AI
and Healthcare
How can AI bring down the cost of Health
care?
Use of AI led to cost reductions including a 25 percent
drop in hospital length of stay and 91 percent reduction in discharges to
nursing facilities.
Total joint replacement surgery
is one of the most prevalent and expensive surgeries in the U.S., and a study published in the
Annals of Translational Medicine indicates that costs and outcomes for such
surgeries can be improved by using artificial intelligence platforms.
Specifically, the research
examined the efficacy of PreHab AI technology from mobile technology company
PeerWell. Offering pre-operative education, PreHab was associated with a
reduction in surgery costs of $1,215 -- with one big catch: It had to be
delivered in person by a physical therapist.
Many insurance plans only
allow for a small number of paid physical therapy sessions per year, making
surgeons reluctant to use them before surgery.
IMPACT
The platform was able to
deliver effective preoperative optimization without the need for clinicians,
findings showed.
A patient's use of PeerWell
led to significant cost reductions including a 25 percent drop in hospital
length of stay, an 80 percent increase in going home without the need for home
care, and a 91 percent reduction in discharges to skilled nursing facilities.
The platform uses patient data
to create personalized daily plans to get patients ready for surgery. Plans
include video physical therapy, nutrition counseling, comprehensive anxiety
management and pain resilience training, home preparation guidance and medical
risk management.
By using machine learning,
PeerWell can also glean clinically relevant data from ordinary smartphones. For
example, using the accelerometer and gyroscope, it can track range of motion.
Or, by using the smartphone camera, it can identify trip and fall hazards in
the home.
THE TREND
The largest insurers in the
world, including Medicare, have changed regulations to put the onus on care
providers to reduce costs while maintaining high quality. This dynamic has left
many surgeons and hospitals in a bind, shouldering more administrative work for
less reimbursement.
Medicare's randomized trial of
a new bundled payment model for hip and knee replacement surgeries led to $812
in savings per procedure, or a 3.1 percent reduction in costs, when compared
with traditional means of paying for care, research found this
month.
The bundled payment model was
also associated with a reduction in use of skilled nursing care after the
hospitalization, but had no effects on complication rates among patients.
Bundled payments are an
alternative payment strategy that health plans, Medicare and Medicaid are
experimenting with to reduce expenses. Unlike traditional fee-for-service
payments, bundled payments provide a single, fixed payment for a procedure and
follow-up care rather than individually paying all parties separately.
How can predictive analysis help in the
healthcare Business?
AI has the potential to enable faster
development of life-saving drugs, saving billions in costs that can be
transferred to health ecosystems. Most recently, a start-up supported by the
University of Toronto programmed a supercomputer with an algorithm that
simulates and analyses millions of potential medicines to predict their
effectiveness against Ebola, saving costly physical tests and – most
importantly - lives, by repurposing existing drugs.
In clinical trials, AI can optimize drug development using biomarker monitoring platforms – biomarkers allow for gene-level identification of diseases – and millions of patient data points, which can be analyzed in seconds from a drop of blood using at-home devices.
In clinical trials, AI can optimize drug development using biomarker monitoring platforms – biomarkers allow for gene-level identification of diseases – and millions of patient data points, which can be analyzed in seconds from a drop of blood using at-home devices.
Source: https://www.weforum.org/agenda/2018/05/four-ways-ai-is-bringing-down-the-cost-of-healthcare/
Which are the countries looking at doing
robotic surgeries?
In 2009,
Penn State Milton S. Hershey Medical Center began establishing best practices
for medical centers using surgical robots. The Journal of the Society
of Laparoendoscopic Surgeons noted that the
facility initially used robots for only a small assortment of procedures.
However, the diversity of uses has increased over the years, with the most
growth in gynecology and urology.
While the
medical center has used Intuitive Surgical’s da Vinci brand of robots, it
has expanded its use of automation to better serve patients.
Many people
struggle with the finances for surgery, and some travel to specialized
facilities to receive the best available care. Therefore, the priority that the
Penn State Milton S. Hershey Medical Center is putting on automation could be
an example of how hospitals can gain competitive advantage with surgical
robots.
The da
Vinci surgical system is a market leader, but other options are emerging,
including models for specific procedures. Since some key da Vinci patents
recently expired, other companies could seize market share.
Robotic surgery has fascinated surgeons
since its inception almost 30 years ago. US Food and Drug Administration (FDA)
approval of the Da Vinci surgical system in 2000 led to the expansion of
robotic-assisted laparoscopic surgery—most rapidly in urology but also in
gynaecology, cardiothoracics, head and neck, and general surgery. But has this
innovation in surgery translated to benefits for patients?
The Da Vinci surgical system (Intuitive
Surgical Inc) is the only robot approved by the FDA for soft tissue surgery.
The device provides a magnified 3D view of the operative field from a console,
from which the surgeon controls the robot which holds a camera and tremor-free
instruments with a greater range of movement than laparoscopic instruments.
“The benefits to the surgeon are fantastic. There is improved vision and
precision. It brings a lot of the benefits of laparoscopic surgery but it's
easier. In terms of surgeon fatigue it's similar to open surgery”, explains
urologist Prokar
Dasgupta, Chair of Robotic Surgery and Urological Innovation at
King's College London.
What is less clear, however, is whether
these surgical advantages translate into benefit for the patient. There have
been no large randomised trials to compare robotic with open or laparoscopic
surgery. Much of the data come from single-centre studies, so it's difficult to
separate out the confounding influences of institutional factors and the skill
of an individual surgeon, as Dasgupta admits: “I think there is evidence now
for robotic prostatectomy but it's less clear for other procedures.” He
estimates that about 80–85% of prostatectomies in the USA are now done robotically
and that this proportion is lower in the UK and Europe but is increasing.
Critics have attributed the huge growth
of robotic surgery to excitement about a novel technique and aggressive
marketing—to both the patient and the surgeon. “There is no question that some
of the gains achieved with the robot have been generalised by both doctors and
patients”, says US urologist Bernard Bochner from Memorial Sloan Kettering Cancer Center. He
also points out that the dominance of robotic surgery in certain fields can
make undertaking further trials difficult.
Accepting randomisation between open
and minimal access surgery can be a challenge. “Many doctors and patients feel
that robotic surgery is so much better that it would be unethical to randomise
patients to an inferior procedure. The window of opportunity for recruiting
patients to randomised trials has passed now”, says Ben Challacombe, a urologist at Guy's and St Thomas'
Hospitals in London. Bochner agrees that this is a problem, but as a coauthor
with Vincent Laudone of a recent randomised trial comparing robotic with
open cystectomy he takes a different perspective. “Public perception and
widespread advertising related to robotic surgery has perhaps closed the window
of opportunity. However, this is not universal. We recognised that patients
were still willing to accept a study of new technology, and in fact about one
third of the patients accepted randomisation in our study.”
Bochner also argues that “the cost of
robotic surgery versus the benefits achieved must be carefully and thoughtfully
studied and addressed”. Robotic surgery is more expensive than open surgery due
to the cost of the robot (an initial outlay of some £1·5 million) and
disposable equipment. The difference in cost is a difficult equation, says
Challacombe, “it's probably about £1500 extra per case, but this may be offset
by other savings, such as reduced length of stay or reduction in complications.
Start-up costs are high so you need 150–200 cases per year to break even.”
However, not all robotic centres are able to generate such a caseload, which
has particular relevance outside large cities and in low-income and
middle-income countries. However, the ability of a robotic surgeon to attract
referrals for all types of surgery has led some hospitals to accept this cost.
Quality assurance had also been a
concern with the rapid growth of robotic surgery, but both the USA and Europe
now have accredited training programmes and certification in robotic surgery.
This type of surgery requires a different skill set from open surgery, which
has raised questions about whether robotic surgeons have the skills required if
they need to convert to an open procedure. “We'll always need our open surgery
colleagues”, says Dasgupta. “The best centres will offer two teams working
closely together.”
It's inevitable that surgeons will try
a promising new technique to see what it can offer. However, experienced
robotic surgeons are now looking carefully at each operation and patient to
work out where this tool offers a real advantage. As Bochner says, “Accepting
new technology only makes sense if it allows doctors to do things better or if
patients experience better outcomes. If not, we have to question the added
costs and the efforts needed to develop these new skills. The fascination with
robotic surgery should not be allowed to drive surgical care.”
How can pharmacy as a field benefit from
AI?
Wikipedia
defines artificial intelligence — or AI — in healthcare as technology that
“uses algorithms and software to approximate human cognition in the analysis of
complex medical data. The primary aim of health-related AI applications is to
analyze relationships between prevention or treatment techniques and patient
outcomes. AI programs have been developed and applied to practices such as
diagnosis processes, treatment protocol development, drug development,
personalized medicine, and patient monitoring and care, among others.”
CURRENT STATE OF AI IN
HEALTHCARE
AI can be of real help in analyzing data and
presenting results that would support decision making, saving human effort,
time, and money, and thus helps save lives.
Medical
and technological advancements that have helped healthcare-related development
of AI include:
·
Overall
evolution of computers, resulting in faster data collection and more powerful
data processing
·
Growth
in the availability of health-related data from personal and healthcare-related
devices and records
·
Development
of pharmacogenomics and gene databases
·
Expansion
and industry adoption of electronic health records
·
Natural
language processing and other advancements in computing that have enabled
machines to replicate human certain processes
In
2011, IBM estimated that the entire healthcare domain had approximately 161
billion GB of data. Think how much data is in the domain today! With
significant amounts of data available, AI is positioned to become a
game-changing opportunity to improve care and curb the current trend of
unsustainable healthcare spend.
Current
technology and its algorithms enable and complement human interaction with
patients today. In our current distributive platforms for technology,
administrative and clinical healthcare functions are not well coordinated, and
in many cases, are handled manually with some degree of success. With AI as the
enabling technology, a single platform would collect data from various
disparate databases and would sense, understand, act, and learn. It can then
play a significant role in supporting healthcare initiatives relating to
prevention and treatment plans in real time. As healthcare value-based outcome
demands continue to significantly grow, healthcare manpower will be positioned
to respond with AI tools.
CURRENT USE
CASES
In the physician space,
artificial intelligence from technology companies like Microsoft is breaking
into the healthcare industry by assisting doctors in finding the right
treatments among the many options for cancer. Capturing data from various
databases relating to the condition, AI is helping physicians identify and
choose the right drugs for the right patients.
In
the pharma space, AI is working with researchers
supporting the decision-making processes for existing drugs and expanded
treatments for other conditions, as well as expediting the clinical trials
process by finding the right patients from a number of data sources. Pharma is
even working to predict with certain accuracy when and where epidemic outbreaks
might occur, using AI learning based on a history of previous outbreaks and
other media sources.
In
the hospital space, AI is being used to prevent medical
errors and reduce hospital readmissions. By analyzing patient data from medical
and medication errors, readmission root causes, and other internal and external
databases, AI will one day identify and prevent high-risk patients from
developing complications, provide prospective care guidance, and diagnostic
support, among many other clinical applications. Additionally, AI will be
useful in workflow optimization and efficiency, helping eliminate redundancy in
cost from duplicate or unnecessary procedures.
Is Pharmacy Ready for AI?
We
may be further along than we think.
In
pharmacy today, we already have an early form of AI in place. It’s called our
pharmacy management system, housing patient utilization and drug data, as well
as potentially identifying drug-related problems through clinical decision
support screening. The next generation in pharmacy technology is the
introduction of a technology-based information expert system to identify timely
drug-related problems based on patient data captured from the pharmacy system
and other external data systems. Consistent with workflow robotics, this would
leave less of the work on the pharmacist to shoulder responsibility of
identifying serious drug-related problems.
In
my view, AI can strongly influence and shift our focus from the dispensing of
medications toward providing a broader range of patient-care services. We can
leverage AI to help people get the most from their medicines and keep them healthier.
Most importantly, AI provides pharmacy an opportunity for more collaboration
across many different entities serving the same patient. For the patient, in
addition to potentially better healthcare services offered by their
professionals, AI may be a useful tool for providing guidance on how and where
to obtain the most cost effective healthcare and how best to communicate with
healthcare professionals; optimizing value of data from wearables; providing
everyday lifestyle guidance; integrating diet and exercise; and supporting
treatment compliance and adherence.
David
J. Fong, PharmD, is president of Dave Fong Rx Consulting, Inc. A former senior
retail pharmacy executive for Fortune 100 and Fortune 500 companies, he is
recognized as one of the U.S. and Canada’s business and professional healthcare
leaders, leveraging his knowledge and experience working with pharmaceutical
manufacturers, distributors, retailers, payers, and healthcare technology
companies to bring value to the industry and the consumer.
Pharmaceutical industry is one of the
few top domains which can benefit the most from emergence of Artificial
Intelligence since it’s direct impact would be argumenting health, the epitome
of evolution.
We can address this question by
answering the following:
1) Why Artificial Intelligence in
Pharma is a good idea?
2) What are the applications in the
present scenario?
3) What are the limitations?
Before answering the question, please
note that Machine Learning is a subset of Artificial Intelligence.
Why Artificial Intelligence in Pharma
is a good idea?
Pharmaceutical Industry can accelerate
innovation by using technological advancements. The recent technological
advancement that comes to mind would be artificial intelligence, development of
computer systems able to perform tasks normally requiring human intelligence,
such as visual perception, speech recognition, decision-making, and translation
between languages. An estimate by IBM shows that entire Healthcare domain has
approx. 161 billion GB of data as of 2011. With humongous data available in
this domain, artificial intelligence can be of real help in analyzing the data
and presenting results that would help out in decision making, saving Human
effort, time, money and thus help save Lives. But what are the various ways and
data sources that make this possible?
What are the applications in the
present scenario?
In the present scenario, artificial
intelligence/Machine Learning is being used to support decision making process
in the following use-cases.:
1) Drug Re-positioning: To identify the best available
molecular starting points to re-initiate a project with re-purposing a known
drug or combination to test if it can treat another related or unrelated
condition based on its mechanism of action, targets and genomic or proteomic
fingerprint
2) Alternative Indication
identification: What are
new promising indications for a particular class of inhibitors? By studying all
the data pertaining to indications and sorting then on quality, quantity and
relevance in published research and trials.
3) Competitive Landscape: Did others try compound x for
indication y? What was their outcome? This helps Pharma companies in cutting
down the possibility of failure and close in on the right compound for the drug
faster.
4) Correlation Detection: What are the correlations that
you can detect?
5) Failure Analysis: Why did a particular class of
inhibitors fail in drug-development cycle?
6) Clinical Trial Research: Applying predictive analytics to
identify candidates for the trial through social media and doctor visits.
7) Epidemic outbreak prediction: Using Machine Learning/ Artificial
intelligence one can study the history of epidemic outbreaks, analyze the
social media activity and predict where and when an epidemic can affect with
considerable accuracy.
Apart from the aforementioned use-cases
there are numerous others like:
·
Personalizing
the treatment
·
Help build new
tools for the patient, physicians etc
This is just the tip of iceberg, it’s
for the brilliant minds to come up with various other applications which could
revolutionize Pharma from its basic roots.
The limitations:
Streamlining electronic records: which are messy and unorganized
across the heterogeneous databases and are to be cleaned first
Transparency: People need transparency in
Healthcare they receive, which is quite a task given the complexity of the
processes involving artificial intelligence
Data governance: Medical data is private and
inaccessible legally. Consent from the public is important
Hesitant to change: Pharma companies are known to be
traditional and resistant to change. We have to break the stigma to give the
best care we can.
Here is a cool AI powered application
which is used in pharmaceutical & life-sciences space -iPlexus Check this to
learn how AI is accelerating innovation in pharma.
Comments
Post a Comment