1. designing a fast and scalable data platform in the cloud – a modern approach
Prakriteswar Santikary, PhD
Vice President and Global Chief Data Officer

2. ABOUT ERT
Founded in 1977; privately held
Supporting Pharmacos, Biotechs & CROs around the world
Operations in 12 countries
2500+ employees
MINIMIZING RISK & UNCERTAINTY, SO YOU CAN MOVE AHEAD QUICKLY WITH CONFIDENCE
│ © Copyright ERT 2018

3. GLOBAL REACH & EXPERIENCE
>50%
new drug approvals
trials
sites spanning 114 languages & 106 countries
of all FDA approvals over the past 4 years
550+
13K+
230K+
patients
3M+
SUPPORT FOR…
Boston, MA
Boulder, CO Bridgewater, NJ
Cleveland, OH
Philadelphia, PA
Raleigh, NC
Rochester, NY
Scotts Valley, CA
St. Louis, MO
Brussels, BE
Estenfeld, GER
Geneva
Nottingham, UK
Peterborough, UK
Tokyo, JP
│ © Copyright ERT 2018

4. Clinical trial Industry Challenges01
Data Collection 02
Data Processing and Access
real time data ingestion at scale
Real time data processing
Data siloes – lack of governance
Difficult to identify issues and resolve them in real time
Lack of visibility into actions being taken to address issues
Multiple data sources
Multiple devices
Multiple data types
Multiple vendors
Patient recruitment
Site qualification
Complexity
In clinical
trials 04
Oversight and Monitoring 03
Data Quality
Patient compliance
Site compliance
Query resolution
Visit compliance
Regulatory compliance
Oversight of trials and sites
Oversight of vendors
Oversight of systems
Monitoring of trial risks
Data security and privacy
│ © Copyright ERT 2018

5. SYSTEM DISPARITY is GROWing WITH SPECIALIZATION
MORE SYSTEMS ARE INTRODUCED IN CLINICAL RESEARCH EACH YEAR
EDC
eCOA
CTMS
PATIENT IDENTIFICATION
IVR
mHEALTH
PATIENT ENGAGEMENT
Established eClinical Systems
mHealth
Images
HOME MONITORING
EMR
Labs
And if we peak into the immediate future, we can see that this is a trend that’s going to continue and become even more challenging as we incorporate new technologies like wearables and mHealth sensors.
From Patient Apps, to Home Monitoring and integration of EMRs, the data we use to execute clinical research is becoming even more specialized. While this is all exciting stuff, it presents a challenge that organizations need to begin planning for now.
eCOA is expanding from validated clinical assessments collected at the site, medication reminders, patient diaries, endpoint data collection, etc.
mHealth (incorporating eCOA) is exploding with wearables from Actigraphy, glucose monitoring, ECG patches, etc.
Patient Engagement leveraging social networks is increasing along with smarter, targeted advertising
EMRs are opening up accessibility through the adoption of FHIR (fire)
Home Monitoring: Think Alexa, Google Assistant, Siri
Patient Identification: As patient access to data becomes a best practices, identification of patients and security will continue to evolve
│ © Copyright ERT 2018

6. Trials GETTING more complex
Increasing interest in building protocols based on real-time outcomes; mitigating risk of protocol change mid trial
Increase in Complex Trials
Continued move to a single Cloud-based platform as trial methodology of choice powered by data. Allows for agility and speed to market. 
Key Insight
Implications
Technology advancements driving highly individualized patient therapeutics administration.
Advancement of Precision Medicine
Ability to do smaller targeted trials improving outcomes based on lifestyle, environment and genetic makeup.
Shift in more active patient engagement - improving access to trials via mHealth, virtual trials and focusing on outcomes.
Patient Centricity
Further investment in clinical trials that meet patient needs – less burdensome, increased diversity and better outcomes.
An explosion of data from wearables, genomics, social, imaging, etc. – driving advances in data interaction and visualization.
More Big Data &
AI Modeling
Need to standardize data sets - mine previous data sets, and better ingest, analyze and manager larger, more complex data. 
The promise of Blockchain to help concerns over privacy, data sharing and reproducibility.
Blockchain
Increased investment in blockchain technology to improve data security – competitive differentiation.
│ © Copyright ERT 2018

7. Exponential Data growth in Life Sciences
VOLUME
Implications
Organizations must implement scalable infrastructures to deal with increased data volumes
More types along with more endpoints
VELOCITY
Leading customer experiences require contemporary insights that can be acted on
Digitization has increased the speed of information
VARIETY
Flexible data models are required to integrate customer information
Clinical, compliance, medical, RWE/commercial and actimetry
VERACITY
Need to enable multiple user groups with consumable insights
Ability to gain insight from aligned data sets
│ © Copyright ERT 2018

8. Waves of information that aren’t actionable
Clinical trial teams are drowning in data
High administrative burden to extract and re-enter data Into other systems
Difficult to filter out noise to identify real issues that require attention
More effort is spent confirming the accuracy of data than interpreting it for decision-making
Cost overrun and delay to time-to-market
Our customers are crying out for help – “Please simplify the complex!”
│ © Copyright ERT 2018

9. MODERN platform architecture
Before we dive into the specifics, let’s set the stage and take a look at some of the drivers of why we need a paradigm shift in our industry. Many of us are familiar with the different factoids floating around the industry that it costs over $2B and take 8 years to develop a compound and bring it to market. But our focus today will be on the the underlying trends that contribute to this dynamic, and how our ability to design efficient studies, manage timelines, and collaborate effectively can impact your organizations succes, and ultimately contribute to managing trials more effectively.

10. Put high quality data in the hands of people who need it – a business imperative01
Data Governance 02
Modern Data Platform
Disparate data sources
Multiple integration paths
Dealing with unstructured data
Dealing with binary data
Dealing with streaming data
Real time ingestion at scale
Self service data access
Who owns what data
How data can be used
Find data, understand it
Find data that matters - fast
Trust the data quality
Make big data meaningful
Framework for collaboration
Our
Approach 04
Master Data Management 03
Data Quality/Regulatory
HIPAA
GDPR
Mitigate risks
Avoid steep penalties
Transparent data access
Single version of truth
Lifecycle of master entities
Technology, Process
Stewardship, clarity
Data Lineage
│ © Copyright ERT 2018

11. Transforming data into strategic business assets using modern, secure, cloud-based data platform
Scale
Cloud based
Modern tech stack
governed
Real time reporting analytics and data science
Data platform architecture at a glance
Lambda architecture (batch and speed layers)
Modular microservices architecture
Serverless Computing
Master data management/data governance
Data ingestion at scale
Adapters and connectors for third party data integration
Modern data visualization architecture
Customer benefits at a glance
Enables real time decision making
Enables self-service reporting and analytics
Enables data monetization;
Reduces complexity and improves quality
Enables Data-driven decision making
Enable Speed to market of life-saving drugs
Centralizes risk and performance management of trials
Enables cost savings & operational efficiencies
Enables AI and ML capabilities – anticipatory oversight
│ © Copyright ERT 2018

12. ERT’s APPROACH - MODERN DATA ARCHITECTURE AND SERVICES
Data Availability
Data Quality
Data Consistency
Data Security
Data Auditability
Reporting, Analytics and Data Science Services
Data Lineage
Data Standards
Data Policies and Procedures
Business Metadata
Technical Metadata
Master Data Management, Metadata Management and Data Governance
Reporting
Self-service BI
Open Data API
Data Science
Relational
Dimensional
In-memory
Polyglot
ERT’s APPROACH - MODERN DATA ARCHITECTURE AND SERVICES
Data Architecture and Data Technology
Structured Data
Unstructured Data
Semi-structured Data
Binary Data
Data Integration, Data Services and Data Adapters
Internal
External
Third party
Future M&A
Data Sources
│ © Copyright ERT 2018

13. Microservices Architecture
Characteristics
Benefits
Challenges
Decentralized
Independent
Do one thing well
Polyglot
API-first Design
You build it; You own it
Agility
Innovation
Quality
Scalability
Availability
Distributed systems
Monolith->Microservices transition not easy
Organizational issues (DevOps)
Skillsets
Build scalable platform and applications
Here are a few key learnings we hope to provide with this presentation that may inspire these organizations to embrace this change as an opportunity to innovate.
Paradigm Shift: Companies embarking on new innovation initiatives to determine feasibility of mHealth solutions for clinical research
Audience Questions:
How many of you currently employ mHealth technologies in your clinical trials?
How may of you currently utilize Actigraphy and/or Continous Monitoring devices in your clinical trials?
How many of you work in organizations that are now tasked with POCs or pilots using mHealth devices?
Data Optimization: Enhancing clinical research with mHealth data requires new techniques against non-conventional sources. mHealth data alone does not enhance clinical research.
Practical Applications: Applied use of mHealth in select therapeutic areas in combination with other clinical source data and/or ways where mHealth data may be combined for more visual insights
| Copyright ERT 2018

14. Serverless Architecture

15. Serverless Architecture
Characteristics
Benefits
Challenges
Function-as-a-service
Compute as a service (100ms interval)
Stateless
Ephemeral
Event-triggered
Vendor lock-in
Vendor control
Monitoring and debugging
Startup latency
Code without provisioning
No server HW to maintain
No server SW to maintain
Increase productivity
Scale your code with HA
Pay-per-use CPU cycle
Zero administration
Build applications without having to manage Server
Here are a few key learnings we hope to provide with this presentation that may inspire these organizations to embrace this change as an opportunity to innovate.
Paradigm Shift: Companies embarking on new innovation initiatives to determine feasibility of mHealth solutions for clinical research
Audience Questions:
How many of you currently employ mHealth technologies in your clinical trials?
How may of you currently utilize Actigraphy and/or Continous Monitoring devices in your clinical trials?
How many of you work in organizations that are now tasked with POCs or pilots using mHealth devices?
Data Optimization: Enhancing clinical research with mHealth data requires new techniques against non-conventional sources. mHealth data alone does not enhance clinical research.
Practical Applications: Applied use of mHealth in select therapeutic areas in combination with other clinical source data and/or ways where mHealth data may be combined for more visual insights
| Copyright ERT 2018

16. Lambda ARCHITECTURE
│ © Copyright ERT 2018

17. Data science PLATFORM at scale01
Data pre-processing 02
Feature Engineering
Difficult step in AI/ML
Time consuming
Requires expert domain knowledge
Feature selection
Feature extraction
Requires Platform that Scales
Garbage-in, garbage-out
Missing value
Outliers
Data quality (cleaning)
Normalization
Transformation
Requires Platform that Scales
Scalable
Data Platform
Enables AI 04
Model Development 03
Algorithm choice
Analytic sandbox
Availability of integrated dataset
Require Platform that Scales
productization
automation
Dynamic training of model
Requires Platform that Scales
│ © Copyright ERT 2018

18. KEY TAKEAWAYS FROM TODAY’S DISCUSSION
Data Governance
To unleash the potential of data - Master data management, data quality, data profiling, data policies and standards – fosters cross-organizational collaboration
Modern Data Foundation
Ingest any data of any type of any velocity,
Data processing at scale, API-first design, Self service, Real time and batch, enables advanced analytics capabilities including AI and ML
Data security and access
Governed data store, transparency, regulatory compliance, privacy and protection
│ © Copyright ERT 2018

19. Questions?
Prakriteswar Santikary, PhD ? …