© 20XX IJNRD | Volume X, Issue X Month 20XX | ISSN: 2456-4184 | IJNRD.

ORG

AI POWERED AUTOMATED PROXY FOR HALENESS REGIME

Dhanasri.T.K ArunaKumari.S
,
Student , Assistant Professor .
Department of CSE,
IFET college of Engineering,INDIA

Abstract : During the pandemic, the need for accessible medical assistance and advice has never been more crucial. With
countless individuals facing health concerns and an increased risk of contracting COVID-19, innovative solutions are essential to
reduce physical contact and prevent the spread of diseases. One promising approach is the introduction of the "Mediconverse"
within healthcare facilities. The Mediconverse, a dynamic interactive agent driven by Natural Language Processing (NLP) and
powered by AI and Deep Learning, holds immense potential for advancing medical diagnostics.

IndexTerms - Healthcare, Mediconverse, Artificial Intelligence, Symptoms.

________________________________________________________________________________________________________
INTRODUCTION
In today's digital age, automated chat robots have emerged as a powerful tool for efficiently addressing frequently asked questions
from users. Initially, these chatbots relied on natural language processing (NLP) techniques, but their accuracy in providing
correct answers was limited. However, with the integration of Deep Learning algorithms in Python, a significant leap in accuracy
has been achieved. This Deep Learning project aims to develop a chatbot application that responds effectively to users' questions
by training deep learning models on a diverse dataset of questions and their corresponding answers.
The process involves training these deep learning models to understand the nuances of language and context, enabling the chatbot
to predict the most appropriate answer when users input a question. This not only enhances user experience but also provides a
cost-effective alternative to the traditional method of employing human resources to handle user queries. With this application,
companies can now efficiently answer user questions without the need for additional manpower, making it a valuable tool in
today's digital customer service landscape.

NEED OF THE STUDY.

The concept of chatbots extends beyond just addressing frequently asked questions. These conversational interfaces, often
referred to as healthcare converses, represent a novel way for individuals to interact with computer systems. Traditionally, users
would rely on search engines or forms to seek information from software programs. However, chatbots allow users to engage in
conversations in a manner similar to how they communicate with humans, making the interaction more natural and user-friendly.
This transformation in user interaction has profound implications for sectors beyond customer service, including healthcare,
where chatbots can provide valuable information and support to patients.

Voice-based chatbots such as Google Assistant, Alexa, and Siri are already well-known and widely used in the market. Chatbots,
in general, are rapidly gaining popularity on various computer chat platforms, and their potential for enhancing user experiences
across industries is vast. In this project's implementation, Python's deep learning neural networks and the Natural Language
Toolkit (NLTK) are leveraged to process and analyze both training and testing text data, thereby enabling the chatbot to become
even more adept at understanding and responding to user queries. This fusion of cutting-edge technology and natural language
understanding is poised to shape the future of human-computer interactions and information retrieval.

II.METHODOLOGY:
To create a robust healthcare conversational system like "MediConverse" empowered by AI and ML, a well-defined methodology
is crucial. Here's a concise outline, with relevant formulas where applicable:

1. Objective Definition and Requirement Analysis:

Begin by clearly defining the primary objectives of the system, which may include symptom analysis, medical advice, and
information retrieval. Identify user requirements and healthcare regulatory guidelines. A formula for objective clarity might be:
`Objective = {Symptom Analysis, Information Retrieval, Advice}`.

2. Data Collection and Preprocessing:

PaperID 25
International Journal of Novel Research and Development (www.ijnrd.org)
 © 20XX IJNRD | Volume X, Issue X Month 20XX | ISSN: 2456-4184 | IJNRD.ORG

Gather a diverse dataset of medical knowledge from reliable sources, and preprocess it. Utilize text preprocessing techniques
such as tokenization and stemming. For example, the formula to calculate Term Frequency-Inverse Document Frequency (TF-
IDF) for data transformation is: `TF-IDF = (Term Frequency) * log(N / Document Frequency)`.

3. Natural Language Processing (NLP) Module:

Develop an NLP module using techniques like named entity recognition (NER) and word embeddings (e.g., Word2Vec) to
understand user queries. A formula for word embeddings might be: `Word2Vec(w) = ∑ (context words c, w)`, where w represents
a target word.

4. Dialog Management and Reinforcement Learning:

Design a dialog management system with reinforcement learning algorithms such as Deep Q-Networks (DQN). An essential
formula for DQN is the Q-value update: `Q(s, a) = Q(s, a) + α * [R + γ * max(Q(s', a')) - Q(s, a)]`.

5. Machine Learning Models:

Implement machine learning models like decision trees or deep learning models, using supervised learning for tasks such as
symptom analysis. For example, the entropy formula for decision trees is: `Entropy(S) = -p * log2(p) - q * log2(q)`, where p and q
represent the proportions of positive and negative examples in a dataset, respectively.

6. User Interface Design:

Develop an intuitive and user-friendly interface using design principles. An essential concept is the user interface prototype
formula: `UI Prototype = f(UI Design Guidelines)`.

7. Regulatory Compliance and Data Security:

Ensure compliance with healthcare regulations and implement data encryption using the Advanced Encryption Standard (AES).
The AES encryption formula for data security is beyond the scope of this text but widely available in cryptographic literature.

8. Testing, Deployment, and Continuous Improvement:

Employ testing methodologies such as precision, recall, and F1-score to evaluate system performance, represented by the F1-
score formula: `F1-Score = 2 * (Precision * Recall) / (Precision + Recall)`. Deploy the system on chosen platforms and create a
feedback loop for continuous improvement, factoring in user feedback.

III.EXISTING SYSTEM

Before exploring new technology, one should examine prior work and learn from past ideas, both succeed and failed attempts.
This section presents a selection of events from the last century, which introduced the ideas that formed the present definition of a
Chabot. It is not an attempt to give an all-encompassing overview about the history of computing, instead the aim is to explain
where the concept of chat bots and the interest of creating them originated.

3.1 Draw backs of Existing System:

• No proper support
• Communication overhead
• High risk
• More Manpower

FIG-1 Existing System Architecture

PaperID 26
International Journal of Novel Research and Development (www.ijnrd.org)
 © 20XX IJNRD | Volume X, Issue X Month 20XX | ISSN: 2456-4184 | IJNRD.ORG

IV. Proposed System:

Mediconverse can be described as software that can chat with people using artificial intelligence. Chatbots are generally used to
respond quickly to users. Chatbots, a common name for automated conversational interfaces, present a new way for individuals to
interact with computer systems. Traditionally, to get a question answered by a software program involves using a search engine or
filling out a form. A Interactive AI allows a user to simply ask questions in the same manner that they would address a human.
There are many well-known voice-based chatbots currently available in the market: Google Assistant, Alexa and Siri. Chatbots
are currently being adopted at a high rate on computer chat platforms. A chatbot can be used anywhere a human is interacting
with a computer system. These are the areas where the fastest adoption is occurring.

4.1Advantages:
• Offers 24/7 Service
• Enhances User Experience

FIG-2 Processing steps for mediconverse

4.2Train Dataset: It is the sample of data used to fit the model. This step involves in extraction of features and train to fit a model
and so on. The observations in the training set form the experience that the algorithm uses to learn. In supervised learning
problems, each observation consists of an observed output variable and one or more observed input variables.

4.3Validation Dataset: The sample of data used to provide unbiased evaluation of a model to fit on the train data set. The
evaluation becomes more biased as skill on the validation dataset is incorporated into the model configuration.

4.4Test dataset: The sample of data used to provide unbiased evaluation of a final model. It used to test if the model is making
accurate predictions.The set of observations used to evaluate the performance of the model using some performance metric. If the
test set does contain examples from the training set, it will be difficult to assess whether the algorithm has learned to generalize
from the training set or has simply memorized it.

V.LITERATURE SURVEY:
A. An AI-Based Medical Chatbot Model for Infectious Disease Prediction
The problem addressed in this paper is the need for the effective promotion and utilization of chatbots within the medical sector to
combat infectious diseases and provide users with access to accurate medical information for disease prevention. The paper seeks
to bridge a knowledge gap in the creation of AI chatbots for lifestyle improvement programs. It proposes an AI Chatbot
interaction and prediction model using a deep feedforward multilayer perceptron and presents an analysis that includes a
comparison of time complexity and testing accuracy. The study aims to enhance the understanding and application of medical
chatbots and their potential to address health crises, particularly during pandemics, such as COVID-19.

B.A NOVEL APPROACH FOR MEDICAL ASSISTANCE USING TRAINED CHATBOT

The problem addressed in this proposal is the lack of a centralized and accessible source for comprehensive information about
diseases, medicines, and their proper usage. To remedy this issue, the proposed solution involves the creation of an artificial
intelligence system capable of diagnosing diseases based on symptoms, providing a list of available treatments, and offering
information on medication compositions and their prescribed uses. This system aims to empower individuals to make informed
health decisions and receive the correct treatment.

C. Healthcare Chatbot system for aged and physically challenged people

It include a lack of technical specificity, unverified or unsupporteclaims regarding the capabilities of chatbots, absence of citations
to back up assertions, and a failure to address the critical ethical and privacy considerations inherent in healthcare chatbots. To
enhance its rigor and credibility, it requires to concrete empirical evidence, appropriate scholarly references, and a comprehensive
examination of potential limitations and ethical concerns.

D. An Intelligent Virtual Medical Assistant

This aims to address the challenges posed by time-consuming in-person medical consultations at hospitals and healthcare centers.
The proposed solution is an automated Chatbot system accessible through a web application, allowing individuals to interact with
a machine for health-related queries. Developed using NLP and Recurrent Neural Network (RNN) algorithms, the system

PaperID 27
International Journal of Novel Research and Development (www.ijnrd.org)
 © 20XX IJNRD | Volume X, Issue X Month 20XX | ISSN: 2456-4184 | IJNRD.ORG

achieves an accuracy rate of 88% and is compared to Artificial Neural Network (ANN) and Convolution Neural Network (CNN)
concepts. The Chatbot offers users simplified prescriptions based on disease diagnosis and facilitates specialist appointments,
offering a more convenient and accessible healthcare alternative.

VI.RESULT:
Our project aims to develop a Mediconverse capable of providing accurate diagnoses and treatment options for various medical
conditions. By incorporating machine learning algorithms, the chatbot learns from historical patient data to make informed
decisions.

FIG-3 Healthcare Mediconverse Master

Key components:
 Pre-processed training and testing data

 Python script for implementing the chatbot logic

 Requirements.txt file for package dependencies

Tools and Libraries:

 PyTorch

 PyTorch Transformers

 NLTK

 SpaCy

 Pandas

 Scikit-learn

CONCLUSION:
Mediconverse, a dynamic virtual assistant empowered by Natural Language Processing (NLP) and AI, represents a significant
and innovative stride forward in the healthcare sector, especially during the pandemic. This cutting-edge technology is addressing
the urgent need for accessible medical assistance and advice, serving as a digital bridge to connect individuals with the
information and guidance they require to manage their health effectively.One of the key features that sets Mediconverse apart is
its ability to engage in text-based conversations, making it convenient and easily accessible to a wide range of users. This

PaperID 28
International Journal of Novel Research and Development (www.ijnrd.org)
 © 20XX IJNRD | Volume X, Issue X Month 20XX | ISSN: 2456-4184 | IJNRD.ORG

conversational interface allows individuals to express their symptoms, concerns, and questions in a natural way, creating a user-
friendly experience that is crucial in a time when in-person healthcare consultations may not always be feasible.Moreover,
Mediconverse's understanding of symptoms and its capacity to provide informed medical guidance play a pivotal role in
enhancing healthcare accessibility. By comprehending user input, it can offer valuable information on common health issues, such
as colds and fevers, effectively acting as a first point of contact for those in need. This is particularly valuable for individuals who
may be looking for immediate advice, reassurance, or guidance on managing their symptoms without needing to visit a healthcare
facility. What truly sets Mediconverse apart is its reliance on advanced NLP and AI technologies. These technologies enable it to
stay up-to-date with the latest medical information and guidelines, including real-time updates on health-related issues like
COVID-19. This ensures that users are receiving accurate and current information, which is essential during a rapidly evolving
health crisis. By providing the most recent recommendations and information, Mediconverse empowers users to make well-
informed decisions regarding their health.

This project's potential impact is substantial. By empowering individuals to take control of their health, make informed decisions,
and receive guidance when they need it, Mediconverse contributes to the collective effort to reduce disease transmission and
improve overall well-being. It not only eases the burden on healthcare systems but also promotes self-sufficiency and healthcare
literacy among the general population. This is particularly critical during a pandemic, as it can help mitigate the spread of diseases
by reducing unnecessary visits to healthcare facilities and promoting proactive health management.
Mediconverse is a groundbreaking innovation in healthcare accessibility, leveraging NLP and AI to provide timely, reliable, and
user-friendly medical assistance and advice. Its potential to empower individuals and contribute to public health efforts is
significant, making it a valuable resource during the pandemic and beyond.

REFERENCES
[1] Srivastava, P., & Singh, N (2020, February). Automatized medical chatbot (medibot). In 2020 International Conference on
Power Electronics & IoT Applications in Renewable Energy and its Control (PARC) (pp. 351-354). IEEE.
[2] Kandpal, P., Jasnani, K., Raut, R., & Bhorge, S. (2020, July). Contextual Chatbot for healthcare purposes (using deep
learning). In 2020 Fourth World Conference on Smart Trends in Systems, Security and Sustainability (WorldS4) (pp. 625-634).
IEEE.
[3] Athota, L., Shukla, V. K., Pandey, N., & Rana, A. (2020, June). Chatbot for Healthcare System Using Artificial Intelligence.
In 2020 8 th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions)
(ICRITO) (pp. 619-622). IEEE.
[4] Karri, S. P. R., & Kumar, B. S. (2020, January). Deep learning techniques for implementation of chatbots. In 2020
International Conference on Computer Communication and Informatics (ICCCI) (pp. 1-5). IEEE.
[5] Bharti, U., Bajaj, D., Batra, H., Lalit, S., Lalit, S., & Gangwani, A. (2020, June). Medbot: Conversational artificial intelligence
powered chatbot for delivering tele-health after covid-19. In 2020 5 th International Conference on Communication and
Electronics Systems (ICCES) (pp. 870-875). IEEE.
[6] Milla T Mutiwokuziva, Melody W Chanda, Prudence Kadebu, Addlight Mukwazvure, Tatenda T Gotora, “A Neural-network
based Chat Bot” in ICCES,2017
[7] Gentner, T., Neitzel, T., Schulze, J., & Buettner, R. (2020, July). A Systematic literature review of medical chatbot research
from a behavior change perspective. In 2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC)
(pp. 735-740). IEEE.
[8] Gupta, J., Singh, V., & Kumar, I. (2021, March). Florence-A Health Care Chatbot. In 2021 7 th International Conference on
Advanced Computing and Communication Systems (ICACCS) (Vol. 1, pp. 504-508). IEEE. 34
[9] S. Divya, Indumathi, S. Ishwarya, M. Priyasankari, S. Kalpanadevi | A Self-Diagnosis Medical Chatbot Using Artificial
Intelligence | Institute of Electrical and Electronics Engineers June 2019 Softić, A., Husić, J. B., Softić, A., & Baraković, S.
(2021, March). Health Chatbot: Design, Implementation, Acceptance and Usage Motivation. In 2021 20th International
Symposium INFOTEH-JAHORINA (INFOTEH) (pp. 1-6). IEEE.
[10] Badlani, S., Aditya, T., Dave, M., & Chaudhari, S. (2021, May). Multilingual Healthcare Chatbot Using Machine Learning.
In 2021 2 nd International Conference for Emerging Technology (INCET) (pp. 1-6). IEEE.

PaperID 29
International Journal of Novel Research and Development (www.ijnrd.org)