PES’s Modern College of Engineering

Department of Information Technology

Parkinson’s Disease
Detection

Swapnil Parasahre(37060)
Atharva Patil(37062)
Jayesh Lohade(37045)
Hrishikesh Suryakar(37077)

1
 INDEX
Contents Page No.
1.Introduction 3
2. REQUIRMENT SPECIFICATION 4
AND ANALYSIS

3.Work Flow 8

4.DESIGN DETAILS AND 9

IMPLEMENTATION

5.Conclusion 11
6.Refrence 12
2
● Introduction-
❏ The brain is the main controller of our body. Therefore, any
damage to this sensitive part of the human body will affect
badly on the other organs.
❏ One of these negative effects is Parkinson’s disease.
Parkinson’s disease (PD) is a chronic, progressive,
neurodegenerative disorder which begins when a certain
area of the brain has been damaged. PD symptoms overlap
with other diseases like normal ageing and essential tremor,
especially in the early stages of these diseases.
❏ Thus, it is important to differentiate between PD and other
diseases in order to give the right treatment to the patient.

3
❖ REQUIRMENT SPECIFICATION AND ANALYSIS-
Languages Used: -Python – Main language used for Data-Science related
projects.

● Libraries Used: -
1. Matplotlib – Library used for visualizing datasets.
2. Scikt-Learn – Used for training and implementing.
3. NumPy
4. pandas
5. sklearn.model_selection 4
● Algorithm Used: -
SVM (Support Vector Machine): Another algorithm for the
analysis of classification and regression is the support vector machine. It is a
supervised machine algorithm used. Image classification and hand-written recognition
are where the support vector machine comes to hand used. It sorts the data in one
out of two categories and displays the output with the margin between the two as far
as possible.

5
● Algorithm-
Support Vector Machine Algorithm:

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.

SVM chooses the extreme points/vectors that help in creating the hyperplane. These
extreme cases are called as support vectors, and hence algorithm is termed as Support
Vector Machine. Consider the below diagram in which there are twodifferent categories that
are classified using a decision boundary or hyperplane: 6
7
● Work Flow Diagram -

8
DESIGN DETAILS AND IMPLEMENTATION-

● Dataset description:
This dataset is composed of a range of biomedical voice measurements from 31 people, 23 with
Parkinson's disease (PD). Each column in the table is a particular voice measure, and each row
corresponds one of 195 voices recording from these individuals ("name" column). The main aim of the
data is to discriminate healthy people from those with PD, according to "status" column which is set to 0
for healthy and 1 for PD.

● Data pre-processing:

In the main database, not all measurements are provided for each patient. As most machine learning
algorithms require fully-ranked data, this necessitated preprocessing. Several strategies were
considered:
· _ Dropping patients that did not have measurements for all tests reported.
· _ Dropping tests that did not have measurements for all patients. 9
● Result-

10
 ● Conclusion-

As demonstrated, a machine learning model can effectively learn to diagnose Parkinson's disease in a patient
with high accuracy (94%), precision (95%),and recall (91%) across the data of over 2800 patients. Because this
diagnosisrelies on a small subset of medical tests, it is possible to assist clinicians in making Parkinson's
diagnoses with confidence. This high sample size is an important step forward in understanding improved
diagnosis and lends a great deal of confidence and credibility in the machine learning.

Further research could examine the ability of combining a supervised algorithm to isolate
predictive features with unsupervised learning to improve two-dimensional projections of the
data. Further research into new predictors of Parkinson's disease particularly at an early stage is
also needed. Additionally, only healthy patients were used in this analysis. A machine learning
model with similar accuracy, precision, and recall may be possible for a model considering
11
multiple related diagnoses.
● References-

1. Parkinson’s Disease Detection using Machine Learning Techniques by Radha

N, Sachin Madhavan RM, Sameera holy S

2. Machine Learning for Effective Parkinson's Disease Diagnosis by Brennon

Brimhall

3. Early detection of parkinson’s disease using machine learning by Anitha ,

Nandhini , Sathish Raj , Nikitha

4. Parkinson’s Disease Diagnosis Using Machine Learning and Voice by Timothy

Wroge, Yasin Serdar Ozkanca, Cenk Demiroglu

12
Thank You

13