This article was written by Lisa Miller.
Enterprises across every sector are continually involved in the collection, processing, and analysis of massive flows of big data to improve efficiency and profitability. The healthcare industry, notably hospitals, is no exception as they attempt to balance quality health care delivery with revenue growth while functioning on historically thin operating margins. The use of data analytics can help hospitals successfully navigate these challenges by promoting cost savings and spend management initiatives across an organization.
Why Use Data Analytics?
Data is one of the most crucial components used in the decision-making process. However, raw data consisting of scattered facts and figures from numerous and varied sources must be systematically converted into a meaningful format using analytics. This task is accomplished through an automated process utilizing specialized software that uses complex algorithms and formulas to process and sort the data. The resulting output converts into a readable display for online dashboards that include graphs, tables, and printable reports that clinicians and hospital leadership can readily interpret.
Hospitals are also continually under scrutiny by state and federal agencies and are required to report patient care and financial data to ensure cooperation with established guidelines. As a result, the urgency to report accurate data in a timely manner has never been greater. Data analytics assist hospital administrators with this responsibility in addition to providing a clear-cut view of revenue impacts.
Without data analytics, it is impossible to fully understand how a complex organization like a hospital is doing or how to manage spend while improving the quality of care. Data analytics allows an organization to uncover areas of waste and make more informed decisions regarding how to use hospital resources. It provides an accurate view of what is actually happening and can support decisions that will ultimately lead to cost savings. Consulting with an advisor or developing an internal team to manage data analytics remains a worthwhile investment into the future success of any healthcare organization.Consulting with an advisor or developing an internal team to manage data analytics remains a worthwhile investment into the future success of any healthcare organization. Click To Tweet
Hospital Data Sources And Applications
Health care data originate from many sources, including electronic health records (EHRs), medical imaging, payor records, pharmaceuticals, wearables, and medical devices.  This data dramatically differs from that of other industries in that it streams in higher volumes and velocities. Thanks to technological advances in analytics, hospitals can store and analyze this data using software tools to make smarter and cost-effective decisions.
The analyzed data is used in several applications, resulting in increased cost savings: 
- Operational efficiency
Data collected from admissions and discharges is used to analyze staff efficiency and productivity during varying patient volumes. This analysis can lead to more efficient use of personnel resources while improving patient care.
- Proactive medical care
Big data garnered from electronic health records (EHRs) such as clinical data, conditions, and diagnoses are used to study more effective treatments for patients. Being proactive with inpatient treatment lowers the duration of hospital stays, decreasing costs for both the health care facility and the patient.
- Medical equipment maintenance
Critical medical equipment, such as MRI scanners requires preventative maintenance to ensure proper operation 24/7. Data from sensors in the machines can predict when it’s time to replace critical components and prevent sudden, costly breakdowns.
- Physical infrastructure maintenance
As is the case in other structures, a hospital building uses sensors to monitor such resources as energy consumption, heating and air conditioning systems, as well as fire and security systems. Monitoring and analyzing this data facilitates uninterrupted operation of these systems, preventing costly repair or replacement.
Data Analytics Enhance Patient Safety, Save Costs
Adverse outcomes such as hospital-acquired infections (HAIs) and medical errors present a substantial financial threat to hospitals. Not only do they require additional expensive treatment, but they can also lead to costly penalties in the form of disciplinary action and lawsuits.
EHR and bedside computer data contain valuable data on encounters, lab results, medications, vital signs, notes, and diagnoses. Applying predictive analytics and machine learning to this data can be used to prevent medically adverse events and forecast longer stays, inpatient mortality, and unexpected readmissions.
Hospital-acquired conditions (HACs) and hospital-acquired infections (HAIs) are reportable conditions that are considered preventable. Since they originate in the facility, Medicare will not reimburse the hospital for these conditions, resulting in higher patient care costs. Hospitals also lose valuable points on their safety indicators that result in reimbursement reductions. However, by implementing various analytical tools, potential adverse events are identified, and proactive measures are taken to avoid their occurrence.
An example of using analytics in patient care is demonstrated at Augusta Health in Virginia.  Combining EHR data with geocoded hospital floor plans, a visual map was created of how multi-drug resistant organisms spread. The resulting information provided a better understanding of how C.diff and MRSA infections spread to help avoid future HAIs from occurring.
Algorithms using historical and real-time data are making meaningful predictions for effective clinical decision-making. A recent survey from the Society of Actuaries demonstrated that 60 percent of healthcare executives had adopted predictive analysis and 39% of those who responded have saved costs. 
Other potential applications for predictive analytics in hospitals are for more efficient patient scheduling, early treatment of sepsis, prevention of falls and monitoring patient flows to optimize both staff and equipment resources.
Applying Data Analytics To Decrease Claim Denials
Denied insurance claims represent a significant revenue obstacle to many hospitals. Tracing the reason for the denial often involves a complex series of steps, making the process a difficult undertaking. Data analytics can be used to circumvent this process through the use of the following tools. 
An analytical dashboard is an easy-to-read display used to provide insights into the data for decision-making purposes. In this case, a general claims management dashboard with denial rates and other related information is presented in a clear, concise format using graphs, tables, and other formats.
- Interactive reports
Interactive reports contain clickable options enabling viewers to select and filter a variety of criteria as needed. For example, a user can filter out a specific payer to only view their claim denials. This information can also be filtered down to a specific CPT code.
- Actionable claims data
The claims office benefits from viewing errors compared to reported data. Having this data on hand speeds up the correction and submission process.
The use of data analytics in claims processing has positive impacts on hospital revenue. Unfortunately, 55% of facilities reported that they do not yet have a system in place. However, 45% of this group stated they are planning to implement one.
How Data Analytics Benefit Patient Financials
Claims denials and the patient’s inability to pay their share have the most significant negative impact on hospital revenue. In 2017, health care systems and hospitals wrote off 90% more in uncollectible claim denials than six years previously.  The time consumed and costs generated in appeals are particularly taxing to hospital revenue. However, by applying data analytics to the process from the beginning, claims denials are significantly reduced as discussed below. 
The technology behind the verification of patient deductibles and co-insurance costs utilizes data analytics that precisely analyzes eligibility information and procedure pricing. This can result in a more accurate estimation of the patient’s financial responsibility, avoiding any surprise expenses that the patient is unable to meet.
- Confirming eligibility for the government and third-party insurance payers is more efficient with the use of data analytical tools. These tools can identify coverage for each patient with greater accuracy and safeguard against errors in identification.
- Presumptive analytics can assess if a patient qualifies for charitable assistance with their share of medical expenses. This process is especially useful for identifying self-pay and uninsured patients who need this type of financial aid.
- Analytics assist personnel in reducing the number of patient accounts that go to collections. Only those accounts without coverage that are flagged by analytics need follow up.
- The mapping of claims adjustment reason codes (CARCs) into analytic data systems helps capture, report, and share the information to build processes and reduce future denials.
Data Analytics and the Supply Chain
Supply chain spend is rapidly overtaking labor costs in hospitals. Approximately 30 percent ($25.4 billion) of all hospital spending in the US goes to supply chain overspend.  This is due, in large part, to supply chain data that is often siloed and inaccurate. Changes in reimbursement along with other external forces, including the COVID-19 pandemic, have made supply chain management increasingly more complex, but no less crucial to the successful operation of any hospital.
Benchmarking is critical to identifying opportunities for cost savings and data analytics makes it possible to find where a hospital is overspending in the supply chain. Data analytics also enables an organization to provide accurate price transparency, which is essential for delivering care according to current value-based payment models. A full understanding of costs can be obtained through the collection and analysis of real-time data, paving the way for supply chain optimization that will result in cost savings and better spend management. When it comes to the hospital supply chain, there are clear financial advantages to clean, comprehensive data.
Other Ways Hospitals Use Analytics To Save Costs
By using predictive analytics, hospitals are not only improving the patient care experience but optimizing resources. Here are other areas hospitals are applying analytics to help cut costs. 
- Using predictive analysis, hospitals identify which patients are prone to poor outcomes and are likely to be readmitted. Since CMS and other payers may impose readmission penalties, this measure can result in substantial cost savings.
- Patients who fail to arrive on time for scheduled procedures lead to revenue loss. By using predictive analytics with patients’ EHRs, hospitals can identify those that have an increased chance of missing their scheduled procedure. The hospital then double-books the same slot with a patient who is more likely to show up. This method increases productivity and avoids revenue losses.
- Delays in attending to patients in emergency rooms and critical care centers result in higher mortality rates, increased lengths of stay, and medical errors, which result in financial losses. Using predictive analysis, hospital administrators can pinpoint the inflow of patients at specific time intervals for staff optimization.
- As mentioned previously, the hospital supply chain benefits from using data analytics when determining what materials are needed on hand at any given time. Hospitals can proactively manage device inventory and supplies more efficiently.
The Current State of Data Analytics in Healthcare
The benefits of data analytics in the healthcare industry are undeniable. Unfortunately, hospitals today are faced with the common hurdle of inefficiency. According to Dr. Alan Weiss, Founder and CEO of Summit Consulting Group, healthcare organizations must be well-managed and efficient in order to be effective. Hospitals often work with a sense of urgency because they deal with matters of life and death. This means they may “ignore things that don’t immediately pertain to health and safety.” This may be unintentional or it may be out of necessity. The need for an experienced consultant becomes clear for hospitals that have not developed a strong data analytics process.
Even hospitals that have established the use of data analytics face the challenge of using their data to make real-time adjustments that lead to better cost savings. As a consultant, VIE Healthcare Consulting understands the importance of collecting, processing, and analyzing large amounts of data in a timely manner. This led to the development of Invoice ROITM, our automated and patented technology that reconciles thousands of line-item details instantly, eliminating manual processes so healthcare workers can focus on delivering quality care. Invoice ROITM gives hospitals the ability to reduce waste and manage spend more efficiently without reducing the quality of care. In fact, the revenue growth that is realized from real-time data analytics allows hospitals to spend more money, energy, and time on patient care and other initiatives that can drastically improve the patient outcomes.
Today’s hospitals face many challenges as they juggle operational efficiency with the delivery of quality health care. The application of data analytics across several areas in the hospital helps administrators make key decisions that result in increased revenue and decreased costs. Patients also benefit from data analytics as their care is better managed, and staffing and supply resources optimized.
VIE Healthcare Consulting has over 21 years of experience in assisting client hospitals with non-labor expense reduction. Our team has collectively saved clients $720 million through various cost savings and optimization processes.
Contact us for more information on how our consulting services can increase your hospital’s revenue and improve operating efficiency.