book

Hands-On Healthcare Data

by Andrew Nguyen

August 2022

Beginner to intermediate

242 pages

7h 22m

English

O'Reilly Media, Inc.

Book available

Read now

Unlock full access

Conventions Used in This BookUsing Code ExamplesO’Reilly Online LearningHow to Contact UsAcknowledgments
The Enterprise MindsetThe Complexity of Healthcare DataSources of Healthcare DataElectronic Health RecordsClaims DataClinical/Disease RegistriesClinical Trials DataData Collection and How That Affects Data ScientistsProspective studiesRetrospective studiesConclusion
Basic Introduction to Docker and ContainersInstalling and Testing DockerConceptual Introduction to DatabasesACID ComplianceOLTP SystemsOLAP SystemsSQL Versus NoSQLSQL Databases(Labeled) Property Graph DatabasesHypergraph DatabasesResource Description Framework DatabasesConclusion
Controlled Vocabularies, Terminologies, and OntologiesKey ConsiderationsPre-coordination Versus Post-coordinationCase Study Example: EHR DataCommon TerminologiesCPTICD-9 and ICD-10LOINCRxNormSNOMED CTKey TakeawaysUsing the Unified Medical Language SystemSome Basic DefinitionsConcept OrientationWorking with the UMLSUMLS and Relational DatabasesPreprocessing the UMLSUMLS and Property Graph DatabasesUMLS and Hypergraph DatabasesReview of the UMLSConclusion
Publicly Accessible DataMedical Information Mart for Intensive CareSyntheaData ModelsGoalsExamples of Data ModelsCase Study: MedicationsThe Medication Harmonization ProblemTechnical Deep DiveConnecting to the UMLSDifficulties Normalizing Structured Medical DataConclusion
Publicly Accessible Data—SynPUFData ModelsChoosing a Data ModelCombining Claims and EHR DataCase Study: Combining Diagnoses and MedicationsOMOP Versus GraphsConsiderations When Combining Different Sources of Healthcare DataConclusion
A Primer on Machine LearningWhat Is Feature Engineering?Graph-Based Deep LearningExtracting Data as a TableTo SQL or Not to SQLQuerying OMOP DataFrom Graphs to DataframesWhy Add the Complexity of Graphs?Machine Learning and Feature Engineering with GraphsGraph Embeddingsnode2veccui2vecmed2vecsnomed2vecSome Final Thoughts About EmbeddingsMaking the Case for Graph-Based AnalysisConclusion
Federated Learning and Federated AnalyticsHow Does Federated Learning Work?Why Federated Analytics/Learning?The Data Harmonization Challenge in a Federated ContextGraphs and Federated ApproachesNatural Language ProcessingConcept ExtractionBeyond Concept ExtractionClinical NLP ToolsCommercial Clinical NLP SolutionsKey Differences Between Clinical NLP and Other Applications of NLPConclusion
Other Types of Healthcare RWDData Normalization and HarmonizationMerging DatasetsBridging IT and the BusinessIt’s a Human, Not Technical, ProblemGraphs Can Be Part of the SolutionGraphs Are Not a Silver BulletConclusion

Overview

Healthcare is the next frontier for data science. Using the latest in machine learning, deep learning, and natural language processing, you'll be able to solve healthcare's most pressing problems: reducing cost of care, ensuring patients get the best treatment, and increasing accessibility for the underserved. But first, you have to learn how to access and make sense of all that data.

This book provides pragmatic and hands-on solutions for working with healthcare data, from data extraction to cleaning and harmonization to feature engineering. Author Andrew Nguyen covers specific ML and deep learning examples with a focus on producing high-quality data. You'll discover how graph technologies help you connect disparate data sources so you can solve healthcare's most challenging problems using advanced analytics.

You'll learn:

Different types of healthcare data: electronic health records, clinical registries and trials, digital health tools, and claims data
The challenges of working with healthcare data, especially when trying to aggregate data from multiple sources
Current options for extracting structured data from clinical text
How to make trade-offs when using tools and frameworks for normalizing structured healthcare data
How to harmonize healthcare data using terminologies, ontologies, and mappings and crosswalks