usage of open source software for real world data analysis in pharmaceutical companies and...

36
Usage of open source software for “Real World Data Analysis” in pharmaceutical companies & healthcare institutions APRIL 20, 2016 Kees van Bochove, CEO & Founder, The Hyve

Upload: kees-van-bochove

Post on 23-Jan-2017

551 views

Category:

Health & Medicine


3 download

TRANSCRIPT

Page 1: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

Usage of open source software for “Real World Data Analysis” in pharmaceutical companies & healthcare institutions

APRIL 20, 2016

Kees van Bochove, CEO & Founder, The Hyve

Page 2: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

2

Agenda

1.  Introduction: Secondary use of healthcare data for research

2.  Overview of OMOP Data Model & Mapping Process

3.  Overview of OHDSI data analytics tools

Page 3: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

1.

INTRODUCTION

SECONDARY USE OF HEALTHCARE DATA FOR RESEARCH

3

Page 4: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

4

The Hyve

u  Professionalsupportforopensourceso0wareforbioinforma4csandtransla4onal

researchso0ware,suchastranSMART,cBioPortal,i2b2,Galaxy,ADAMandOHDSI

MissionEnablepre-compe44vecollabora4oninlifescienceR&Dbyleveragingopensourceso,ware

Corevalues ShareReuseSpecialize

OfficeLoca5onsUtrecht,NetherlandsCambridge,MA,UnitedStates

ServicesSo0waredevelopmentDatascienceservicesConsultancyHos4ng/SLAs

Fast-growingStartedin201235peoplebynow

Page 5: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

Interdisciplinary team

so0ware engineers, data scien4sts, project managers & staff; exper4se inbioinforma4cs,medicalinforma4cs,so0wareengineering,biosta4s4csetc.

5

Page 6: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

What Ewan Birney has to say about it … (GA4GH Leiden 2015)

6

Page 7: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

Time To Market: 11 – 18 years

6

Neg

otia

tion

for R

eim

burs

emen

t 27

mem

ber S

tate

s

EMA

Fili

ng

Pre-

Clin

ical

Res

earc

h Cl

osed

& O

pen

Inno

vatio

n

Clinical Trials

EMA

App

rova

l for

Sal

e

HTA

App

rova

l

Phase 1 Phase 2 Phase 3

5,000 10,000

Compounds

250 Compounds

3 – 6 Years 6 – 7 Years

5 Therapies

1 Therapy

2 – 5 Years

Number of Patients/Subjects

20-100 100-500 1000-5000

Regulatory Review

Drug Discovery

Pre Clinical Testing

PhV Monitoring

Total Cost: $2 - $4 Billion USD

Sources: Drug Discovery and Development: Understanding the R&D Process, www.innovation.org;

CBO, Research and Development in the Pharmaceutical Industry, 2006;

Forbes, Matthew Herper, “The Truly Staggering Cost Of Inventing New Drugs”, February 10, 2012

Current EU “Patient Journey” is expensive and slow

New therapies don’t reach

patients until here

Phase 4 : $0.6B Drug Development : $2.6B

Page 8: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

Secondary use of health data to enrich research

8 The value of healthcare data for secondary uses in clinical research and development — Gary K. Mallow, Merck, HIMSS 2012

1 2 3 4 5 6 7 8 9

1,000

10,000

100,000

1 million

Years

#Pa

tient

Exp

erie

nce

s /

Rec

ord

s

The “burning platform” for life sciences Pharma-owned highly controlled clinical trials data Clinical practice, patients, payers and providers own the data

Product Launch

R&D Phase IV

Challenge

Today, Pharma doesn’t have ready access to this data, yet insights for safety, CER and other areas are within this clinical domain, which includes medical records, pharmacy, labs, claims, radiology etc.

Page 9: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

9

Clinical Trials vs Observational Studies Clinical Trials Observational Studies

Study Design Controlled (hypothesis driven) “Real world” data

Sample Size Small (10.000 is large) Large (millions of people)

Endpoints Efficacy, safety Effectiveness, economic value

Statistics Descriptive statistics (e.g. ANOVA) Epidemiological modeling

Cost Expensive Not so expensive

Perspective Study population Society in general

Page 10: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

To become the trusted European hub for health care data intelligence,

enabling new insights into diseases and treatments

EMIF vision

10

Discover

Assess

Reuse

Page 11: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

Data available through EMIF consortium

§  Large variety in “types” of data

§  Data is available from more than 53 million subjects from seven

EU countries, including

Primary care data sets

Hospital data

Administrative data Regional record-linkage systems

Registries and cohorts (broad and disease specific)

Biobanks

>25,000 subjects in AD cohorts

>90,000 subjects in metabolic cohorts

Page 12: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

>40

mill

ion

MAAS

SDR

EGCUT

PEDIANET

SCTS

IMASIS

HSD

AUH

IPCI

ARS

SIDIAP

PHARMO

THIN

100 1,000 10,000 100,000 1,000,000 10,000,000 100,000,000

Ap

pro

xim

ate

tota

l (c

umul

ativ

e)

num

be

r of s

ubje

cts

Available data sources in EMIF

12

EMIF-Platform

EMIF-Available Data Sources; EXAMPLES

1K

2K

52K

400K

475K

2.8M

2.3M

10M

Status Jan 2016

3.6M

1.6M

1M

12M

6M

Page 13: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

13

OMOP & OHDSI - Overview

u  OMOP: Common Data Model for observational healthcare data:

persons, drugs, procedures, devices, conditions etc.

u  OHDSI: Large-scale analytics tools for observational data

An open source community, a.o. developing:

u  Tools to support the ETL / mapping process into OMOP (White Rabbit etc.)

u  Tools to perform analytics: e.g. Achilles for data profiling, Calypso for

feasibility assessment

www.omop.org

www.ohdsi.org

Page 14: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

2.

OMOP MODEL & DATA MAPPING PROCESS

14

Page 15: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

15

OMOP Common Data Model v5.0

v  OMOP =

Observational

Medical

Outcomes

Partnership

v  CDM = Common

Data Model

v  SQL Tables

Page 16: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

16

OMOP-CDM Clinical data tables

Page 17: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

17

Mapping the source data to OMOP CDM

ETL design

ETL implementation

White Rabbit Source data inventarisation

Rabbit in a Hat Map source tables to CDM structure To

ols

use

d

Usagi Map source terms to CDM ontologies (vocabulairies)

syntactic mapping semantic mapping

ETL verification

Achilles Review database profiles Review data quality assesment (Achilles Heel)

Page 18: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

18

Output from White Rabbit Tab “Overview”: fields for each table

Tab “Medication”: per table values in fields and frequencies

=Medication name

Page 19: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

19

Mapping of tables to CDM

Page 20: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

20

v  All coded items (gender, race etc) need to be mapped

v  Mapping of Medication, Diagnosis, procedures values to

appropriate ontology (RXNorm, ICD-9 etc)

Map terms to target vocabularies

NHANES Gender code NHANES Gender description

Equivalent OMOP SOURCE_CODE

OMOP SOURCE_CODE_DESCRIP

TION

SOURCE_TO_CONCEPT_MAP_ID

. missing U UNKNOWN 8551

1 Male M MALE 8507

2 Female F FEMALE 8532

Page 21: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

21

Overview of ontologies used in OMOP

SNOMED-CT

READ

ICD-9-CM RXNorm

ICD-9-Procedures

CPT-4

HCPCS

Page 22: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

3.

OHDSI – ANALYTICS TOOLS

22

Page 23: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

23

Open Source in Precision Medicine

Study design:

Biobanking:

Scientific compute:

Data visualisation:

Workflows & Storage:

Datawarehousing:

Imaging:

Clinical / Healthcare:

Page 24: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

24

Tools on GitHub

Page 25: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

25

Active Open Source Community!

Page 26: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

26

Page 27: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

27

ACHILLES: Database overview

Page 28: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

28

ACHILLES: Achilles Heel Report

Page 29: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

29

ACHILLES: Conditions Overview

Page 30: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

30

HERACLES: Cohort Characterization

Slide from P. Ryan, Janssen

Page 31: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

31

CALYPSO: Query Definition

Page 32: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

32

CALYPSO: Query Definition

Page 33: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

33

CALYPSO: Query Definition

Page 34: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

34

CALYPSO: Query Results

Slide from P. Ryan, Janssen

Page 35: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions

Re-use of healthcare data

35

Prof. Johan van der Lei Erasmus MC University Medical Center

“We need to learn from experience and find ways to unite the large volumes of data in Europe. At

the end of the day, we are in this for better health care.”

Co-coordinator EMIF-Platform

EMIF-Platform

Page 36: Usage of open source software for Real World Data Analysis in pharmaceutical companies and healthcare institutions