This document discusses the history and applications of artificial intelligence in orthopaedics. It begins with definitions of AI and provides examples of early AI pioneers. It then outlines the current and potential future uses of AI in orthopaedics, including for analyzing medical images, assisting with surgical navigation and procedures, and evaluating treatments. While AI may replace some tasks, the document argues that AI will likely change and enhance the role of orthopaedic surgeons rather than replace them entirely. It closes by acknowledging challenges with AI and calling for maintaining the important doctor-patient relationship.
2. WHAT IS AI?
In computer science artificial intelligence or machine intelligence is the
intelligence demonstrated by machine in contrast to the natural intelligence
displayed by humans and other animals.
According to KAPLAN AND HAENLEIN – A systems ability to correctly
interpret external data, to learn from such data, and to use these learning to
achieve specific goals and tasks through flexible adaptations.
3. HISTORY OF ARTIFICIAL INTELLIGENCE
In 1940s and 1950s mathematician Alen
Turing led the M16 team that cracked the
unbreakable code of the German Enigma
coding machine during world war II, as
well as created a test for a machine’s
apparent intelligence when interacting
with humans.
4. HISTORY OF ARTIFICIAL INTELLIGENCE
AI did not becomes a discipline until
the late 1950.
In 1950 Arthur Samuel coined the
term machine learning.
He developed a checkers- playing
program which was the first self
learning program with human
interaction.
5. Artificial intelligence---- A scientific
fantasy
I, ROBOT – A SciFi novel by ISAAC
ASIMOV in 1950 produced the three law
to protect human from AI--------
“A robot may not injure a human being or
through inaction, allow a human being to
come to harm.”
“A robot must obey orders given by a
human being unless it conflicts with the
First Law.”
“A robot must protect its own existence as
long as such protection won’t conflict with
the First or Second Laws.”
7. Why AI is important in our field?
AI can learn from prior data and
draw knowledge from cases, and
use those outcomes to help
healthcare professionals analyze
future cases.
The potential to drive
improvements in quality, cost, and
access has made AI a notable fact in
healthcare. The AI health market is
growing rapidly and is forecasted to
reach $6.6 billion by 2021
9. AI will change the way
healthcare work is performed. AI
will fill the gaps we all know are
coming in the future, such as
the labor shortage in healthcare.
Through AI, we will empower
clinicians and give workers tools
to increase their productivity.
Healthcare institutions will need
an AI-trained workforce and
culture.
10. Application of AI in orthopaedics
We are currently developing big data through registries like the American Joint Replacement
Registry (AJRR), and as we look to find a useful home for AI in orthopaedics, AJRR could be
one place to start.
Can be use to follow up a bone tumor’s response to chemotherapy.
Computer assisted navigation currently use in orthopedics.
11. Application of AI in orthopaedics
Kenneth Urish, MD, PhD, is currently
working on AI as a way to evaluate
MRI data to detect osteoarthritis and
track cartilage loss over time. This
approach may have many implications
as this can evaluate the usefulness of
treatments like lubricants, platelet-rich
plasma, and stem cells, as well as
medical treatments for inflammatory
arthropathies
12. AI in Computer-Assisted Navigation
Orthopedics surgeons use robots since
1990 but recent advances making the
machine more useful.
Orthopedic surgeons have had access to
robotic technology to help them
position screws, prosthesis, or tunnels
for some time, but AI enhanced
applications are in development. For
example, one device named OPTOTRAK
3020 (NDI MEASUREMENT SCIENCE)
utilizes infrared light to locate bones
intraoperatively.
13. Robots use in orthopaedics
The ROBODOC (Curexo
Technology) uses a form of AI
to mill the canal for a prosthesis
using prepared surgical plan
based on CT scans.
14. Robot use in TKR and THR
In total hip surgery, computer assistance in placing the cup of the
prosthesis is reported to have more accurate than traditional methods.
Other robot have used CT to provide a real time virtual model of the
surgical field.
In cases of knee replacement surgery, AI-supplemented robotics
technology assists to align prostheses.
15. Robot use in spine surgery
In spine surgery, AI-enhanced computer-assisted navigation helps
surgeons avoid neurovascular structures, and place thoracic and lumbar
pedicle screws accurately.
It is reported that the incidence of poorly placed screws has reached 42
percent with conventional surgical techniques, according to some studies,
but is as low as 10 percent with AI-based computer assistance.
16. Robot use in arthroscopy
In arthroscopy surgery robot are able to position tunnel in femur as well as
tibia more accurately than manual surgeons using conventional means and
thus potentially reducing the risk of ACL reconstruction.
In shoulder arthroplasty computer aid navigation is becoming useful. It is
also effective where normal anatomy of the shoulder was distorted , for
example, with # in revisions cases, and in glenoid wear or dysplasia.
17. AI for analysing radiographs
AI could be used to screen radiographs for subtle
abnormalities, back up an emergency department
doctor’s nighttime fracture readings with a
machine-learning-based second opinion.
A team of researchers at Karolinska Institutet,
Danderyd Hospital, and the Royal Institute of
Technology in Stockholm,Sweden recently
developed an artificial intelligence system for
reading radiographs.
18. AI for analysing radiographs
To teach computer networks to read radiographs, they fed them 256,458
hand, wrist, and ankle radiographs with labels stating whether or not the
images contained fractures, the body part, laterality (left or right), exam
view (anteroposterior/frontal, lateral, or oblique [two different types]), and
four scaphoid-specific views (proximal, distal, ulnar, and radial).
19. AI for analysing radiographs
Fifty-six of the images contained fractures. For fractures, the best
computer network had an accuracy of 83% in identifying fractures in these
images. By comparison, the human reviewers were accurate in 82% of the
time.
On another subset of images, the computer networks reached an accuracy
of 99% on body part, 95% on exam view, and 90% on laterality. This is
exactly human-level performance.
20. AI for analysing radiographs
More than 80% of orthopedic surgeons’ clinical decisions are made on the
basis of radiographs;
The next step would be for artificial intelligence systems to use images to
quantify risk, perhaps telling one patient that a knee replacement has an
80% chance of eliminating the pain and telling another that the procedure
has a 50% chance.
21. Problems with AI
High cost
Longer duration of operation.
Long time of anaesthesia.
Need extra skills to operate.
The HOPE –
In case of spine surgery
improved accuracy merits
the extra cost.
22. Will they replace us in future?
Orthopedics has a reputation of a high tech low touch profession. We need to
work on bedside manners.
Now a days patient shows a great interest on robotic surgery.
If AI dominate our field and take clinical decisions then there will be absolute
loss of doctor patient relationship.
There will be legal ramifications as even the best robot guided by best AI will
make mistake.
If that occurs then WHO WILL BE LIABLE?
the surgeon who nominally supervising the procedure.
OR
the manufacturers of the robot.
23. In the near future surgeons role may be like a pilot
who assist in landing and take off.
Robotics and AI always be there in future, and I feel
relationship between the creator and the robot
don’t END UP WITH the story of Frankenstein
because
“the true sign of intelligence is not
knowledge but imagination”
Albert Einstein