2. WHAT IS
The use of healthcare analytics can potentially reduce the cost of
treatment, predict disease outbreaks, circumvent preventable
illnesses and generally improve the quality of care and life of
Big data essentially takes vast quantities of information, digitizes
it and then consolidates and analyses it with specific
physicians’ decisions are more frequently based on evidence,
research and clinical data provided by healthcare analytics is in
much higher demand.
With data analytics in healthcare, it can become easier to gather
medical data and convert it into relevant and helpful insights, which
can then be used to provide better care. Below are some examples
of how healthcare analytics can be used to foresee problems and
prevent them before it’s too late, as well as evaluate current
methods, actively involve patients in their own healthcare, speed up
and improve treatment, and track inventory more efficiently.
Finding the perfect balance so that managers don’t overstaff and
lose money, or understaff and have poor patient outcomes, can be
remedied by healthcare analytics. Hospitals in Paris used big data to
analyse 10 years' worth of hospital admissions records, allowing
them to find patterns and forecast visit and admission rates 15 days
in advance.This enabled them to pre-emptively schedule extra staff
when a high number of patients were expected, which led to
reduced wait times and a higher quality of care for their patients.
most common application of big data in healthcare in the U.S. 94
percent of hospitals have adopted EHRs. Each patient has their own
digital health record which includes everything from allergies to
demographic information. Every record is made up of a single
adjustable file, allowing doctors to complete changes through the
years with no paperwork and no risk of repeating data.
Many potential patients are also consumers who are already
utilizing smart devices that double as wearable health devices that
track their steps, heart rates, hydration levels, sleep patterns, etc.
Patients are directly involved in monitoring their health, and
incentives from health insurance companies can motivate them to
lead a healthier lifestyle.
Patients who utilize wearable health devices can track
specific health trends and upload them to the cloud where their
physicians can observe them. Patients with asthma or high blood
pressure may be able to reduce visits to the doctor and gain more
independence with these devices.
According to the Centre for Disease Control (CDC), on average, 130
Americans die every day from an opioid overdose. In fact, in 2017
opioid overdose became the most common cause of accidental
death in the U.S., overtaking road accidents.The application of
healthcare analytics can help solve this critical problem. Blue Cross
Blue Shield started working with analytics experts to analyse years
of insurance and pharmacy data.They were able to identify 742 risk
factors that predict with high accuracy whether or not someone is at
risk for opioid abuse
Predictive analytics is one of the biggest business intelligence
trends, but their potential reaches much farther than just the
business field. Optum Labs, a U.S. health services innovation
company, collected the EHRs of more than 30 million patients to
create a database for predictive analytics tools that will help
enhance and streamline the delivery of patient care.Their goal is to
use data and advanced analytics to achieve the "TripleAim of
improved outcomes, reduced costs and an improved patient
experience."They help doctors make data-driven decisions within
seconds, and can even predict and prevent the onset or progression
of some conditions.
9. 4 Emerging
Researchers are developing new strategies to overcome key barriers
hindering the use of big data analytics in healthcare.
Big data analytics technologies have demonstrated their promise in
enhancing multiple areas of care, from medical imaging and chronic
disease management to population health and precision medicine.
These algorithms could increase the efficiency of care delivery,
reduce administrative burdens, and accelerate disease diagnosis.
Despite all the good these tools could potentially achieve, the harm
these algorithms could cause is nearly as great.
Concerns about data access and collection, implicit and explicit bias,
and issues with patient and provider trust in analytics technologies
have hindered the use of these tools in everyday healthcare
delivery. Healthcare researchers and provider organizations are
working to find solutions to these issues, facilitating the use of big
data analytics in clinical care for better quality and outcomes.
In healthcare, it’s widely understood that the success of big data
analytics tools depends on the value of the information used to
train them. Algorithms trained on inaccurate, poor quality
data will yield erroneous results, leading to inadequate care
However, obtaining quality training data is a difficult, time-
intensive effort, leaving many organizations without the resources
to build effective models.
Researchers across the industry are working to overcome this
challenge. In 2019, a team from MIT’s Computer Science and
Artificial Intelligence Library (CSAIL) developed an automated
system that can gather more data from images used to train
machine learning models, synthesizing a massive dataset of
distinct training examples.
The dataset can be used to improve the training of machine
learning models, enabling them to detect anatomical structures in
BIAS IN DATA
As healthcare organizations become increasingly reliant on
analytics algorithms to help them make care decisions, it’s critical
that these tools are free of implicit or explicit bias that could
further drive health inequities.
With the existing disparities that pervade the healthcare industry,
developing flawless, bias-free algorithms is often challenging. In a
2019 study, researchers from the University of California Berkeley
discovered racial bias in a predictive analytics platform referring
high-risk patients to care management programs.
To remove bias from big data analytics tools, developers can work
with experts and end-users to understand what clinical measures
are important to providersWhile communicating with providers
and end-users during algorithm development is extremely
important, often this step is only half the battle. Collecting the
high-quality data needed to develop unbiased analytics tools is a
time-consuming, difficult task.
Researchers from the Perelman School of Medicine at the
University of Pennsylvania also recently developed a solution to
protect patient confidentiality. In a study published in Scientific
Reports, the team described a new technique that enables
clinicians to train machine learning models while preserving
patient data privacy.
Using an emerging approach called federated learning, clinicians
could train an algorithm across multiple decentralized devices or
servers holding local data samples without exchanging them.
In a recent report from the American HospitalAssociation (AHA),
the organization noted that one way organizations could secure
provider trust in these tools is to use AI to manage unsustainable
Researchers from MIT’s CSAIL have also worked to increase
providers’ trust of analytics tools.A team recently developed a
machine learning tool that can adapt when and how often it defers
to human experts based on factors such as the expert’s availability
and level of experience.