Augmented Intelligence The Next Frontier (English - White Paper)

Download as pdf or txt
Download as pdf or txt
You are on page 1of 12

Health Imaging

AUGMENTED INTELLIGENCE
THE NEXT FRONTIER

White Paper
THOUGHT LEADER’S PERSPECTIVE
Enterprise Imaging is key to enabling intelligent workflows
In Loving Memory of Ada Lovelace
Ada Byron (1815–82)

Countess of Lovelace, was the daughter


of the poet Lord Byron. At the age of 19, she met
Charles Babbage who arguably invented computers.

Their partnership was the birth of computer science,


as he invented the hardware, while she has gone down
in history as the first programmer.

The computer language Ada is called after her.


AI

Synopsis:
The field of medical imaging has witnessed a context of workflows and systems that healthcare
revolution thanks to the digital transformation practitioners operate and interact with. Unlike
initiatives and availability of advanced clinical Artificial Intelligence, which tries to replicate human
applications in imaging. New imaging techniques intelligence, Augmented Intelligence works with and
are helping Radiologists, Cardiologists, Oncologists, amplifies human intelligence.
and other diagnosticians with greater anatomical
and clinical details, highlighting the need for fast Agfa HealthCare’s approach of building an ecosystem
access to imaging reports and results, collaborative of Augmented Intelligence powered by Machine
workflows and Augmented Intelligence. Learning, Cognitive Reasoning and Task-based
rules engine will help enable delivery of innovative
Augmented Intelligence is the intersection of solutions to enhance care delivery. Agfa HealthCare
machine learning and advanced applications, where Enterprise Imaging platform is standards-based,
clinical knowledge and medical data converge on a designed for interoperability and enables a
single platform. The potential benefits of Augmented leading-edge approach to seamlessly embed
Intelligence are realized when it is used in the machine learning algorithms.
Thought Leader’s Perspective
Enterprise Imaging is key to enabling intelligent workflows

While Radiology has been leading from the front when it comes
to digital transformation with transition from film to PACS
(Picture Archiving and Communication Systems), this transition
in other medical imaging specialties has been slow, or followed a
standards based approach.

Even within Radiology, the challenge of enabling collaborative


workflows between Oncologists and Radiologists, or within
Cardiology between invasive and non-invasive workflows remained
unaddressed with departmental PACS solutions.

AI
When it comes to Pathology, the digital transformation has left a
lot to be desired and has been preeminently non-standard based,
unlike Radiology where we benefited from DICOM protocols.

Physicians and some of the brightest minds specializing in


the field of Machine Learning and Cognitive Computing are
facilitating conversations and exploring the potential of Augmented
Intelligence in clinical practice.

At Thought Leadership industry events and international


conferences, the physician community, academia, young
graduates and industry leaders interested in the intersection of
machine learning, and medicine, are discussing application of
Augmented Intelligence into the practice of medicine.

Agfa HealthCare’s Thought Leadership in the field of medical


imaging is well recognized and we envision following factors
to consider when it comes to enabling intelligent workflows in
medicine:

 Helping reduce care variance


 Leveraging clinical data for learning and decision making
 Task-based workflow optimization
 Role of medical imaging in helping improve quality of care
 Facilitating early adoption of AI and smart technology
for care providers
The Agfa HealthCare approach
A modular Enterprise Imaging platform
with the power of Cognitive, AI and Machine Learning

From Enterprise Imaging


to Augmented Intelligence

SMART APPLICATIONS
PERSONALIZED MEDICINE Smart Apps and workflows powered by AI & ML

AI & MACHINE LEARNING


DIAGNOSTIC INTELLIGENCE Descriptive and Predictive analytics in context

REALTIME COLLABORATION
VISUAL HEALTH Foster real-time collaborative care ecosystem

WORKFLOW OPTIMIZATION
CLINICAL ENABLEMENT Task-based workflow rules

IMAGING HEALTH RECORD


CONSOLIDATION Images and Reports in context

THOUGHT LEADER’S PERSPECTIVE


We reached out to senior Radiologists, Surgeons, Academics, Clinical
Leaders, Department Chairs, Operations Directors and Industry
Analysts around the world, and have included their responses in the
following five perspectives.
Remove departmental imaging silos
1
and consolidate Imaging Health Records

What did we learn from EMRs ? (Electronic Medical Records)

With EMRs, care organizations were successful thanks to smart applications and devices; the
in consolidating patient centered medical record traditional departmental PACS approach has
data, however, a consolidated imaging health created not only clinical collaboration challenges,
record gap still remained unaddressed, because but Information Technology infrastructure and
images remained in their own vertical silos. integration issues as well.

Keeping in mind the recent advancements in Thought leader care organizations are leading
medical imaging, and as radiology moves out from the front when it comes to enabling
of the traditional basement to operating rooms, Enterprise Imaging workflows and governance
to the point of care and even patient’s home, models to bring this all together.

THERE IS A NEED FOR CONSOLIDATED


20% IMAGING HEALTH RECORDS

Fully Agree

Partially Agree

80% Neither Agree or Disagree

Partially Disagree

Fully Disagree

“For our medical school, we’re building a data repository for all “Data Lake &
clinical data that we call a “data lake”. The idea is that all of the
clinical data will sit in the data lake in a de-identified fashion,
Machine Learning”
available for research and to feed into our machine learning
projects.”

Dr. Max Rosen


Chair of the Department of Radiology
UMass Memorial Medical Center, USA
Task-based
2
Workflow Optimization

AI will not replace Radiologists or other


physicians, but in fact enhance and streamline AUGMENTED INTELLIGENCE SHOULD
their workflow even further by empowering OPTIMIZE A TASK-BASED WORKFLOW
them in their ecosystem, and help them make
collaborative and intelligent decisions. If AI
or Machine Learning is not embedded into the
clinical workflow, the perceived benefits will not
be realized. 10%
As technology advances further and diagnostic
capabilities improve, so does the impact on how
caregivers provide care, demanding more access
to diagnosticians in a fast and efficient manner. It

90%
is not the Radiologists who are demanding more
visibility on the frontlines, it is bidirectional, and
there has never been more demand by caregivers
and referring physicians, and even patients,
seeking consultative dialogue with radiologists.

Radiologists will be at the forefront when it


comes to helping deliver quality care, with
Fully Agree Partially Disagree
diagnostic reports and peer collaboration;
Enterprise Imaging powered by AI, will help Partially Agree Fully Disagree
improve radiology tasks even further with
Neither Agree or Disagree
task-based workflow optimization. Physicians
will benefit from fast access to critical results
that require immediate attention, helping reduce
wait times and improve referral services for
cases that require necessary and urgent patient Agfa HealthCare’s Enterprise Imaging solution
care coordination. includes task-based workflow optimization
capabilities, which provide several advantages,
Our respondents emphasized the need for compared to not using a workflow engine.
exploring capabilities of machine learning and The organization of day-to-day work can be
AI in addressing certain mistakes and errors that optimized to permit hospital workflow specific
could alert radiographers and radiologists, and customizations.
automate certain non-essential tasks to ease
workload.

“We should free our experts to undertake expert work by “That’s where
removing as many non-essential tasks for them as possible.”
Artificial Intelligence
Angie Craig comes in.”
Assistant Director of Operations and Performance
Leeds Teaching Hospitals Trust, NHS UK
Enable Multi-disciplinary
3
visual collaboration

Technology should enable cross-departmental


real-time communication and specialist
collaboration, to help improve care-pathways.

Agfa HealthCare’s modern Enterprise


Imaging platform not only removes traditional
barriers to medical imaging, but also enables
multispecialty care team collaboration.

Clinicians engaged in academic research


will realize more benefits with an Enterprise
Imaging solution that helps foster collaborative
engagement between clinical and research
teams.

THERE IS A NEED FOR MULTI


DISCIPLINARY COLLABORATION

40%

60%

Fully Agree Partially Disagree

Partially Agree Fully Disagree

Neither Agree or Disagree


Disseminate Diagnostic
4
Intelligence with AI

As we breakdown silos of imaging workflows


and enable multidisciplinary consolidation WHERE COULD AUGMENTED
and collaboration, the power of a consolidated INTELLIGENCE HELP TO IMPROVE
platform results in creation of a vast data lake, DIAGNOSTIC INTELLIGENCE
ready for analysis by radiologists, diagnosticians,
researchers and academics to help improve
quality of care by better understanding disease
and population health data.
15%
This helps care organizations progress from
Descriptive to Predictive Analytics models
to improve early detection of diseases, and 14%
57%
introduce care plan models that help enforce and
improve patient engagement and compliance.

14%
“A.I. needs to be verified.”
“One still needs fully trained diagnostician
to verify AI. Medicine and Radiology is still
(at least partially) an art.”
Early Cancer Detection Neurological
Dr. Heshan Panditaratne Disorders
Consultant Radiologist Chest Diseases
Calderdale and Huddersfield NHS Foundation Trust, UK All of the
Cardiac Conditions above

During discussions with senior Radiologists


and Diagnosticians, we witnessed consensus
regarding the clinical application of AI “A.I. for triaging and
to help address screening challenges
prioritisation.”
associated with pressing healthcare problems
that include cancers, chronic chest diseases, “In my group, we’ve already demonstrated
musculoskeletal conditions, neurological that an AI system for chest x-ray triaging
disorders, cardiac conditions and detection of and prioritization can lead to much faster
various other clinical conditions.
reporting turn around time. We’ve also
shown potential diagnostic benefits in early
When it comes to Oncology, our respondents
detection of lung cancer.”
discussed the significance of AI not only for
initial diagnosis, but also for follow up after the Giovanni Montana
treatment in helping track the potential Professor of Data Science
recurrence. Warwick University, UK
Personalized Medicine
5
and Smart Applications

Care organizations and health authorities across the globe are faced with pressing population health
challenges. Whether it comes to detecting cancers, or chronic diseases, Machine Learning and Advanced
Analytics will help improve radiologists and diagnosticians focus less on manual repetitive tasks, and
more on improving care pathways.

12% WHERE COULD AUGMENTED


INTELLIGENCE HELP TO IMPROVE
23% CARE PATHWAYS?
18%
Contextual EHR History

12% Comparison with similar cases

Preliminary Reports

35% Incidental Findings

All of the above

“I think one of the biggest contributions deep learning / “A.I. will streamline
artificial intelligence will realistically make to me as a
my workflow and
Radiologist in the near future is not directly helping with image
interpretation, but in bringing the relevant information out of the will be a major step
clinical information system (CIS) / electronic medical record towards more
(EMR) and presenting it to me in a meaningful way to better personalized
inform my clinical judgment.  Incorporating this directly into
the report will be how we can really add value as Radiologists medicine in
using deep learning.  It not only will streamline my workflow Radiology.”
but also be a major step towards more personalized medicine
in Radiology.”

“This definitely will help the patient directly but also better
inform their clinician about tailored options for their precise care
as personalized medicine expands.  The image “pre-screening”
will be in select areas and grow over time. Where it leads and
how quick it gets there is obviously the big question.”

Dr. Bill Anderson


Zone Medical Director Diagnostic Imaging  
Alberta Health Services Edmonton Zone, Canada
The Interoperability Challenge Future of Radiology is Intelligent,
Our Thought Leader customers emphasized explore it with Agfa HealthCare
the need for standards and interoperability. Machine Learning will not replace Radiologists
Data is the new commodity for our or other Diagnosticians, but in fact enhance their
millennium. The data ecosystem of today workflows. Algorithm developers will benefit from
includes PACS, VNA, EMR and Ancillary Systems, a collaborative framework that enables a secure
Health Records and IT, Personal Health Data and and consolidated ecosystem, is standards based,
much more. All this further signifies the need and improves interoperability.
for interoperability to unlock the potential and
gain valuable clinical insights. Hospitals are a
powerhouse of clinical minds and talent, and the
confluence of Enterprise Imaging and Augmented
Intelligence will help deliver modern healthcare
for years to come.
“One of the top-of-mind questions the radiology
community is wrestling with right now is:

“Man versus Machine, or


Man-only versus Man+Machine?”
“With our migration from PACS to the
Enterprise Imaging platform, including VNA, “For our part, we believe the next decade is
we are expecting a centralized location not just going to be about the augmented radiologist.
for our radiology images, but for all patient-re- The combination of AI with the human intelli-
lated data and information. That’s our vision: gence that imaging professionals bring to the
table today, with their ability to understand the
An overall view of the patient big-picture of a patient and the context of their
along the continuum of care.” disease.”

Paul Bauwens Nadim Daher


ICT Architect Principal Analyst
Meander Medical Center, Netherlands Frost & Sullivan

LET’S TALK
As Agfa HealthCare celebrates 150 years of innovation in the field of imaging, join us for a dialogue and
allow us to provide you, the thought leaders, a hands-on learning experience to “Explore, Invent and
Transform” Radiology through innovation, and create positive impact on patient care.

We encourage you to reach out to us, to discuss your Imaging workflow challenges, and how we may help
you transition towards our Next Gen Enterprise Imaging solution powered by Augmented Intelligence.
Author:
Dr. Anjum M. Ahmed (MBBS, MBA, MIS, ITIL)
Global Director – Imaging IT Solutions - Agfa HealthCare
www.linkedin.com/in/dranjum/

Dr. Anjum Ahmed began his clinical career as a practicing GP and over the last 19 years has been focused on change
management initiatives and helping set the path to the digital transformation throughout hospitals and health
authorities across USA, Canada, Latin America, Europe, Middle East, South Africa and Asia Pacific. Dr. Ahmed leads
strategic solution development initiatives at Agfa HealthCare to help healthcare organizations enable value-based
care models that are centered around patients, helping healthcare organizations improve care and maximize value
with their health IT investments.

Agfa and the Agfa rhombus are trademarks of Agfa-Gevaert N.V. Belgium or its affiliates. All rights reserved.
All information contained herein is intended for guidance purposes only, and characteristics of the products and
services described in this publication can be changed at any time without notice. Products and services may
not be available for your local area. Please contact your local sales representative for availability information.
Agfa HealthCare diligently strives to provide as accurate information as possible, but shall not be responsible for
any typographical error.

You might also like