Professional Documents
Culture Documents
Synopsis
Submitted for the partial fulfillment of the requirement for the award of Degree of
BACHELOR OF TECHNOLOGY
IN
COMPUTER SCIENCE AND ENGINEERING
I hereby declare that the work which is being presented in the Synopsis
Major Project “MediQue- Artificial Intelligence based Chatbot” submitted
in partial fulfillment of the requirement for the award of Bachelor Degree
in Computer Science & Engineering. The work has been carried out at
University Institute of Technology, RGPV, Bhopal is an authentic record of
our work carried under the guidance of Prof. Praveen Kaithal, Department
of Computer Science and Engineering,UIT-RGPV, Bhopal.
The matter written in this synopsis has not been submitted by us for the
award of any other degree.
Shriya Pandey
Atiya Akhtar
Sambodhi Dubey
Shubhanshi Bhandari
ACKNOWLEDGEMENT
1. Introduction
2. Literature Survey and related work
3. Problem Description
4. Proposed Work
5. Design and Modeling of Work
6. Description of tools/hardware/software which will be used in the
project
7. Expected Outcome
8. Conclusion and Expected Future work
INTRODUCTION
Medical advances have got to the point where we can treat a wider
number of diseases, there are new diagnostic and treatment methods
emerging, pharmacology produces an increasingly higher number of
drugs for different diseases, ages, body types, etc. This creates a huge
amount of reference information that doctors must either know or be able
to remember, which requires many years of practice and continuous
learning. At the very least, they need easy access to that information.
Here is what the AI-powered chatbots aim to do. As for patients, chatbots
help them to make decisions about whether they should see a specialist
and if so, which one, provides answers to basic questions and reminds
them to take their medication. Doctors may prescribe medications to help
patients manage various health conditions. But one of the biggest
challenges is getting patients to take their medications as recommended.
A study found that approximately 50% of patients don’t take their
medications properly or forget to do so altogether. Chatbots can not only
be used to dispense medical advice, but also to send daily reminders to
patients.
Medical chatbots are AI-powered conversational solutions that help
patients, insurance companies, and healthcare providers easily connect
with each other. These bots can also play a critical role in making relevant
healthcare information accessible to the right stakeholders, at the right
time. From enhancing patient experience and helping medical
professionals, to improving healthcare processes and unlocking
actionable insights, medical or healthcare chatbots can be used for
achieving various objectives. Medical chatbots are one of the most
matured and influential AI-powered healthcare solutions developed so far.
Literature Survey and Related Work
● Your.MD
Designed to help patients find the healthcare information they need
to stay healthy, MD offers various features and functions. However,
what stands apart from all the other features is its symptom checker.
Available on the web and as a stand-alone app, it acts as a personal
health assistant allowing users to check symptoms, ask a question,
or take a health quiz.
Pros: The chatbot uses a vast repository of reliable healthcare
information to offer relevant answers to all user queries. And best of
all, it is available for free.
Cons: Language understanding capabilities are limited in this
chatbot, which negatively impacts the experience.
● Sensely
Sensely helps insurers, healthcare service providers, businesses,
and pharma companies build custom solutions to bridge the gap
between low fidelity chatbots and high-quality human
communications. From underwriting, claims handling, and symptom
assessment to customer service, employee wellness, and clinical
trials, it offers a wide range of capabilities. It is important to
understand that Sensely is not a chatbot; instead, it offers the
platform and pre-built capabilities required to build different types of
medical chatbots.
Pros: It is possible to build a unique brand persona using various
characters with Sensely.
Cons: We are still a long way from truly embodying empathy with AI.
While the concept is good, its practical implications remain to be
seen.
● NINA (AskNestlé)
Built using Senseforth’s conversational AI platform A.ware, NINA is
one of India’s first AI-powered digital nutritionists. NINA helps young
parents create a daily meal plan for their children. Parents can
customize the meal plan to address specific nutritional requirements,
find innovative recipes to make the fussy eaters happy, set
reminders, and even keep a food journal. Parents can interact with
Nina on Google Assistant or the website. The bot handles around
50,000 queries each month.
Pros: Information provided by the chatbot is very interesting and
contextual.
Cons: Content has been curated keeping Indian audience in mind.
Hence, a lot more contextualization is required to cater to the needs
of a global audience.
● Ada
This medical chatbot brings together doctors, scientists, and industry
pioneers to improve the quality of personal healthcare. Instead of
banking only on a repository of information, Ada compares user
queries with thousands of similar cases. It then analyzes its findings
against the information available in the medical library to craft a
much more relevant and contextual response.
Pros: Ada puts access in the hands of the users.
Cons: Again, limited natural language understanding capabilities
negatively impact the user experience.
● SafedrugBot
This is another good example of how a simple solution like a chatbot
can make a huge difference. SafedrugBot offers guidance to medical
practitioners about the usage of drugs by breastfeeding mothers.
From understanding the side effects of various drugs to finding safer
alternatives, it helps doctors tap into a vast knowledge hub to
augment their capabilities. This chatbot is available on Telegram.
Pros: SafedrugBot helps doctors easily verify drug-related
information.
Cons: It’s available on only one messaging platform and fails to
deliver an omnichannel experience.
UML showing the use cases of MediQue Chatbot:
Data flow diagram of the medical chatbot:
LITERATURE REVIEW
Here the studies are based on recognizing emotions classification using
AI methods. The studies train emotions classification models from a lot of
labelled data based on recurrent neural network (RNN), deep learning,
and convolutional neural network. Linguistic interaction is most important
in counselling using Natural Language Processing (NLP) and
Natural-language generation (NLG) to understand dialogues of users.
Here the multi-modal approach is used for emotion-recognition. They
have collected corpuses to learn semantic information of words and
represent them as vectors using the word vector, synonym knowledge of
lexicals are collected.
Here they use n-gram technique for extracting the words from the
sentences. Here n-gram is used for comparison and deduction of the
input with case data using Moro phonemes and phonemes as the
deciding parameter. Probability analysis for the closest match is
performed. The final expression is redirected through an expert system.
The chatbot developed here for healthcare purposes for the android
application. The user sends the text message or voice message using
Google API. Here the user gets only related answer from the chatbot.
SVM algorithm is used to classify the dataset. Here the Porter algorithm
is used to discard unwanted words like suffixes or prefixes.
Here the chatbot is created for the customer service that functions as
public health service. The application uses Ngram, TF-IDF and cosine
similarity. The knowledge base is created for storing the question and
answer. The application clearly shows extracted the keyword from the
question and by using unigram, bigram, and trigram which helps in fast
answering.
1) Waiting Time
5) Appointment Scheduling
Scheduling an appointment over the phone can be extremely
time-consuming for all parties involved. A patient would need to phone
their local clinic and the operator would need to check their schedule to
see what slots are available. All of this back-and-forth can lead to higher
administrative costs.
7) Patient Feedback
Software Requirement:
● Windows 7 or higher
● WAMP Server
● Notepad++
● My SQL 5.6
● Google Chrome Browser
EXPECTED OUTCOME
This is just one example of how chatbots are being used in the
healthcare industry. Another benefit is that chatbots are
available 24/7 to help people in need.
Chatbots can also link to relevant pages. For example, a user
looking for medical alert systems can be directed to the right
page or connect with a representative if they still have
additional questions.
● Appointment Scheduling
● Patient Feedback
2. Amato, F., Marrone, S., Moscato, V., Piantadosi, G., Picariello, A., Sansone, C.:
4. Bali, M., Mohanty, S., Chatterjee, S., Sarma, M., Puravankara, R.: Diabot: A
5. Bao, Q., Ni, L., Liu, J.: Hhh: an online medical chatbot system based on
knowledge