Machine
Learning (ML) and Artificial Intelligence (AI): Healthcare – Part Six
by
Dr. RGS Asthana
Senior Member IEEE
Figure
1: ML and AI in Healthcare [11]
Summary
ML, AI, mobile
technology, Big Data and Robotics and many other technologies are being applied
to Healthcare in a major way and are showing their impact almost in all areas
related to Healthcare. We have reviewed this field and divide the applications
in three major areas: first
Tele-medicine and Tele-health apps. These apps came first and are really low
hanging fruits. The second category was for improving service delivery and
exploiting Robotics and 3D printing technologies for benefits of the human
being. The third category included apps
for personal
genetics, drug discovery and disease identification and management. All three
categories used AI and ML to some degree. The third used AI/ML in a major way
and exploited Big Data techniques too. We expect that multi-disciplinary
approach to healthcare will grow further in coming years and will show amazing
results.
Keywords
Machine
Learning (ML) Tools, Artificial
Intelligence (AI), Neural
Networks, Internet
of Things (IoT), Deep Mind, IBM’s
Watson, Deep Genomics
Prelude
ML,
AI, Mobile Technology, Big Data, 3D Printing and Robotics are playing very
important role in healthcare (see figure 1). The primary goal of healthcare is
to help people live longer and live better and peaceful lives and this goal has
led to the most innovative startups in the world. We do describe here a few
apps which are established but need to be revamped with application of ML and
AI techniques. We also cover some of the
important apps developed using AI and other upcoming technologies.
The
improvements in service delivery is obtained by following multi- disciplinary
approach and by automating manual processes by digitizing data to make it
usable by the software and also exploiting smart phone technology available
ubiquitously. Further, we refer to a few apps which use 3D printing and
robotics with AI to further improve healthcare for the benefit of patients by
making prosthetics and human body parts available on a customized basis hopefully
in very near future at affordable rates.
The
use of ML and AI techniques—are accelerating the pace of innovation in
healthcare and motivating growth also in the following areas:
·
Personal genetics
·
Drug discovery
·
Disease identification and management
Biotech
companies such as Cloud Pharmaceuticals [32] and Berg [24] are combining AI and
big data to identify new drug compounds. Johnson & Johnson [33] and Sanofi
[31] are using IBM’s Watson [20] to find
new targets for FDA approved drugs. Johnson & Johnson’s [30] 3D Printing Center
of Excellence is working to change healthcare through 3D printing innovations. In fact, companies are competing among themselves
to gain the first movers advantage to market with a sustainable product.
Healthcare Apps
Tele-medicine
and tele-health apps
These are making healthcare
more beneficial to individual wellness, are less expensive to use and cater
mainly for preventive aspects. These applications need to
be further enhanced using new AI techniques particularly using NLP.
Doctor on Demand
It is a medically certified
mobile application which permits a Certified professionals {read doctor} to
treat non-emergency routine medical cases through video consultation such as
cold and flu symptoms, sports injuries, heartburn, respiratory infections and
allergies, urinary tract infections as well as many pediatric issues. The doctor can prescribe
medicine for travel purposes and refill existing prescriptions.
Microsoft HealthVault [34]
This healthcare service allows facility
to store personal health information
and let customers participate in new ways which
are safe and up to date. The health information can only be shared with
healthcare bodies, e.g., hospitals,
pharmacies, and lab testing companies
You can either enter your health
data manually or have it done automatically by simply connecting HealthVault to
any medical device, such as, fitness tracker, Wi-Fi bathroom scales, and other
apps. Using ML and analytics, HealthVault is
designed to generate new comprehensions about patient health, ensures adherence
to care plans, and encourages patient commitment.
Epocrates
This is a mobile application
for pharmacists and is HIPPA compliant. It has comprehensive medical
information, including drug interaction checker and a pill identification tool,
texting service that allows physicians and other hospital personnel to text
each other with convenience. It keeps doctors up to date on important news
stories, essential resources, clinical guidelines, ICD-10 codes, disease
information and other important information.
PingMD
It is basically a messaging app.
It allows medical professionals to connect with other specialists as well
as with their patients. It is HIPAA compliant and also lets a patient connect
with his/her physicians the same way one might communicate with a friend via
text messaging or image sharing.
Apps
Developed using AI
Heart Attack Forecast
It
is very difficult to predict Heart attacks. An AI system [10] based on routine medical data can
forecast which patients will have heart attacks within 10 years.
Figure
2: Heart Attack Prediction using AI
[15]
During a new
study, Stephen Weng, epidemiologist at the University of Nottingham, U. K. (see figure 2) compared four machine learning
algorithms (viz. random forest, gradient boosting, neural networks, and
logistic regression) to the ACC/AHA guidelines. The training of the AI system
was done by searching through nearly 300.000 medical records from 2005 to not
only find patterns associated with cardiovascular events leading to heart
failures but also to predict which patients would suffer their first cardiovascular
event within the next decade and then compare answers
to the 2015 records. Each of the four AI
methods executed better than the ACC/AHA guidelines, however, the best results
came by using neural networks as it correctly predicted 7.6% more events
and raised 1.6% less false alarms than the ACC/AHA guidelines. However, no AI
technique (out of the four used) projected diabetes as the reason although the guidelines
show this as one reason.
Lung
Cancer Identification [12]
A team of
experts from the University of Warwick, Intel Corporation, the Alan Turing
Institute and University Hospitals Coventry & Warwickshire NHS Trust (UHCW)
is formed to use AI and examine pathology images of lung and arrive at computer-assisted
diagnosis and grading of cancer, if found. This project is likely to increase both the
accuracy and reliability of analysis of cancerous tissue specimen.
Brain-computer
interfaces (BCI) [13]
These are making
brain control possible. Today, a paralyzed person can control Exoskeletons with their
thoughts. Developed at the University of Melbourne, the device connects
into the brain without need to perform any surgery on the skull. In fact, interface uses stents and slides
through an incision made in the jugular vein up to a blood vessel near the
motor cortex in the brain. At the end of the stent, a metallic mesh with
electrodes is used to pick up brain activity and relays this information
to a recording device in the wearer’s chest, which wirelessly transmits it to
an external computer that will control the exoskeleton. When a wearer wishes
to move in a particular direction say, left — the brain fires and generates a
pattern. By detecting the pattern from the brain, BCI and the system not only reads
the thoughts of the person but also translates those into actions which can be
followed by the Exoskeleton (see figure 3).
Figure 3: Exoskeleton controlled by brain
of a paralyzed person
Prosthetics
Biomedical engineers at Newcastle University in the
UK [14] have developed a prosthetic hand with an incredible new skill: the
ability to "see" by using camera to assess shape and size by taking
picture of any object in front of the hand and then taking appropriate action
by activating a series of movements in the hand.
3D printing is one technology which is boon for the
patients who need prosthetics as one can print them customized for each and
every patient.
3D printing in healthcare
[17, 30]
Scientists
are finding the best way to 3D print human organs for transplant. Northwestern University's Feinberg School of
Medicine and McCormick School of Engineering, joint team is developing 3D-printed ovaries that can boost
hormone production and restore fertility and successfully tested it on mice
that not only produced healthy pups but mothers also nursed their young.
The
ovaries were 3D printed using gelatin scaffolding. The team loaded the
structures with immature egg cells before implanting them into their test
subjects. The main cause of the success
lies in the temperature used while 3D printing the structure but the team's
biosynthetic ovaries can even be considered for use in humans will take long
time. 3D printing technologies use all type of materials from
metals to polymers to biomaterials—materials that mimic living tissue—to create
objects.
3D
printing is used to customize instruments used by orthopedic surgeon specifically
for each patient, so he does not bother about so many different sizes into
surgery.
Figure 4: 3D printing of mouse ovaries at
Northwestern University
Personal genetics
The most significant
application of AI and ML in genetics understands how DNA impacts life and also what
influences life and biology; we need to first understand the language that is
DNA. This is where ML algorithms play a big role and big players, such as; Google’s
Deep Mind [19] and IBM’s Watson [20] are in the fray. Technologies like big data detect patterns from
enormous amounts of data (e.g. patient records, clinical notes, diagnostic
images, treatment plans).
Deep Genomics [21] is developing
the capability to interpret DNA by creating a system that predicts the
molecular effects of genetic variation. Their database is able to explain how
hundreds of millions of genetic variations can impact a genetic code. This will
provide personalized insights to individuals based on their biological dispositions. This trend is
indicative of a new era of “personalized genetics,” whereby individuals are
able to take full control of their health through access to unprecedented information
about their own bodies. As is the case
with any application of AI/ML and also Big Data, the technology must have
access to vast amounts of data in order to better curate lifestyle changes for
individuals.
Develop
drugs of the future
Application of AI/ML
in healthcare is not only reshaping the industry and making what was once was
considered impossible task but also helping in the reduction of both cost and
time in drug discovery.
Atomwise [22]—a San
Francisco-based startup—is considering to use supercomputers instead of test
tubes in the drug development procedure. The company uses ML and 3D neural
networks that search through a database of molecular structures to find out
therapies, discover the effectiveness of new chemical compounds on diseases and
identifying existing medications that can be used to cure another ailment.
Berg Health [24]—a Boston-based
Bio-pharma company—uses a different approach for drug discovery and works on
patient biological data using AI to determine why some people survive diseases,
and then applies this insight to improve current therapies or create new ones.
Figure
5: Cloud technology used for drug
discovery
Cloud Pharmaceuticals
[32] is using AI design innovations to discover and generate new novel drugs
using cloud technology (see figure 5).
There are many new
companies working on drug discovery exploiting ML/AI to the hilt to discover
drugs and the future of this field is encouraging. It may be worth mentioning
that the cost and time of drug development in the usual way varies between USD 0.5
to 3 Billion and may take more than a decade to reach the user.
Discovering
new diseases
Most diseases are far
more than just a simple gene mutation. Although the healthcare system generated
enormous amounts of (unstructured) data—which is gradually refining and
improving in quality—but we did not possess the necessary hardware and software
in place to investigate it and produce telling results.
Disease diagnosis
involves a number of factors, like the texture of a patient’s skin to the
amount of sugar level in his blood. So far,
we have worked on symptomatic detection, e.g. if one has a fever and stuffy nose,
he is diagnosed most likely to have the flu.
Systems can now predict the molecular effects of genetic variation [21],
opening a new and exciting path to discovery for disease diagnostics and
therapies.
But often the arrival
of detectable symptoms is too late, especially when dealing with diseases such
as cancer and Alzheimer’s. With ML, the hope is that faint signatures of
diseases can be discovered well in advance of detectable symptoms, increasing
the probability of survival and/or treatment options.
Freenome [25, 28]—a San Francisco-based startup—is a technology company developing proprietary
algorithms and novel methods to enable accurate diagnosis of clinical
conditions. Freenome platform—an Adaptive Genomics Engine—dynamically
detects disease signatures in your blood. The company uses your Freenome—the dynamic
collection of genetic material floating in your blood and is constantly
changing over time and it’s like a genomic thermometer of who you are as you
grow, live and age. As per CEO of the company, ‘our aim is to bring accurate,
accessible, and non – invasive screenings to doctor to proactively treat cancer
and other diseases at their most manageable stages’.
Enlitic [26] uses deep
learning techniques to empower doctors with necessary data to not only become
faster but also accurate. This is
possible as doctors look at disease diagnosis and treatment plans by coupling
deep learning with medical data and extract actionable insights from billions
of clinical cases. IBM’s Watson is working with Memorial Sloan Kettering in New
York to analyze data on cancer patients and treatments used over decades to
present and suggest treatment options to doctors in dealing with unique cancer
cases.
Google’s Deep Mind will
scan 1 million medical records of Moorfields Eye Hospital [27] and will analyze
these digital scans of the eye will be
used to train an AI system to help doctors better understand and diagnose eye
disease. Google has estimated that up to 98% of sight loss happens due to
diabetes and can be prevented with timely and early treatment.
Way forward
The data
Scientist today is playing a major role in preprocessing large amount of data
and making it meaningful for the ML algorithm to show good and acceptable
results. It is well known fact that ML algorithms give better results with more
and more of the training and test data.
The rule for maintaining good ratio of training and test data is amid 65:35
to 75:25. The combination of Big Data and ML/AI techniques play an interesting and
decisive role in analyzing and handling enormous amount of data (which medical
fraternity possesses) and deriving meaningful and more accurate results.
While robots
and computers will never completely replace doctors and nurses, machine
learning/deep learning and AI are changing the healthcare industry, improving not
only results but also discovering new medicines to
attack diseases, and changing the very mode doctors think today of providing
care. ML/AI is improving diagnostics,
predicting results and tomorrow doctors may be in position to give even personalized
care.
IBM’s Watson
[20] helps oncologist to make the best care decisions for their patients.
The Care team helps doctors devise and understand the best care protocols
for cancer patients.
AiCure is
using mobile technology and facial recognition technologies to determine if a
patient is taking the right medications at the right time to help doctors
confirm that the patient is taking their medications and alert them if
something goes wrong [23] (see figure 6). This approach may help doctors to
face biggest hurdles in healthcare, i.e., patient come back to hospital after
discharge and doctor don’t know why?
Figure
6: Amalgamation of mobile and AI tech for doctor feedback
Healthcare start-ups are using ML/AI, Big-data and even
deep learning to make it flexible for all the development phases and areas for
all kind of users in healthcare. Industry
analysts forecast that 30 percent of health providers will use cognitive
analytics with patient data by 2018. In near future [29] robots will help children with autism and
diseases will be diagnosed by a breathalyzer.
References
[1] Progress and Perils of
Artificial Intelligence (AI)
[2] Invited Chapter 6 - Evolutionary Algorithms and Neural Networks, Pages 111-136, R.G.S. Asthana
in book, Soft Computing and Intelligent Systems (Theory and Applications),
Academic Press Series in Engineering, Edited by:Naresh K. Sinha, Madan M. Gupta
and Lotfi A. Zadeh ISBN: 978-0-12-646490-0
http://www.sciencedirect.com/science/book/9780126464900
[3] Future 2030
by Dr. RGS Asthana, Senior Member IEEE
[4] Machine
Learning (ML) and Artificial Intelligence (AI) – Part 1, by Dr. RGS Asthana, Senior Member IEEE
[5] Machine Learning
(ML) and Artificial Intelligence (AI) – Part Two, by Dr. RGS Asthana, Senior
Member IEEE
[6] Internet of Things (IoT)
[7] Machine
Learning (ML) and Artificial Intelligence (AI): Cognitive Services and Robotics
– Part Three by Dr. RGS Asthana, Senior Member IEEE
[8] Machine
Learning (ML) and Artificial Intelligence (AI): Big Data and 3 D Printing
– Part four by Dr. RGS
Asthana, Senior Member, IEEE.
[9] Machine Learning
(ML) and Artificial Intelligence (AI): Drones and Self-driving Cars– Part
Five by, Dr. RGS Asthana, Senior Member IEEE
[10] Confirmed: AI
Can Predict Heart Attacks and Strokes More Accurately Than Doctors
[11] Google Image
[12] The Huffington
Post: Using AI to spot lung cancer
[13] Brain implant allows
paralyzed people to control Exoskeleton with their mind
[14] UK Engineers
Develop Prosthetic Hand That Can 'See'
[15] Self-Taught
Artificial Intelligent Increases Heart Attack Prediction Rate Significantly
[16] 5 apps changing
how the healthcare industry works
[17] 3D-printed
ovaries successfully produce healthy mice pups
[18] Advances in AI
and ML are reshaping healthcare
[19] Deep mind
website
[20] IBM Watson
Website
https://www.ibm.com/watson/
[21] Changing the
course of genomic medicine
[22] Atomwise website: Artificial Intelligence for
Drug Discovery
[23] How ML, Big Data and AI are changing Healthcare
forever
[24] Berghealth website
[25] Freenome website
[26] Enlitic website
[27] Google's DeepMind to peek at
NHS eye scans for disease analysis
[28] Freenome
[29] The Future of Artificial
Intelligence & Machine Learning In Healthcare
https://www.eventbrite.co.uk/e/the-future-of-artificial-intelligence-machine-learning-in-healthcare-tickets-32955561973#
[30] The power of 3D Printing: How
this technology is blazing new medical frontiers
[31] AI is using in dynamic phases
of Healthcare start-ups
[32] Cloud Pharmaceuticals website
[33] Johnson & Johnson Looks to IBM’s
Watson to Predict Patient Outcomes
[34] Microsoft Health Vault website