Workflow framework for mining Diagnostic rules from ehrs Roxana Danger



Similar documents
Derek Corrigan Work Package Lead: WP4 Decision Rules and Evidence Royal College of Surgeons in Ireland

TRANSFoRm: Vision of a learning healthcare system

CREATING AND APPLYING KNOWLEDGE IN ELECTRONIC HEALTH RECORD SYSTEMS. Prof Brendan Delaney, King s College London

Didacticiel Études de cas. Association Rules mining with Tanagra, R (arules package), Orange, RapidMiner, Knime and Weka.

Translational Medicine and Patient Safety in Europe

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

TRANSFoRm: TRANSFoRming health care research and its implementation

KNIME TUTORIAL. Anna Monreale KDD-Lab, University of Pisa

The Learning Healthcare System: a European perspective

D3.5 Software Integration Plan

CHAPTER 3 PROPOSED SCHEME

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

Health Foundations Module

Bench to Bedside Clinical Decision Support:

Clinic + - A Clinical Decision Support System Using Association Rule Mining

2 Decision tree + Cross-validation with R (package rpart)

Association Technique on Prediction of Chronic Diseases Using Apriori Algorithm

Research Article Translational Medicine and Patient Safety in Europe: TRANSFoRm Architecture for the Learning Health System in Europe

What s Cooking in KNIME

Prediction of Heart Disease Using Naïve Bayes Algorithm

Better Healthcare with Data Mining

Electronic Medical Records Getting It Right and Going to Scale

Knowledge Discovery and Data Mining

LEVERAGING CLINICAL ANALYTICS TO DESIGN PERSONALISED MEDICINE. Dr. S. B. Bhattacharyya MBBS, MBA Healthcare Domain Consultant

Distributed Networking

KnowledgeSEEKER Marketing Edition

Hitachi s Plans for Healthcare IT Services

Copyright Soleran, Inc. esalestrack On-Demand CRM. Trademarks and all rights reserved. esalestrack is a Soleran product Privacy Statement

DATA MINING AND REPORTING IN HEALTHCARE

Promises and Pitfalls of Big-Data-Predictive Analytics: Best Practices and Trends

Mining an Online Auctions Data Warehouse

An intelligent tool for expediting and automating data mining steps. Ourania Hatzi, Nikolaos Zorbas, Mara Nikolaidou and Dimosthenis Anagnostopoulos

Connecting Basic Research and Healthcare Big Data

ICT Perspectives on Big Data: Well Sorted Materials

Big Data Analytics and Healthcare

Better Business Through Data Analysis & Monitoring

KNIME opens the Doors to Big Data. A Practical example of Integrating any Big Data Platform into KNIME

Mercy Health System. St. Louis, MO. Process Mining of Clinical Workflows for Quality and Process Improvement

Security Middleware Infrastructure for Medical Imaging System Integration

Applying Data Mining of Fuzzy Association Rules to Network Intrusion Detection

HETEROGENEOUS DATA INTEGRATION FOR CLINICAL DECISION SUPPORT SYSTEM. Aniket Bochare - aniketb1@umbc.edu. CMSC Presentation

1. Classification problems

Introduction to openehr Archetypes & Templates. Dr Ian McNicoll Dr Heather Leslie

PHARMACEUTICAL BIGDATA ANALYTICS

How can you unlock the value in real-world data? A novel approach to predictive analytics could make the difference.

Data modelling methods in clinical trials: Experiences from the CTMND project (ctmnd.org)

Big Data. Fast Forward. Putting data to productive use

D A T A M I N I N G C L A S S I F I C A T I O N

SAP InfiniteInsight 7.0 SP1

Data Mining Fundamentals

Il lavoro di armonizzazione. e HL7

Clinical Decision Support Systems An Open Source Perspective

Ensembles and PMML in KNIME

Semantically Steered Clinical Decision Support Systems

More details on the inputs, functionality, and output can be found below.

Architectural Patterns: From Mud to Structure

Your mission is our mission

SALUS: Enabling the Secondary Use of EHRs for Post Market Safety Studies

KNIME Enterprise server usage and global deployment at NIBR

Enabling the Big Data Commons through indexing of data and their interactions

Research Agenda for General Practice / Family Medicine and Primary Health Care in Europe Summary EGPRN

JOURNAL OF MEDICAL INFORMATICS & TECHNOLOGIES Vol. 21/2012, ISSN

Keywords data mining, prediction techniques, decision making.

IBM's Fraud and Abuse, Analytics and Management Solution

Welcome! E-Health and Data Analytics: Behavioral Health

How To Write An Electronic Health Record

A Review of Data Mining Techniques

Two-Phase Data Warehouse Optimized for Data Mining

Decision Support for Quality Improvement. Objective. Clinical Decision Support (CDS) Meaningful Use

Archive I. Metadata. 26. May 2015

Person Responsible for Module (Name, Mail address): Dr. Javier Soriano,

Find the signal in the noise

New Matrix Approach to Improve Apriori Algorithm

warehouse landscape for HINC

Adventures in EHR Computable Phenotypes: Lessons Learned from the Southeastern Diabetes Initiative (SEDI)

Achilles a platform for exploring and visualizing clinical data summary statistics

Conquering the Astronomical Data Flood through Machine

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

Data processing goes big

Analytics on Big Data

Using Normalized Status Change Events Data in Business Intelligence. Mark C. Cooke, Ph.D. Tax Management Associates, Inc.

Business Intelligence. Tutorial for Rapid Miner (Advanced Decision Tree and CRISP-DM Model with an example of Market Segmentation*)

The Data Mining Process

Structural Health Monitoring Tools (SHMTools)

Post-Implementation EMR Evaluation for the Beta Ambulatory Care Clinic Proposed Plan Jul 6/2012, Version 2.0

Clinical Decision Support Systems The revolution for a better health care

In-Database Analytics

Data Science. Research Theme: Process Mining

Accelerating variant calling

ENABLING DATA TRANSFER MANAGEMENT AND SHARING IN THE ERA OF GENOMIC MEDICINE. October 2013

Performance Analysis of Naive Bayes and J48 Classification Algorithm for Data Classification

Data Mining for Business Analytics

Data Mining Applications in Manufacturing

Database Marketing, Business Intelligence and Knowledge Discovery

Mining of predictive patterns in Electronic health records data

A Case of Study on Hadoop Benchmark Behavior Modeling Using ALOJA-ML

Contents. Dedication List of Figures List of Tables. Acknowledgments

Binary Diagnostic Tests Two Independent Samples

Improvement of the quality of medical databases: data-mining-based prediction of diagnostic codes from previous patient codes

Data Domain Profiling and Data Masking for Hadoop

Transcription:

Workflow framework for mining Diagnostic rules from ehrs Roxana Danger Department of Computing Imperial College London KNIME User Day, University of Westminster, June 25th, 2013

Outline EU-FP7 TRANSFoRm project Universal repository of diagnostic rules Data type heterogeneity Definition of analysis goals Selection of algorithms and quality measures Selection of working environment Results presentation Summary 2

TRANSFoRm Translational Research & Patient Safety in Europe 3

Knowledge In Healthcare and TRANSFoRm role Specific Research Knowledge Produced from clinical trials From controlled populations With well-defined questions Routinely Collected Knowledge Actionable Knowledge A vast quantity of data Captured in ehr systems With large population coverage May lack in detail and quality Distilled scientific findings Usable in clinical practice To support decision making 4

TRANSFoRm aims and objectives TRANSFoRm will develop a digital infrastructure that facilitates the reuse of primary care real world electronic Health Records (ehr) data to improve both patient safety and the conduct and volume of Clinical Research in Europe. The project will drive the advanced integration of clinical practice and research data to: Support clinical research with participant identification and evaluation of outcomes Support epidemiological research with large scale phenotype-genotype association studies and follow-up on trials Support clinical care on diagnosis and monitoring of patients 5

TRANSFoRm Data mining ehr BDs Data Mining Preproc Dataset Mining MCERs Filtering Filtered MCERs DSS Repository Updating Manual reviewed, interpretation and creation of CPRs Initial set of CPRs Validation CPRs DSS Repository CPRs from bibliog. 6

MCERs Measured clinical evidence rules Derek, 2012 DemographicFeatures, RFEs, Symptoms, Signs, Riskfactors, Test performed Diagnosis(QM) 7

Data from GPRD, TRANSHIS, NIVEL 8

ehrs Data mining Data type heterogeneity CDIM Terminologies and their mappings EHR BD 1 DSM 1 C D I M CDIM - DSM 1 C D I M CDIM - Dataset 1 EHR BD 2 EHR BD 3 DSM 2 DSM 3 M a p p i n g CDIM - DSM 2 CDIM - DSM 3 Q u e r y CDIM - Dataset 2 CDIM - Dataset 3 9

Definition of analysis goals First consultation of an EoC DemographicFeatures, RFEs, Symptoms, Signs, Riskfactors Diagnosis(QM) Consequent consultations of an EoC DemographicFeatures, RFEs, Symptoms, Signs, Riskfactors, Test performed, Time from previous consultation Diagnosis(QM) (DemographicFeatures, RFEs, Symptoms, Signs, Riskfactors, Test performed, Time from previous consultation) (DemographicFeatures, RFEs, Symptoms, Signs, Riskfactors, Test performed, Time from previous consultation) Diagnosis(QM) 10

Algorithms and quality measures (1) Fast implementations, easily parallelizable Easy to understand outputs, from which MCERs can be easily extracted. Association rules (Apriori, Kingfisher) Decision trees (C4.5) Sequential patterns (Sequential Kingfisher) 11

Algorithms and quality measures (2) Part I: Consequent (disease) interest Prior probability Part III: Itemsets characterization Support Error rate Part II: Variables characterization Posterior probability (+/-) Likelihood ratio Odd Ratio Part IV: Rules characterization Lift Confidence Sensitivity Specificity Likelihood ratio Odd Ratio 12

KNIME workflow environment (1) Our KNIME extensions: Database nodes Filter rows Filter columns Rename Resort columns Derive Group by Join Data mining nodes Kingfisher Quantifiers 13

KNIME workflow environment (1) 14

KNIME workflow environment (2) Configuring 15

KNIME workflow environment (4) Model learners 16

KNIME workflow environment (4) Quality measures computing 17

Results presentation 156.17.131.215/RulesAssessment/#rulesViewer 18

KNIME workflow for text mining 19

Summary Universal repository of diagnostic rules Data type heterogeneity Definition of analysis goals Selection of algorithms and quality measures Selection of working environment Results presentation Workflows defined (first results are promising) Future work Provenance CDIM integration 20

Workflow framework for mining Diagnostic rules from ehrs Thanks to team of data mining task in TRANSFoRm: Derek Connigan (RSCI) Jean K. Soler (Synapse) Tomasz Kajdanowicz (WROC) Przemyslaw Kazienko (WROC) Vasa Curcin (IC) KNIME User Day, University of Westminster, June 25th, 2013