Big Data Provides Opportunities, Challenges and a Better Future in Health and Research

Big Data Provides Opportunities,
Challenges and Better Future in
Health and Research
Dr Ashraf Mina

 What is Big Data?
Why is Big Data Important?
Big Data and Artificial Intelligence (AI)
What does Big Data Mean for Patients?
What does Big Data Mean for Payers?
What does Big Data Mean for Devise Makers?
What does Big Data Mean for Pharma?
Examples of Current Application of Big Data
How are Wearables Devices Poised to Transform Medicine?
How are Smart Phones/Devices are Poised to Transform Medicine?
Big Data and AI Promise Huge Opportunities, but Raises Huge Issues
Overview

• Big data is a term that describes the large volume of data –
both structured and unstructured – that inundates a business
or operation on a day-to-day basis.
• Big data can be analysed for insights that lead to:
a) Better decisions
b) Strategic business moves
What is Big Data?

• “It’s not the amount of data that’s important. It’s what
organizations do with the data that matters”. Do you agree?
• You can take data from any source and analyse it to find answers
that enable:
 Smart decision making
 Strategic business or operation moves
 Cost reductions
 Time reductions
 New product development and optimise productivity
Why is Big Data Important?

• Traditional analytics tools are not well suited to capturing
the full value of big data.
• The volume of data is too large for comprehensive analysis,
and the range of potential correlations and relationships
between disparate data sources are too great for any
analyst to test all hypotheses and derive all the value
buried in the data.
Big Data and Artificial Intelligence (AI)

• The combination of Big Data and AI/machine learning will drive
incredible innovation across pretty much every industry, including
medicine.
• The Big Data opportunity is probably even bigger than people thought.
• As Big Data continues to mature, however, the term itself will probably
disappear. Successful enabling technologies will become widespread,
and eventually invisible.

Driverless trucks move all iron ore at Rio Tinto's
Pilbara mines, in world first. Additionally, $483 M
investment in 40 driverless train.

When big data is combined with high-powered analytics, The following tasks can be
achieved:
 Determining root causes of failures
 Determining Issues and defects in near-real time
 Recalculating entire risk portfolios in minutes.
 Detecting fraudulent behaviour before it affects your organization.
 Smart decision making
 Strategic business planning
 Cost reductions
 Time reductions
 New product/service development

• The life sciences are not the first to encounter big data. We have information-power
companies like
 Google
 Amazon
 Facebook
• A lot of the algorithms that are applied there, to predict what kind of movie you like
to watch or what kind of foods you like to buy, use the same machine-learning
techniques.
• Those same types of methods, the infrastructure for managing the data, can all be
applied in medicine.

• The role of Big Data in medicine is one where we can:
 Build better health profiles
 Better predictive models around individual patients so that we can better
diagnose and treat disease.
• It is not going to be a discrete event—that all of a sudden we go from not using big
data in medicine to using big data in medicine.
• It is more of an evolution. As we begin building these models, aggregating big data,
we’re going to be testing and applying the models on individuals, assessing the
outcomes, refining the models, and so on.

• Questions will become easier to answer.
• The modelling becomes more informed as we start pulling in all of this
information.
• It is going to go very fast, because there’s great maturity in the information
sciences beyond medicine.

• Patients will be engaged as a partner in this new mode of understanding their
health and wellness better and understanding how to make better decisions.
• Most of their data collection will be passive, so individuals won’t have to be
active every day—logging things.
• They’ll agree to have their data used in this way because they get some
perceived benefit.
What does Big Data Mean for Patients?

• All of the following should diminish:
 The number of doctor visits patient
 The number of times patient was sick
 The number of times patient progressed into a given disease state
• Patients will be looking at dashboards about themselves.
• Patients will not be blind to the information. They’re able to see it every day
and understand what it means.
• Patients will not be dependent on a physician to interpret it for them.

• The integration of genomic data with other RWD sources can enable further
stratification of populations leveraging multiple clinical indicators and modelling
algorithms.
• The combination of clinical diagnoses, lab test data and genomic information can
be used to identify and stratify patient sub-populations to support biomarker
identification, predictive analytics or prospective study development.
• The application of genomic data within RWD is poised to drive significant changes
across the drug R&D pipeline. With the rapid development of sequencing and
analysis technologies, the use of genomic data will soon become routine in the
development of many types of drugs.

What does Big Data Mean to Patients?
• Using real-world data and advanced analytics to find undiagnosed patients with rare
diseases.
• Patients with rare diseases already face huge challenges in accessing treatments that
will help them. Often, they aren’t diagnosed with their condition until the later stages
where even exceptional treatments are less effective. What if we could change that?
Rare diseases are not that rare:
 350m people worldwide have a rare disease
 7,000 rare diseases have been identified
 50% of rare disease sufferers are children
 40% of patients are misdiagnosed initially
 7.3 physicians (avg.) are seen before diagnosis
 4.8 years (avg.) before an accurate diagnosis

Finding the needle in the haystack…..?
• Increased availability of RWD and advances in pattern recognition
techniques mean that rare disease detection algorithms now represent a
potentially highly effective way of finding undiagnosed patients.
• Detailed RWD on symptomology, diagnoses, treatment history, lab tests and
more, which is routinely collected from patients anonymously, presents a
rich foundation that can be harnessed exactly for this purpose.
• Predictive analytics can exploit often complex, subtle patterns in the data of
diagnosed patients with rare conditions to identify new undiagnosed
sufferers of a disease.

• IMS Health combined RWD and predictive analytics to help detect undiagnosed
cases of rare diseases.
• Largest international fit-for-purpose RWD portfolio of 500 million+ patients, with
expertise in data management and sourcing.
• Dedicated rare disease detection strategy team supported by highly qualified
biostatisticians, data scientists, epidemiologists and clinical experts providing deep
disease understanding.
• Pioneering methodologies that incorporate predictive analytics in healthcare,
applying modern machine learning methods to solve complex problems.
• Driving clinically relevant insights, partnering with providers to improve clinical
practice for rare diseases.

• 70,000 randomly selected
patients by initial algorithm
based on risk score.
• Advanced machine learning
predictive analysis algorithm.

Identifying health system barriers causing under-diagnosis:
• In a process based on literature and data profiling, a cohort selection algorithm
was developed leveraging Hospital Episode Statistics data covering outpatient,
inpatient and A&E activity over more than five years in England.
• This revealed a high number of events for three years ahead of a formal diagnosis,
with over 90% of patients being known to the hospital system within the three-year
time frame, and a wide variety in the types of diagnostic pathways to reach a
tertiary center initially.
• Furthermore, the study identified substantial variability in the incidence rate per
100K population.

Number of patients diagnosed by center

What does Big Data Mean for Payers?

• Payers are perhaps among the top of the chain as far as who can benefit from this.
• Payers want to constrain the cost of each patient. They care about the health of the
patient, but they want to do whatever they can to motivate both the patients and
the medical systems that treat them to:
 Minimize the cost through better preventative measures
 Better targeted therapies,
 Increased compliance for medication usage

• Payers are getting a better benefit from drugs being taken, because they’re
able to see that the drug is being taken as prescribed or that it’s not having the
effect on the patient so the patient can be switched earlier to a more effective
treatment.
• If we’re able to intervene sooner in the course of a patient’s health, before they
slide into a disease state, then we’re going to save money on:
• Unexpected hospitalizations
• Emergency-room visits
• Physician visits
What Big Data Means for Payers?

• General risk profiling of patients: payers care a lot about understanding the overall
risk of a patient and what they’re likely to cost year over year.
e.g. For example, say we’re able to generate genomic information that tells us
what the heritable cancer risk of every patient is; we don’t need to wait until a
lump is felt or the person’s at a later stage of cancer, when it’s much more
expensive. Those better risk profiles will be an incentive for payers to pay
attention and to actually be involved in that development.

• For device makers, this is a revolution if the industry embrace the development
of consumer wearable devices or sensors, more generally, in environments
where every person is buying a device versus one of a handful of medical
systems. That’s a better business model that’s going to generate lots of revenue.
• And so it’s up to the device maker to embrace that revolution and even start
transforming some of the devices they’re already making into consumer-grade
devices that can be not just recreation grade but higher grade, on toward the
clinical grade.
What does Big Data Mean for Devise Makers?

• Regeneron Pharmaceuticals and Geisinger engaging the Geisinger Health
System and sequencing 100,000 person to create a better understanding of
disease and protections against disease to do therapeutics.
• It’s doing it mainly from the genomics arena, but it’s also approaching it from
the standpoint of better understanding disease, having a better understanding
of the causal players of disease, and using that or the causal protectants against
disease to directly develop therapeutics
What does Big Data Mean for Pharma?

This methodology has several advantages that will accelerate the drug
development process by enabling researchers to
• Identify and query cohorts on demand without the need for costly patient
recruitment, consent and sample sequencing
• Further augment or refine the disease cohorts in real time, analysing co-
morbidities and other demographic information without the need for additional
recruitment
• Molecularly tailor therapies based on the actual mechanism of the disease and
apply this knowledge throughout the drug development pipeline
What does Big Data Mean for Pharma?

Examples of Current Application of Big Data

Update:
To date they have sequenced over 50,000 exomes from patient
volunteers
• 20 novel candidate gene targets or biomarkers found associated with
disease.
• Predicted loss of function (LoF) variants that offer insights on a certain
gene’s role in health and disease have been identified for all targeted
genes.

The George Institute
for Global Health

The George
Institute for Global
Health

Icahn Institute: In the past three or four years, they hired more than 300 people,
to cover the following specialities:
• Hardware engineers
• Big data computing to the sequence informatics
• Bioinformatics to the genomics core to generate the information to the
machine-learning
• Predictive-modelling experts
• Quantitative data experts, to build the models
All o the above is linked up to all the different disease-oriented institutes at
Mount Sinai Hospital, and to some of the clinics directly, to start pushing this
information-driven decision making into the clinical arena.

• Wearable devices today are in this more recreational-grade state, they’re
changing incredibly rapidly into research grade and ultimately clinical grade.
e.g. glucose monitors that are FDA (US Food and Drug Administration)
approved that individuals can wear and that interface with digital apps,
which then connect directly with healthcare providers.
• It is estimated that in the next few years accurate information about our health
will exist more outside the health system than inside the health system. And that
will force the engagement of that information by the medical community.
How are Wearables Poised to Transform Medicine?

• Cosmed’s K5 can measure metabolic parameters like VO2, VCO2, ventilation,
HR, energy and many more.
• The power suit includes an integrated camera-mount-screw-thread, a
headphone for real-time communication, USB-device port for PC
communication, real-time testing and data download.
• The system is a result of more than 25 years of experience in compact
metabolic systems exploring human exercise physiology.
Breath analysers for fitness and sports

• Fabulyzer is working on a handheld device which detects specific breath volatile
organic compounds (particularly acetone) to provide an accurate indication of
fat burning during physical activity.
• The device will also detect metabolism habits and will actively help you to
optimize your exercise menu according to your fat-burn requirements.
Breath analysers for fitness and sports

• Adamant Technologies has created a computer chip that can take the sense of smell and
taste and digitize them.
 That means your phone, computer or device can smell for itself.
 Possible applications are metabolic tracking, monitoring medical conditions like asthma
or diabetes or test blood alcohol.
• KAIST developing a quick and efficient way to diagnose diseases like diabetes or lung
cancer.
 The device uses a highly-sensitive exhaled breath sensor which can be mounted on a
smartphone.
 Made of tin dioxide nanofibers coated with catalytic platinum nanoparticles, the
sensor can detect the presence of acetone (a diabetes signal) or toluene (a lung cancer
signal) even at concentrations of less than 100 parts per billion.
How are Smart Phones/Devices Poised to Transform Medicine?

• Every 3 minutes one woman is diagnosed with breast cancer.
 Cycardia Health has developed a smart bra iTBra for monthly breast scanning.
 iSono Health is developing a platform to facilitate regular self-monitoring at
home for early breast cancer detection.
 Researches at Georgia Institute of Technology and the Winship Cancer
Institute of Emory University are developing a breath test for detecting lung
and breast cancer. A patient breathes into the device where a sensor examines
chemical compounds found in their breath. Based on the recordings, it can be
determined if cancer is present.

• Issues raised:
• Not all the physicians were on board
• Fear about what kind of world we’re going transform into if we are basing medical
decisions on sophisticated models where nobody really understands what’s
happening.
• Mechanisms in place:
• Partnering with key physicians who were viewed and carrying out the right kinds
of studies.
• What has been built is a sort of a hub network that all different disease-oriented
institutes will be able to link to enable them to take advantage of this great engine.
Big Data and AI Promise Huge Opportunities, but Raises Huge Issues

Cirdan
State of the art Mobile Health platform which
brings people and information together to
provide new levels of quality healthcare
Why the ULTRA LIS?
• 72 labs in 6 countries
• Modern proven LIS designed using globally developed
workflows, standards & best practices.
• Designed for large multi-entity, multi discipline
laboratories.
• Detailed specimen tracking system, ULTRA analyser
library is extensive.
• Opens the door to further opportunities by providing
strong business intelligence and data analytics tools to
its users.
Imaging software (PathLite Compact + VividPath PACS)
Macro Imaging | Micro Imaging

Big Data Provides Opportunities, Challenges and a Better Future in Health and Research

Empfohlen

Empfohlen

Weitere ähnliche Inhalte

Was ist angesagt?

Was ist angesagt? (20)

Ähnlich wie Big Data Provides Opportunities, Challenges and a Better Future in Health and Research

Ähnlich wie Big Data Provides Opportunities, Challenges and a Better Future in Health and Research (20)

Mehr von Cirdan

Mehr von Cirdan (20)

Kürzlich hochgeladen

Kürzlich hochgeladen (20)

Big Data Provides Opportunities, Challenges and a Better Future in Health and Research