You are on page 1of 12

Savitribai Phule Pune University

K. K. Wagh Institute of Engineering Education and Research, Nashik


Department of Computer Engineering
Presentation on Artificial Intelligence & Robotics (AI&R)
Mini Project

Cancer Prediction in Early Stages


PID: 26
Guided By: Prof. S.M. Malao
Group members:
DIVISION ROLL NO. NAME OF THE STUDENT
BE-B 29 Ashutosh Srivastava
BE-B 30 Vaibhav Bhavsar
BE-B 31 Vaibhav Chalse
BE-B 32 Vinay Deokar

Monday, July 05, 2021 Cancer Prediction in Early Stages 1


PROBLEM STATEMENT

• The cancer like lung, prostrate, and colorectal cancers contribute up to


45% of cancer deaths. If cancer predicted in its early stages, then it
helps to save the lives. To predict the chances of getting cancer using
Artificial Intelligence/Machine learning techniques before it reaches to
serious stages

Monday, July 05, 2021 Cancer Prediction in Early Stages 2


OBJECTIVES

• Analyzing and exploring the dataset by using data preprocessing


libraries
• Analyzing the dataset by plotting various graphs and visual
representations
• Applying various algorithms on the processed dataset to predict the
chances of getting cancer using classification techniques of Artificial
Intelligence/Machine learning

Monday, July 05, 2021 Cancer Prediction in Early Stages 3


OUTCOMES

• A classification Machine Learning Model to predict the chances (High,


Medium, Low) of getting cancer is developed
• Implemented 4 ML algorithms for improving the efficiency and
accuracy score
• Decision Tree model is giving the best result for each fold

Monday, July 05, 2021 Cancer Prediction in Early Stages 4


DATASET

• There are multiple variables in the dataset which may/may not be the
symptoms getting cancer like pollution, lung diseases, smoking, chest
pain, dry cough, swallowing difficulty, obesity, genetic risk, weight
loss and many more
• The dataset contains 21 different variables and data of over 1000+
patients

Monday, July 05, 2021 Cancer Prediction in Early Stages 5


TOOLS & LIBRARIES USED

TOOLS LIBRARIES

Anaconda Navigator Numpy

Jupyter Notebook Pandas

Language: Python 3.8 Matplotlib

Seaborn

Scikit Learn

Monday, July 05, 2021 Cancer Prediction in Early Stages 6


ALGORITHMS USED

• Logistic Regression
• KNN (K- Nearest Neighbor)
• Decision Tree
• SVM (Support Vector Machine)

Monday, July 05, 2021 Cancer Prediction in Early Stages 7


DEMO

Monday, July 05, 2021 Cancer Prediction in Early Stages 8


EVALUATION MATRICS COMPARISON
JACCARD
ALGORITHM F1 SCORE
SCORE
Logistic Regression 0.985 0.985

Decision Tree 1.0 1.0

KNN 0.985 0.985


SVM (Support
0.985 0.985
Vector Machine)

Decision Tree model is giving the best result for each fold

Monday, July 05, 2021 Cancer Prediction in Early Stages 9


APPLICATIONS
• Medical Science: Artificial Intelligence/Machine Learning is frequently
used in cancer diagnosis and detection. More recently ML has been applied
to cancer prognosis and prediction
• AI methods can be used to substantially (15–25%) improve the accuracy of
predicting cancer susceptibility, recurrence and mortality
• This capability of machines to “learn” from data is particularly well-suited
to medical applications, especially those that depend on complex
proteomic and genomic measurements

Monday, July 05, 2021 Cancer Prediction in Early Stages 10


CONCLUSION

• A Machine Learning model to predict the chances of getting cancer


using AI/ML techniques is developed
• Logistic Regression, KNN, Decision Tree and SVM algorithms are
used while building ML models
• Decision Tree model is giving the best result for each fold

Monday, July 05, 2021 Cancer Prediction in Early Stages 11


THANK YOU!

Monday, July 05, 2021 Cancer Prediction in Early Stages 12

You might also like