Healthcare has always been about educating people. Without knowledge, there can be no understanding, and without understanding, there can be no change. Until the 2016 arrival of “big data,” little information existed to describe how health was changing in the U.S. It’s no surprise that the U.S. spends less on healthcare than any other industrialized country.
But with the deluge of data that has come from social media posts, wearable technology, smartphones and other digital devices that track many aspects of health, physicians, researchers and patients are gaining a new understanding of health and disease.
Although the cost-saving benefits of the Affordable Care Act may not be realized anytime soon, some new tools and strategies are being employed to help bring down the costs of healthcare now. And Big Data analytics is one of those tools.
The current state of big data in healthcare
Enabling healthcare professionals to capture and analyze mountains of digitized healthcare data to obtain new insights, Big Data cloud platforms are ushering in a new era of high-quality patient care at lower costs. According to a recent report on big data by Alltech magazine, in the future Big Data could save Americans $450 billion annually. Part of that future has already arrived.
While the coronavirus pandemic has slowed progress on medical big data projects, new initiatives are moving ahead. The U.S. government has provided nearly $5 billion to 45 states to help them build digital health records systems, and the National Institutes of Health has awarded $5.8 billion in contracts to support the development of precision medicine. Big data, predictive analytics and artificial intelligence are helping healthcare providers find better ways to treat patients, reduce costs and provide better care.
“Big data” has been the buzzword in healthcare for the past several years. From predicting hospital deaths to tracking doctor performance, even predicting when a patient will have a heart attack, there has been no shortage of uses for data in the healthcare industry. But the biggest impact we’ve seen on healthcare has been in the realm of clinical decision-making.
That’s because, as the healthcare industry faces more pressure to reduce costs and improve patient outcomes, data can help healthcare professionals make the best decisions possible. As hospitals face unprecedented pressure to manage unprecedented numbers of patients, new tools are helping them identify which patients need urgent care.
Here’s a look at 5 big ways Big Data is reducing healthcare costs today.
Faster time to treatment
With today’s huge patient loads, treating patients sooner saves both lives and healthcare costs. For physicians, delivering a fast and accurate diagnosis and treatment requires them to make informed decisions quickly. By monitoring vital signs with wearable sensors, tracking physical activity with apps, and collecting and analyzing personal data, AI-powered big data is helping doctors and hospitals better manage patients.
Big data analytics tools help expedite the process by factoring in unique circumstances, such as lifestyle choices and demographics, along with the patient’s symptoms to help physicians make a more accurate diagnosis and formulate the best treatment regimen in real time. Data analytics is even reshaping how small healthcare practices work.
Reduced hospitalizations and readmissions
One of the best ways to curb healthcare costs is to keep patients from entering the hospital in the first place.
Using new data tools that send automatic alerts when patients are due for immunizations or lab work, more and more physicians can reduce hospitalizations by practicing better preventive care.
We can use new sensor devices that deliver constant streams of data to patients at home and on the go. This helps patients avoid hospitalization by self-managing their conditions.
For hospitalized patients, physicians can use predictive analytics to optimize outcomes and reduce readmissions. Parkland Hospital in Dallas Texas has been using analytics and predictive modeling to identify high-risk patients in their coronary care unit and predict likely outcomes once patients are sent home. As a result, Parkland has reduced 30-day readmissions back to Parkland and all area hospitals for Medicare patients with heart failure by 31 percent. For Parkland, that represents an estimated savings of $500,000 annually, not to mention the savings patients realize by avoiding readmission.
Improved physician performance
The ability to capture and analyze physician data is having a major impact on optimizing patient outcomes while reducing healthcare costs. One example is Memorial Care – a six-hospital system in Fountain Valley, CA – where physician performance analytics are currently being used to track the performance of both hospitalists and outpatient providers. So far the results are impressive.
According to MemorialCare, doctor performance tracking has reduced the average cost per adult patient by $280, resulting in annual savings to the 6-hospital system of $13.8 million. Just as important, those savings reflect a reduction in readmissions, mortality, and complications attributed to physicians delivering a higher standard of patient care.
Risk stratification
This data analytics tool helps hospitals track and identify the sickest—and often the costliest—patients in a proactive way. But the beauty of this predictive tool is that, along with symptoms, it brings other patient risk factors such as missed doctor appointments and poor blood sugar control, into the mix. If these potentially costly patients are flagged and categorized or “stratified” in terms of risk, physicians can target higher-risk patients. Then they can intervene early to prevent more drastic and costly hospitalizations/treatments.
Improved medication therapy management (MTM)
Adverse drug events plague today’s healthcare system to the tune of thousands of patient deaths and hundreds of billions of dollars in expenses. Many of these problems are due to physicians handling mountains of patient data. The data must be properly evaluated to ensure optimal drug therapy. Clinical pharmacists’ job is to monitor and manage drug therapies. But they shouldn’t be overburdened as patients take multiple medications.
Fortunately, Big Data cloud analytics is helping clinicians and clinical pharmacists to better co-manage drug therapies by identifying drug interactions, adverse side effects, and additive toxicities, all in real-time. While playing a vital role in reducing patient deaths, better MTM reduces healthcare costs through fewer doctor and emergency room visits, hospitalizations, and readmissions
As hospitals race to digitize records, gather data, and phase out paper, they are coming up with a “big” idea to help patients monitor and manage their health. Healthcare professionals who use data are predicting the “personal health cloud” will “revolutionize” healthcare, and someday help patients more proactively communicate with providers.
Big data has been helping companies understand consumer behavior and improve efficiency for years. But the healthcare industry is enjoying a particularly fruitful relationship as hospitals and doctors use data to spot problems early, monitor patient health, and predict and prevent illness.
Healthcare organizations face a dilemma:
Data creates efficiencies and can save money, but it also poses privacy risks and raises potential legal issues.
As healthcare institutions increasingly rely on data, they must figure out how to balance the need to protect patient privacy with the right to access information.
Hopefully, we will see more content about big data on London time 🙂
