Modernizing Medical Research: AI and Medical Records, by Bill Inmon, David Rapien, and Sylvia Sydow, MD
Unlock the hidden potential of medical research with cutting-edge data analytics—discover how structured and unstructured (textual) medical data can revolutionize patient care, drive groundbreaking discoveries, and transform the future of healthcare.
Unlocking the treasure trove
Research and medical records
The challenges of looking at a population
Text as an obstacle
Textual disambiguation
A step by step approach
Heuristic analysis
From ah? to aha!
The need for speed
Obstacles to achieving speed of analysis
Autonomy of analysis
In summary
Taxonomies
Relevance
Completeness of the taxonomy
Unique identification
Medical taxonomies
How are taxonomies used?
A real world, external foundation
The size of the taxonomy
Periodic maintenance
Ontologies
In summary
Privacy and the law
Storage media
Images
Medical record selection
Medical record structure
Managing volumes of data
Different data formats
The Internet
In print
Spreadsheets
On a voice recording
In summary
Medical journals
Clinical trials and patient records
Text and clinical trials
The structure of the study
The number of studies/clinical trials
Reading the entire document
Resolving terminology differences
In summary
Encoding
Measurement
Language
Common structure
Spelling
Grouping similar objects
Acronyms
Homographs
Calculations
Further elucidation
Formatting adjustments
Different name for the same object
In summary
The basic interface
Simple questions
The Datavox database
Adjusting the vocabulary
A closer look at the output data
In summary
Exploration and clinical trials
Computer systemization
The potential of no resolution
Lessons learned from an exploration
Different approaches to exploration
Scatter diagrams
Correlation
A Pearson coefficient matrix
The need for speed
In summary
Many forms of analysis
Operating from the same database
Textual database versus a structured database
Different types of analytical tools
Spreadsheet data analysis – Excel
Genai based query suite – Thoughtspot
Knowledge graphs – Neo4j
Dashboards – Tableau
Analytics in the structured environment
Analytics on both structured and textual data
Different organizations of data
Intersecting data
Connectors
Stable/unstable connectors
Types of relationships
No relationship
Universal relationship
Direct relationship
Indirect relationship
Classification-based relationship
Different connections
An example of blending textual and structured data
In summary
A “normal” procedure
Flexibility
Length of time
Speed of textual ETL
Attitude
Reconsidering the study
Medical research is at a crossroads—traditional methods of analyzing patient records, clinical trials, and research journals are no longer enough to keep pace with the rapid evolution of medicine. Modernizing Medical Research unveils a revolutionary approach that bridges the gap between raw medical text and structured databases, enabling researchers to extract critical insights with unprecedented speed and accuracy. Whether you’re a healthcare professional, data scientist, or medical researcher, this book provides the key to unlocking a new era of medical discovery.
At the heart of modern medical research lies an untapped goldmine: unstructured text. Millions of patient records, research papers, and clinical trial reports contain invaluable information, yet much of it remains inaccessible due to the limitations of traditional database analysis. This book presents a groundbreaking methodology for converting raw text into structured data, making it possible to analyze vast datasets efficiently and uncover patterns that were previously impossible to detect.
This book combines technical expertise with real-world medical applications. It delves into crucial topics such as text ingestion, taxonomies, ontologies, and heuristic analysis, providing a roadmap for researchers and analysts to leverage artificial intelligence, machine learning, and natural language processing in the pursuit of medical advancements.
One of the greatest challenges in healthcare analytics is overcoming the complexity and ambiguity of medical text. Modernizing Medical Research explains how textual contextualization—an advanced Extract, Transform, and Load (ETL) technique—can convert messy, unstructured medical data into structured databases ready for analysis. The result? Faster, more reliable insights that can drive better clinical decisions, improve patient outcomes, and accelerate medical breakthroughs.
The book also explores how structured databases enable large-scale population studies, revealing trends and correlations that individual case studies cannot capture. From early disease detection to the identification of treatment effectiveness, these analytical techniques have the potential to reshape medical research and usher in an era of precision medicine. Researchers will learn how to efficiently organize and analyze vast amounts of medical information, leading to evidence-based practices that can improve healthcare globally.
A must-read for healthcare and information technology professionals, this book offers a practical and highly accessible guide to implementing modern data techniques in medical research. It details step-by-step processes for handling large datasets, integrating structured and unstructured data, and applying AI-driven analytics to uncover hidden relationships in medical records.
For those working with clinical trials and medical journals, Modernizing Medical Research demonstrates how computational tools can enhance study design, streamline data extraction, and improve the reliability of research findings. By providing concrete examples and real-world case studies, the authors illustrate how modern analytics can reduce research bottlenecks and speed up the journey from hypothesis to discovery.
In an age where healthcare data is expanding at an exponential rate, traditional research methods are no longer sufficient. This book presents a forward-thinking, innovative approach that will empower medical researchers, healthcare organizations, and policymakers to harness the full power of data-driven insights. The future of medicine lies in our ability to process and analyze vast amounts of information quickly—and Modernizing Medical Research shows exactly how to make that future a reality.
If you’re ready to take medical research to the next level—combining the power of big data, artificial intelligence, and healthcare analytics—then this book is your ultimate guide. Modernizing Medical Research is essential for anyone looking to transform how we understand, analyze, and advance medical science in the digital age.
About Bill:
Bill Inmon, the “father of the data warehouse,” has written 60 books published in nine languages. ComputerWorld named Bill one of the ten most influential people in the history of the computer profession. Bill’s latest adventure is the building of technology known as textual disambiguation.
About Dave:
David Rapien is an Associate Professor – Educator of Information Systems and Business Analytics at the University of Cincinnati’s Lindner College of Business. Along with teaching for over 25 years, Dave has developed and managed data integration systems in the Sports Management, Medical, Insurance, Banking, Legal, Horse Racing, and School Administration industries. David owes his success to his wife, Laura, and his four children for their constant support, and to his dad, for teaching him how to explain complex ideas in simple terms.
About Sylvia:
Sylvia Sydow is a graduate of the University of Nebraska Medical School and is a retired board certified emergency medicine physician. Her retirement years are filled with her interest in gardening and raising Scottish terriers.
Please complete all fields.