International Journal of Recent Technology and Engineering (IJRTE)
ISSN: 2277-3878, Volume-8 Issue-5, January 2020
5353
Published By:
Blue Eyes Intelligence Engineering
& Sciences Publication
Retrieval Number: E6754018520/2020©BEIESP
DOI:10.35940/ijrte.E6754.018520
Prediction of Prostate Cancer using Machine
Learning Algorithms
Muktevi Srivenkatesh
Abstract: Background/Aim: Prostate cancer is regarded as
the most prevalent cancer in the word and the main cause of
deaths worldwide. The early strategies for estimating the prostate
cancer sicknesses helped in settling on choices about the
progressions to have happened in high-chance patients which
brought about the decrease of their dangers. Methods: In the
proposed research, we have considered informational collection
from kaggle and we have done pre-processing tasks for missing
values .We have three missing data values in compactness
attribute and two missing values in fractal dimension were
replaced by mean of their column values .The performance of the
diagnosis model is obtained by using methods like classification,
accuracy, sensitivity and specificity analysis. This paper proposes
a prediction model to predict whether a people have a prostate
cancer disease or not and to provide an awareness or diagnosis
on that. This is done by comparing the accuracies of applying
rules to the individual results of Support Vector Machine,
Random forest, Naive Bayes classifier and logistic regression on
the dataset taken in a region to present an accurate model of
predicting prostate cancer disease. Results: The machine
learning algorithms under study were able to predict prostate
cancer disease in patients with accuracy between 70% and 90%.
Conclusions: It was shown that Logistic Regression and Random
Forest both has better Accuracy (90%) when compared to
different Machine-learning Algorithms.
Keywords: Cardiovascular disease, Machine Learning
Algorithms, Performance Evaluators, toxins
I. INTRODUCTION
Classification is significant component of data mining
.Classification is the way toward finding a model (or
capacity) that depicts and recognizes information classes or
ideas. The model is inferred dependent on the investigation
of a lot of preparing
Prostate data (i.e., data objects for which the class marks
are known).
The model is utilized to foresee the class name of items
for which the class name is having the prostate cancer
malady or not having prostate cancer ailment that is obscure.
Machine Learning examines how computers can learn (or
improve their exhibition) in view of prostate cancer
information. The primary research zone is for computer
projects to consequently figure out how to perceive complex
examples and settle on clever choices dependent on Prostate
Cancer data.
Supervised learning is fundamentally an equivalent word
for arrangement. The supervision in the taking in originates
from the named models in the Prostate Cancer preparing
data collection.
Revised Manuscript Received on January 24, 2020.
Dr. M, Srivenkatesh, Associate Professor, Department of Computer
Science, GITAM Deemed to be University, Visakhapatnam, India.
Email:msvenkatesh9@gmail.com
Prostate Cancer is very important health issue and needs
to have very much need to take care. There has been a lot of
research on cancer diagnosis by using machine learning
techniques. In [1], Decision Tree, Logistic Regression (LR)
and Artificial Neural Network (ANN) are employed to
evaluated prostate cancer survivability. Cancer survival
forecasting may be attempted using model constructed
through predictive techniques of various kinds, including
statistical multivariate regression and machine learning [2].
The remaining of the research discussion is organized as
follows: Section II briefs Literature , Section III describes
brief description of selected machine learning algorithms
Section IV describes Patient Data Set and attributes, Section
V discusses Proposed Technique ,Section VI describes
analysis of various algorithms, Section VII Describes
Performance measure of classification, Section VIII briefs
discussion and evaluated Results, and Section X determines
the Conclusion of the research work and last Section
describes References.
Prostate Cancer and its Symptoms
Prostate malignant growth is a typical sort of disease in
guys, however it is exceptionally treatable in the beginning
times. It starts in the prostate organ, which sits between the
penis and the bladder.
The prostate has different capacities, including:
producing the liquid that sustains and ship sperm.
secreting prostate explicit antigen (PSA), a protein that
assists semen withholding its fluid state.
helping aid urine control.
Guys who do encounter side effects may take note:
difficulty beginning and looking after urination
a visit desire to urine, particularly around evening time
blood in the urine or semen
painful urination
in a few cases, torment on discharge
difficulty getting or keeping up an erection
pain or uneasiness when sitting, if the prostate is
broadened
Propelled indications
Propelled prostate malignant growth can include the
accompanying indications:
bone break or bone torment, particularly in the hips,
thighs, or shoulders
edema, or growing in the legs or feet
weight misfortune
tiredness
changes in gut propensities
back torment