SlideShare une entreprise Scribd logo
1  sur  21
A SEMINAR ON
KNOWLEDGE DISCOVERY IN MEDICINE
: CURRENT ISSUES AND FUTURE TREND
Guided by: Presented by:
Prof. B.R. Bombade Avinash M. Hanwate
2016MNS013
CONTENTS
• INTRODUCTION
• MOTIVATION OF STUDY
• DATA MINING AND MEDICAL DATA MINING
• REVIEW AND ANALYSIS
• CURRENT ISSUES AND FUTURE TRENDS
• CONCLUSION
• REFERENCES
INTRODUCTION
• Data mining is a powerful method to extract knowledge from data.
Raw data faces various challenges that make traditional method
improper for knowledge extraction.
• Data mining is supposed to be able to handle various data types in
all formats.
• Medical data mining is a multidisciplinary field with contribution
of medicine and data mining.
• each paper is studied based on the six medical tasks: screening,
diagnosis, treatment, prognosis, monitoring and management.
• In each task, five data mining approaches are considered:
classification, regression, clustering, association and hybrid.
MOTIVATION OF STUDY
• Workflow applied for extraction of medical data mining papers:
• Contains four processes:
1. Broad search
2. Refine search
3. Extract basic concepts
4. Analyze
Fig. Workflow to collect related papers with the aim of provide this
survey
• Previous reviews in context of knowledge extraction in medicine:
• We can consider each of these review papers from two points of
view:
1. Algorithm
2. Medicine
• Scope of this study:
• The study of review papers in previous section shows that
application of knowledge extraction from medicine is started
from last decade and therefore it is located in a teenage period.
DATA MINING AND MEDICAL
DATA MINING
• Data mining:
Data mining process divided into three phase: data pre-processing,
data modeling, and data post-processing.
• Data Pre-processing:
• Data description and summarization:
• Data Cleaning
• Data Integration
• Attribute Transformation
• Discretization and Binarization
• Data Reduction
Fig. Main data pre-processing approaches
DATA MODELING:
• All the tasks in data modeling step can be divided into predictive and
descriptive categories. Predictive algorithms are divided into
classification and regression based on type of target variable (discrete
or continuous).
• Descriptive algorithms are also classified as clustering and
association rule mining.
Fig. Process of classification.
DATA POST-PROCESSING:
• visualization and evaluation of extracted knowledge is taken into
account.
• Visualization is stated as the essential matter in data mining. It is
considered as an advantage for an algorithm.
• There are various predictive and descriptive algorithms for
knowledge extraction.
MEDICAL DATA MINING:
• Definition and goal
• Extraction of implicit, potentially useful and novel
information from medical data to improve accuracy, decrease
time and cost, construct decision support system with the aim
of health promotion.
• This definition contains three parts:
1. Data mining
2. Medical nature
3. Goals
MEDICAL DATA:
• Medical data is one of the most difficult data type for mining.
• This type of data is generated by several sources such as medical
examinations, imaging and tests. We need to select an appropriate
data mining algorithm regarding the type of data.
• In this study only structural data are considered and other types
such as text are not considered.
• In Fig. frequency of using each data types in literature are shown.
Fig. Percentage of medical data types that used by literature.
Fig. Medical data challenges.
MEDICAL NATURE CHALLENGES:
• High risk:
• Medicine can be known as high risk due to the association
with human life.
• Medical activities outcome is death or life and this is
different from engineering view such as optimization.
Mistake or failure can lead to punishment.
• Interaction with a wide variety of users:
• Patient
• Physician
• Nurse
• Health care system
MEDICAL DATA MINING ADAPTIVE
STANDARD FRAMEWORK
• Problem understanding
• Data understanding
• Data pre-processing
• Data processing
• Data post-processing
• Deployment
Fig. Medical data mining adaptive standard framework.
MEDICAL DATA MINING TREND
• In Fig. medical data mining trend is presented and compared with
data mining.
Fig. Medical data mining trend compared with data mining.
REVIEW AND ANALYSIS
• All activities in medicine can be divided into six domains that we
know as ‘‘medical tasks’’:
1. Screening
2. Diagnosis
3. Treatment
4. Prognosis
5. Monitoring
6. Management
CURRENT ISSUES
• Twelve important issues in medical data mining are considered:
1. Medical data mining goals
2. Types of data
3. Integration
4. Scalability
5. Medical data mining challenges
6. Users
7. Medical tasks
8. Diseases
9. Data pre-processing
10. Data modeling
11. Classification
12. Data post-processing
FUTURE TREND
• The decision tree is known as the most popular algorithm in medical
data mining, its usage has decreased in recent years.
• In contrast, SVM has been more used in recent works.
• Hybrid approaches try to combine two or more algorithms with the
aim of enhancing performance.
• Three approaches have appeared to be combined with data mining
algorithms: fuzzy, expert system and evolutionary algorithms.
• Fuzzy approach has more attention to construct hybrid models.
• Hence, SVM and fuzzy approach are expected to be popular methods
in the future.
CONCLUSION
• In this study, we focused only on a structural data.
• Therefore as for future works, provide a review on application of
text mining in medicine is recommended.
• Also, Introducing the tools, package and successful implemented
programs in this field is proposed.
• Finally we can conclude this paper around three points:
• Based on six medical tasks
• Based on disease
• Based on data mining
REFERENCES
1] Chapman, P., Clinton, J., Kerber, R., Khabaza, T., Reinartz, T.,
Shearer, C., & Wirth, R.(2000). CRISP-DM 1.0 step-by-step data
mining guide. In The CRISP-DM consortium.
2] Organization, W. H. (2007). World health statistics 2007: WORLD
HEALTH ORGN.
3] Ngai, E. W. T., Xiu, L., & Chau, D. C. K. (2009). Application of data
mining techniques in customer relationship management: A literature
review and classification.Expert Systems with Applications, 36,
2592–2602.
4] Fayyad, U., Piatetsky-Shapiro, G., & Smyth, P. (1996). From data
mining to knowledge discovery in databases. AI Magazine, 17, 37–
54.

Contenu connexe

Tendances

Role of statistics in biomedical research
Role of statistics in biomedical researchRole of statistics in biomedical research
Role of statistics in biomedical research
eman youssif
 
Evaluation of medlars
Evaluation of medlarsEvaluation of medlars
Evaluation of medlars
silambu111
 

Tendances (19)

Bioststistic mbbs-1 f30may
Bioststistic  mbbs-1 f30mayBioststistic  mbbs-1 f30may
Bioststistic mbbs-1 f30may
 
Role of statistics in biomedical research
Role of statistics in biomedical researchRole of statistics in biomedical research
Role of statistics in biomedical research
 
Biostatistics
BiostatisticsBiostatistics
Biostatistics
 
Research methodology and biostatistics
Research methodology and biostatisticsResearch methodology and biostatistics
Research methodology and biostatistics
 
Evaluation of medlars
Evaluation of medlarsEvaluation of medlars
Evaluation of medlars
 
Intoduction to biostatistics
Intoduction to biostatisticsIntoduction to biostatistics
Intoduction to biostatistics
 
Introduction to biostatistics
Introduction to biostatisticsIntroduction to biostatistics
Introduction to biostatistics
 
Extracting patient data from tables in clinical literature
Extracting patient data from tables in clinical literatureExtracting patient data from tables in clinical literature
Extracting patient data from tables in clinical literature
 
Basics of Systematic Review and Meta-analysis: Part 3
Basics of Systematic Review and Meta-analysis: Part 3Basics of Systematic Review and Meta-analysis: Part 3
Basics of Systematic Review and Meta-analysis: Part 3
 
Stat Methods in ayurveda
Stat Methods in ayurvedaStat Methods in ayurveda
Stat Methods in ayurveda
 
Research design (1)
Research design (1)Research design (1)
Research design (1)
 
MULTI-CRITERIA DECISION SUPPORT GUIDED BY CASE-BASED REASONING
MULTI-CRITERIA DECISION SUPPORT GUIDED BY CASE-BASED REASONINGMULTI-CRITERIA DECISION SUPPORT GUIDED BY CASE-BASED REASONING
MULTI-CRITERIA DECISION SUPPORT GUIDED BY CASE-BASED REASONING
 
Lecture 3. planning data analysis
Lecture 3. planning data analysisLecture 3. planning data analysis
Lecture 3. planning data analysis
 
Ahmed Negida, MBBCh - Biography
Ahmed Negida, MBBCh - BiographyAhmed Negida, MBBCh - Biography
Ahmed Negida, MBBCh - Biography
 
Meta analysis
Meta analysisMeta analysis
Meta analysis
 
Systematic review and meta analaysis course - part 2
Systematic review and meta analaysis course - part 2Systematic review and meta analaysis course - part 2
Systematic review and meta analaysis course - part 2
 
What are the applications of Biostatistics in Pharmacy?
What are the applications of Biostatistics in Pharmacy?What are the applications of Biostatistics in Pharmacy?
What are the applications of Biostatistics in Pharmacy?
 
How to extract data from your paper for systemic review - Pubrica
How to extract data from your paper for systemic review  - PubricaHow to extract data from your paper for systemic review  - Pubrica
How to extract data from your paper for systemic review - Pubrica
 
Collection & Editing of data
Collection & Editing of dataCollection & Editing of data
Collection & Editing of data
 

Similaire à Knowledge discovery in medicine

Computer System Validation - privacy zones, eSource and EHR data in clinical ...
Computer System Validation - privacy zones, eSource and EHR data in clinical ...Computer System Validation - privacy zones, eSource and EHR data in clinical ...
Computer System Validation - privacy zones, eSource and EHR data in clinical ...
Wolfgang Kuchinke
 
Computer System Validation with privacy zones, e-source and clinical trials b...
Computer System Validation with privacy zones, e-source and clinical trials b...Computer System Validation with privacy zones, e-source and clinical trials b...
Computer System Validation with privacy zones, e-source and clinical trials b...
Wolfgang Kuchinke
 
Data collection methods RSS6 2014
Data collection methods RSS6 2014Data collection methods RSS6 2014
Data collection methods RSS6 2014
RSS6
 
RESEARCH PROPOSAL.pptx
RESEARCH PROPOSAL.pptxRESEARCH PROPOSAL.pptx
RESEARCH PROPOSAL.pptx
nagendrasai12
 
Big Data Mining Methods in Medical Applications [Autosaved].pptx
Big Data Mining Methods in Medical Applications [Autosaved].pptxBig Data Mining Methods in Medical Applications [Autosaved].pptx
Big Data Mining Methods in Medical Applications [Autosaved].pptx
HemaSenthil5
 
Theory and Practice of Integrating Machine Learning and Conventional Statisti...
Theory and Practice of Integrating Machine Learning and Conventional Statisti...Theory and Practice of Integrating Machine Learning and Conventional Statisti...
Theory and Practice of Integrating Machine Learning and Conventional Statisti...
University of Malaya
 

Similaire à Knowledge discovery in medicine (20)

Clinical Research Informatics Year-in-Review
Clinical Research Informatics Year-in-ReviewClinical Research Informatics Year-in-Review
Clinical Research Informatics Year-in-Review
 
Data analytics in Healthcare
Data analytics in HealthcareData analytics in Healthcare
Data analytics in Healthcare
 
Computer System Validation - privacy zones, eSource and EHR data in clinical ...
Computer System Validation - privacy zones, eSource and EHR data in clinical ...Computer System Validation - privacy zones, eSource and EHR data in clinical ...
Computer System Validation - privacy zones, eSource and EHR data in clinical ...
 
Computer System Validation with privacy zones, e-source and clinical trials b...
Computer System Validation with privacy zones, e-source and clinical trials b...Computer System Validation with privacy zones, e-source and clinical trials b...
Computer System Validation with privacy zones, e-source and clinical trials b...
 
Data mining (DM) in the pharmaceutical industry
Data mining (DM) in the pharmaceutical industryData mining (DM) in the pharmaceutical industry
Data mining (DM) in the pharmaceutical industry
 
Machine learning in disease diagnosis
Machine learning in disease diagnosisMachine learning in disease diagnosis
Machine learning in disease diagnosis
 
STATISCAL PAKAGE.pptx
STATISCAL PAKAGE.pptxSTATISCAL PAKAGE.pptx
STATISCAL PAKAGE.pptx
 
Data collection methods RSS6 2014
Data collection methods RSS6 2014Data collection methods RSS6 2014
Data collection methods RSS6 2014
 
Meps secondary data analysis talk 20080806
Meps secondary data analysis talk 20080806Meps secondary data analysis talk 20080806
Meps secondary data analysis talk 20080806
 
statistical analysis
statistical analysisstatistical analysis
statistical analysis
 
RESEARCH PROPOSAL.pptx
RESEARCH PROPOSAL.pptxRESEARCH PROPOSAL.pptx
RESEARCH PROPOSAL.pptx
 
Biostatisitics.pptx
Biostatisitics.pptxBiostatisitics.pptx
Biostatisitics.pptx
 
Embi cri yir-2017-final
Embi cri yir-2017-finalEmbi cri yir-2017-final
Embi cri yir-2017-final
 
Big Data Mining Methods in Medical Applications [Autosaved].pptx
Big Data Mining Methods in Medical Applications [Autosaved].pptxBig Data Mining Methods in Medical Applications [Autosaved].pptx
Big Data Mining Methods in Medical Applications [Autosaved].pptx
 
Operations research within UK healthcare: A review
Operations research within UK healthcare: A reviewOperations research within UK healthcare: A review
Operations research within UK healthcare: A review
 
Research team meeting mrs
Research team meeting mrsResearch team meeting mrs
Research team meeting mrs
 
Surgical Audit & Research
Surgical Audit & ResearchSurgical Audit & Research
Surgical Audit & Research
 
Theory and Practice of Integrating Machine Learning and Conventional Statisti...
Theory and Practice of Integrating Machine Learning and Conventional Statisti...Theory and Practice of Integrating Machine Learning and Conventional Statisti...
Theory and Practice of Integrating Machine Learning and Conventional Statisti...
 
Data Science Deep Roots in Healthcare Industry
Data Science Deep Roots in Healthcare IndustryData Science Deep Roots in Healthcare Industry
Data Science Deep Roots in Healthcare Industry
 
Psychologists and Quality Improvement 3.pdf
Psychologists and Quality Improvement 3.pdfPsychologists and Quality Improvement 3.pdf
Psychologists and Quality Improvement 3.pdf
 

Dernier

Call Girl In Pune 👉 Just CALL ME: 9352988975 💋 Call Out Call Both With High p...
Call Girl In Pune 👉 Just CALL ME: 9352988975 💋 Call Out Call Both With High p...Call Girl In Pune 👉 Just CALL ME: 9352988975 💋 Call Out Call Both With High p...
Call Girl In Pune 👉 Just CALL ME: 9352988975 💋 Call Out Call Both With High p...
chetankumar9855
 
Call Girl in Indore 8827247818 {LowPrice} ❤️ (ahana) Indore Call Girls * UPA...
Call Girl in Indore 8827247818 {LowPrice} ❤️ (ahana) Indore Call Girls  * UPA...Call Girl in Indore 8827247818 {LowPrice} ❤️ (ahana) Indore Call Girls  * UPA...
Call Girl in Indore 8827247818 {LowPrice} ❤️ (ahana) Indore Call Girls * UPA...
mahaiklolahd
 
🌹Attapur⬅️ Vip Call Girls Hyderabad 📱9352852248 Book Well Trand Call Girls In...
🌹Attapur⬅️ Vip Call Girls Hyderabad 📱9352852248 Book Well Trand Call Girls In...🌹Attapur⬅️ Vip Call Girls Hyderabad 📱9352852248 Book Well Trand Call Girls In...
🌹Attapur⬅️ Vip Call Girls Hyderabad 📱9352852248 Book Well Trand Call Girls In...
Call Girls In Delhi Whatsup 9873940964 Enjoy Unlimited Pleasure
 

Dernier (20)

Premium Call Girls In Jaipur {8445551418} ❤️VVIP SEEMA Call Girl in Jaipur Ra...
Premium Call Girls In Jaipur {8445551418} ❤️VVIP SEEMA Call Girl in Jaipur Ra...Premium Call Girls In Jaipur {8445551418} ❤️VVIP SEEMA Call Girl in Jaipur Ra...
Premium Call Girls In Jaipur {8445551418} ❤️VVIP SEEMA Call Girl in Jaipur Ra...
 
Night 7k to 12k Navi Mumbai Call Girl Photo 👉 BOOK NOW 9833363713 👈 ♀️ night ...
Night 7k to 12k Navi Mumbai Call Girl Photo 👉 BOOK NOW 9833363713 👈 ♀️ night ...Night 7k to 12k Navi Mumbai Call Girl Photo 👉 BOOK NOW 9833363713 👈 ♀️ night ...
Night 7k to 12k Navi Mumbai Call Girl Photo 👉 BOOK NOW 9833363713 👈 ♀️ night ...
 
Manyata Tech Park ( Call Girls ) Bangalore ✔ 6297143586 ✔ Hot Model With Sexy...
Manyata Tech Park ( Call Girls ) Bangalore ✔ 6297143586 ✔ Hot Model With Sexy...Manyata Tech Park ( Call Girls ) Bangalore ✔ 6297143586 ✔ Hot Model With Sexy...
Manyata Tech Park ( Call Girls ) Bangalore ✔ 6297143586 ✔ Hot Model With Sexy...
 
Call Girl In Pune 👉 Just CALL ME: 9352988975 💋 Call Out Call Both With High p...
Call Girl In Pune 👉 Just CALL ME: 9352988975 💋 Call Out Call Both With High p...Call Girl In Pune 👉 Just CALL ME: 9352988975 💋 Call Out Call Both With High p...
Call Girl In Pune 👉 Just CALL ME: 9352988975 💋 Call Out Call Both With High p...
 
Call Girl in Indore 8827247818 {LowPrice} ❤️ (ahana) Indore Call Girls * UPA...
Call Girl in Indore 8827247818 {LowPrice} ❤️ (ahana) Indore Call Girls  * UPA...Call Girl in Indore 8827247818 {LowPrice} ❤️ (ahana) Indore Call Girls  * UPA...
Call Girl in Indore 8827247818 {LowPrice} ❤️ (ahana) Indore Call Girls * UPA...
 
Russian Call Girls Service Jaipur {8445551418} ❤️PALLAVI VIP Jaipur Call Gir...
Russian Call Girls Service  Jaipur {8445551418} ❤️PALLAVI VIP Jaipur Call Gir...Russian Call Girls Service  Jaipur {8445551418} ❤️PALLAVI VIP Jaipur Call Gir...
Russian Call Girls Service Jaipur {8445551418} ❤️PALLAVI VIP Jaipur Call Gir...
 
Premium Bangalore Call Girls Jigani Dail 6378878445 Escort Service For Hot Ma...
Premium Bangalore Call Girls Jigani Dail 6378878445 Escort Service For Hot Ma...Premium Bangalore Call Girls Jigani Dail 6378878445 Escort Service For Hot Ma...
Premium Bangalore Call Girls Jigani Dail 6378878445 Escort Service For Hot Ma...
 
Best Rate (Patna ) Call Girls Patna ⟟ 8617370543 ⟟ High Class Call Girl In 5 ...
Best Rate (Patna ) Call Girls Patna ⟟ 8617370543 ⟟ High Class Call Girl In 5 ...Best Rate (Patna ) Call Girls Patna ⟟ 8617370543 ⟟ High Class Call Girl In 5 ...
Best Rate (Patna ) Call Girls Patna ⟟ 8617370543 ⟟ High Class Call Girl In 5 ...
 
Model Call Girls In Chennai WhatsApp Booking 7427069034 call girl service 24 ...
Model Call Girls In Chennai WhatsApp Booking 7427069034 call girl service 24 ...Model Call Girls In Chennai WhatsApp Booking 7427069034 call girl service 24 ...
Model Call Girls In Chennai WhatsApp Booking 7427069034 call girl service 24 ...
 
Call Girls in Delhi Triveni Complex Escort Service(🔝))/WhatsApp 97111⇛47426
Call Girls in Delhi Triveni Complex Escort Service(🔝))/WhatsApp 97111⇛47426Call Girls in Delhi Triveni Complex Escort Service(🔝))/WhatsApp 97111⇛47426
Call Girls in Delhi Triveni Complex Escort Service(🔝))/WhatsApp 97111⇛47426
 
Call Girls Madurai Just Call 9630942363 Top Class Call Girl Service Available
Call Girls Madurai Just Call 9630942363 Top Class Call Girl Service AvailableCall Girls Madurai Just Call 9630942363 Top Class Call Girl Service Available
Call Girls Madurai Just Call 9630942363 Top Class Call Girl Service Available
 
Andheri East ) Call Girls in Mumbai Phone No 9004268417 Elite Escort Service ...
Andheri East ) Call Girls in Mumbai Phone No 9004268417 Elite Escort Service ...Andheri East ) Call Girls in Mumbai Phone No 9004268417 Elite Escort Service ...
Andheri East ) Call Girls in Mumbai Phone No 9004268417 Elite Escort Service ...
 
9630942363 Genuine Call Girls In Ahmedabad Gujarat Call Girls Service
9630942363 Genuine Call Girls In Ahmedabad Gujarat Call Girls Service9630942363 Genuine Call Girls In Ahmedabad Gujarat Call Girls Service
9630942363 Genuine Call Girls In Ahmedabad Gujarat Call Girls Service
 
Call Girls Jaipur Just Call 9521753030 Top Class Call Girl Service Available
Call Girls Jaipur Just Call 9521753030 Top Class Call Girl Service AvailableCall Girls Jaipur Just Call 9521753030 Top Class Call Girl Service Available
Call Girls Jaipur Just Call 9521753030 Top Class Call Girl Service Available
 
🌹Attapur⬅️ Vip Call Girls Hyderabad 📱9352852248 Book Well Trand Call Girls In...
🌹Attapur⬅️ Vip Call Girls Hyderabad 📱9352852248 Book Well Trand Call Girls In...🌹Attapur⬅️ Vip Call Girls Hyderabad 📱9352852248 Book Well Trand Call Girls In...
🌹Attapur⬅️ Vip Call Girls Hyderabad 📱9352852248 Book Well Trand Call Girls In...
 
Trichy Call Girls Book Now 9630942363 Top Class Trichy Escort Service Available
Trichy Call Girls Book Now 9630942363 Top Class Trichy Escort Service AvailableTrichy Call Girls Book Now 9630942363 Top Class Trichy Escort Service Available
Trichy Call Girls Book Now 9630942363 Top Class Trichy Escort Service Available
 
Call Girls Raipur Just Call 9630942363 Top Class Call Girl Service Available
Call Girls Raipur Just Call 9630942363 Top Class Call Girl Service AvailableCall Girls Raipur Just Call 9630942363 Top Class Call Girl Service Available
Call Girls Raipur Just Call 9630942363 Top Class Call Girl Service Available
 
Independent Call Girls In Jaipur { 8445551418 } ✔ ANIKA MEHTA ✔ Get High Prof...
Independent Call Girls In Jaipur { 8445551418 } ✔ ANIKA MEHTA ✔ Get High Prof...Independent Call Girls In Jaipur { 8445551418 } ✔ ANIKA MEHTA ✔ Get High Prof...
Independent Call Girls In Jaipur { 8445551418 } ✔ ANIKA MEHTA ✔ Get High Prof...
 
Call Girls Hosur Just Call 9630942363 Top Class Call Girl Service Available
Call Girls Hosur Just Call 9630942363 Top Class Call Girl Service AvailableCall Girls Hosur Just Call 9630942363 Top Class Call Girl Service Available
Call Girls Hosur Just Call 9630942363 Top Class Call Girl Service Available
 
Call Girls Rishikesh Just Call 9667172968 Top Class Call Girl Service Available
Call Girls Rishikesh Just Call 9667172968 Top Class Call Girl Service AvailableCall Girls Rishikesh Just Call 9667172968 Top Class Call Girl Service Available
Call Girls Rishikesh Just Call 9667172968 Top Class Call Girl Service Available
 

Knowledge discovery in medicine

  • 1. A SEMINAR ON KNOWLEDGE DISCOVERY IN MEDICINE : CURRENT ISSUES AND FUTURE TREND Guided by: Presented by: Prof. B.R. Bombade Avinash M. Hanwate 2016MNS013
  • 2. CONTENTS • INTRODUCTION • MOTIVATION OF STUDY • DATA MINING AND MEDICAL DATA MINING • REVIEW AND ANALYSIS • CURRENT ISSUES AND FUTURE TRENDS • CONCLUSION • REFERENCES
  • 3. INTRODUCTION • Data mining is a powerful method to extract knowledge from data. Raw data faces various challenges that make traditional method improper for knowledge extraction. • Data mining is supposed to be able to handle various data types in all formats. • Medical data mining is a multidisciplinary field with contribution of medicine and data mining. • each paper is studied based on the six medical tasks: screening, diagnosis, treatment, prognosis, monitoring and management. • In each task, five data mining approaches are considered: classification, regression, clustering, association and hybrid.
  • 4. MOTIVATION OF STUDY • Workflow applied for extraction of medical data mining papers: • Contains four processes: 1. Broad search 2. Refine search 3. Extract basic concepts 4. Analyze Fig. Workflow to collect related papers with the aim of provide this survey
  • 5. • Previous reviews in context of knowledge extraction in medicine: • We can consider each of these review papers from two points of view: 1. Algorithm 2. Medicine • Scope of this study: • The study of review papers in previous section shows that application of knowledge extraction from medicine is started from last decade and therefore it is located in a teenage period.
  • 6. DATA MINING AND MEDICAL DATA MINING • Data mining: Data mining process divided into three phase: data pre-processing, data modeling, and data post-processing. • Data Pre-processing: • Data description and summarization: • Data Cleaning • Data Integration • Attribute Transformation • Discretization and Binarization • Data Reduction
  • 7. Fig. Main data pre-processing approaches
  • 8. DATA MODELING: • All the tasks in data modeling step can be divided into predictive and descriptive categories. Predictive algorithms are divided into classification and regression based on type of target variable (discrete or continuous). • Descriptive algorithms are also classified as clustering and association rule mining. Fig. Process of classification.
  • 9. DATA POST-PROCESSING: • visualization and evaluation of extracted knowledge is taken into account. • Visualization is stated as the essential matter in data mining. It is considered as an advantage for an algorithm. • There are various predictive and descriptive algorithms for knowledge extraction.
  • 10. MEDICAL DATA MINING: • Definition and goal • Extraction of implicit, potentially useful and novel information from medical data to improve accuracy, decrease time and cost, construct decision support system with the aim of health promotion. • This definition contains three parts: 1. Data mining 2. Medical nature 3. Goals
  • 11. MEDICAL DATA: • Medical data is one of the most difficult data type for mining. • This type of data is generated by several sources such as medical examinations, imaging and tests. We need to select an appropriate data mining algorithm regarding the type of data. • In this study only structural data are considered and other types such as text are not considered.
  • 12. • In Fig. frequency of using each data types in literature are shown. Fig. Percentage of medical data types that used by literature.
  • 13. Fig. Medical data challenges.
  • 14. MEDICAL NATURE CHALLENGES: • High risk: • Medicine can be known as high risk due to the association with human life. • Medical activities outcome is death or life and this is different from engineering view such as optimization. Mistake or failure can lead to punishment. • Interaction with a wide variety of users: • Patient • Physician • Nurse • Health care system
  • 15. MEDICAL DATA MINING ADAPTIVE STANDARD FRAMEWORK • Problem understanding • Data understanding • Data pre-processing • Data processing • Data post-processing • Deployment Fig. Medical data mining adaptive standard framework.
  • 16. MEDICAL DATA MINING TREND • In Fig. medical data mining trend is presented and compared with data mining. Fig. Medical data mining trend compared with data mining.
  • 17. REVIEW AND ANALYSIS • All activities in medicine can be divided into six domains that we know as ‘‘medical tasks’’: 1. Screening 2. Diagnosis 3. Treatment 4. Prognosis 5. Monitoring 6. Management
  • 18. CURRENT ISSUES • Twelve important issues in medical data mining are considered: 1. Medical data mining goals 2. Types of data 3. Integration 4. Scalability 5. Medical data mining challenges 6. Users 7. Medical tasks 8. Diseases 9. Data pre-processing 10. Data modeling 11. Classification 12. Data post-processing
  • 19. FUTURE TREND • The decision tree is known as the most popular algorithm in medical data mining, its usage has decreased in recent years. • In contrast, SVM has been more used in recent works. • Hybrid approaches try to combine two or more algorithms with the aim of enhancing performance. • Three approaches have appeared to be combined with data mining algorithms: fuzzy, expert system and evolutionary algorithms. • Fuzzy approach has more attention to construct hybrid models. • Hence, SVM and fuzzy approach are expected to be popular methods in the future.
  • 20. CONCLUSION • In this study, we focused only on a structural data. • Therefore as for future works, provide a review on application of text mining in medicine is recommended. • Also, Introducing the tools, package and successful implemented programs in this field is proposed. • Finally we can conclude this paper around three points: • Based on six medical tasks • Based on disease • Based on data mining
  • 21. REFERENCES 1] Chapman, P., Clinton, J., Kerber, R., Khabaza, T., Reinartz, T., Shearer, C., & Wirth, R.(2000). CRISP-DM 1.0 step-by-step data mining guide. In The CRISP-DM consortium. 2] Organization, W. H. (2007). World health statistics 2007: WORLD HEALTH ORGN. 3] Ngai, E. W. T., Xiu, L., & Chau, D. C. K. (2009). Application of data mining techniques in customer relationship management: A literature review and classification.Expert Systems with Applications, 36, 2592–2602. 4] Fayyad, U., Piatetsky-Shapiro, G., & Smyth, P. (1996). From data mining to knowledge discovery in databases. AI Magazine, 17, 37– 54.