CORD Rare Drug Conference, June 8 - 9, 2022 Opportunities and Challenges for Data Management Real-World Data and Real-World Evidence • Patient support programs: Sandra Anderson, Innomar Strategies • AI for Data Management and Enhancement: Aaron Leibtag, Pentavere • Patient Support and RWE: Laurie Lambert, CADTH

1. Real World Evidence and
Patient Support Programs
Sandra Anderson,
SVP, Commercialization and Strategy
September 22nd , 2021

2. Real world data collection through PSP
Data collection
Patient
enrolment
Treatment
update
Treatment
discontinuation
Treatment
follow-ups
Program
RWE Connect/PSP Database
Baseline information
Patient characteristics including age, weight (dose related), and
treatment dose
Baseline characteristics e.g., age at diagnosis, disease severity
Treatment patterns
• Duration of therapy
• Reasons for discontinuation
• Medication adherence
Healthcare resource
utilization
Healthcare utilization/burden e.g., physician visits, ER visits,
hospitalizations, costs to system
Productivity and Societal
outcomes
• Work/school productivity
• Disability
• Caregiver burden questionnaires
Health outcomes
(Secondary Measures)
Baseline and clinical response measures
§ Laboratory reports
QoL measures
Other Market Research
and KOL Opportunities
PSP Satisfaction Surveys
Abstract and Publications
Conference Presentations
2
Confidential

3. 6/14/22
Confidential
Innomar
Strategies
3

4. RWE through the patient journey
Confidential
Innomar
Strategies
4
• Consent management
• Various mediums to
communicate with
patients (phone, portal
etc.)
• PSP validated CRM
• Adverse Events reporting
• Side effect management
§ Patient Registries
§ Pharmacy
§ Wholesale
§ Hospitals
§ EMR
§ Health case
management
§ Chart Audits
Patient Support Programs Data Sources
§ Burden of illness
§ Drug utilization and
treatment patterns
§ Meta-analyses
§ Budget Impact and
Cost-effectiveness
analyses
§ Retrospective and
Prospective studies
§ Publications
Evidence Generation
Leverage insights across the therapeutic lifecycle
Data that is payer driven for
PLAs, OBAs, Renewal Criteria

5. Registries and
Real-World Data
Opportunities and Challenges for Data
Management Real-World Data and
Real-World Evidence
CORD Conference June 2022 - Building Canada’s SMART
Rare Disease & Rare Drug System

6. DARWENTM AI by Pentavere, An Artificial Intelligence
Clinical Discovery Company
Ø Pentavere is a digital health company
that has developed a breakthrough,
proprietary Artificial Intelligence (AI)
engine called DARWEN™AI that
dramatically accelerates discovery of
insights buried in clinical text data
Ø The clinical text that DARWEN™AI can
rapidly discover, catalog, organize, and
analyze includes electronic health
records, physician notes, pathology
reports, physician transcriptions and
many other sources
Ø AI Discovery from clinical text is the
missing molecule to a more cost
effective and personalized healthcare
system
“Everyone talks about AI and is
intrigued by AI but what I’ve seen from
Pentavere is how we can actually
apply AI. Pentavere’s implementation
strategy breaks down information
barriers and unlocks valuable data
revealing opportunities for
improvement in patient care”
DR. SHELLEY ZIEROTH
Director, Heart Failure
& Transplant Clinics
“Pentavere generates Real World Data
at an incredible scale, speed and
accuracy. We are just scratching the
surface in what is possible with
Pentavere’s AI technology”
DR. GEOFFREY LIU
Medical Oncologist & Senior Scientist
“The use of DARWEN provides
opportunity for real-world evidence
studies at a larger scale than ever
before. DARWEN AI was not only faster
than manual extraction but, for many
features, was also more accurate than
a traditional manual approach”
IASLC World Lung Conference 2021 Oral Presentation
Validation of scalable, automated data
extraction in an advanced lung
cancer patient population
“The accuracy of the data derived by
Pentavere was exceptional – much
more than we had hoped for.
DARWEN™ extracts data directly
from our transcribed clinic notes
with no extra human resources
required.”
DR. JANE BATT
Medical Director TB Program

7. There is a large data void for evidence generation and
knowledge, critical to improving the lives of rare disease
patients in Canada
Phase I Phase II
Phase III
Approval
Number
of
Patients
Time
Data
Void
Real World Continuous Data
Collection
3
Ø 3 million Canadians, or ~1 in 12
Canadians suffer from a rare disease
Ø 50% of rare diseases begin in childhood
Diagnosis can take up to 5-7 years,
requiring visits to as many as eight
different specialists.
Ø In Canada, a child dies of a rare disease
every 18 minutes.
Ø Rare disease costs the Canadian
economy about $111 billion per year in
direct medical costs, nonmedical cost,
and productivity costs
1. “RARE Disease Facts - Global Genes". Global Genes, 2022, https://globalgenes.org/rare-disease-facts/.
2. “About GARD". National Institute Of Health, 2022, https://rarediseases.info.nih.gov/about/.
3. "Our Work". Canadian Organization for Rare Disorders, 2022, https://www.raredisorders.ca/our-work/.

8. The Reality of Data in The Real World
Ø Lack of data governance in different levels of
health system
Ø Lack of data sharing agreement (Information
blocking)
Ø Complexity of privacy rules
Ø Lack of record linkage
Ø Lack of interoperability/
complexity of data standards
Ø Lack of data quality
Ø Lack of big data management
Ø Lack of infrastructure
Study: Ontario’s Health Data Landscape for Implementing Precision Medicine Conclusions From Study:

9. In recent years there has been much enthusiasm for the Electronic Health Record
(EHR). The potential value of EHR’s has yet to be fully realized. Clinicians indicate
they are spending more time interacting with the EHR system and less time with
their patients.1
“The field of IT has put forward concepts such as big data, advanced analytics, and
learning systems that are frequently mentioned as solutions, that will transform
health care. However, such concepts are far ahead of today’s EHR capabilities” 2
Learning Health System- A continuous loop in which scientific evidence informs
clinical practice, while data gathered from clinical practice informs care and
scientific investigation. The latter part of the loop is often missing because data is
often siloed and/or unstructured, making it unsuitable for analysis with
conventional statistical techniques 3
The Reality of the Electronic Health Record
1. Gawande A. Why Doctors Hate Their Computers. Https://www.newyorker.com/magazine/2018/11/12/why-doctors-hate-their-computers
2. Feeley TW, et al. The agenda for the next generation of health care technology. N Eng J Med Catalyst Vol 1 (3) April 15, 2020
3. Nwaru et al “Can learning health systems help organisations deliver personalised care?” 2017.
Meaner et al “A framework for value-creating learning health systems” 2019.
Institute of Medicine Roundtable on Evidence-Based M. In: Olsen L, Aisner D, McGinnis JM, editors. The Learning Healthcare System: Workshop Summary

10. “For rare diseases the ability to use the whole of
their experience and clinical observations to
inform diagnosis and best management is a
game changer that could prove as impactful as
decoding the human genome.”
DURHANE WONG-RIEGER
President & CEO of the Canadian
Organization for Rare Disorders

11. How Can AI Extract, Transform, and Aggregate Rich Real
World Data
SOLUTIONS
Data Access,
Analysis, Sharing
RWD/RWE
Breakthrough
AI
Data
Privacy &
Governance
Patient
Centricity
Clinical Knowledge
& Expertise

12. It Starts with Data… Identifying and Leveraging all the
Different Types of Data
Clinical Trials
Electronic Health Records
Patient Support
Registries
Patient Reported Data
Public / Proprietary Data
Patients generate a wealth of data
throughout their journey about the path to
diagnosis, treatments, specialist visits,
overall well-being, and outcomes

13. Patients generate data about their well-being, treatments, and care through the entirety of their journey
9
Public / Proprietary Data
Patient Reported Data
Registries
Patient Support
Electronic Health Records
Clinical Trial
Data Access Data Analysis Data Sharing
It Starts with Data… Identifying and Leveraging all the
Different Types of Data

14. AUTHORITY
The ability to access data, use, and share data
Ø Legislation (Ex. PHIPA,
PIPEDA, GDPR)
Ø Governance
Ø Agreements (Authorities to
access, use, and share)
Ø Protocols
Ø Data Management Plan
Ø Quality Assurance
o People
o Processes
o Controls
Ø Verification
Ø Validation
o Clinical
o Algorithmic
RELEVANCY
Does the data adequately address a question (clinical and/or regulatory)
RELIABILITY
Are there assurances and controls to demonstrate quality
Get Governance Right At The Start
FAIR
Findable, Accessible,
Interoperable. Reusable

15. TimeLine of a Data Science Project
22% 20% 13% 26% 8% 11%
0% 25% 50% 75% 100%
Data Gathering Data Cleaning Data Visualization* Model Building/Selection
Model
Deployment
Finding
Insights
Curation
(Automated-) AI
Operationalization
Data based on Internal client study Titled: Timeline of a Data Scient Project
Average time spent by a Research Scientist
*Data in a format that a data scientist can begin to model the data
“It’s time to evolve past novelty publications and click bait, and demonstrate its ability to materially impact health and disease.”
“In our own shop, we’ve been working on a few big projects, and we’ve had to spend most of the time just cleaning the data sets
before you can even run the algorithm. That’s taken us years just to clean the datasets. I think people underestimate how little
clean data there is out there, and how hard it is to clean and link the data.” Vasant Narasimhan, CEO, Novartis
Forbes -Novartis CEO Who Wanted To Bring Tech Into Pharma Now Explains Why It's So Hard

16. Curation
(Automated-) AI
Operationalization
0% 25% 50% 75% 100%
Data Abstraction +
Data Cleaning
Data
Visualization
20%* 21% 5% 50%
Model Building/Selection
Model
Deployment Finding Insights
4%
Real World Impact of AI (DARWEN™) to Accelerate Speed
to Insight
“Automated extraction required significantly less time (<1 day) than manual extraction (~225 person-hours)”
Gauthier, M.-P., Law, J. H., Le, L. W., Li, J. J. N., Zahir, S., Nirmalakumar, S., Sung, M., Pettengell, C., Aviv, S., Chu, R., Sacher, A., Liu, G., Bradbury,
P., Shepherd, F. A.,; Leighl, N. B. (2022). Automating Access to Real World Evidence. JTO Clinical Research Reports,

17. Data
Impact
DARWEN
AI
Clinical Trials
Electronic Health Records
Patient Support
Registries
Patient Reported Data
Public / Proprietary Data
Greatest Impact Comes from a Cross Functional Multi
Discipline Approach
Clinician
Patient
Data
Scientist

18. Patient
Impact
Deployment that
closes the loop
Breakthrough AI
Data & Clinical Expertise
Data Governance & Privacy
The patient is always at
the core of the approach

20. For More
Information
Aaron Leibtag, CEO
aleibtag@pentavere.ai

21. RWE
Real-World Data
and Real-World
Evidence at CADTH
Laurie Lambert
Lead, Real World Evidence

22. RWE
2
• Real world data (RWD) is an umbrella term for data collected
outside of the randomized clinical trial (RCTs) paradigm.
• Real world evidence (RWE) is derived from the analysis of data
collected outside of randomized controlled trials.
• RWE is considered complimentary to RCTs, not a replacement.
• It includes data from medico-administrative databases,
registries, observations from clinical practice, and patient-
reported information.

23. RWE
Launch of CADTH’s RWE for Rare Disease learning period
in October 2021
Real-World Evidence for Decision-Making | CADTH
3

24. RWE
RWE Goals
4
1. Provide learnings to Health Canada to support rare disease
strategy
2. Develop methods and standards for CADTH for appraisals and
reviews of drugs for rare disease or complex therapies

25. RWE
Develop Strategies Within 4 Key Areas
5
• Best Brains Exchange
• Literature review
• Expert support and advice
• Learning by doing
• Stakeholder feedback
• Inform development of process
• Literature review
• Expert support and advice
• Stakeholder feedback
• Inform development of process and
standards
• DSEN Data Access WG
• Literature review
• Expert support and advice
• Data holder network
• Learning by doing
• Inform development of process and standards
• Partnership with Health Canada
• Partnerships with data holders and
facilitators
• RWE Steering Committee with pan
Canadian Health Organizations
• International partners
Multistakeholder
engagement +
dialogue
RWD Generation
+Access
Guidance Real
World Evidence
for HC+CADTH
Collaborative
Partnerships
Develop infrastructure, governance, guidance and tools

26. RWE
6
1
2
3
4
Early Dialogue
Identify needs of patients, clinicians, HTA, payers, regulator
Second Dialogue After Pivotal Trial, but Before Official HTA Submission
Identify and plan response to remaining uncertainties
Post HTA Dialogue
Discuss evidence generation after launch in the real world setting and its consequences
Postmarket Dialogue
Reassessment of new evidence
Vision:
Iterative dialogue for drugs for rare disease at all 4 timepoints
Multistakeholder Decision-Making Focus
through the Drug Lifecycle

27. RWE
Multistakeholder dialogue strategy : Progress Report
7
• Literature review of keys to success and challenges in multistakeholder engagement is now
available for public feedback
• Multistakeholder Engagement Strategy to integrate RWE into decision-making about care
for rare disease | CADTH
• Learning by doing
• Dementia Concerns and Considerations: A CADTH Panel of People With Lived
Experience (Technology Review, Apr 1, 2022)
• Meeting with patients/caregivers with lived experience in pediatric glioma
• Meeting with clinicians/care providers (dementia, pediatric glioma)
• Multistakeholder meeting concerning pediatric glioma planned for summer 2022
• Learning projects will inform the development of guidance and tools for multistakeholder
engagement/dialogue to support decision-making about drugs for rare disease

28. RWE
8
RWE Guidance Strategy: Progress Report
• Translation of INESSS literature review on RWE guidance and tools into
English
• Updated literature review commissioned by CADTH
• Establishment of an expert panel with representation from key
organizations
§ Health Canada; CIHI; Statistics Canada; INESSS; IHE;
§ FDA; NICE; Harvard; Oxford
• Adapted Delphi process to develop expert consensus on RWE principles
• First call for feedback on preliminary guidance document in autumn 2022

29. RWE
Partnerships Strategy: Progress Update
9
CADTH – CIHI
• CADTH and the Canadian Institute for Health Information (CIHI) Real-World Evidence
Feasibility Collaboration | CADTH
CADTH – Statistics Canada – Canadian Neuromuscular Disease Registry
• Collaborative learning project to evaluate burden of care for ALS
• Second learning project with Statistics Canada is in planning
CADTH - HDRN Canada
§ in progress
CADTH - RWE4Decisions
§ RWE4Decisions – Real World Evidence for Decisions

30. RWE
10
Pan-Canadian RWE Steering Committee
INESSS pCPA CIHR CORD IMC/BIOTECanada
Statistics Canada CIHI HDRN Invited Experts (ad hoc)
Members
Oversight
Health Canada (co-Chair)
CADTH (Chair)
RWE
Demonstration
Projects
INESSS: Institut National d’Excellence en Sante et Services Sociaux
pCPA: Pan-Canadian Pharmaceutical Alliance
CIHR: Canadian Institute of Health Research
CORD: Canadian Organization for Rare Disorders
IMC: Innovative Medicines Canada
CIHI: Canadian Institute of Health Information
HDRN: Health Data Research Network Canada

31. RWE
RWD Generation and Access Strategy: Progress Report
11
• Exploring and learning about use of the EUnetHA REQUEST tool in collaboration
with rare disease registries
§ REQueST Tool and its vision paper – EUnetHTA
• Inventory of potential sources of RWD in rare disease registries in Canada
§ In progress
• Identifying and sharing important learnings through case studies of RWD
generation for decision-making
§ In progress

32. RWE
Post-Market Drug Evaluation (PMDE) Program
12
Background: In 2021 the Canadian Institutes of Health Research (CIHR) and Health
Canada announced the intention to transfer the Drug Safety and Effectiveness
Network (DSEN) to CADTH. The new CADTH program will be called the Post-Market
Drug Evaluation (PMDE) Program and will launch September 1, 2022.
Purpose of the program: to respond, with credible and timely evidence, to queries from
senior health-care decision-makers situated within the Federal, Provincial and
Territorial governments related to post-market drug safety and effectiveness.
https://www.cadth.ca/post-market-drug-evaluation-pmde-program

33. RWE
RWE at CADTH : Progress report
13
Framework for Drugs for Rare Diseases | CADTH
• CADTH conducted an Environmental Scan to identify, describe, and compare how health technology
assessment agencies in Canada and internationally make reimbursement recommendations on
DRD. The report provides a comparison of the review and decision-making processes for agencies in
Canada, the UK, Australia, New Zealand, Germany, France, and the US. The report also presents
information on how selected public drug programs in Canada and internationally evaluate and make
funding decisions on DRD.
Scientific Advice | CADTH
• CADTH is expanding its Scientific Advice program to include applications for advice on real-world
evidence (RWE) generation plans after protocols for pivotal trials have been finalized. This is an
opportunity for pharmaceutical companies to enhance their engagement with CADTH regarding
RWE.
Finding the Evidence: Literature Searching Tools in Support of Systematic Reviews | CADTH
CADTH Consultation: Proposal for Non-Sponsored Reimbursement Review
• CADTH has launched consultations on a proposed process for non-sponsored reimbursement
reviews and a streamlined process for drug class reviews.

34. RWE
In conclusion, we are collaboratively learning by doing
to guide implementation of RWE into decision-making
Real-world evidence has the potential to fill gaps in clinical
evidence …and can facilitate a more comprehensive assessment
of the safety, efficacy, and effectiveness of drugs or health
technologies to a broader population, over a longer time period,
and which considers the context of the Canadian health care
system.
Real-World Evidence: A Primer | CADTH
14

35. RWE
@CADTH_ACMTS
facebook.com/cadth.acmts
linkedin.com/company/cadth
requests@cadth.ca
15