Special Issue - 2019 International Journal of Engineering Research & Technology (IJERT)

ISSN: 2278-0181
CONFCALL - 2019 Conference Proceedings

Health Diagnosis by using Machine Learning

Algorithm
N. Tejaswini P. Veeramuthu
Dept of CSE Assisant Professor
Besant Theosophical College Dept of CSE
Besant Theosophical College

Abstract:- In medical imaging, Computer Aided Diagnosis tries to find out the similarities between the input data and
(CAD) is a rapidly growing dynamic area of research. In based on these similarities, un-supervised learning
recent years, significant attempts are made for the technique classify the data. This is also known as density
enhancement of computer aided diagnosis applications estimation. Unsupervised learning contains clustering
because errors in medical diagnostic systems can result in
seriously misleading medical treatments. Machine learning is
[1].Clustering: it makes clusters on the basis of similarity.
important in Computer Aided Diagnosis. After using an easy
equation, objects such as organs may not be indicated 3) SEMI SUPERVISED LEARNING: Semi supervised
accurately. So, pattern recognition fundamentally involves learning technique is a class of supervised learning
learning from examples. In the field of bio-medical, pattern techniques. This learning also used unlabeled data for
recognition and machine learning promise the improved training purpose (generally a minimum amount of labeled-
accuracy of perception and diagnosis of disease. They also data with a huge amount of unlabeled-data). Semi-
promote the objectivity of decision-making process. For the supervised learning lies between unsupervised-learning
analysis of high-dimensional and multimodal bio-medical data, (unlabeled-data) and supervised learning (labeled-data).
machine learning offers a worthy approach for making classy
and automatic algorithms. This survey paper provides the
comparative analysis of different machine learning algorithms
for diagnosis of different diseases such as heart disease,
diabetes disease, liver disease, dengue disease and hepatitis
disease. It brings attention towards the suite of machine
learning algorithms and tools that are used for the analysis of
diseases and decision-making process accordingly.

Keywords: Machine Learning, Artificial Intelligence, Machine

Learning Techniques

INTRODUCTION:

Artificial Intelligence can enable the computer to think.

Computer is made much more intelligent by AI. Machine
learning is the subfield of AI study. Various researchers
think that without learning, intelligence cannot be
developed. There are many types of Machine Learning 4) REINFORCEMENT LEARNING: This learning is
Techniques that are shown in Figure 1. Supervised, encouraged by behaviorist psychology. Algorithm is
Unsupervised, Semi Supervised, Reinforcement, informed when the answer is wrong, but does not inform
Evolutionary Learning and Deep Learning are the types of that how to correct it. It has to explore and test various
machine learning techniques. These techniques are used to possibilities until it finds the right answer. It is also known
classify the data set. as learning with a critic. It does not recommend
improvements. Reinforcement learning is different from
1) SUPERVISED LEARNING: Offered a training set of
supervised learn-ing in the sense that accurate input and
examples with suitable targets and on the basis of this
output sets are not offered, nor suboptimal actions clearly
training set, algorithms respond correctly to all feasible
précised. Moreover, it focuses on on-line performance.
inputs. Learning from exemplars is another name of
Supervised Learning. Classification and regression are the 5) EVOLUTIONARY LEARNING: This biological
types of Supervised Learning .Classification: It gives the evolution learning can be considered as a learning process:
prediction of Yes or No, for example, “Is this tumor biological organisms are adapted to make progress in their
cancerous?”, “Does this cookie meet our quality survival rates and chance of having off springs. By using
standards?”Regression: It gives the answer of “How much” the idea of fitness, to check how accurate the solution is,
and “How many”. we can use this model in a computer
2) UNSUPERVISED LEARNING: Correct responses or 6) DEEP LEARNING: This branch of machine learning is
targets are not provided. Unsupervised learning technique based on set of algorithms. In data, these learning

Volume 7, Issue 11 Published by, www.ijert.org 1

Special Issue - 2019 International Journal of Engineering Research & Technology (IJERT)
ISSN: 2278-0181
CONFCALL - 2019 Conference Proceedings

algorithms model high-level abstraction. It uses deep disease prediction. In terms of time execution, Naives
graph with various processing layer, made up of many bayes takes less time as compared to the SVM.
linear and nonlinear transformation.
Proposed system :Discussions and Analysis of Machine
EXISTING SYSTEM: Diagnosis of Diseases by Using Learning Techniques For diagnosis of Heart, Diabetes,
Different Machine Learning Algorithms Many researchers Liver, Dengue and Hepatitis diseases, several machine-
have worked on different learning algorithms for disease learning algorithms perform very well. From existing
diagnosis. Researchers have been accepted that machine- literature, it is observed that Naive Bayes Algorithm and
learning algorithms work well in diagnosis of different SVM are widely used algorithms for detection of diseases.
diseases. Figurative approach of diseases diagnosed by Both algorithms offer the better accuracy as compare to
Machine Learning Techniques is shown in Figure 2. In this other algorithms. Artificial Neural network is also very
survey paper diseases diagnosed by MLT are heart, useful for prediction. It also shows the maximum output
diabetes, liver, dengue and hepatitis. but it takes more time as compared to other algorithms.
Trees algorithm are also used but they did not attain wide
acceptance due to its complexity. They also shows
enhanced accuracy when it responded correctly to the
attributes of data set. RS theory is not widely used but it
presents maximum output.

HEART DISEASE:

Otoometal. [5] presented a system for the purpose of

analysis and monitoring. Coronary artery disease is
detected and monitored by this proposed system. Cleveland
heart data set is taken from UCI. This data set consists of
303 cases and 76 attributes/features. 13 features are used
out of 76 features. Two tests with three algorithms Bayes CONCLUSION:
Net, Support vector machine, and Functional Trees FT are
performed for detection purpose. WEKA tool is used. Statistical models for estimation that are not capable to
produce good performance results have flooded the
DIABETES DISEASE: assessment area. Statistical models are unsuccessful to hold
categorical data, deal with missing values and large data
Iyer et al. [11] has performed a work to predict diabetes points.
disease by using decision tree and Naive Bayes. Diseases
occur when production of insulin is insufficient or there is All these reasons arise the importance of MLT. ML plays a
improper use of insulin. Data set used in this work is Pima vital role in many applications, e.g. image detection, data
Indian diabetes data set. Various tests were performed mining, natural language processing, and disease
using WEKA data mining tool. In this data-set percentage diagnostics. In all these domains, ML offers possible
split (70:30) predict better than cross validation. J48 shows solutions. This paper provides the survey of different
74.8698% and 76.9565% accuracy by using Cross machine learning techniques for diagnosis of different
Validation and Percentage Split Respectively. Naive Bayes diseases such as heart disease, diabetes disease, liver
presents 79.5652% correctness by using PS. Algorithms disease, dengue and hepatitis disease. Many algorithms
shows highest accuracy by utilizing percentage split test. have shown good results because they identify the attribute
accurately. From previous study, it is observed that for the
LIVER DISEASE: detection of heart disease, SVM provides improved
accuracy of 94.60%. Diabetes disease is accurately
Vijayarani and Dhayanand [17] predict the liver disease by diagnosed by Naive Bayes. It offers the highest
using Support vectormachine and Naive bayes
classification accuracy of 95%. FT provides 97.10% of
Classification algorithms. ILPD data set is obtained from
correctness for the liver disease diagnosis. For dengue
UCI. Data set comprises of 560 instances and 10 attributes.
disease detection, 100% accuracy is achieved by RS theory.
Comparison is made on the basis of accuracy and time
The feed forward neural network correctly classifies
execution. Naive bayes shows 61.28% correctness in hepatitis disease as it provides 98% accuracy. Survey
1670.00 ms. 79.66% accuracy is attained in 3210.00 ms by highlights the advantages and disadvantages of these
SVM. For implementation, MATLAB is used. SVM shows
algorithms. Improvement graphs of machine learning
highest accuracy as compared to the Naive bayes for liver
algorithms for prediction of diseases are presented in detail.

Volume 7, Issue 11 Published by, www.ijert.org 2

Special Issue - 2019 International Journal of Engineering Research & Technology (IJERT)
ISSN: 2278-0181
CONFCALL - 2019 Conference Proceedings

From analysis, it can be clearly observed that these [18] Gulia, A., Vohra, R. and Rani, P. (2014) Liver Patient
Classification Using Intelligent Techniques. (IJCSIT) International
algorithms provide enhanced accuracy on different diseases.
Journal of Computer Science and Information Technologies, 5,
This survey paper also provides a suite of tools that are 5110-5115.
developed in community of AI. These tools are very useful [19] Rajeswari, P. and Reena,G.S. (2010) Analysis of Liver Disorder
for the analysis of such problems and also provide Using Data Mining Algorithm. Global Journal of Computer
Science and Technology, 10, 48-52.
opportunity for the improved decision making process.
[20] Tarmizi, N.D.A., Jamaluddin, F., Abu Bakar, A., Othman, Z.A.,
Zainudin, S. and Hamdan, A.R. (2013) Malaysia Dengue Outbreak
REFERENCES: Detection Using Data Mining Models. Journal of Next Generation
Information Technology (JNIT), 4, 96-107.
[1] Marshland, S. (2009) Machine Learning an Algorithmic
Perspective. CRC Press,New Zealand, 6-7.
[2] Sharma, P. and Kaur, M. (2013) Classification in Pattern
Recognition: A Review. International Journal of Advanced
Research in Computer Science and Software Engineering, 3, 298[3]
[3] Rambhajani, M., Deepanker, W. and Pathak, N. (2015) A Survey
on Implementation of Machine Learning Techniques for
Dermatology Diseases Classification. International Journal of
Advances in Engineering & Technology, 8, 194-195.
[4] Kononenko, I. (2001) Machine Learning for Medical Diagnosis:
History, State of the Art and Perspective. Journal of Artificial
Intelligence in Medicine, 1, 89-109.[5] Otoom, A.F., Abdallah,
E.E., Kilani, Y., Kefaye, A. and Ashour, M. (2015)
[5] Effective Diagnosis and Monitoring of Heart Disease. International
Journal of Software Engineering and Its Applications. 9, 143-156.
[6] Vembandasamy, K., Sasipriya, R. and Deepa, E. (2015) Heart
Diseases Detection Using Naive Bayes Algorithm. IJISET-
International Journal of Innovative Science,Engineering &
Technology, 2, 441-444.
[7] Chaurasia, V. and Pal, S. (2013) Data Mining Approach to Detect
Heart Disease. International Journal of Advanced Computer
Science and Information Technology
(IJACSIT), 2, 56-66.
[8] Parthiban, G. and Srivatsa, S.K. (2012) Applying Machine
Learning Methods in Diagnosing Heart Disease for Diabetic
Patients. International Journal of Applied Information Systems
(IJAIS), 3, 25-30.
[9] Tan, K.C., Teoh, E.J., Yu, Q. and Goh, K.C. (2009) A Hybrid
Evolutionary Algorithm for Attribute Selection in Data Mining.
Journal of Expert System with Applications, 36, 8616-8630.
https://doi.org/10.1016/j.eswa.2008.10.013
[10] Karamizadeh, S., Abdullah, S.M., Halimi, M., Shayan, J. and
Rajabi, M.J. (2014) Advantage and Drawback of Support Vector
Machine Functionality. 2014 IEEE InternationalConference on
Computer, Communication and Control Technology (I4CT),
Langkawi, 2-4 September 2014, 64-65.
https://doi.org/10.1109/i4ct.2014.6914146
[11] Iyer, A., Jeyalatha, S. and Sumbaly, R. (2015) Diagnosis of
Diabetes Using Classification Mining Techniques. International
Journal of Data Mining & Knowledge Management Process
(IJDKP), 5, 1-14. https://doi.org/10.5121/ijdkp.2015.5101
[12] Sen, S.K. and Dash, S. (2014) Application of Meta Learning
Algorithms for the Prediction of Diabetes Disease. International
Journal of Advance Research in Computer Science and
Management Studies, 2, 396-401.
[13] Kumari, V.A. and Chitra, R. (2013) Classification of Diabetes
Disease Using Support Vector Machine. International Journal of
Engineering Research and Applications (IJERA), 3, 1797-1801.
[14] Sarwar, A. and Sharma, V. (2012) Intelligent Naïve Bayes
Approach to Diagnose Diabetes Type-2. Special Issue of
International Journal of Computer Applications (0975-8887) on
Issues and Challenges in Networking, Intelligence and Computing
Technologies-ICNICT 2012, 3, 14-16.
[15] Ephzibah, E.P. (2011) Cost Effective Approach on Feature
Selection using Genetic Algorithms and Fuzzy Logic for Diabetes
Diagnosis. International Journal on Soft Computing(JSC), 2, 1-10.
https://doi.org/10.5121/ijsc.2011.2101
[16] Archana, S. and DR Elangovan, K. (2014) Survey of Classification
Techniques in Data Mining. International Journal of Computer
Science and Mobile Applications, 2, 65-71
[17] Vijayarani, S. and Dhayanand, S. (2015) Liver Disease Prediction
using SVM and Naïve Bayes Algorithms. International Journal of
Science, Engineering and Technology Research (IJSETR), 4, 816-
820.

Volume 7, Issue 11 Published by, www.ijert.org 3