IRJET- Review on Knowledge Discovery and Analysis in Healthcare using Data Mining
0 likes17 views
This document summarizes a research paper that reviews the use of data mining techniques in healthcare and medicine. It discusses how data mining can help healthcare organizations make better decisions, identify effective treatments, and provide more affordable care by analyzing large amounts of complex healthcare data. The document then reviews several past studies on applying data mining for medical tasks like predicting diseases. It also summarizes different data mining algorithms that have been used, such as Apriori for association rule mining. Finally, the document proposes a system to recommend lower-cost alternative medicines to users based on clustering similar drugs and classifying inputs.
![International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 05 Issue: 03 | Mar-2018 www.irjet.net p-ISSN: 2395-0072
© 2018, IRJET | Impact Factor value: 6.171 | ISO 9001:2008 Certified Journal | Page 1457
Review on Knowledge Discovery And Analysis in Healthcare Using
Data Mining
Miss. Sheetal A. Tayade1, Prof. Parag D. Thakare2
1M.E. Scholar, Department of Computer Science & Engineering, Jagadambha College of Engineering & Technology,
Yavatmal, Maharashtra, India
2Professor, Department of Computer Science & Engineering, Jagadambha College of Engineering & Technology,
Yavatmal, Maharashtra, India
----------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - On the Internet, where the number of choices is
overwhelming, there is need to filter, prioritize and
efficiently deliver relevant information in order to alleviate
the problem of information overload, which has created a
potential problem to many Internet users. The Proposed
System solve this problem by searching through large
volume of dynamically generated information to provide
users with personalized content and services. The focus of
this paper will be on pharmaceutical institutions and
information regarding medicines. Frequent unbalanced
distribution of medicines in healthcare institutions may
result with serious threats to the health condition of a
person. This provides health care institutions, medicine
manufacturers and public in general to have insight to the
information of the medicine. Thus the proposed system
called Alternate Medicine System will be use to create a
public awareness about alternative drugs for a particular
medicine, availability of that alternative medicine in a
locality This is very useful for public.
Key Words: Data Mining, Healthcare, Predictive
Analytics
1. INTRODUCTION
Data mining technology provides a user oriented
approach to novel and hidden information in the data.
Valuable knowledge can be discovered from application of
data mining techniques in healthcare system. Data mining
in healthcare medicine deals with learning models to
predict patients’ disease. Data mining applications can
greatly benefit all parties involved in the healthcare
industry. For example, data mining can help healthcare
insurers detect fraud and abuse, healthcare organizations
make customer relationship management decisions,
physicians identify effective treatments and best practices,
and patients receive better and more affordable
healthcare services. The huge amounts of data generated
by healthcare transactions are too complex and
voluminous to be processed and analyzed by traditional
methods. Data mining provides the methodology and
technology to transform these mounds of data into useful
information for decision making.
2. LITERATURE REVIEW
In this section, an attempt has been made to briefly
touch upon some of the mentionable reviews in this
domain that has been conducted in last 9-10 years. Paper
[12], is a reference work with survey in medical data and
biomedicine, and covers elaborate reviews on machine
learning models. However, the focus has been more
machine learning and data mining oriented and in some
cases the categorizations have been not very clear. In
another paper [13], authors have discussed few
motivating cases of data mining in healthcare along with
the results. The paper focuses primarily on classification
tasks in healthcare and discusses three models, namely
rule induction, decision tree and neural network. In the
seminal work presented in [2], the authors have given
various cross sectional views (By tasks, By Models, By type
of data) of the data mining use cases. However, the
discussions have not been from the point of view of the
health care entities. [3] Discusses some interesting aspects
of data mining in healthcare, however, it focuses more on
public health and medicine and coverage of machine
learning models are also limited. Some of the surveys have
been more specific. As an example [4], focuses on the
application of a particular model (Neural Network) in
medical science. Some of the surveys have been on
narrowed scopes where they have reviewed particular
health care problems as example prediction of heart
disease [5], [6], [7].
Different algorithms used in Different papers. The AIS
algorithm is the first published algorithm developed to
produce all large itemsets in a transaction database [10].
This algorithm has targeted to discover qualitative rules.
This technique is limited to only one item in the
consequent. This algorithm makes multiple passes over
the entire database. The SETM algorithm is proposed in
[8] and motivated by the desire to use SQL to calculate
large itemsets [11]. In this algorithm each member of the
set large itemsets, Lk, is in the form <TID, itemset> where
TID is the unique identifier of a transaction Similarly, each
member of the set of candidate itemsets, Ck, is in the form
<TID, itemset>. Similar to [10], the SETM algorithm makes
multiple passes over the database. The Apriori algorithm
[9] is a great success in the history of mining association
rules. It is by far the most well-known association rule](https://image.slidesharecdn.com/irjet-v5i3328-190122054855/85/IRJET-Review-on-Knowledge-Discovery-and-Analysis-in-Healthcare-using-Data-Mining-1-320.jpg)
![International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 05 Issue: 03 | Mar-2018 www.irjet.net p-ISSN: 2395-0072
© 2018, IRJET | Impact Factor value: 6.171 | ISO 9001:2008 Certified Journal | Page 1458
algorithm. This technique uses the property that any
subset of a large itemset must be a large itemset.
Data mining technique is most important technique
which is used in Knowledge Discovery in
Database(KDD).KDD has different types of steps like Data
cleaning, Data integration, Data selection, Data
transformation, Data mining, Pattern evaluation,
Knowledge presentation etc.
The Proposed System are information filtering
systems that deal with the problem of information
overload by filtering vital information fragment out of
large amount of dynamically generated information
according to medicines based on their cost analysis and
many different parameters. This System are beneficial to
both service providers and users. They reduce transaction
costs of finding and selecting items in an online shopping
environment. Recommendation systems have also proved
to improve decision making process and quality. In e-
commerce setting, Alternate Medicine System enhance
revenues, for the fact that they are effective means of
selling more products.
3. PROPOSED METHODOLOGY:
Suppose Medicine X and Y both have a target actions
potassium-sparing diuretic, prescribed for
hyperaldosteronism, low potassium levels, and for edema
(fluid retention) caused by various conditions. It works by
blocking the hormone aldosterone. The drug contained by
them is Gliclazide with dosage 10mg/50mg but Medicine X
is priced at Rs.56 whereas Medicine Y has dosage
20mg/50mg Rs.64.30. This pinpoints that there isn’t much
difference between the price but surely dosage difference,
this may not be suggested as a cheaper alternative but as a
low power alternative to the same Medicine, although it is
not advised to consume a higher dosage medicine without
doctor’s prescription.
Fig -1: Model diagram of Proposed System
4.MODULES:
4.1 Dataset Generation
Medicine dataset needs to be generated for multiple
medicines having same ratio which can be provided as an
alternative to each other. Also for cost analysis it is
necessary to know the market cost for such medicines.
This dataset will be created for a total of 50 medicines.
4.2 Dataset Preprocessing
As dataset gets generated it is necessary to preprocess
it for any null values if provided and the data should be
cleaned and stored into Database for further processing.
4.3 Data Clustering based on contents and costing
Data clustering needs to be done for grouping similar
medicines based on their contents and also it is required
for cost based analysis as well.
4.4 Medicine classification and recommendation
At last ones the user inputs some medicine there is a
requirement of finding alternate medicines for users
which can only be done using classification of input
medicines using some classification algorithm.
CONCLUSION
Medicine availability and costing are two major issues
in health care system these days. Many time the medicines
prescribed by doctor are not available or are very costly
based on brand names. But recently many new medicine
developers have stepped into market with low cost
medicines with high availability. Our proposed system is
going to provide users with such medicine information
that are less costly as compared to prescribed medicines
and at the same time have high availability in market thus
helping users in avoid higher cost in health care.
REFERENCES
[1] Monali Dey, Siddharth Swarup Rautaray, “Study and
Analysis of Data Mining Algorithms for Healthcare
Decision Support System”, Vol. 5 (1), 2014, 470-477
[2] Iavindrasana, J., G. Cohen, A. Depeursinge, H. Müller, R.
Meyer, and A. Geissbuhler. "Clinical data mining: a review."
Yearb Med Inform 2009 (2009): 121-133.
[3] Canlas, R. D. "Data mining in healthcare: Current
Applications and Issues." School of Information Systems &
Management, Carnegie Mellon University, Australia
(2009).](https://image.slidesharecdn.com/irjet-v5i3328-190122054855/85/IRJET-Review-on-Knowledge-Discovery-and-Analysis-in-Healthcare-using-Data-Mining-2-320.jpg)
![International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 05 Issue: 03 | Mar-2018 www.irjet.net p-ISSN: 2395-0072
© 2018, IRJET | Impact Factor value: 6.171 | ISO 9001:2008 Certified Journal | Page 1459
[4] Patel, Jigneshkumar L., and Ramesh K. Goyal.
"Applications of artificial neural networks in medical
science." Current clinical pharmacology 2, no. 3 (2007):
217-226.
[5] K.Srinivas, B.Kavihta Rani and Dr.A.Govrdhan.
"Applications of Data Mining Techniques in Healthcare
and Prediction of Heart Attacks." International Journal on
Computer Science and Engineering (IJCSE) Vol. 02, No. 02,
2010, 250- 255
[6] K.Sudhakar and Dr. M. Manimekalai."Study of Heart
Disease Prediction using Data Mining ." International
Journal of Advanced Research in Computer Science and
Software Engineering 4(1),January - 2014, pp. 1157-1160
[7] JyotiSoni, Ujma Ansari, Dipesh Sharma and SunitaSoni.
"Predictive Data Mining for Medical Diagnosis:An
Overview of Heart Disease Prediction”, International
Journal of Computer Applications (0975 – 8887)Volume
17– No.8, March 2011.
[8] M. Houtsmal and A. Swami (1995). Set-Oriented Mining
for Association Rules in Relational Databases,Proceedings
of the 11th IEEE International Conference on Data
Engineering, pp. 25- 34, Taipei,Taiwan.
[9] Rakesh Agrawal and Ramakrishnan Srikant.(1994).
Fast Algorithms for Mining Association Rules in Large
Databases, Proceedings of the Twentieth International
Conference on Very Large Databases, pp. 487-499,
Santiago, Chile.
[10] R. Agrawal, T. Imielinski, A. Swami.(1993). Mining
Associations between Sets of Items in Massive Databases,
Proc. of the ACM-SIGMOD Int'l Conference on Management
of Data,Washington D.C.
[11] Ramakrishnan Srikant (1996). Fast Algorithms for
Mining Association Rules and Sequential Patterns,Ph. D.
Dissertation,University of Wisconsin, Madison.
[12] Yoo, Illhoi, Patricia Alafaireet, Miroslav Marinov, Keila
Pena- Hernandez, RajithaGopidi, Jia-Fu Chang, and Lei
Hua. "Data mining in healthcare and biomedicine: a survey
of the literature." Journal of medical systems 36, no. 4
(2012): 2431-2448.
[13] Kaur, Harleen, and Siri Krishan Wasan. "Empirical
study on applications of data mining techniques in
healthcare." Journal of Computer Science 2, no. 2 (2006):
194-200.](https://image.slidesharecdn.com/irjet-v5i3328-190122054855/85/IRJET-Review-on-Knowledge-Discovery-and-Analysis-in-Healthcare-using-Data-Mining-3-320.jpg)
IRJET- Review on Knowledge Discovery and Analysis in Healthcare using Data Mining
- 1. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 05 Issue: 03 | Mar-2018 www.irjet.net p-ISSN: 2395-0072 © 2018, IRJET | Impact Factor value: 6.171 | ISO 9001:2008 Certified Journal | Page 1457 Review on Knowledge Discovery And Analysis in Healthcare Using Data Mining Miss. Sheetal A. Tayade1, Prof. Parag D. Thakare2 1M.E. Scholar, Department of Computer Science & Engineering, Jagadambha College of Engineering & Technology, Yavatmal, Maharashtra, India 2Professor, Department of Computer Science & Engineering, Jagadambha College of Engineering & Technology, Yavatmal, Maharashtra, India ----------------------------------------------------------------------***--------------------------------------------------------------------- Abstract - On the Internet, where the number of choices is overwhelming, there is need to filter, prioritize and efficiently deliver relevant information in order to alleviate the problem of information overload, which has created a potential problem to many Internet users. The Proposed System solve this problem by searching through large volume of dynamically generated information to provide users with personalized content and services. The focus of this paper will be on pharmaceutical institutions and information regarding medicines. Frequent unbalanced distribution of medicines in healthcare institutions may result with serious threats to the health condition of a person. This provides health care institutions, medicine manufacturers and public in general to have insight to the information of the medicine. Thus the proposed system called Alternate Medicine System will be use to create a public awareness about alternative drugs for a particular medicine, availability of that alternative medicine in a locality This is very useful for public. Key Words: Data Mining, Healthcare, Predictive Analytics 1. INTRODUCTION Data mining technology provides a user oriented approach to novel and hidden information in the data. Valuable knowledge can be discovered from application of data mining techniques in healthcare system. Data mining in healthcare medicine deals with learning models to predict patients’ disease. Data mining applications can greatly benefit all parties involved in the healthcare industry. For example, data mining can help healthcare insurers detect fraud and abuse, healthcare organizations make customer relationship management decisions, physicians identify effective treatments and best practices, and patients receive better and more affordable healthcare services. The huge amounts of data generated by healthcare transactions are too complex and voluminous to be processed and analyzed by traditional methods. Data mining provides the methodology and technology to transform these mounds of data into useful information for decision making. 2. LITERATURE REVIEW In this section, an attempt has been made to briefly touch upon some of the mentionable reviews in this domain that has been conducted in last 9-10 years. Paper [12], is a reference work with survey in medical data and biomedicine, and covers elaborate reviews on machine learning models. However, the focus has been more machine learning and data mining oriented and in some cases the categorizations have been not very clear. In another paper [13], authors have discussed few motivating cases of data mining in healthcare along with the results. The paper focuses primarily on classification tasks in healthcare and discusses three models, namely rule induction, decision tree and neural network. In the seminal work presented in [2], the authors have given various cross sectional views (By tasks, By Models, By type of data) of the data mining use cases. However, the discussions have not been from the point of view of the health care entities. [3] Discusses some interesting aspects of data mining in healthcare, however, it focuses more on public health and medicine and coverage of machine learning models are also limited. Some of the surveys have been more specific. As an example [4], focuses on the application of a particular model (Neural Network) in medical science. Some of the surveys have been on narrowed scopes where they have reviewed particular health care problems as example prediction of heart disease [5], [6], [7]. Different algorithms used in Different papers. The AIS algorithm is the first published algorithm developed to produce all large itemsets in a transaction database [10]. This algorithm has targeted to discover qualitative rules. This technique is limited to only one item in the consequent. This algorithm makes multiple passes over the entire database. The SETM algorithm is proposed in [8] and motivated by the desire to use SQL to calculate large itemsets [11]. In this algorithm each member of the set large itemsets, Lk, is in the form <TID, itemset> where TID is the unique identifier of a transaction Similarly, each member of the set of candidate itemsets, Ck, is in the form <TID, itemset>. Similar to [10], the SETM algorithm makes multiple passes over the database. The Apriori algorithm [9] is a great success in the history of mining association rules. It is by far the most well-known association rule
- 2. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 05 Issue: 03 | Mar-2018 www.irjet.net p-ISSN: 2395-0072 © 2018, IRJET | Impact Factor value: 6.171 | ISO 9001:2008 Certified Journal | Page 1458 algorithm. This technique uses the property that any subset of a large itemset must be a large itemset. Data mining technique is most important technique which is used in Knowledge Discovery in Database(KDD).KDD has different types of steps like Data cleaning, Data integration, Data selection, Data transformation, Data mining, Pattern evaluation, Knowledge presentation etc. The Proposed System are information filtering systems that deal with the problem of information overload by filtering vital information fragment out of large amount of dynamically generated information according to medicines based on their cost analysis and many different parameters. This System are beneficial to both service providers and users. They reduce transaction costs of finding and selecting items in an online shopping environment. Recommendation systems have also proved to improve decision making process and quality. In e- commerce setting, Alternate Medicine System enhance revenues, for the fact that they are effective means of selling more products. 3. PROPOSED METHODOLOGY: Suppose Medicine X and Y both have a target actions potassium-sparing diuretic, prescribed for hyperaldosteronism, low potassium levels, and for edema (fluid retention) caused by various conditions. It works by blocking the hormone aldosterone. The drug contained by them is Gliclazide with dosage 10mg/50mg but Medicine X is priced at Rs.56 whereas Medicine Y has dosage 20mg/50mg Rs.64.30. This pinpoints that there isn’t much difference between the price but surely dosage difference, this may not be suggested as a cheaper alternative but as a low power alternative to the same Medicine, although it is not advised to consume a higher dosage medicine without doctor’s prescription. Fig -1: Model diagram of Proposed System 4.MODULES: 4.1 Dataset Generation Medicine dataset needs to be generated for multiple medicines having same ratio which can be provided as an alternative to each other. Also for cost analysis it is necessary to know the market cost for such medicines. This dataset will be created for a total of 50 medicines. 4.2 Dataset Preprocessing As dataset gets generated it is necessary to preprocess it for any null values if provided and the data should be cleaned and stored into Database for further processing. 4.3 Data Clustering based on contents and costing Data clustering needs to be done for grouping similar medicines based on their contents and also it is required for cost based analysis as well. 4.4 Medicine classification and recommendation At last ones the user inputs some medicine there is a requirement of finding alternate medicines for users which can only be done using classification of input medicines using some classification algorithm. CONCLUSION Medicine availability and costing are two major issues in health care system these days. Many time the medicines prescribed by doctor are not available or are very costly based on brand names. But recently many new medicine developers have stepped into market with low cost medicines with high availability. Our proposed system is going to provide users with such medicine information that are less costly as compared to prescribed medicines and at the same time have high availability in market thus helping users in avoid higher cost in health care. REFERENCES [1] Monali Dey, Siddharth Swarup Rautaray, “Study and Analysis of Data Mining Algorithms for Healthcare Decision Support System”, Vol. 5 (1), 2014, 470-477 [2] Iavindrasana, J., G. Cohen, A. Depeursinge, H. Müller, R. Meyer, and A. Geissbuhler. "Clinical data mining: a review." Yearb Med Inform 2009 (2009): 121-133. [3] Canlas, R. D. "Data mining in healthcare: Current Applications and Issues." School of Information Systems & Management, Carnegie Mellon University, Australia (2009).
- 3. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 05 Issue: 03 | Mar-2018 www.irjet.net p-ISSN: 2395-0072 © 2018, IRJET | Impact Factor value: 6.171 | ISO 9001:2008 Certified Journal | Page 1459 [4] Patel, Jigneshkumar L., and Ramesh K. Goyal. "Applications of artificial neural networks in medical science." Current clinical pharmacology 2, no. 3 (2007): 217-226. [5] K.Srinivas, B.Kavihta Rani and Dr.A.Govrdhan. "Applications of Data Mining Techniques in Healthcare and Prediction of Heart Attacks." International Journal on Computer Science and Engineering (IJCSE) Vol. 02, No. 02, 2010, 250- 255 [6] K.Sudhakar and Dr. M. Manimekalai."Study of Heart Disease Prediction using Data Mining ." International Journal of Advanced Research in Computer Science and Software Engineering 4(1),January - 2014, pp. 1157-1160 [7] JyotiSoni, Ujma Ansari, Dipesh Sharma and SunitaSoni. "Predictive Data Mining for Medical Diagnosis:An Overview of Heart Disease Prediction”, International Journal of Computer Applications (0975 – 8887)Volume 17– No.8, March 2011. [8] M. Houtsmal and A. Swami (1995). Set-Oriented Mining for Association Rules in Relational Databases,Proceedings of the 11th IEEE International Conference on Data Engineering, pp. 25- 34, Taipei,Taiwan. [9] Rakesh Agrawal and Ramakrishnan Srikant.(1994). Fast Algorithms for Mining Association Rules in Large Databases, Proceedings of the Twentieth International Conference on Very Large Databases, pp. 487-499, Santiago, Chile. [10] R. Agrawal, T. Imielinski, A. Swami.(1993). Mining Associations between Sets of Items in Massive Databases, Proc. of the ACM-SIGMOD Int'l Conference on Management of Data,Washington D.C. [11] Ramakrishnan Srikant (1996). Fast Algorithms for Mining Association Rules and Sequential Patterns,Ph. D. Dissertation,University of Wisconsin, Madison. [12] Yoo, Illhoi, Patricia Alafaireet, Miroslav Marinov, Keila Pena- Hernandez, RajithaGopidi, Jia-Fu Chang, and Lei Hua. "Data mining in healthcare and biomedicine: a survey of the literature." Journal of medical systems 36, no. 4 (2012): 2431-2448. [13] Kaur, Harleen, and Siri Krishan Wasan. "Empirical study on applications of data mining techniques in healthcare." Journal of Computer Science 2, no. 2 (2006): 194-200.