1

A SYNOPSIS ON

BLOCKCHAIN AND ML BASED HEALTHCARE SYSTEM

Submitted in partial fulfilment of the requirement for the award of the degree of

BACHELOR OF TECHNOLOGY
IN
COMPUTER SCIENCE & ENGINEERING

Submitted by:
TARUN KHANDURI University Roll No. 2018816
ROHAN SINGH NEGI University Roll No. 2018658
ROHIT SINGH University Roll No. 2018666
PREETAM RAWAT University Roll No. 2018571

Under the Guidance of

Ms. Manisha Aeri

Department of Computer Science and Engineering

Graphic Era Hill University
Dehradun, Uttarakhand
2023-2024
2

CANDIDATE’S DECLARATION
We hereby certify that the work which is being presented in the Synopsis entitled “Blockchain
And ML Based Healthcare System” in partial fulfillment of the requirements for the award
of the Degree of Bachelor of Technology in Computer Science and Engineering in the
Department of Computer Science and Engineering of the Graphic Era Hill University,
Dehradun shall be carried out by the undersigned under the supervision of Ms. Manisha Aeri,
Department of Computer Science and Engineering, Graphic Era Hill University, Dehradun.

TARUN KHANDURI University Roll No. 2018816

ROHAN SINGH NEGI University Roll No. 2018658
ROHIT SINGH University Roll No. 2018666
PREETAM RAWAT University Roll No. 2018571

The above mentioned students shall be working under the supervision of the undersigned on
the “Blockchain And ML Based Healthcare System”

Signature Signature
Supervisor Head of the Department

Internal Evaluation (By DPRC Committee)

Status of the Synopsis: Accepted / Rejected

Any Comments:

Name of the Committee Members: Signature with Date

1.
2.
3

Table of Contents

Chapter No. Description Page No.

Chapter 1 Abstract 4

Chapter 2 Introduction and Problem Statement 5-7

Chapter 3 Background/ Literature Survey 8-10

Chapter 4 Objectives 11-12

Chapter 5 Possible Approach/ Algorithms 13-16

References 17
4

Chapter 1

Abstract

Our Major project focuses on complex healthcare platform using Ethereum blockchain

technology to securely store data, apply machine learning and deep learning techniques for

accurate medical diagnosis, and use blockchain principles to protect user data. By integrating

these cutting-edge technologies, we address critical issues around patient data privacy and

security, deliver accurate medical assessments, and provide a means to connect patients with

Doctors.

Blockchain-powered data security:

We will put our healthcare infrastructure on the Ethereum blockchain to ensure data security

and transparency. This blockchain-powered approach ensures that medical records are stored

seamlessly and gives patients complete control over their own data. The use of smart contracts

automates data management and sharing aspects, increasing platform security and reliability.

User-centered design:

Utilizing modern web development technologies, we will design intuitive and user-friendly

interfaces to provide an intuitive and efficient healthcare experience for all users.

Machine Learning for Specificity:

Our Major Project will use Deep learning algorithms to predict the possible disease and to

recommend precautions. The algorithms will be at the core of our healthcare system, improving

the quality of care patients receive.

5

Chapter
2
Introduction and Problem Statement

2.1 Introduction

Health is a major concern, and the ability to swiftly determine whether one is affected by a

serious or non-serious disease is of immense importance. Real-time disease prediction systems,

combined with immediate precaution recommendations, offer a groundbreaking solution. They

empower individuals to take control of their well-being by providing instant insights into their

health status, enabling early detection of potential health risks, and delivering personalized

guidance on precautionary measures. This reduces the severity and impact of diseases while

enhancing the overall quality of life. In a world where health is the most precious asset, these

systems become a vital ally in the pursuit of well-being and longevity.

Integrating technology into healthcare has become a priority in our ever-evolving world,

leading to online disease prediction and precautionary recommendation systems These new

digital tools offer many benefits and play a vital role in healthcare flexibility, making it more

proactive, accessible and effective.

Timely detection and prevention of diseases Online disease prediction systems harness the

power of machine learning and artificial intelligence to predict the disease based on symptoms

a person is experiencing, lifestyle and genetic predisposition Such discovery this timeliness can

lead to early intervention and preventive measures, which can save lives and reduce the burden

on health care systems. Identifying risk factors and symptoms can alert individuals to the need

for medical advice or lifestyle changes before the disease progresses .

6

Private health care One of the key features of online disease prediction is its ability to provide

relevant health recommendations. By analyzing a person’s data, these systems can provide

precautions which will help a person to create healthy lifestyle. This ensure that patients receive

not only effective but also manageable and sustainable treatment.

In the accessibility feature In a time-constrained world, online disease forecasts and

precautionary tips offer unparalleled convenience. Patients will be able to access health advice

and recommendations in the comfort of their own homes, reducing the need to physically visit

health care facilities. This access is particularly useful for individuals in remote or underserved

areas who may have limited access to health services.

Protecting patient data is a very important issue in healthcare, and the use of Ethereum

blockchain technology appears as an important solution we can understand the importance of

protecting patient data through Ethereum blockchain under the following special features.

Data Privacy and Security: The Ethereum blockchain, which is decentralized and immutable,

provides a robust solution to protect sensitive patient information. By encrypting and storing

data on the blockchain, health systems can prevent unauthorized access and data breaches, and

ensure that patient privacy remains inviolable This level of protection is especially important

at a time when healthcare is a major target of cyberattacks.

Data ownership and control: The Ethereum blockchain empowers patients by giving them

ownership and control over their medical records. Patients can access, share and manage their

data securely, allowing them to communicate seamlessly with healthcare professionals, while

retaining full control over the information.

7

Communication: Blockchain’s ability to facilitate communication across health systems and

organizations ensures that patient information can be shared seamlessly and securely with

authorized users. This allows healthcare professionals to work more closely together, leading

to more accurate diagnosis and personalized treatment plans.

2.2 Problem Statement

The problem statement for the present work can be stated as follows: In an era of exploding
health information and an ever-greater need for accurate timely disease prediction, there is an
urgent challenge: creating a comprehensive health care system that stores patient data controls
and monitors, while at the same time providing improved disease prognosis and precautionary
recommendations Existing healthcare systems often suffer from data security vulnerabilities,
fragmented medical records, and inadequate real-time predictive capabilities, hindering the
efficient delivery of healthcare services This Problem Statement To ensure the privacy and
security of patient data, provide accurate medical research, including blockchain and machine
learning These by integrating well-designed technologies and laying the foundation for
healthcare establishing a complex Seek to address critical issues Facilitates the process of
connecting patients with appropriate health care professionals. The challenge is to create simple
and secure healthcare systems that provides an efficient solution for healthcare information
management, predictive healthcare, and access to healthcare providers quickly.
8

Chapter 3

Background/ Literature Survey

Electronic Health Record

Support Vector Machine or SVM is one of the most popular Supervised Learning algorithms,
which is used for Classification as well as Regression problems. However, primarily, it is used
for Classification problems in Machine Learning.

The goal of the SVM algorithm is to create the best line or decision boundary that can segregate
n-dimensional space into classes so that we can easily put the new data point in the correct
category in the future. This best decision boundary is called a hyperplane.

EHRs using svm algo it is used for predicting diagnoses this research work done and
successfully applied on healthcare facility on Liang et al. 2014 [26]

Long Short-Term Memory Networks is a deep learning, sequential neural network that allows
information to persist. It is a special type of Recurrent Neural Network which is capable of
handling the vanishing gradient problem faced by RNN.

Early detection of preventable diseases is important for better disease management, improved
inter-venations, and more efficient health-care resource allocation. Various machine learning
approached shave been developed to utilize information in Electronic Health Record (EHR)
for this task

In this work we propose a general multi-task framework for disease onset prediction that
combines both free-text medical notes and structured information. We compare performance
of different deep learning architectures including CNN, LSTM and hierarchical this http URL
contrast to traditional text-based prediction models, our approach does not require disease
specific feature engineering, and can handle negations and numerical values that exist in the
text. Our results on a cohort of about 1 million patients show that models using text

outperform model using just structured data, and that models capable of using numerical values
and negations in the text, in addition to the raw text, further improve performance.
Additionally, we compare different visualization methods for medical professionals to interpret
model predictions.
9

Medical Imaging

A Convolutional Neural Network (CNN) is a type of Deep Learning neural network

architecture commonly used in Computer Vision. Computer vision is a field of Artificial
Intelligence that enables a computer to understand and interpret the image or visual data.

When it comes to Machine Learning, Artificial Neural Networks perform really well. Neural
Networks are used in various datasets like images, audio, and text. Different types of Neural
Networks are used for different purposes, for example for predicting the sequence of words we
use Recurrent Neural Networks more precisely an LSTM, similarly for image classification
we use Convolution Neural networks. In this blog, we are going to build a basic building block
for CNN.

Skin cancer, the most common human malignancy, is primarily diagnosed visually, beginning
with an initial clinical screening and followed potentially by dermoscopic analysis, a biopsy
and histopathological examination. Automated classification of skin lesions using images is a
challenging task owing to the fine-grained variability in the appearance of skin lesions. Deep
convolutional neural networks (CNNs) show potential for general and highly variable tasks
across many fine-grained object categories. Here we demonstrate classification of skin lesions
using a single CNN, trained end-to-end from images directly, using only pixels and disease
labels as inputs. We train a CNN using a dataset of 129,450 clinical images-two orders of
magnitude larger than previous datasets-consisting of 2,032 different diseases. We test its
performance against 21 board-certified dermatologists on biopsy-proven clinical images with
two critical

binary classification use cases: keratinocyte carcinomas versus benign seborrheic keratoses;
and malignant melanomas versus benign nevi. The first case represents the identification of the
most common cancers, the second represents the identification of the deadliest skin cancer.

https://pubmed.ncbi.nlm.nih.gov/28117445/
 1

MRI

A Deep Belief Network (DBN) is a sophisticated generative model that employs a deep
architecture. In this article, we are going to learn all about it. After reading this article, you will
have a better understanding of what a Deep Belief Network is, how it works, where to use it,
and how to code your own Deep Belief Network.

Early detection of Alzheimer's disease (AD) is the key of preventing, slowing, and stopping
the disease. An early detection of AD can be performed by analysing the neuro-imaging data.
The magnetic resonance image (MRI) can be used as a modality of neuro-imaging data in order
to detect AD. The MRI also have several advantages such as high-quality of spatial resolution,
widely availability, adequate contrast and without requiring radioactive pharmaceutical
injection during acquisition process. However, the main challenge of structural MRI data
classification is the high dimensionality of the data. Therefore, this study proposes a
classification method of AD based on structural modalities using Deep Belief Network (DBN)
which is has power in term of predictive models. Support vector machine (SVM) has been used
as a comparative classification model against DBN. The result shows that this approach
outperforms SVM and current method in previous study. The DBN achieves 0.9176, 0.9059
and 0.9296 in accuracy, sensitivity and specificity.

https://ieeexplore.ieee.org/document/8265643
1

Chapter 4

Objectives

The objectives of the proposed work are as follows:

4.1 Immutability, decentralization, and transparency

Immutability in blockchain is the property of data stored on a blockchain that cannot be altered,

deleted, or tampered with once it has been added.

This is achieved through:

 Cryptographic hashing

 A decentralized network that stores a copy of the blockchain on each participating node

Decentralization means there is no central control of the blockchain, when a new node is added,

all the other nodes verify it, which makes the transaction more transparent.

4.2 Cryptographic and distributed architecture

The patient’s health records are saved in blockchain in cryptographic form, that only trusted

and authenticated entities can access. Since all the other nodes have copy of complete

blockchain, the blocks cannot be altered without anyone noticing. So data security is provided

by blockchain by this way.

4.3 Patient privacy

The privacy is important for everyone , since the patients have things that they don’t wish to

share with anyone . The records are saved in different blocks using a cryptographic function ,

which hides the actual data so the patient privacy is also provided.
1

4.4 Data integrity and incorruptibility

blockchain specifically protect against manipulation of data, which is immutable once it goes

on the shared ledger. Once data is entered and confirmed through the consensus process,

blockchain technology provides strong protection from further changes, since those changes

would be easily noticed by other participants on the network. Thus, blockchain helps to

establish a higher level of traceability and auditability to data so that any data that was entered

inaccurately prior to consensus can be traced back to its origin.

4.5 Patient control

Patients retain control over how their data is managed and distributed among healthcare

providers, insurance companies, and other stakeholders.

4.6 Disease Prediction Precautions Recommendation

Using ML based algorithms like decision tree algorithm, neural network to predict various

diseases based on the symptoms experienced by the patient which will help patients to take

required precautions that will lead user towards a healthy lifestyle.

 1

Chapter 5

Possible Approach/ Algorithms

5.1 Decision Tree Algorithm

A decision tree is a flowchart-like tree structure in which each node denotes an object, branches
denote a rule and branches denote the results of the algorithm It is a versatile supervised
machine-learning algorithm, used for classification and regression problems. It is one of the
most powerful algorithms. And it is also applied to Random Forest to train various subsets of
training data, making random forest one of the most powerful algorithms in machine learning.

A decision tree works by analysing a set of data to determine how to classify it. It starts at the
root node of the tree, where the algorithm finds the value of the root attribute compared to the
record attribute in the actual data set and follows the branches to the next node based on the
comparison.

The algorithm repeats this process for each subsequent node by comparing its attribute values
with those of the sub-nodes and continuing the process. This is repeated until reaches the leaves
of the tree.
 1

The entire mechanism can be well described using the algorithm described below.

Step 1: Initialize the root node, say S, with the entire data structure.

Step 2: Find the best attribute in the dataset using Attribute Selection Measure (ASM).

Step 3: Divide S into smaller subsets with possible values of the best attributes.

Step 4: Create a decision tree node, with best attributes.

Step 5: Recursively make new decision trees using subsets of the dataset created in Step -3.
Continue this process until you reach a stage where you can no longer classify nodes and call
the last node as the leaf node Classification and Regression Tree algorithm.

5.2 Neural Networks

Neural networks are used to solve Deep Learning problems. Connections of biological neurons
are modelled as weights between nodes. Positive scales reflect stimulatory connections,
whereas negative values indicate inhibitory relationships. All inputs are transformed and
summed with a single weight. This function is called a linear combination. Finally, an
activation function controls the amplitude of the output. For example, the acceptable number
of outputs is usually 0 to 1, or it can be −1 to 1 . These artificial networks can be used for
predictive modelling, adaptive control, and applications that can be trained with a dataset.
1

There are seven types of neural networks.

Multilayer perceptron (MLP): A type of feedforward neural network with three or more layers,
including an input layer, one or more hidden layers, and an output layer It uses nonlinear
activation functions.

Convolutional Neural Network (CNN): A neural network designed to process input data with
a grid-like structure such as an image. It uses a convolutional layer and a pooling layer to
extract features from the input data.

Recursive Neural Network (RNN): A neural network that can operate on a sequence of inputs
of variable length, such as text. Uses weights for structured forecasting.

Recurrent neural network (RNN): A type of neural network that provides connections between
neurons in directed cycles, so that sequential information can be processed.

Long-Term Short-Term Memory (LSTM): A type of RNN designed to overcome the vanishing
gradient problem in training RNNs. It uses memory cells and gateways to selectively read,
write, and delete information.

Sequence-to-Sequence (Seq2Seq): A type of neural network that uses two RNNs to map input
sequences to output sequences, such as translation from one language to another.

Shallow neural networks: Neural networks with only one hidden component, typically used for
simple tasks or as building blocks for larger networks.

5.3 Blockchain

A blockchain is a shared, immutable ledger that makes it easy to record transactions and track
assets between transactions Assets can be tangible (house, car, money, land) or intangible
(ideas). internal property, license, copyright, brand). In fact, anything of value can be tracked
and traded on the blockchain network, reducing risk and reducing costs for all involved.
 1

How blockchain works :

As each transaction progresses it is recorded as a “piece” of data Those interactions determine

the movement of an asset that can be tangible (material) or intangible (conceptual). The data
block can record arbitrary information: who, what, when, where quantity and even status —
such as the temperature of food delivered Each section is linked to the sections before and after
it These parts form the data chain as assets move from location to location or ownership
changes hands. Blocks highlight the precise timing and order of execution and combine blocks
carefully so that no block is modified or a block is inserted between two existing blocks
Transactions are blocked in an immutable chain: blockchain Each block added is a validation
of the previous block thus strengthening the entire blockchain. This makes the blockchain
tamper-clear and puts more emphasis on immutability. This eliminates the chance of being
modified by a malicious party — and allows you and other network members to rely on a ledger
of transactions.
1

References

[1] Decision Tree Algorithm Geeks for geeks = https://www.geeksforgeeks.org/decision-tree/

[2] Neural Networks Wikipedia = https://www.wikiwand.com/en/Neural_network

[2] Blockchain IBM = https://www.ibm.com/topics/blockchain