Big Data in Healthcare: Statistical Analysis of the Electronic Health Record
- 7h 47m
- Farrokh Alemi
- Health Administration Press
- 2020
Data from electronic health records (EHRs) play an increasingly vital role in improving patient care and generating system-wide efficiencies. Organizations that can tap this vast resource have a significant advantage; organizations that do not will likely fall behind. Is your organization prepared to capitalize on this invaluable flood of data?
Big Data in Healthcare: Statistical Analysis of the Electronic Health Record provides the statistical tools that healthcare leaders need to organize and interpret their data. Designed for accessibility to those with a limited mathematics background, the book demonstrates how to leverage EHR data for applications as diverse as healthcare marketing, pay for performance, cost accounting, and strategic management. Topics include:
- Using real-world data to compare hospitals’ performance.
- Measuring the prognosis of patients through massive data
- Distinguishing between fake claims and true improvements
- Comparing the effectiveness of different interventions using causal analysis
- Benchmarking different clinicians on the same set of patients
- Remove confounding in observational data
This book can be used in introductory courses on hypothesis testing, intermediate courses on regression, and advanced courses on causal analysis. It can also be used to learn SQL language. Its extensive online instructor resources include course syllabi, PowerPoint and video lectures, Excel exercises, individual and team assignments, answers to assignments, and student-organized tutorials.
Big Data in Healthcare applies the building blocks of statistical thinking to the basic challenges that healthcare leaders face every day. Prepare for those challenges with the clear understanding of your data that statistical analysis can bring—and make the best possible decisions for maximum performance in the competitive field of healthcare.
Appropriate Courses
Appropriate courses for this textbook include Introduction to Statistics, Advanced Statistics, Statistical Process Control, Regression Analysis, Causal Analysis, SQL Databases, and Quality Improvement.
About the Author
Dr. Farrokh Alemi, PhD, was trained as an operations researcher and industrial engineer and has worked in both academia and healthcare. He maintains patents on sentiment analysis, measurement of episodes of illness, and personalized medicine. He has published more than 120 peer-reviewed articles in journals such as Health Services Research, Medical Care, and Palliative Medicine. His research focuses on causal analysis of massive data available in electronic health records. His publications have contributed to predictive medicine, precision medicine, comparison of medication effectiveness, natural language processing, the risk-adjusted analysis of cost-effectiveness, causal networked models, tracking trajectories of diseases, and determining the prognosis of patients with multiple morbidities. Dr. Alemi is the creator of the widely used multimorbidity index. He has analyzed data from diverse groups of patients, including children; nursing home residents; and patients with diabetes, major depression, heart failure, anemia, hypertension, trauma, drug use disorder, and other conditions. Dr. Alemi was a pioneer in online management of patients and has provided congressional testimony on the role of the internet in healthcare delivery. He is the author of three books, including Decision Analysis for Healthcare Managers (Health Administration Press, 2006).
In this Book
-
Introduction
-
Preparing Data Using Structured Query Language (SQL)
-
Introduction to Probability and Relationships
-
Distributions and Univariate Analysis
-
Risk Assessment—Prognosis of Patients with Multiple Morbidities
-
Comparison of Means
-
Comparison of Rates
-
Time to Adverse Events
-
Analysis of One Observation per Time Period—Tukey's Chart
-
Causal Control Charts
-
Regression
-
Logistic Regressino
-
Propensity Scoring
-
Multilevel Modeling—Intercept Regression
-
Matched Case Control Studies
-
Stratified Covariate Balancing
-
Application to Benchmarking Clinicians—Switching Distributions
-
Stratified Regression—Rethinking Regression Coefficients
-
Association Network
-
Causal Networks
