THE ICA INTEGRATED COGNITIVE ASSESSMENT - TACKLINGDEMENTIAWHEN IT COUNTS - Cognetivity Neurosciences
←
→
Page content transcription
If your browser does not render page correctly, please read the page content below
THE ICA
I N T E G R AT E D C O G N I T I V E A S S E S S M E N T
TACKLING DEMENTIA WHEN IT COUNTS
CONTENTS
INTRODUCTION 03
THE PROBLEM 04
THE OPPORTUNITY 05
WHO WE ARE 06
THE ICA 07
BENEFITS 13
OPTIMIND 24
COMMERCIALIZATION 28
2
DEM E N T I A
is the biggest healthcare challenge of the 21st century
Between 2000 and 2018, deaths in the US from heart disease fell by 7.8% while
deaths from Alzheimer’s increased by 146%.
Alzheimer’s on its own is the sixth-largest cause of death in the US, killing more than
breast, prostate & pancreatic cancer combined.
Dementias are the leading cause of death in the UK, accounting for 12.7% of deaths.
1 in 3 US seniors die with Alzheimer’s or another dementia…
… yet in high-income countries, around 1 in 2 people never receive a formal
diagnosis, increasing to 9 in 10 in poorer countries – on average, an estimated 75%
of the global dementia population.
Sources: Alzheimer’s Association, 2020; UK Office for National Statistics, 2018;
Centers for Disease Control and Prevention, 2017; Alzheimer’s Disease International, 20153
T H E R E I S A P R O B L E M with diagnosing dementia
Existing assessment methods suffer from…
PRECISION PRACTICAL LANGUAGE EDUCATION A LEARNING
LIMITATIONS BURDENS DEPENDENCE BIAS EFFECT
Current assessment methods Traditional tests are pen-and- Tests relying on any use of Generally, the higher a With existing methods, a
are limited by imprecision, paper-based, requiring face- language can be greatly patient’s level of education, the patient can seem to be getting
assessor bias and differences to-face administration by an affected if a patient is not a better they will score in better over time, when in fact
in interpretation. They are expert clinician. As the age of native speaker; and tests taken knowledge- and memory- they are simply learning how to
suited to late-stage diagnosis telemedicine dawns, they in different languages cannot be based testing. The same goes do the test.
but display a lack of sensitivity offer no capacity for remote meaningfully compared. for their cultural background.
to early-stage disease for testing.
timely diagnosis.
4
Sources: Alzheimer’s Association, 2018; 2020
ENORMOUS OPPORTUNITY
for health economic savings
Investment in improved diagnostics could save the
healthcare system trillions
“ … governments should ‘spend to save’ – in other words,
invest now to save in the future … the costs associated
with an earlier dementia diagnosis are more than offset
by the cost savings from the benefits of anti-dementia
drugs and caregiver interventions. These benefits include
delayed institutionalisation and enhanced quality of life
of people with dementia and their carers”
Alzheimer’s Disease International, World Alzheimer Report 2011
5
OUR MANAGEMENT TEAM
A Cambridge University spin-out, we are proud that our team has grown to include…
DR SEYED RAZAVI Co-founder, CSO
DR SINA HABIBI Co-founder, CEO
PhD (Computational Neuroscience), University of Cambridge;
PhD (Engineering, Nanobiotechnology), University of Cambridge;
previously a postdoctoral researcher in Artificial Intelligence at the
formerly Chair of Cambridge University Entrepreneurs (CUE)
Massachusetts Institute of Technology (MIT)
DR THOMAS SAWYER Chief Operating Officer
DR CHRIS KALAFATIS Chief Medical Officer
PhD (Life Sciences), University of Glasgow; MBA, University of
Consultant in Old Age Psychiatry at Maudsley Hospital, London;
Cambridge; over 15 years’ experience in entrepreneurship,
Affiliate of King’s College London, running clinical trials in dementia at
consulting and private equity in biotechnology, pharmaceuticals,
Institute of Psychiatry, Psychology & Neuroscience
logistics and information technology across the globe
DR MARK PHILLIPS Chief Compliance Officer
ROB BROUGHAM Commercial Director
PhD (Management), University of Cambridge; 30 years’ experience
Over 25 years’ experience in senior commercial roles, successfully
in the pharmaceutical and life science industries; previously Senior
achieving sales up to £1 billion in value, including more than 6 years
Vice President in R&D and Head of Diagnostic Development and
in digital health selling innovative solutions to the NHS
Supply at GlaxoSmithKline (GSK)
6
S O LV I N G T H E P R O B L E M
with platform technology
Self-administered testing on a variety of
widely-available hardware solutions
Overcoming existing testing flaws
with an Integrated Cognitive
Assessment – the ICA
7
T H E I N T E G R AT E D C O G N I T I V E A S S E S S M E N T ( I C A )
A rapid visual categorization task using natural images
Images are displayed for a fraction of a second. Tap to classify each in turn as animal or non-animal.
STIMULUS INTERVAL MASK ANIMAL?
Our Artificial Intelligence engine compares your speed and accuracy to test data from
healthy and cognitively impaired individuals.
The test takes advantage of millions of years of human evolution –
the human brain’s strong reaction to animal stimuli
8
I C A T H E O R Y AT T H E M I C R O L E V E L
Information processing times give powerful insight into cognitive health for two reasons
Healthy Affected
1. SPEED OF INFORMATION
TRANSMISSION IS SLOWER IN
AFFECTED NEURONS
2. FEWER NEURONS MEAN
MORE PROCESSING TIME
Fast Slow
9
Engaging large volumes of neuronal pathways and
I C A T H E O R Y AT T H E
brain structures gives greater sensitivity to mild
MACRO LEVEL
impairment than memory-focused tests
“Detecting the first disruptions to brain
circuitry, and tracking the anatomical and
physiological damage underlying the steady
cognitive decline that is symptomatic of
Alzheimer's, will require tools that operate at
the 'mesoscopic' scale: techniques that probe
the activity of thousands or millions of
networked neurons.”
Kenneth S. Kosik,
Nature: 503, 31–32 (07 November 2013)
10UTILISING ARTIFICIAL INTELLIGENCE
Reaction times and accuracy are used as predictive classifiers of disease status with a high degree of sensitivity
Reaction Accuracy
(ms) (%)
2427 98
2488 45
1876 82
1160 21 PATIENT
DATA
SUMMARY FEATURE AI CLOUD PROCESSING PREDICTION DELIVERED
TEST DATA
EXTRACTION TO EHR
A patient takes an ICA test, Summary features are The AI engine computes their risk EHR integration enables secure
generating raw data extracted and combined with of cognitive impairment through delivery of results and offers a
demographic data as inputs to comparison to hundreds of route to highly personalized
the AI engine medical care
previous test-takers
11D E V E LO P E D FO R U N I V E RS A L H A R D WA R E
Delivered on reliable, trusted hardware for security and scalability
UBIQUITOUS PLATFORM SECURE & SAFE CLOUD HOSTING
By developing the ICA for commonplace Data storage and processing conform to Storage of user information and
hardware that is trusted by the market, we international best practice standards and processing and generation of test results are
remove the need for specialist equipment the entire system is HIPAA-compliant with carried out on our secure cloud-
and carve ourselves a path for rapid fully encrypted databases to ensure based servers, so we can seamlessly
upscaling patient data security integrate with and deliver analysis directly
into existing EHR systems, wherever they are
12SPEED
A 5-minute test, self-administered under non-expert supervision,
leading to increased patient throughput and cost-efficiency
SENSITIVITY AND ACCURACY
Potential to detect cognitive impairment significantly earlier
than current methods
AVOIDANCE OF BIAS
Consistency across individuals from different cultural
and educational backgrounds
BENEFITS FOR
H E A LT H C A R E REMOTE DELIVERY
Potential to assess patients in the comfort of their homes
PROVIDERS…
LONGITUDINAL MONITORING
Numerous competitive advantages in
clinical practice Long-term tracking of pre-dementia patients (MCI) or
responses to treatment
Ipad with stats screen
13CONTINUAL IMPROVEMENT
Thanks to our AI engine, the ICA is always improving in sensitivity and scope
SENSITIVE
HEALTHY MCI MILD AD
Our AI engine uses multinomial logistic regression to
create accurate hyperplanes, enabling the ICA to be
extraordinarily sensitive to a new test-taker’s score
through comparison to learnt clusters
ADAPTABLE
Existing diagnostic tools remain static and never change.
Through machine learning, our AI engine can be
continually updated with clinical data from more patients
to improve its sensitivity and specificity over time.
USER-SPECIFIC • Patterns of ICA test responses from healthy, MCI and mild AD participants
Our AI-powered system can take into account an
unlimited number of patient attributes, including sex, age, • Each cell in the matrix represents the relationship of accuracy and reaction
education level and much more, through EHR integration. for a pair of images
Current testing methods ignore a wealth of relevant data
that is crucial to generate meaningful and accurate results • These features are by the AI engine in making classifications
for diagnosis.
14…AND FURTHER AFIELD
Clear potential to add value in a range of
healthcare-related industries
DRUG DISCOVERY
Sensitivity to early-stage disease offers a solution to the difficulties of
subject recruitment for clinical trials, while the lack of learning effect
improves the capacity to detect therapeutic efficacy
HEALTH INSURANCE
A clinical-grade assessment tool for risk identification and stratification in
determining premiums
CORPORATE HEALTH
Empower large companies to look after their employees’ health
and wellbeing with objective measures of performance over time –
scope for company-wide insights through data aggregation
CONSUMER WELLNESS
Availability on ubiquitous hardware, user-friendly set-up – track
performance over time and make necessary lifestyle adjustments
15P U B L I S H E D E X P E R I M E N TA L R E S U LT S
Alzheimer’s and MCI
Data collected from 10 NHS Trusts in England show a significant positive relationship between the ICA and established
standard-of-care tests for the diagnosis of dementia
253 participants 243 participants
r= 0.61 r= 0.58
pP U B L I S H E D E X P E R I M E N TA L R E S U LT S
Multiple sclerosis (MS)
True Positive Rate
n= 174 n= 174 n= 174
r= 0.82 r= 0.71 r= 0.6
AUC = 0.95
pC O R E S C I E N T I F I C V A L I D AT I O N
EEG and fMRI have further substantiated the ICA’s underlying science
Animal vs. non-animal image decoding Engagement of the critical brain areas affected in
pre-symptomatic Alzheimer’s
8
4
0
EEG results demonstrate the effectiveness of animacy stimuli. In a task-based fMRI investigation, the ICA engages brain areas such as
Individuals with MCI show a significant reduction in speed and accuracy the transentorhinal region, fusiform gyrus and the inferior and middle
of processing ICA information compared to healthy controls. temporal gyruses, which are anatomically identified as being among the
earliest areas affected by tau-pathology and amyloid deposits in pre-
symptomatic stages of AD.
18C O R E S C I E N T I F I C V A L I D AT I O N
Clear differences in the level and areas of activation in the brain
among individuals of differing disease status
H E AT H Y C O N T R O L S MCI MILD ALZHEIMER’S
In red: neural activation recorded by fMRI while the ICA is attempted
19A S E N S I T I V E B I O M A R K E R for physiological change
The ICA is directly correlated with brain cell damage and can track changes in cognition
Strong correlation between ICA score and severity of neural damage Sensitivity to differential changes in cognition
r= -0.79* r= -0.75*
• MS patients were divided into a control group and a group
receiving an 8-week physical and cognitive rehabilitation program
i ne i ne
basel l) fol l ow
-up basel ) rehab
ro b post-
• In the rehab group, ICA scores rose while NfL levels fell (cont (re a
h
d= -0.4, p>0.05 d=0.8, pC O M PA R I N G D I F F E R E N T D I A G N O S T I C M E T H O D O L O G I E S
Across speed, cost, invasiveness, applicability…
NON- EARLY-STAGE DELIVERABLE
METHOD QUICK LOW-COST
INVASIVE
SENSITIVE
DETECTION REMOTELY
The ICA ✓ ✓ ✓ ✓ ✓ ✓
Traditional pen-and-paper tests ✗ ✓ ✓ ✗ ✗ ✗
Computerized traditional tests ✗ ✗ ✓ ✗ ✗ ✓
Biomarker analysis (CSF sampling) ✗ ✗ ✗ ✓ ✗ ✗
Neuroimaging (MRI, CT) ✗ ✗ ✓ ✓ ✓ ✗
21P L AT F O R M T E C H N O L O G Y powering a wide range of solutions
Multiple cognitive assessment products for multiple markets
Product Market Revenue Model Development Plan Competitive Advantage
Speed
Screening Expansion from
ICATM
HEALTHCARE
Charge per test Accuracy
(Primary care) secondary care market Non-expert administration
Speed
Specialist diagnostics UK sales
ICATM (Secondary care)
Charge per test
FDA approval
Sensitivity
Cost-efficiency
Sensitivity
CLINICAL
FDA approval
TRIAL
ICA_CTTM Drug development Subscription
International sales
Lack of learning effect
Remote deliverability
Sensitivity
Monitoring of chronic Expansion from
OptiMindTM Subscription (B2B2C) Lack of learning effect
CONSUMER-
health conditions secondary care market Remote deliverability
FACING
Sensitivity
UK sales
OptiMindTM Consumer wellness Subscription (B2B2C)
White-label development
Lack of learning effect
Cross-platform integration
22I C A _ C E : clinical cognitive assessment powered by the ICA
A case study in US primary care
CRUDE MEMORY-BASED, PEN-AND-PAPER
COGNITIVE TESTS ARE THE STATUS QUO
FDA 510(k) substantial equivalent to Cognivue (DEN130033)
Positive percent agreement of 56% with SLUMS compared to the ICA’s positive percent
agreement of 85% with ACE and 82% with MoCA
Existing CPT codes
96132 – Neuropsychological testing evaluation services by physician or other
qualified HCP – $133.71 per hour
96116 – Neurobehavioral status exam – $97.31 per hour
Enormous market
c. 130,000,000 annual visits to primary healthcare by over-65s
Source: 2016 National Ambulatory Medical Survey (NAMCS) In-depth revenue forecast on page 28 23Also introducing:
• Consumer-facing personalized cognition tracking
• Powered by the ICA, developed for iPhone
• Able to generate revenue without the need
for regulatory approval
• Slick interface and personalized results,
tuned to the individual
• CPT code 96146 – Psychological and neuropsychological testing
with automated administration – $2.16 per test
24OptiMind functions as an
individual data collection
tool, generating
personalised insights and
r= 0.41 recommendations to r= 0.25
pProfile of a high-performing, highly cognitively stable individual
Highly sensitive longitudinal monitoring enables
OptiMind to spot individuals experiencing
significant dips in cognitive performance that
would otherwise go unnoticed.
Simultaneous lifestyle tracking means that
VS.
causes of these dips can be identified.
Someone with greater variation in scores with outlier performances
Aggregating this data across all participating
users offers the potential to identify trends and
causes on a population-wide level.
26A B2B2C case study
OptiMind is being deployed to hundreds of employees, first at AXA PPP healthcare and then at one of its corporate customers, Volkswagen
Financial Services, as part of AXA’s Proactive Health offering, adding a much-needed cognitive component to an established wellbeing
programme
Enormous market reach through collaboration with one of the largest providers of private health insurance in the UK,
owned by the world’s largest insurance group (AXA Group)
27MILESTONES
We’ve been busy, with a lot more to come…
2013-2019 2020 2021
ü Incorporation and IPO (listed on Canadian Stock ü UK Commercial launch o US commercial launch
Exchange, OTCQB & FSE)
ü Revenue generation o Completion of Android app
ü Cloud-based AI and iOS apps developed
development
ü Proof of concept and validation completed ü Collaboration with big pharma and
medical device manufacturers o Completion of EHR integration
ü Global IP covered (patents, trademarks and
copyrights granted) ü Partnership with health insurers o Publication of independent health
ü CE mark approval (December 2019) economic validation study
ü Government grant extension
ü Pre-submission to FDA o VR and AR development
ü Publication of MS paper
ü First commercial agreement signed
o Adjunct tech research
o Deployment in UK clinical care
ü Major government grant awarded
ü Collaborative partnerships established with
o FDA filing and approval
healthcare providers and leading research
o Independent health economic research
organisations
commissioned
ü Peer-reviewed scientific publications
28O N G O I N G D E V E L O P M E N T S T R AT E G I E S
Our patented assessment technique and extensive AI capability offer multiple expansion routes
EXPANDING OUR ENABLING NEW LOOKING BEYOND
CLINICAL REACH HEALTHCARE PARADIGMS HEALTHCARE
Adapting to other classical neurological Using big data and telemedicine to Applying clinical-grade medical
conditions and a broader array of usher in a new era of clinical care technology to a host of fertile
conditions with cognitive symptoms
Personalized medicine market opportunities
Multiple sclerosis (MS)
Remote assessment Pharma | Health insurance
Parkinson’s disease
Longitudinal monitoring Recruitment
Traumatic brain injury (TBI),
EHR integration Individual and corporate wellness
including concussion
Population-wide screening Performance/Risk monitoring
Attention deficit hyperactivity
and optimization
disorder (ADHD) Artificial Intelligence (AI)
VR and AR | Big data
Depression | Diabetes | HIV
29PA R T N E R S H I P S A N D C O L L A B O R AT I O N S
30G L O B A L M E D I A are taking notice
It’s easy to see why we are being talked in…
BBC Business Live: Cognetivity CEO, New Scientist Interview Cognetivity CEO: Heroes in Health Tech: Dr Sina Habibi Winners of the AXA ‘Health Tech + You’
Dr. Sina Habibi discusses dementia Can an app tell if you have dementia discusses the benefits of early detection competition 2018
and testing for early diagnosis years before your doctor?
Forbes: five young companies making an
Biotech and Money: Cognetivity’s AI- Winners of CambridgeElevator award
impact on the world to watch in 2019
Driven congnitive test speaks to address
Forbes: Cognetivity Neurosciences CEO dementia diagnosis challenge
Sina Habibi: Why Leaders Should Care
About Dementia
31C O M PA N Y S U M M A R Y
July 2020
Cognetivity Neurosciences Ltd.
CSE:CGN
FWB:1UB
OTCQB:CGNSF
N America office:
Suite 1980, 1075 W. Georgia St.
Vancouver BC, V6E 3C9
Canada
European office:
3 Waterhouse Square
138 Holborn
London EC1N 2SW
UK
32You can also read
