This book presents data mining methods in the field of healthcare management in a practical way. Healthcare quality and disease prevention are essential in today’s world. Healthcare management faces a number of challenges, e.g. reducing patient growth through disease prevention, stopping or slowing disease progression, and reducing healthcare costs while improving quality of care. The book provides an overview of current healthcare management problems and highlights how analytics and knowledge management have been used to better cope with them. It then demonstrates how to use descriptive and predictive analytics tools to help address these challenges. In closing, it presents applications of software solutions in the context of healthcare management.
Given its scope, the book will appeal to a broad readership, from researchers and students in the operations research and management field to practitioners such as data analysts and decision-makers who work in the healthcare sector.
Author(s): David L. Olson, Özgür M. Araz
Series: International Series in Operations Research & Management Science, 341
Publisher: Springer
Year: 2023
Language: English
Pages: 194
City: Cham
Preface
Contents
Chapter 1: Urgency in Healthcare Data Analytics
1.1 Big Data in Healthcare
1.2 Big Data Analytics
1.3 Tools
1.4 Implementation
1.5 Challenges
References
Chapter 2: Analytics and Knowledge Management in Healthcare
2.1 Healthcare Data Analytics
2.2 Application Fields
2.2.1 Disaster Management
2.2.2 Public Health Risk Management
2.2.3 Food Safety
2.2.4 Social Welfare
2.3 Analytics Techniques
2.4 Analytics Strategies
2.4.1 Information Systems Management
2.4.2 Knowledge Management
2.4.3 Blockchain Technology and Big Personal Healthcare Data
2.5 Example Knowledge Management System
2.6 Discussion and Conclusions
References
Chapter 3: Visualization
3.1 Datasets
3.1.1 Healthcare Hospital Stay Data
3.1.2 Patient Survival Data
3.1.3 Hungarian Chickenpox Data
3.2 Conclusions
References
Chapter 4: Association Rules
4.1 The Apriori Algorithm
4.1.1 Association Rules from Software
4.1.2 Non-negative Matrix Factorization
4.2 Methodology
4.2.1 Demonstration with Kaggle Data
4.2.2 Analysis with Excel
4.3 Review of Applications
4.3.1 Korean Healthcare Study
4.3.2 Belgian Comorbidity Study
4.4 Conclusion
References
Chapter 5: Cluster Analysis
5.1 Distance Metrics
5.2 Clustering Algorithms
5.2.1 Demonstration Data
5.2.2 K-means
5.2.3 EWKM
5.3 Case Discussions
5.3.1 Mental Healthcare
5.3.2 Nursing Home Service Quality
5.3.3 Classification of Diabetes Mellitus Cases
5.4 Conclusion
References
Chapter 6: Time Series Forecasting
6.1 Time Series Forecasting Example
6.2 Classes of Forecasting Techniques
6.3 Time Series Forecasts
6.4 Forecasting Models
6.4.1 Regression Models
6.4.2 Coincident Observations
6.4.3 Time
6.4.4 Lags
6.4.5 Nonlinear Data
6.4.6 Cycles
6.5 OLS Regression
6.6 Tests of Regression Models
6.6.1 Sum of Squared Residuals (SSR)
R-Squared
Adjusted R-Squared
6.7 Causal Models
6.7.1 Multicollinearity
6.7.2 Test for Multicollinearity
6.8 Regression Model Assumptions
6.8.1 Autocorrelation
6.8.2 Heteroskedasticity
6.9 Box-Jenkins Models
6.10 Conclusions
References
Chapter 7: Classification Models
7.1 Basic Classification Models
7.1.1 Regression
7.1.2 Decision Trees
7.1.3 Random Forest
7.1.4 Extreme Boosting
7.1.5 Logistic Regression
7.1.6 Support Vector Machines
7.1.7 Neural Networks
7.2 Watson Healthcare Data
7.2.1 Initial Decision Tree
7.2.2 Variable Selection
7.2.3 Nurse Data
7.3 Example Case
7.4 Summary
Reference
Chapter 8: Applications of Predictive Data Mining in Healthcare
8.1 Healthcare Data Sources
8.2 Example Predictive Model
8.3 Applications
8.3.1 General Hospital System Management
8.3.2 Disease-specific Applications
8.3.3 Genome Research
8.3.4 Internet of Things Connectivity
8.3.5 Fraud Detection
8.4 Comparison of Models
8.5 Ethics
8.6 Summation
References
Chapter 9: Decision Analysis and Applications in Healthcare
9.1 Selection Criteria
9.2 Decision Tree Analysis
9.3 Decision Analysis in Public Health and Clinical Applications
9.4 Decision Analysis in Healthcare Operations Management
References
Chapter 10: Analysis of Four Medical Datasets
10.1 Variable Selection
10.2 Pima Indian Diabetes Dataset
10.3 Heart UCI Data
10.4 India Liver Data
10.5 Watson Healthcare Data
10.6 Conclusions
References
Chapter 11: Multiple Criteria Decision Models in Healthcare
11.1 Invasive Breast Cancer
11.2 Colorectal Screening
11.3 Senior Center Site Selection
11.4 Diabetes and Heart Problem Detection
11.5 Bolivian Healthcare System
11.6 Breast Cancer Screening
11.7 Comparison
References
Chapter 12: Naïve Bayes Models in Healthcare
12.1 Applications
12.2 Bayes Model
12.2.1 Demonstration with Kaggle Data
12.3 Naïve Bayes Analysis of Watson Turnover Data
12.4 Association Rules and Bayesian Models
12.5 Example Application
12.6 Conclusions
References
Chapter 13: Summation
13.1 Treatment Selection
13.2 Data Mining Process
13.3 Topics Covered
13.4 Summary
Name Index
Subject Index
