Big Data in Healthcare
IOT devices have a major role to play in healthcare, the analyst firm
Gartner projects that by 2020 there will
be more than 25 billion connected devices in the IoT. These sensors collect trillions of data events
can be further mapped to measures of health risk/benefits for patients.
The medical industry collects a huge amount of data but often it is siloed in archives controlled
doctors’ surgeries, hospitals, clinics and administrative departments. There is a need for aggregating
of research data, clinical trends and data from IOT.
Bigdata Experts at Sentienz understand the game of scale,
healthcare companies easily hit petabyte storage. Also
we respect the existing IT Infrastructure and allow smooth adoption. Our platform enables you to fasten
road to advanced analytics.
Bigdata Healthcare “Scope”
McKinsey estimates that big data analytics can enable more than $300 billion in savings per year
healthcare, two thirds of that through reductions of approximately 8% in national healthcare
Clinical operations and R & D are two of the largest areas for potential savings with $165
and $108 billion in waste respectively .
Bigdata the “Opportunity”
For Big Data to transform the Healthcare services in real time, a wave of emerging technologies
need to converge. These will include pervasive sensors (the Internet of Everything) and
localized, predictive analytics, including machines that “learn” from the data. In turn, this
will drive new approaches to traditional patient diagnosis, medical practices and processes.
Bigdata “What” Data
Bigdata in healthcare points to Electronic health data sets that are complex and massive, cannot
managed with traditional hardware and legacy software architectures, methods and tools. Bigdata
a wave not only because of data volume but also because of diversity of data sources, types and
Bigdata Healthcare Usecase
Patient Profile and monitor vitals
Healthcare devices are now able to emit patient vitals at regular
frequencies in a day, these measurements
can be streamed into the processing cluster, also this data is very useful for monitoring patient
and generating real time alerts which are signals and patient has to be given utmost care
Apply advanced analytics to patient profiles (e.g., segmentation and predictive modelling) to
individuals who would benefit from proactive care or lifestyle changes, for example, those patients
risk of developing a specific disease (e.g., diabetes) who would benefit from preventive care. With
help of clinical records we can reduce the patient length of stay
Personalized Patient care
Results would be tailored to the particular needs of the patient and delivered fast. Doctors and
get more time for focusing on the less time-sensitive and life-or-death aspects of medicine — that
relationship building and preventive care.
Personalized health-plan selection based on past and projected use (doctors visits, drugs
Personalized cost comparison on procedures, labs and drugs along with high quality information
Personalized alerts on excessive charges
Hospitalizations account for more than 30% of the 2 trillion annual cost of healthcare in the
Around 20% of all hospital admissions occur within 30 days of a previous discharge. Medicare
hospitals that have high rates of readmissions among patients with heart failure, heart attack, and
Hence its important to identify patients who will be admitted to hospitals with in next year using
claims data. Identifying patients at risk of readmission can guide efficient resource utilization and
potentially save millions of healthcare dollars each year, bigdata analytics will help predict the
of days a patient will spend in a hospital in the next year.
Improve the efficiency in Medical practices
Streamline workflow, shift clinical tasks from doctors to nurses, reduce
unnecessary testing, and improve
patient satisfaction. Like any business, big data made it clear where processes could be improved.
Consider Westmed Medical Group in Westchester County, New York. This practice grew from 16
in 1996 to 250 physicians today seeing 250,000 patients, with annual revenue of $285 million. As the
grows, it needs to be more efficient in order to succeed. Using big data, the practice was able to
more than 2,200 processes and procedures [Source: ingrammicroadvisor ]
Better preparation for potential peak admissions times
Hospital staff can use historic patient data to identify trends when it comes to high-traffic times
year, or even hours in the day where there are increased admissions. This means they can adjust
levels accordingly, Providing higher-level care during peak periods and Giving doctors and nurses a
extra rest during times they might not be as needed.
Optimizations and recommendations
Drill into patterns of room usage and staff availability to identify inefficiencies and avert
Being able to predict equipment failures in advance, based on maintenance standards as well as
and maintenance, ensures that equipment will be available when needed and perform reliably
Fraud cases mostly arise and overlap with insurance and billing patterns.
Once we are in a position to go back into history and analyze the large datasets of historical
and further use appropriate algorithms to detect anomalies, we can identify frauds. At the same time
real-time we can match against business rules, anomalies , social media data to prevent frauds.
Supply chain management
The complexity and size of the health care supply chain, however, makes it extremely difficult to
eye on that spending.
Address fragmentations in supply Digging into historic data helps us understand where we are
the right supplies, drugs and equipment of the right quality at the right location at the right
in the right quantity for the right patient—is critical to optimizing patient care and safety