best chatbots. There are still complications in the formation of
4. Let 𝑀𝐿 be the 𝑀𝐿 model, which can make
chatbots. The work has effectively measured several processes
predictions and provide personalized assistance to
to find the best possible ways to make chatbots that can
patients. 𝑀𝐿 techniques can include regression,
understand the utterances from human mouths and interpret
classification, and clustering.
them to provide the most satisfactory responses.
𝑀𝐿 = 𝑡𝑟𝑎𝑖𝑛𝑚𝑙_𝑚𝑜𝑑𝑒𝑙(𝑒𝑥𝑡𝑟𝑎𝑐𝑡𝑒𝑑_𝑖𝑛𝑓𝑜𝑟𝑚𝑎𝑡𝑖𝑜𝑛)
According to it, the function of AI could be more fruitful 𝑝𝑟𝑒𝑑𝑖𝑐𝑡𝑖𝑜𝑛𝑠
in making the best chatbots. Since human beings have = 𝑎𝑝𝑝𝑙𝑦𝑚𝑙_𝑚𝑜𝑑𝑒𝑙(𝑀𝐿,𝑒𝑥𝑡𝑟𝑎𝑐𝑡𝑒𝑑_𝑖𝑛𝑓𝑜𝑟𝑚𝑎𝑡𝑖𝑜𝑛)
different measures of pronunciation and different tongue
functions, the pronunciation may vary along with the 5. Let 𝐶 be the chatbot application, which can interact
utterance. Therefore chatbots, known as chatter robots, might with patients and provide real-time assistance based
miss several communicational actors with humankind. The on their queries and needs. The chatbot is developed
work has critically explained the key failures of chatbots [15]. based on the trained 𝑀𝐿 model.
𝐶 = 𝑑𝑒𝑣𝑒𝑙𝑜𝑝𝑐ℎ𝑎𝑡𝑏𝑜𝑡(𝑀𝐿)
Chatbots have become increasingly important in
healthcare, providing patients with fast and efficient 6. Let 𝐸 be the evaluation of the chatbot and underlying
information and services. 24/7 healthcare chatbots. 𝑁𝐿𝑃 and 𝑀𝐿 models. Evaluation can be based on
Information is available 24/7 to patients. Chatbots answer feedback received from users and healthcare
patients quickly. This aids patient decision-making and professionals.
prevents unnecessary hospitalizations. Chatbots can give 𝐸 = 𝑒𝑣𝑎𝑙𝑢𝑎𝑡𝑒𝑐ℎ𝑎𝑡𝑏𝑜𝑡(𝐶)
patients personalized advice based on their health history and 𝑚𝑎𝑘𝑒𝑖𝑚𝑝𝑟𝑜𝑣𝑒𝑚𝑒𝑛𝑡𝑠(𝐶)
symptoms, improving patient engagement and experience.
Cost-effective healthcare chatbots Automating routine tasks

Authorized licensed use limited to: HKBK College of Engineering. Downloaded on October 09,2024 at 05:04:16 UTC from IEEE Xplore. Restrictions apply.
 As per this research, the use of SMF is impactful as it
helps to identify the key context of the long conversation and
helps the chatbot to find the context zone and match it with the
internal programming. The matching vectors are analyzed to
critically identify the accurate response in the context. With
this wide informative structure and presentation, it is quite
clear that the researchers have not only gathered the
information from past scholars, but they have significantly
analysed it as well. However, there is one factor to be noted
here. This first past work is not listed in the reference list
below, which could be a critical mistake relating to the
copyright measures [22-25].

Mental and Physical

Health
300

200

100

0
May be No Yes
Fig. 1. Proposed workflow diagram
Mental Physical
III. RELATED WORKS
This section highlights the works of past scholars. Four
Fig. 3. NLP is used for awareness finding on mental and physical health
scholars and their works are critically analysed in this section.
Firstly, the researchers have focused on a paper discussing
The second analysis is about the research paper by [26].
retrieval-based chatbots that can identify the answers to a long
conversation. They have considered that the conversation's The visualization of the analysis is shown in Figure 2. Here, it
response and context must be connected to answer the is analysed that the medical chatbots work as virtual doctors.
questions. The authors have further discussed that there could At the same time, real-time human doctors might not always be
be varieties of context. There are no limitations to the present. Robots and chatbots can mitigate the issues and
conversational context. Therefore, transforming to a fixed- shortage of doctors with virtual availability [27]. The
length vector from a context is highly impactful [20]. This is development process of these chatbots using the Python
known as a sequential matching framework (SMF) that can not language is further assessed. Thus, this section is highly
only help develop the functional capabilities of the chatbots but impactful for the readers to understand and evaluate the entire
also limits the chatbots' challenges and false medical prediction journey of different chatbots. It is further measured that, almost
[21]. 80% of the time, the chatbots come up with accurate answers,
Chatbots offer Field Length vectors, Long conversation while the remaining 20% could be an ambiguous, vague or
analysis, sequential matching framework, and improper assessment by the chatbots [28]. Using such
contextualization, as shown in Figure 1. qualitative and realistic data enhances the reliability of the
work.
In the third related work by [29], it is analysed that AI is
highly impactful to make medical assumptions and even
predictions from certain symptoms. AI performs best to make
these assumptions if a patient is periodically or regularly
analysed by the doctor [30] and the conceptual visualization is
shown in figure 3. Furthermore, this work is profoundly
impacting not directly on the use of chatbots but on the use of
AI in the healthcare system. The varieties of past works and the
relevance of these works to the current research are made
through these connections.
Fig. 2. The use of fixed length vectors for better function of chatbots in NLP Furthermore, The final and fourth work by [31], is
reflecting the recommendations for enhancing medical

Authorized licensed use limited to: HKBK College of Engineering. Downloaded on October 09,2024 at 05:04:16 UTC from IEEE Xplore. Restrictions apply.
chatbots. For this measure, an AIML-based Chatter bean is Source Method Result Gap
suggested use. With this programming implementation, communication overlooks
chatbots can convert NLP and natural language into SQL barriers and remote their proper
communication programming
queries to read and interpret them more accurately [32]. This issues. and
final work has been conducted through the use of primary data development
through the analysis of 97 sample questions. Therefore, the with modern
reliability of this information is more significant. Besides, the SQL
converters
researchers have used the works of both secondary and primary and echo
data to strengthen the validity of the structure. technology.

Discussing Mental &

Physical Health with
interviewer
300

200

100
Fig. 5. NLP relation with other medical units and customer support in views
0 of Palanica et al. 2019
May be No Yes Figure 5 displays the relationship of NLP with other medical units and
customer support from various perspectives.
Mental Physical

Fig. 4. Using NLP discussing physical health with interviewer

IV. ANALYSIS BASED ON RESULTS

TABLE I. ANALYSIS OF REFERENCES

Source Method Result Gap

Chatbots are useful It doesn't
administratively. address
A web-based They have a chatbots'
survey was significant impact recent
conducted to (around 78%) on failures in
Fig. 6. Chabot’s in use for patient support in education and course assistance
examine the scheduling doctor's evaluating
in views of Frangoudes et al. 2021
experience of 100 appointments, and
[33]
US-based particularly in communicati
physicians with customer service. ng with Figure 6 illustrates the utilization of chatbots in providing
chatbot They also have a customers or patient support for educational and course assistance purposes.
technologies in the significant impact clarify the The term "Chatbot architecture hierarchy" refers to the
medical sector. on scheduling and absence of
providing healthcare NLP
organizational structure and arrangement of components and
advice. functions. modules within a chatbot system, as shown in Figure 6.
The study used
PRISMA guidelines A systematic
A systematic for a systematic literature
literature review literature review, review and
and the use of enhancing reliability the use of
[34]
PRISMA have and validity by PRISMA
been followed promoting have been
here. transparency in followed
reporting methods here.
and results.
The study examines The study
A systematic
chatbot design discusses
analysis of the past
techniques like chatbots'
literature and
[35] Chat.io and Collect natural
explanatory
chat, highlighting language and
research design is
their role in semantic
used here.
reducing patterns, but Fig. 7. Chatbot architecture hierarchy in views of Ahmad et al. 2018

Authorized licensed use limited to: HKBK College of Engineering. Downloaded on October 09,2024 at 05:04:16 UTC from IEEE Xplore. Restrictions apply.
 V. DISCUSSION the healthcare system has a significant impact. With the help of
Chatbots are highly impactful in the healthcare system. this programming implementation, chatbots can transform NLP
From predicting diseases to customer service, the use of and natural language into SQL queries for better reading and
chatbots is manifold. The basic process of the chatbot is shown interpretation [40-42]. The chatbot support views are
in Figure 8. visualized in Figure 9.
VI. CONCLUSION AND FUTURE WORK
Artificial intelligence has been used for technological
advancement and digital enhancement for a long time.
However, since the advent of AI, artificial intelligence has
been working to create the finest chatbots possible. There are
still issues with how chatbots are created. The work has
successfully measured several procedures to determine the best
methods for creating chatbots that can comprehend the words
of human beings and interpret them to offer the most
appropriate responses. The use of AI is not as effective in
creating the best chatbots. The pronunciation may vary along
with the utterance because each human has a unique range of
pronunciation and tongue function. The different use and
impact of MLP functions of chatbots are further analysed here.
Future work on this issue can be highly significant with the
critical discourse presented in this study.
REFERENCES
[1] Nawaz, N. and Gomes, A.M., 2019. Artificial intelligence chatbots are
new recruiters. IJACSA) International Journal of Advanced Computer
Science and Applications, 10(9).
Fig. 8. The functional process of a chatbot [2] BORKAN, "www.blog.casper.com," 21 september 2016. [Online].
Available: https://blog.casper.com/meetinsomnobot-3000/.
Robots and apps can help solve problems when human [3] Sameera, A. K. and Woods, J., 2015. "Survey on Chatbot Design
doctors are unavailable [36-37]. This study analyses Python- Techniques in Speech Conversation Systems", (IJACSA) International
Journal of Advanced Computer Science and Applications, vol. 6, no. 7,.
based chatbot development to give readers a complete picture
[4] Lamba, S., Baliyan, A. &Kukreja, V. A novel GCL hybrid classification
of their path. Chatbots are accurate 80% of the time, with 20% model for paddy diseases. Int. j. inf. Technol. (2022).
giving unclear, vague, or incorrect replies [38]. Actual and https://doi.org/10.1007/s41870-022-01094-6.
qualitative data improves study reliability. Figure 8 shows this [5] Janssen, A., Cardona, D.R., Passlick, J. and Breitner, M.H., 2022. How
data. to Makechatbots productive-A user-oriented implementation framework.
International Journal of Human-Computer Studies, 168, p.102921.
[6] Divya, S., Indumathi, V., Ishwarya, S., Priyasankari, M. and Devi, S.K.,
mental health of 2018. A self-diagnosis medical chatbot using artificial intelligence.
Journal of Web Development and Designing, 3(1), pp.1-7.
employees with [7] S. M. Sasubilli, A. Kumar and V. Dutt, "Improving Health Care by Help
of Internet of Things and Bigdata Analytics and Cloud Computing,"
employers 2020 International Conference on Advances in Computing and
Communication Engineering (ICACCE), 2020, pp. 1-4, doi:
10.1109/ICACCE49060.2020.9155042.
300
[8] Rahman, A.M., Al Mamun, A. and Islam, A., 2017, December.
200 Programming challenges of chatbot: Current and future prospective. In
2017 IEEE Region 10 Humanitarian Technology Conference (R10-
100
HTC) (pp. 75-78). IEEE.
0 [9] Qader, R., Portet, F. and Labbé, C., 2019. Semi-supervised neural
May be No Yes text generation by joint learning of natural language generation and
natural language understanding models. arXiv preprint
Mental Physical arXiv:1910.03484.
[10] S. Lamba, A. Baliyan and V. Kukreja, "Generative Adversarial
Networks based Data Augmentation for Paddy Disease Detection using
Fig. 9. NLP is used for discussing the mental health of employees with Support Vector Machine," 2022 10th International Conference on
employers Reliability, Infocom Technologies and Optimization (Trends and Future
Directions) (ICRITO), 2022, pp. 1-5, doi:
10.1109/ICRITO56286.2022.9964506.
Additionally, AI performs better in establishing these
[11] Yang, S. and Evans, C., 2019, November. Opportunities and challenges
assumptions if a patient is periodically or routinely examined in using AI chatbots in higher education. In Proceedings of the 2019 3rd
by a physician [39]. Furthermore, even though the usage of International Conference on Education and E-Learning (pp. 79-83).
chatbots is not directly affected by this work, the use of AI in

Authorized licensed use limited to: HKBK College of Engineering. Downloaded on October 09,2024 at 05:04:16 UTC from IEEE Xplore. Restrictions apply.
[12] Ryuichiro Higashinaka et al. 2014. Towards an open-domain [30] S. A. Kumar, A. Kumar, V. Dutt and R. Agrawal, "Multi-Model
conversational system fully based on natural language processing. In Implementation on General Medicine Prediction with Quantum Neural
COLING'14, pages 928-939. Networks," 2021 Third International Conference on Intelligent
[13] S. A. Kumar, A. Kumar, V. Dutt and R. Agrawal, "Multi-Model Communication Technologies and Virtual Mobile Networks (ICICV),
Implementation on General Medicine Prediction with Quantum Neural 2021, pp. 1391-1395, doi: 10.1109/ICICV50876.2021.9388575.
Networks," 2021 Third International Conference on Intelligent [31] Androutsopoulou, A., Karacapilidis, N., Loukis, E. and Charalabidis, Y.,
Communication Technologies and Virtual Mobile Networks (ICICV), 2019. Transforming the communication between citizens and
2021, pp. 1391-1395, doi: 10.1109/ICICV50876.2021.9388575. government through AI-guided chatbots. Government information
[14] Androutsopoulou, A., Karacapilidis, N., Loukis, E. and Charalabidis, Y., quarterly, 36(2), pp.358-367.
2019. Transforming the communication between citizens and [32] Abd-Alrazaq, A.A., Rababeh, A., Alajlani, M., Bewick, B.M. and
government through AI-guided chatbots. Government information Househ, M., 2020. Effectiveness and safety of using chatbots to improve
quarterly, 36(2), pp.358-367. mental health: systematic review and meta-analysis. Journal of medical
[15] Abd-Alrazaq, A.A., Rababeh, A., Alajlani, M., Bewick, B.M. and Internet research, 22(7), p.e16021.
Househ, M., 2020. Effectiveness and safety of using chatbots to improve [33] S. Lamba, A. Baliyan and V. Kukreja, "GAN based image augmentation
mental health: systematic review and meta-analysis. Journal of medical for increased CNN performance in Paddy leaf disease classification,"
Internet research, 22(7), p.e16021. 2022 2nd International Conference on Advance Computing and
[16] S. Lamba, A. Baliyan and V. Kukreja, "GAN based image augmentation Innovative Technologies in Engineering (ICACITE), Greater Noida,
for increased CNN performance in Paddy leaf disease classification," India, 2022, pp. 2054-2059, doi:
2022 2nd International Conference on Advance Computing and 10.1109/ICACITE53722.2022.9823799.
Innovative Technologies in Engineering (ICACITE), Greater Noida, [34] Wu, Y., Wu, W., Xing, C., Xu, C., Li, Z. and Zhou, M., 2019. A
India, 2022, pp. 2054-2059, doi: sequential matching framework for multi-turn response selection in
10.1109/ICACITE53722.2022.9823799. retrieval-based chatbots. Computational Linguistics, 45(1), pp.163-197.
[17] S. Srivastav, P. K. Singh, and D. Yadav, “An Approach for fast [35] Saurav Kumar Mishra, DhirendraBharti, Nidhi Mishra, 2017." Dr.Vdoc:
Compressed text Matching and to avoid false Matching using WBTC A Medical Chatbot that Acts as a virtual Doctor", Journal of Medical
and Wavelet Tree,” EAI Endorsed Trans. Scalable Inf. Syst., vol. 30, pp. Science and Technology, Volume: 6, Issue 3.
1–10, 2021. [36] Zhang, H. and Zheng, J., 2021. The Application Analysis of Medical
[18] Saurav Kumar Mishra, DhirendraBharti, Nidhi Mishra, 2017." Dr.Vdoc: Chatbots and Virtual Assistant. The Frontiers of Society, Science and
A Medical Chatbot that Acts as a virtual Doctor", Journal of Medical Technology, 3(2).
Science and Technology, Volume: 6, Issue 3. [37] Lamba, Shweta, Vinay Kukreja, Anupam Baliyan, Shalli Rani, and Syed
[19] Mehra, P. S., Goyal, L. M., Dagur, A., & Dwivedi, A. K. (Eds.). (2022). Hassan Ahmed.(2023). "A Novel Hybrid Severity Prediction Model for
Healthcare Systems and Health Informatics: Using Internet of Things. Blast Paddy Disease Using Machine Learning" Sustainability (SCI) 15,
CRC Press. no. 2: 1502. https://doi.org/10.3390/su15021502
[20] Dwivedi, A. K., & Sharma, A. K. (2021). I‐FBECS: improved fuzzy [38] V. Dutt, S. M. Sasubilli and A. E. Yerrapati, "Dynamic Information
based energy efficient clustering using biogeography based optimization Retrieval With Chatbots: A Review of Artificial Intelligence
in wireless sensor network. Transactions on Emerging Methodology," 2020 4th International Conference on Electronics,
Telecommunications Technologies, 32(2), e4205. Communication, and Aerospace Technology (ICECA), Coimbatore,
[21] Madhu, D., Jain, C.N., Sebastain, E., Shaji, S. and Ajayakumar, A., India, 2020, pp. 1299-1303, DOI: 10.1109/ICECA49313.2020.9297533.
2017, March. A novel approach for medical assistance using trained [39] Abbasi, S., Kazi, H. and Hussaini, N.N., 2019. Effect of Chatbot
chatbot. In 2017 international conference on inventive communication Systems on Student's Learning Outcomes. Sylwan: English Edition,
and computational technologies (ICICCT) (pp. 243-246). IEEE. 163(10), pp.49-63.
[22] Davenport, T. and Kalakota, R., 2019. The potential for artificial [40] Satu, M.S. and Parvez, M.H., 2015, November. Review of integrated
intelligence in healthcare. Future healthcare journal, 6(2), p.94. applications with aiml based chatbot. In 2015 International Conference
[23] Abbasi, S., Kazi, H. and Hussaini, N.N., 2019. Effect of Chatbot on Computer and Information Engineering (ICCIE) (pp. 87-90). IEEE.
Systems on Student's Learning Outcomes. Sylwan: English Edition, [41] Ahmad, N.A., Che, M.H., Zainal, A., AbdRauf, M.F. and Adnan, Z.,
163(10), pp.49-63. 2018. Review of chatbots design techniques. International Journal of
[24] Satu, M.S. and Parvez, M.H., 2015, November. Review of integrated Computer Applications, 181(8), pp.7-10.
applications with aiml based chatbot. In 2015 International Conference [42] S. R. Swarna, A. Kumar, P. Dixit and T. V. M. Sairam, "Parkinson's
on Computer and Information Engineering (ICCIE) (pp. 87-90). IEEE. Disease Prediction using Adaptive Quantum Computing," 2021 Third
[25] Palanica, A., Flaschner, P., Thommandram, A., Li, M. and Fossat, Y., International Conference on Intelligent Communication Technologies
2019. Physicians' perceptions of chatbots in health care: a cross- and Virtual Mobile Networks (ICICV), 2021, pp. 1396-1401, doi:
sectional web-based survey. Journal of medical Internet research, 21(4), 10.1109/ICICV50876.2021.9388628
p.e12887.
[26] S. Boyapati, S. R. Swarna, V. Dutt and N. Vyas, "Big Data Approach
for Medical Data Classification: A Review Study," 2020 3rd
International Conference on Intelligent Sustainable Systems (ICISS),
Thoothukudi, India, 2020, pp. 762-766, doi:
10.1109/ICISS49785.2020.9315870.
[27] Ahmad, N.A., Che, M.H., Zainal, A., AbdRauf, M.F. and Adnan, Z.,
2018. Review of chatbot design techniques. International Journal of
Computer Applications, 181(8), pp.7-10.
[28] Srivastav, S., Singh, P.K. & Yadav, D. A novel approach to solve exact
matching problem using multi-splitting of text patterns. Int J Syst Assur
Eng Manag 14, 1457–1466 (2023). https://doi.org/10.1007/s13198-023-
01948-7.
[29] Dwivedi, A. K., Mehra, P. S., Pal, O., Doja, M. N., & Alam, B. (2021).
EETSP: Energy ‐ efficient two ‐ stage routing protocol for wireless
sensor network‐assisted Internet of Things. International Journal of
Communication Systems, 34(17), e4965.

Authorized licensed use limited to: HKBK College of Engineering. Downloaded on October 09,2024 at 05:04:16 UTC from IEEE Xplore. Restrictions apply.