semantic web mining for pharmaceutical business intelligence
DESCRIPTION
DIA disclosure meeting, Bethesda 2011TRANSCRIPT
Applying Semantic Web Mining to Analyze Global Research Activityand Render Business Intelligence
David CockerMDCPartners Belgium
Clinical Trial Disclosures Bethesda
The views and opinions expressed in the following PowerPoint slides are those of the individual presenter and should not be attributed to Drug Information Association, Inc. (“DIA”), its directors, officers, employees, volunteers, members, chapters, councils, Special Interest Area Communities or affiliates, or any organization with which the presenter is employed or affiliated.
These PowerPoint slides are the intellectual property of the individual presenter and are protected under the copyright laws of the United States of America and other countries. Used by permission. All rights reserved. Drug Information Association, DIA and DIA logo are registered trademarks or trademarks of Drug Information Association Inc. All other trademarks are the property of their respective owners.
2www.diahome.orgDrug Information Association
You can use my slides if you want…
• What is Business intelligence?• What is semantic web mining? • How can you use the data from the web to augment
strategy?• More disclosure means more data to evaluate! • Output data treatments
Basic flow of this presentation
Drug Information Association www.diahome.org 3
• Data which is useful to a commercial company• Supports an assumption(s)• Monitors strategy• Help notice a change in homeostasis• GET QUICKER TO THE TRUTH
What is business intelligence
Drug Information Association www.diahome.org 4
Make better choices
Development Plan
Scientific Question Protocol Enrolment Retention Data
analysis
Submission access to market
Disease management knowledge
Competitive intelligence update
Engaging with Key Opinion Leaders
Other Medical-Marketing Activities
Supporting Value Demonstration
Engaging with Key Opinion Leaders
Competitive intelligence update
Disease management knowledge
Decision Lifecycle
Planning Phase
Implementation Phase
Requirements
Specification
Design
Alignment
Execution & Monitoring
Rapid Response to Change
Security
Quality Assistance
Decision Engineering…..when do you need the info
These changes have led to reduced warning times and compressed decision cycles.
Interdependence and complexity, creating greater uncertainties, systemic risk and a less predictable future.
Scientific Question
Retention
How can you use the data from the web to augment strategy
How can you use the data from the web to augment strategy
Drug Information Association www.diahome.org 7
The Big Bang
What is semantic web mining?
What is semantic web mining?
Drug Information Association www.diahome.org 9
Ontology Vocabulary
Proof
Trust Rules
Look up an animal on Google:• Dog• Cow • Armadillo
No concept of animal
No concept of musical
What is semantics?It’s easier if you are a human
04/13/2023
Various sources available
Information
TopicTopic
Diseases Respiratory Tract Diseases
Lung Diseases
Lung Diseases, Fungal
Lung Diseases, Interstitial
Lung Diseases, Obstructive
Asthma
Bronchitis
Pulmonary Disease, Chronic Obstructive Bronchitis,
Chronic
Lung Diseases, Parasitic
Lung Neoplasm's
Nose Diseases
Pleural Diseases
Respiration Disorders
Eye Diseases
Male Urogenital Diseases
Treatment mapping
Condition Treatment useSubstance
COPD
Condition
04/13/2023
Inferred data
Inferred data
Bad Lauterberg Germany
investigator Site
ConditionTreatment
use
Substance
Sponsor Trial
Top KOL
http://www.roche.com/med-cor-2008-06-10Results from Manual Search
What a hit
Inferred data: source CT.gov
Drug Information Association www.diahome.org 15
Argentina, Buenos Aires
Hospital Britanico-Buenos Aires
Ciudad Autonoma de Buenos Aires, Buenos Aires, Argentina, C1280AEB
UAI Hosp. Universitario
Ciudad Autonoma de Buenos Aires, Buenos Aires, Argentina, C1437BZL
Sanatorio Otamendi
Ciudad Autonoma de Buenos Aires, Buenos Aires, Argentina, C1115AAB
Instituto del Corazon Denton A. Cooley
Ciudad Autonoma de Buenos Aires, Buenos Aires, Argentina, C1416A
HIGA Hospital Interzonal General de Agudos Oscar Allende
Mar del Plata, Buenos Aires, Argentina, 07600 Clinica Independencia MunroMunro, Buenos Aires, Argentina, 01605
Hospital Italiano de CordobaCordoba, Argentina, X5004 FJE Sanatorio AllendeCordoba, Argentina, X5000JHQ Instituto de Cardiologia J.F. CabralCorrientes, Argentina, W3400AMZ
Inferred data with added information from PubMed
Drug Information Association www.diahome.org 16
Where are the new trials going ?
Oncology Diabetes
??? ???
1 2 3 4 5 6 7 8 9 100
10
20
30
40
50
60
Economic blockAfricaAsiaCentral AmericaChinaEurope EastIndiaMiddle EastRussiaSouth AmericaSouthern Hemisphere
Enrolment statistics over Diabetes, Blue chip, ignoring the economic blocks North America, Europe, Europe West, Japan
Trial count
Liver Cancer
Meta-analysis of all trials in Liver Cancer
Diabetes
Meta-analysis of all trials in Diabetes
Individuals who can help you in your research
Profiling
Sponsor activity Drug research sponsored Investigator Institutional score Therapeutic
Academic score
Number of trials active, recruiting and completed, for a given organisation or department
specific drug or drug class research as an active sponsor
Individuals found in trial registries, regulatory websites & publishers on clinical trial activity Impact assessment of TA-targeted publications
Ranked assessment of the organisation by weight of publications pertaining to the therapy area
Organization Ranking System
60 1 302 30
TA specific Journal categories:
• Top 10%: High Impact Journal (HIJ)• 11 – 40%: Medium Impact Journal (MIJ)• 41 – 100%: Low Impact Journal (LIJ)
Person Academic score
Calculation of scores
snips of data sources
KOL profileTop centre in DMT2
Sponsor conducting trial @
Company disclosure $$
Participated in trials
Expert in regulatory review
Works with ABC Pharma Co. on new GLP-1
Information rendered Data Source examples
Well he knows his stuffDiabetes. And works for hospital X PubMed
OH, he’s worked for Sponsor on xyz wonder drug last year. clinicaltrials.gov
And he gets money from XYZ Pharma Co. as a speaker Corporate databases
He’s been an investigator for a while now BioMonitor
He’s speaking next week at the big US event Google
Expert in DiabetesOn review panel EMEA
(Competent authorities)
GLP-1 Drug databases
He works for ABC Pharma Co. too on their GLP-1 Corporate databases
Speaker @ American Diabetes Association
No c
onfli
cts o
f int
eres
ts
Docu
men
ted
colla
tera
l
Colla
bora
tive
Cred
ibili
ty
Influ
entia
l with
pee
rs
Wel
l con
nect
ed
Acce
pted
by a
ll sta
keho
lder
s
+ - ++ Hum Well Should be
Yes Yes
Objective
Subjective
• Transparent data capture procedure• Inferred data not enough
• New mechanisms to catch & update information• Real-time
• Objective, measurable components (=accepted)• Compliant with codes of conduct
• Portable data • globally accessible
• Metrics• Dashboard approach
• Robust privacy , secure technologies opted in/out
Key Components of KOL Systems going forward
Drug Information Associationwww.diahome.org 26
Wilmington
50 miles
Washington
New York
Allentown
50 miles50 miles Philadelphia
Baltimore
Where will my patients come from?
Making choices about trial placement
Time – Cost – Quality
Current environment Commercial risk analysis
Investment choices
Debrecn-Budapest=216 km
Debrecn population
206,225
- Density442.53/km2 (1,146.1/sq mi)
Szeged population
169,678
Density 604.2/km2 (1,564.9/sq mi)
Debrecn-Szeged=220 km
Budapest (2009)
- City ▲ 1,712,210
- Density 3,241.5/km2
- Urban ▲ 2,503,205
- Metro ▲ 3,271,110
Ovarian Cancer Alzheimer's
Add population statistics to measure patient referral
Who
What
When
Where
Classify system to research questions
Critical emerging regions
1996 1998 2000 2002 2004 2006 2008 20100
0.10.20.30.40.50.60.7
Regional Site Utilisation (1998 - 2008)
1999 2000 2001 2002 2003 2004 2005 2006 20077
7.58
8.59
9.510
10.511
Site by trial ratio (1999 – 2007)
19.7%
7.4%
6.3%
.4%
Source: MDCpartners
Where will I be doing my oncology trials in 2012?
• Can we leverage these expanding public data sources?
• Can advances in technology optimise information gathering?
• If we have the information can we apply it at the right time to enhance efficiency?
Leverage information