OR Manager - May 2019 - 9

SPECIAL SERIES
where between supervised and unsupervised
learning. In this case, the
machine learns based on its ability to
maximize an established reward. In essence,
the machine tries to accomplish
a task, such as coming to a medical
decision, while learning from its own
successes. Controlling an artificial pancreas
system is an example of reinforcement
learning in action.
Artificial neural networks (ANNs)
ANNs process signals in a way similar
to what occurs in humans (sidebar, p
7). A 2016 study by Monsalve-Torra and
colleagues found that ANNs could analyze
data such as patient history, blood
pressure, and medications to help predict
in-hospital mortality after open repair
of an abdominal aortic aneurysm
with an accuracy of 95.4%. And a 2018
study by Lee and colleagues used an
ANN and intraoperative electronic medical
record data to help predict in-hospital
mortality of patients who underwent
a variety of surgical procedures.
It's worth noting that a neural network
only learns what it is told to
learn-at least at this stage of AI development.
Gambus and Shafter say
humans use their knowledge to extrapolate
and apply what they know to new
situations. Neural networks have to be
fed large amounts of data until extrapolation
isn't necessary.
Deep learning refers to a neural network
that has a hierarchy of layers, with
each layer transforming the input data
into more abstract representations. This
type of neural network is more complex
than ANN, so it can learn more complex
features. However, large amounts of
data are needed for learning.
Natural language processing
(NLP)
NLP focuses on building a computer's
ability to understand human language.
NLP lets the machine infer meaning
from unstructured data such as providers'
comments in the electronic health
www.ormanager.com
Analytics and artificial intelligence
Artificial intelligence (AI) functions with greater sophistication than other types of
analytics. Data analytics are based on past events. Organizations are increasingly
turning to predictive analytics, which, according to Shaily Kumar, an analytics expert,
involves three fundamental components:
➤ data (refers to historic data, which must be of high quality)
➤ statistical modeling (statistical techniques used to derive meaning,
insight, and inference)
➤ assumptions (the conclusions drawn from the analyzed data typically
assume that the future will follow past patterns).
Predictive analytics pulls from many sources of data. AI is similar to predictive
analytics, but can recalibrate models in real time.
" Predictive analytics and AI can make clinical decision support smarter, " says
Whende Carroll, MSN, RN-BC, founder of Nurse Evolution, a company that looks
at how healthcare technology, data analytics, and innovation concepts can be
used to improve health and how healthcare is delivered. For example, clinical decision
support tools in electronic health records have used simple rules and basic
sources of data, such as laboratory results, to alert clinicians that a patient may
be at risk for sepsis. But being able to look at more sources of data from different
places, such as claims data, enables a more fine-tuned approach. " We can look at
comorbidities, medications, and number of previous ED [emergency department]
visits, and compare the data with similar data sets from other patients, " Carroll
says. " Then we have smarter, more precise clinical decision support tools. " The key
is to have a large amount of data that is complete, unbiased, and structured.
record (EHR). In a 2016 study by Soguero-Ruiz
and colleagues, NLP enabled
the computer to scan EHRs to identify
words and phrases in operative reports
and progress notes that predicted anastomotic
leak after colorectal resections
and was ultimately able to predict leaks
with a sensitivity of 100% and a specificity
of 72%. " Being able to process unstructured
language also helps identify
social determinants, so we can better
care for patients, " Carroll says.
Computer vision (CV)
CV enables machines to learn from images
and videos that are fed into them.
CV is being used for analysis of patient
cohorts, longitudinal studies, and decision-making
in surgery.
" We used video data and AI to build
a model that identified with 93% accuracy
the steps of a sleeve gastrectomy
procedure in real time, noting any missing
or unexpected steps, " Dr Hashimoto
says. Instead of manually evaluating
videos of procedures, he and his team
trained a computer to classify segments
of the videos into operative steps. Deviation
from the expected operative path
identifies possible undesirable events
(sidebar, p 8).
The ultimate goal is to be able to
warn surgeons of missing or unexpected
steps in real time, so that an
adverse event can be avoided. " AI can
learn from hundreds or thousands of
surgical procedures simultaneously, but
a surgeon learns from one surgery at a
time, " Dr Hashimoto says.
AI also taps into the power of data
analytics (sidebar above).
A booming market
The healthcare AI market is expected to
grow from $2.1 billion in 2018 to $36.1
billion by 2025. Allied Market Research
Continued on page 10
OR Manager | May 2019
9
http://www.ormanager.com
OR Manager - May 2019

Table of Contents for the Digital Edition of OR Manager - May 2019
