Achilles a platform for exploring and visualizing clinical data summary statistics



Similar documents
Next-generation Phenotyping Using Interoperable Big Data

How to extract transform and load observational data?

Learning from observational databases: Lessons from OMOP and OHDSI

Sisense. Product Highlights.

Open-Source Big Data Analytics in Healthcare

Connecting Basic Research and Healthcare Big Data

Theodoros. N. Arvanitis, RT, DPhil, CEng, MIET, MIEEE, AMIA, FRSM

Utility of Common Data Models for EHR and Registry Data Integration: Use in Automated Surveillance

Classifying Adverse Events From Clinical Trials

Lost in Space? Methodology for a Guided Drill-Through Analysis Out of the Wormhole

Searching biomedical data sets. Hua Xu, PhD The University of Texas Health Science Center at Houston

Summary of Responses to the Request for Information (RFI): Input on Development of a NIH Data Catalog (NOT-HG )

Find the signal in the noise

An EVIDENCE-ENHANCED HEALTHCARE ECOSYSTEM for Cancer: I/T perspectives

Real-Time Market Monitoring using SAS BI Tools

Business Intelligence & Product Analytics

Integrated Enterprise Reporting

Karl Lum Partner, LabKey Software Evolution of Connectivity in LabKey Server

Preparing Electronic Health Records for Multi-Site CER Studies

Exploration and Visualization of Post-Market Data

From Fishing to Attracting Chicks

In this presentation, you will be introduced to data mining and the relationship with meaningful use.

How To Choose A Business Intelligence Toolkit

Visual Analytics to Enhance Personalized Healthcare Delivery

MED 2400 MEDICAL INFORMATICS FUNDAMENTALS

School of Nursing University of Minnesota Informatics Competencies across the Curriculum

Oracle Big Data SQL Technical Update

Big Data R&D Initiative

QAD Business Intelligence Data Warehouse Demonstration Guide. May 2015 BI 3.11

MEDICAL DATA MINING. Timothy Hays, PhD. Health IT Strategy Executive Dynamics Research Corporation (DRC) December 13, 2012

Environmental Health Science. Brian S. Schwartz, MD, MS

Adam Rauch Partner, LabKey Software Extending LabKey Server Part 1: Retrieving and Presenting Data

Meaningful use. Meaningful data. Meaningful care. The 3M Healthcare Data Dictionary (HDD): Implemented with a data warehouse

NATIONAL CENTER FOR PUBLIC HEALTH INFORMATICS (CPE)

Know more Act Better: Launching KPI Reporting & Benchmarking Framework

Ernesto Ongaro BI Consultant February 19, The 5 Levels of Embedded BI

Secondary Uses of Data for Comparative Effectiveness Research

The course will run simultaneously with the MSCI students.

Building patient-level predictive models Martijn J. Schuemie, Marc A. Suchard and Patrick Ryan

An interdisciplinary model for analytics education

Business Intelligence, Analytics & Reporting: Glossary of Terms

Frequently Asked Questions

3M Health Information Systems

Geodatabase Programming with SQL

Use of Electronic Health Records in Clinical Research: Core Research Data Element Exchange Detailed Use Case April 23 rd, 2009

Big Data Architecture & Analytics A comprehensive approach to harness big data architecture and analytics for growth

Comparative Analysis of the Main Business Intelligence Solutions

How To Use Data Analysis To Get More Information From A Computer Or Cell Phone To A Computer

Deploy. Friction-free self-service BI solutions for everyone Scalable analytics on a modern architecture

A GENERAL TAXONOMY FOR VISUALIZATION OF PREDICTIVE SOCIAL MEDIA ANALYTICS

OpenAdmin Tool for Informix (OAT) October 2012

11. CASE STUDY: HEALTHCARE ANALYTICAL DASHBOARDS USING TABLEAU

Disrupting The Market: Predictive Analytics As A Service

Big Data to Knowledge (BD2K)

FDA's Mini-Sentinel Program to Evaluate the Safety of Marketed Medical Products. Progress and Direction

Building Open-Source Based Architecture of Enterprise Applications for Business Intelligence

Business Intelligence in Healthcare: Trying to Get it Right the First Time!

Business Intelligence and Healthcare

Data Management for Large Studies Robert R. Kelley, PhD. Thursday, September 27, 2012

PLATFORA INTERACTIVE, IN-MEMORY BUSINESS INTELLIGENCE FOR HADOOP

JAVASCRIPT CHARTING. Scaling for the Enterprise with Metric Insights Copyright Metric insights, Inc.

Please contact Cyber and Technology Training at for registration and pricing information.

Data Mining, Predictive Analytics with Microsoft Analysis Services and Excel PowerPivot

What you can do:...3 Data Entry:...3 Drillhole Sample Data:...5 Cross Sections and Level Plans...8 3D Visualization...11

CRM Analytics - Techniques for Analysing Business Data

Open is as Open Does: Lessons from Running a Professional Open Source Company

User Guide. Analytics Desktop Document Number:

TIBCO Spotfire Metrics Modeler User s Guide. Software Release 6.0 November 2013

The Big Data Bioinformatics System

Associate Professor, Department of CSE, Shri Vishnu Engineering College for Women, Andhra Pradesh, India 2

Transcription:

Biomedical Informatics discovery and impact Achilles a platform for exploring and visualizing clinical data summary statistics Mark Velez, MA Ning "Sunny" Shang, PhD Department of Biomedical Informatics, Columbia University NIH BD2K biocaddie webinar, August 13 th, 2015

Outline OHDSI ACHILLES demo Applications of ACHILLES 2

What is OHDSI The Observational Health Data Sciences and Informatics (OHDSI) program is a multistakeholder, interdisciplinary collaborative To bring out the value of observational health data through large-scale analytics and evidence generation Clinical characterization Population-level estimation Patient-level prediction 3

What is OHDSI Single observational data source is unlikely to be sufficient for research analysis needs Analyze multiple data sources concurrently Using a common data model and the foundational infrastructure to enable observational research By 2014, 58 databases in CDM > 250 million patients covered 4

What is OHDSI Mission To transform medical decision making by creating reliable scientific evidence about disease natural history, healthcare delivery, and the effects of medical interventions through large-scale analysis of observational health database for populationlevel estimation and patient-level predictions 5

OHDSI Infrastructure Data Source 1 Data Source 2 Data Source 3 Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM) statistical analysis e.g. Treatment pathway Analytic tools ACHILLES CIRCE Others 6

OMOP Common Data Model (CDM) V 5 7

Data transform in CDM Extracting, transforming, and loading (ETL) process WhiteRabbit: analyzes the structure and content of a database RabbitInAHat: connects and maps tables and columns from the raw dataset to the CDM dataset ETL-CDMBuilder: transform raw data to CDM 8

ACHILLES (Automated Characterization of Health Information at Large-scale Longitudinal Evidence Systems) An open source analytics framework Interactively explore population-level summary statistics for the data stored in CDM Profile your CDM data Explore population-level summaries Review data quality assessment Data in CDM Summary statistics Web visualization of statistics 9

ACHILLES implementation ACHILLES R package Oracle / SQL Server / Postgres / Redshift Summary statistics export into Json to prepare data for visualization Visualization by AchillesWeb (HTML5 / JavaScript) create strata tables Data quality queries (Heel) Export to JSON Visualization (AchillesWeb) 10

ACHILLES Summary Statistics 1 Summary of data set / clinical database Size of the database First /Continuous observation 11

Dashboard Summary of clinical dataset 12

ACHILLES Summary Statistics 2 Person demographic information and demographic information over death 13

Person 14

Death 15

ACHILLES Summary Statistics 3 Metadata (e.g. observation periods, data density) Observation periods document time intervals during which health care information captured Data density describes the unit quantity of records and concepts pertains in each database 16

Observation Periods 17

Data Density 18

ACHILLES Summary Statistics 3 Prevalence of condition/condition era/ observation/drug exposure/drug era/procedure/visit Treemap view Table view Drill down view 19

Condition Treemap view 20

Condition Table view 21

Condition Drill down view 1 22

Condition Drill down view 2 23

ACHILLES Summary Statistics 4 Achilles HEEL Data quality control component 24

Achilles Heel Data quality tool 25

ACHILLES Heel Error Types Error Type Clinical facts Example Illogical change Monthly change of count of condition is more than 100% Invalid ids Improper value based on norm Improper value based on inter-relationship Terminology Not standard vocabulary Non-mapped concept Wrong mapping concept Person has invalid provider_id Year of birth is less than 1800 Negative payment A condition is recorded after the patient is dead a concept is not a standard OMOP vocabulary concept Data with unmapped concepts Drug is not coded with RxNorm 26

Applications of ACHILLES Explore summary statistics about the clinical data Public domain (de-identified information) Integrate with clinical systems Achilles integrating other OHDSI tools Framework for other applications 27

ACHILLES collaborating with other OHDSI tools ACHILLES Database profiling CIRCE Cohort definition HERACLES Cohort characterization 28

ACHILLES Framework for other applications biocaddie DDI Suitability Framework 29

Suitability General definition the quality or state of being especially suitable or fitting [Merriam-Webster] In our project The extent to which a clinical dataset to meet the research needs for observational studies Data suitability is how suitable the data are for a specific research purpose 30

Research methods EHR characteristics lit review Suitability conceptual framework Web-based survey Metrics with Columbia EHR Hybrid Approach Categories Measures Implementation by Customizing ACHILLES Observa tional studyderived submeasur e Desider ata studyderived submeasur e 31

Can I access? User -- Researcher What s inside? (content) Suitability of Clinical Database for Observational Study Are data usable? Policy and Administration Data policy documentat ion Administrati ve platform Technical accessibility Relevance Healthcare organization description Data organization documentation Research data inventory Available and retrievable temporal information Descriptive metadata and provenance documentation Data provenance Database content synopsis Usability Data representatio n Usefulness Cohort availability Database linkability Quality Data quality control Database data quality Research sample data quality Accessibility Representation Intrinsic Contextual Data (data characteristics)

Suitability Survey https://www.surveymonkey.com/r/ybrx2tw 33

Implementation 34

Important websites OHDSI http://www.ohdsi.org/ Main GitHub Page: https://github.com/ohdsi/ Forum: http://forums.ohdsi.org/ ACHILLES http://www.ohdsi.org/analytic-tools/achilles-for-datacharacterization/ R Package for Generating Statistics for ACHILLES: https://github.com/ohdsi/achilles Web Application for Viewing ACHILLES Results: https://github.com/ohdsi/achillesweb Demo http://www.ohdsi.org/web/achilles/index.html#/ohdsi%20sam ple%20database/dashboard 35