Data Analytics is Reducing Healthcare Costs
Healthcare data analytics are quickly adding value to a variety of hospitals, medical practices, and health systems. This data is used to improve consumer experience, growth initiatives, and healthcare cost reduction. Read more about this trend.
Hospitals, medical practices and health systems now use data analytics to identify high-risk patients, cut supply-chain costs, and better manage operations.
This is the third article in a series for Insights that focuses on the impact data analytics and algorithms are having on the healthcare sector.
Hospitals, medical practices and health systems in the United States are beginning to shift from a fee-for-service payment model to value-based care, which is transforming the way they manage costs, get paid and deliver care. For a value-based model to succeed, it is critical that these organizations reduce unnecessary variation to contain costs. Thus comes a new and rising need for extensive data analytics, whose insights can be used to reduce costs, improve quality and better treat at-risk patients. Establishing analytic infrastructure may require extensive investment, yet this potential game-changer could be a competitive differentiator and could offer exceptional opportunities for unlocking value and efficiencies.
According to the consulting firm Deloitte, healthcare analytics are quickly adding value to a variety of organizational goals, including consumer experience, growth initiatives and cost reduction. Effective analytics quantifies the entire patient journey and leverages data to drive cost and waste out of the system, while keeping quality high.
This article delves into analytics’ connection to reduced costs and shares providers’ success stories as they have used analytics technology in their operations.
The Value of Predictive Analytics
Analyzing costs is nothing new, but with large quantities of data readily available, healthcare organizations can go far beyond basic cost accounting. Using predictive analytics (PA)—the practice of employing data and tools to identify patterns that help foresee outcomes—can generate detailed and even real-time information for managing costs and patient risk. Instead of simply presenting information about past events, PA estimates the likelihood of a future outcome using patterns spotted in historical data.
Healthcare executives place high value on this technology. A 2018 survey by the Society of Actuaries indicates that 60% of executives currently using PA believe it will save their organizations 15% or more during the next five years. More than half of all executives surveyed plan to dedicate 15% or more of their budget to PA this year and during the next five years as well.
Healthcare executives are hot on analytics because such a system can alert clinicians, financial experts and administrative staff about potential events before they happen, letting them make more informed choices before proceeding with a decision. Provider and payer organizations can apply PA tools to their financial, administrative and data security challenges, for example, and see significant gains in efficiency, cost savings and consumer satisfaction.
Among the many ways that PA data can be used to reduce costs are the following:
Risk Scoring for High-Risk Patients and Hospital Readmissions: Using predictive analytics to create risk scores based on lab testing, biometric data, claims data and patient-generated health data can help healthcare providers identify individuals at higher risk of developing chronic conditions and reduce the likelihood that patients will be readmitted to the hospital after care. The process can give insight into which individuals might benefit from enhanced services early on to avoid long-term health problems that are costly and difficult to treat. The Illinois Behavioral Health Home Coalition, a consortium of six providers using a value-based purchasing model, used PA in this way. It worked with Relias Analytics to analyze raw claims data to identify variations and gaps in care for high users with multiple conditions and improve care. Their work helped reduce inpatient admissions by 57%, emergency department visits by 31%, and total cost of care by 40%. Annual savings associated with the patients in the study was $1 million.
Reducing Appointment No-Shows and Managing Patient Flow: When patients do not arrive for scheduled appointments, the unexpected gaps in a practice’s daily calendar can have financial ramifications and throw off workflow. According to Health IT Analytics, using PA to identify patients likely to skip an appointment without advance notice can cut down on revenue loss, give practices the opportunity to offer freed slots to other patients, and improve customer satisfaction. A Duke University study found that PA using clinic-level data could capture 4,800 patient no-shows a year for higher accuracy.
Predictive analytics can also be used to ascertain when patients may appear at facilities such as emergency departments and urgent care centers, which do not have fixed schedules. The data could help improve staffing levels and minimize wait times.
Supply Chain Costs Management: The supply chain may offer the biggest opportunity for providers to reduce costs. Hospitals, for example, are using PA to reduce variation and gain better data about ordering patterns and use of supplies. Global Healthcare Exchange has found that hospitals have made data analytics a top priority for supply chain management, with supply chain representing 30% of hospital operations costs, ranked second only to labor costs.
Using data analytics could contribute to reducing hospital supply chain costs by $23 billion annually, based on analysis of more than 2,300 hospitals by consulting firm Navigant. Top-performing hospitals have consistently leveraged analytics to:
- Reduce the number of suppliers and contracts for like items
- Optimize the type and frequency of products used based on patient needs
- Engage physicians to standardize use of effective and more economical implantable devices
- Automate requisitions, purchase orders, invoices and other processes to reduce documentation errors
Options for Adopting Analytics
Bringing analytics into a healthcare organization can be a big step. Depending on the size and scope of health entities, there are a variety of ways to adopt such technology. At the ultimate end, perhaps, is the Cleveland Clinic’s continuing five-year partnership with IBM Watson, a research project exploring how data analytics, cognitive computing and artificial intelligence can improve healthcare and reduce costs. IBM is building a 43,000-square-foot analytics facility that will employ 300 people dedicated to analytics near the clinic’s main campus in Ohio. The clinic welcomes the partnership “because the future really is largely about data and the ability to learn from it and apply it going forward,” says Edward Marx, chief information officer for the Cleveland Clinic.
Such a monumental undertaking isn’t feasible for all healthcare organizations, of course. In Chicago, Rush University Medical Center has approached analytics in another way—by creating its own proprietary predictive analytics framework. Using Microsoft Azure in a cloud environment, the medical center has used its analytics system to improve clinical quality, streamline operations and improve costs. It also has helped Rush improve its rating from the Centers for Medicare & Medicaid Services to five stars.
The Best Benefit of All
Rush’s boosted rating is perhaps one of the strongest bonuses for healthcare organizations looking to adopt data analytics. As healthcare itself becomes increasingly consumer-oriented, with patients shopping around for the highest-rated providers, ratings driven in part by analytics could be crucial for ensuring a healthy future for health providers. Reducing costs is important, but using analytics proactively can grow revenue in the long term through improved overall performance and a positive public image.