Chatbot for health awareness

Under the guidance of :- Presented by :-

Mrs. K.Gayatri G. Sohith Chowdary : 201FA07032
L.Siva Kumar : 201FA07029

Department of Information Technology 1

 Contents

 Abstract

 Introduction

 Literature Review

 Methodology Used

 Project Implementation

 Results

 Conclusion

 Refrences
Department of Information Technology 2
 ABSTRACT

The growing importance of health literacy and preventive care in modern healthcare necessitates
innovative solutions to bridge the gap between individuals and reliable health information. In response
to this, our project introduces a novel health awareness chatbot designed to provide accessible,
personalized, and accurate health guidance to users. Leveraging advanced natural language processing
and machine learning algorithms, the chatbot offers an intuitive interface for users to interact
seamlessly and receive tailored recommendations based on their specific health needs. The project
prioritizes data security and user privacy, incorporating robust encryption measures and regulatory
compliance to ensure the confidentiality of user information. The successful implementation of the
chatbot demonstrates its significant impact in enhancing health literacy and promoting a proactive
approach to wellness management
Department of Information Technology 3
 INTRODUCTION

• Our chatbot is your personal gateway to a treasure trove of health insights. From debunking common myths to
shedding light on the latest breakthroughs in the field of medicine, we are committed to keeping you informed
with credible and up-to-date information. Health is not a one-size-fits-all concept. With that in mind, our
chatbot is designed to personalize your health journey. Whether you're striving for a fitter physique, aiming to
embrace a healthier diet, or seeking advice on managing stress, we've got you covered. Expect tailored
recommendations and achievable goal-setting strategies to ensure that your wellness aspirations become a
tangible reality. In the realm of health, questions are bound to arise. Our chatbot is here to address every single
one of them. No query is too small or insignificant.

08/24/2024 Department Of Information Technology

4
 PROBLEM STATEMENT

• The absence of a comprehensive platform that addresses these challenges results in a reactive healthcare
approach, where individuals often seek medical assistance only after the onset of critical health issues,
leading to increased healthcare costs, burdened healthcare systems, and diminished overall quality of life. In
light of these pressing issues, our health awareness chatbot project aims to bridge this gap by providing
accessible, reliable, and personalized health information and guidance. By leveraging cutting-edge
technology and a user-centric approach, we strive to empower individuals to make informed decisions, adopt
preventive measures, and actively engage in managing their own health, ultimately contributing to improved
health outcomes and a more resilient and well-informed community.

5
 LITERATURE REVIEW

• According to recent research approximately 3.9 million people who are at the age of 18 years old and above are
diagnosed with diabetes in Malaysia. This means that there will be 1 adult in 5 who is diagnosed with diabetes.
The prevalence rate has increased from 13.4% in the year 2015 to 18.3% in the year 2019. This research aims
to raise awareness for fellow Malaysians about diabetes and provide additional functionality for personal care
and healthcare professionals to better manage their resources as healthcare resources are extremely scarce
especially during the pandemic. Investigate studies that evaluate the effectiveness of chatbots in promoting
health awareness and encouraging behavior change

6
 LITERATURE REVIEW

Department of Information Technology 7

 METHODOLOGY

A. DATASET AND EVALUATION MEASURES

To the best of our knowledge, there is no dataset available with real or synthetic information that
associates the patient’s symptoms to her condition. Moreover, due to privacy laws, real clinical data may
not be publicly available even if anonymized. Therefore, we follow the strategy already used in [34] for
dealing with the same limitation. For each of the 217 diseases, we generated k synthetic patients whose
symptoms follow the probability distribute on α for that disease.
B. Incorrect symptom-disease association:
Not all symptoms entered by the user are associated to the reported disease in the knowledge
base. It especially occurs for consultations on the following diseases: ‘‘gastritis’’, ‘‘allergy’’, and
‘‘bronchitis’’. While the last class of errors can be solved by expanding the knowledge base, the first two
are consequences of the classification model. In particular, the model does not take into account the
‘‘rarity’’ of the diseases, and the ranking function prefers diseases that match as much symptoms as
possible. In future work, we will try to solve these problems by introducing the rarity of the disease in the
scoring function, and by extending our knowledge base.

Department Of Information Technology 8

 •1. Data Collection-

• Data is collected from different sources.

• The type of data collected depends upon the type of desired project.

•2. Data Preparation-

• Data preparation is done to clean the raw data.

• Data collected from the real world is transformed to a clean dataset.

•3. Choosing Learning Algorithm-

• The best performing learning algorithm is researched.

• It depends upon the type of problem that needs to solved and the type of data we have

9
10
 SOFTWARE AND HARDWARE REQIREMENTS

 Software Used

 Python

 Visual Studio

 Hardware Used Server:

 Database: The database stores the chatbot's knowledge base. It must be able to store and retrieve data quickly and
efficiently.

 Networking equipment: The networking equipment allows the chatbot to communicate with users and to access the
knowledge base.

 Storage devices: Storage devices are used to store the chatbot's software and data. Input/output devices: Input/output
devices are used to interact with the chatbot, such as keyboards, mice, and touchscreens.
Department of Information Technology 11
PROJECT IMPLEMENTATION & model

Department Of Information Technology 12

 RESULTS

08/24/2024 13
 CONCLUSION

Machine learning-powered chatbots for health awareness have the potential to be a valuable tool for promoting
public health and providing users with accurate and informative health information. By addressing the
challenges mentioned above, we can create chatbots that can provide users with reliable and valuable health
information. Future work Here are some specific areas for future work on machine learning-powered chatbots
for health awareness: Develop more accurate and unbiased machine learning models. This could involve using
techniques such as data augmentation, adversarial training, and federated learning. Make machine learning
models for health awareness chatbots more interpretable. This could involve using techniques such as saliency
maps, model explainability, and counterfactual reasoning. Develop ethical guidelines for the development and
use of machine learning models for health awareness chatbots.

Department of Information Technology 14

 REFRENCES

• [1]. A. J. Zhang, L. Albrecht, S.D. Scott. Using twitter for data collection with health-care consumers: A scoping
review. Int J Qual Methods (2018); 17: 1609406917750782. FIGURE 6. To understand public behaviour related
to medical record keeping.
• [2]. K. Jaiswal, S. Sobhanayak, B. K.Mohanta, et al. IoT-cloud based framework for patient’s data collection in
smart healthcare system using raspberry-pi. In: 2017 International conference on electrical and computing
technologies and applications (ICECTA). (2017), pp. 1–4.
• [3]. C. Pomare,J. C. Long , K. Churruca, et al. Social network research in health care settings: design and data
collection. Soc Networks.
• [4]. D. Agniel, I. S. Kohane, G.M. Weber. Biases in electronic health record data due to processes within the
healthcare system: retrospective observational study. Bmj; 361.
• [5]. A. Kumari A, Tanwar S, Tyagi S, et al. Fog computing for Healthcare 4.0 environment: Opportunities and
challenges. Comput Electr Eng (2018); 72: 1–13.

15
 STATUS OF THE PAPER

08/24/2024 16
08/24/2024 17