Hospital systems tap into big data: Actionable analytics optimize enterprise efficiencies, improve revenue cycle management

With increased mergers and acquisitions, hospitals, hospital systems and Integrated Delivery Networks face significant challenges to aggregate and compare colossal datasets, identify problems, and correct the issues.

They must retrieve, review and compare data -- no matter the size, data incompatibility or platform complexity.

Further confounding these challenges is the inability of current systems to alert decision-makers to problems in a timely manner or guide them in devising rapid interventions that correct the inefficiencies, denials and revenue leakage that impact the bottom line.

The sheer magnitude of data is prompting these healthcare organizations to recognize this deficit in their existing systems. As they learn about the value and benefits of actionable analytics to address and solve problems in virtually every aspect of operations, they are adopting new technology that is now available. A key benefit is that these new platforms overlay current transactional systems to deliver a cleaner, smarter and cost-effective solution. Often by adding an actionable auditing system overlaying the current transactional system, replacement of the transactional system does not become necessary, with the high program cost and subsequent cost of interruptions and loss of cash.

The consolidation of data required to perform actionable analytics, allows astute hospital leaders to efficiently retrieve, compare, reconcile and analyze all data through one platform. Without a large upfront investment and without discarding their existing systems, puts organization management in control of aggregating data, and detecting/resolving issues that impact revenue integrity, as well as clinical and operational performance.

Actionable Analytics: opportunity to quickly act upon exceptions to the norm.

An actionable analytic platform triggers alarms and provides a workflow to also execute actions on target systems. It can also automate the assigning of responsibility.

Performs bi-directionally: pulls the data from a system and pushes data to that system – with the term “data” representing anything such as an action, writing a file to a specific file system or other activity.

Address Three Varieties of Data

Healthcare enterprises have three varieties of physical data located within their numerous information systems, each characterized by their data types and purpose within the organization.1

Transactional Data - supports the daily operations of an organization

Transactional data supports the on-going operations of a healthcare organization and is included in the application systems that automate key business processes, including intake, service, diagnostic testing, procedures, purchasing, billing, accounts receivable and accounts payable.

Typically, transactional data refers to the data that is created and updated within the operational systems. Examples include time, place, price, contracted price and payment methods. The systems that produce these transactions are usually efficient and effective in all aspects of getting the transaction completed.

Analytical Data - supports decision-making, reporting, query, and analysis

Analytical data is the numerical values, metrics and measurements that provide business intelligence and support organizational decision making. Analytical data is characterized as being the facts and numerical values in a dimensional model.

Normally, the data resides in fact tables surrounded by key dimensions, such as patient, service code, account, location, and date/time. However, analytical data are defined as the numerical measurements rather than being the describing data. This data is usually extracted from a transactional system, but is made available independently from the transaction that it was used for.

In a good transactional data set, all data is stored in a format that makes it usable with every other piece of data. Generally, analytic data only has meaning when it is related to other pieces of data.

Master Data - represents the key business entities upon which transactions are executed and the dimensions around which analysis is conducted

Master data plays a key role in the core operation of a business, and refers to the key organizational entities that are used by several functional groups, which are typically stored in different data systems across an organization. This data also represents the business entities around which the organization’s business transactions are executed and the primary elements around which analytics are conducted.

Master data is persistent, non-transactional data utilized by multiple systems that defines the primary business entities, and includes information about customers, products, physicians, employees, inventory, suppliers and sites.

Using traditional analytics methods an analyst finds meaningful relationships in all of this data, an analyst must validate the data by checking reality, measuring the data against a norm and reporting the variance to operational personnel for changes in process.

For example, if overtime is deemed too high, using extracted data from the payroll system (transactional system) an analysis is made determining that the problem stems from housekeeping. A manager receives a report about this and limits overtime for housekeeping. This is contrasted to actionable analytics.

Actionable: Meaningful Data Triggers Action

Actionable analytics in a hospital enterprise requires the ability to process massive amounts of data, very quickly, automatically testing data in real time, against norms or pre-determined values. In this way, variances that jeopardize the ability to put out a clean claim, identify non-compliance with contractual requirements, or threaten clinical performance can be identified quickly and dealt with.

Transactional data serves as raw material, and makes analytics possible. The key to success lies in turning analytics data into tangible results, i.e., actionable analytics. Organizations define the rules and set validations and when linked to actionable data create the ability to act immediately.

The most effective, efficient approach to data at the enterprise consolidation level stems from completely merging all data from multiple sources, so that comparable data has the same name and format.

By merging the data, users can create the ability to answer consolidation questions, such as “What was total revenue throughout the enterprise?” From there, organizations can drill down to see all the component parts that make up that revenue number.

The ability to merge data is a powerful capability, and it must be done fast. Once merged and displayed, the data must be presented in a highly flexible way. A comprehensive data capture should also be accurate enough for consolidated reports or alerts when an issue arises.

Keep in mind that transactional systems are more efficient at production work, so it would not make sense to consolidate the data and then perform transactional work, or run a centralized output process around billing, collections and payroll.

Data at the Macro Level

Healthcare system organizations should look for the most cost-effective way to consolidate data, leaving the processing tasks at the hospital level. This allows an enterprise-level executive to compare and contrast hospitals, drilling down into any detail using a common language.

For example, it is probably more efficient for a hospital system to leave payroll processing in each hospital in a transactional system, and use analytics from a platform, like RAID HEALTHCARE, to extract the payroll data from each hospital. The enterprise manager can look at enterprise payroll costs, then drill down into a departmental cost, continue down into “job category,” and then eventually down to an employee category, if required -- unencumbered by which hospital or what operating system the hospitals are using.

Transactional systems perform 95 percent of a hospital’s tasks, while an actionable analytics platform looks for the exceptions, and manages the correction. A growing number of hospital enterprise managers appreciate the unique qualities of unique platforms that are now available -- and perform in multiple and varied clinical, financial and operational areas that not only include revenue cycle management but also -- for auditing length of stay (LOS), infection control, home health -- to name a few. Even the best transactional systems need to be audited on a continuous basis and “tuned up.”

Sophisticated Analytic Tools in Action

Today, only the most sophisticated analytic tools can automate action either directly or through alarms. Data can be measured directly, as it is created, so action can occur before a problem manifests.

Taking the earlier example of overtime hours, by using actionable data, the actual hours are extracted from the time clock, and taken in consideration with the scheduled hours. A predictive model of overtime sounds an alarm so managers can stop the problem before it manifests. It can set off an alarm as the employee checks in for the shift.

This example is rather straight forward and even self-contained within some transactional systems. In contrast, sophisticated action analytics systems allow users to set up alarms using any data from any transactional system to set up sophisticated alarms. Action on controlling LOS, for instance, requires data from multiple transactional based sources.

Analytic data is being generated from multiple transaction systems in real time that when used in logic statements, and predictability algorithms, can tell managers when LOS goals are in jeopardy by patient or hourly -- any desired parameter. Automated corrective actions can go into place, when safe and appropriate.

For example, if a diagnosis is changed, and tests are required, but no orders are received, an alarm is sounded. Orders are then expedited, but an alarm is again sounded because the current schedule of tests will need to be expedited or jeopardize LOS. At the same time, an alarm triggers notification to the revenue cycle team to change pre-certification to the payer, preventing a denial of payment.

Actionable analytics make it possible for hospital organizations to not only extract multiple transactional data, but to also relate it, find discrepancies and act to solve them. It’s important to keep in mind that how the problem is solved represents a defined process that will help resolve issues in a controlled way.

What to Look For in an Actionable Data Platform

Healthcare organizations should look for an efficiency platform that overlays existing systems to help them compare massive amounts of data across their total enterprise, detect exceptions and problems, and guide interventions to improve efficiency that optimizes financial, clinical and operational performance.

Ideally, the platform will demand substantially lower upfront costs it tunes an existing transactional revenue cycle system rather than having to replace it, and by not replacing your current transactional system there is no disruption or retraining of staff required.
Hospital organizations require customizable, exception-based triggers to identify deviations from norms that enable them to reduce errors and denials, improve efficiency and productivity, meet compliance requirements and ensure financial viability.

Look for a platform that is powered with unique actionable analytics, overlays rather than replaced existing transactional and operational systems, and functions as a permanent, protective 24/7 auditing and reporting ‘umbrella’ that makes data comparable.

By choosing the right actionable analytics platform, hospital leaders can rapidly take action while generating significant ROI within months of implementation.

About EFFY
Functioning as a permanent, protective 24/7 auditing and exception reporting “umbrella,” EFFY makes data comparable and actionable, enabling users to correct issues that compromise financial viability, and clinical and operational performance. EFFY empowers hospitals, hospital systems and Integrated Delivery Networks to retrieve, review and compare massive amounts of operational, clinical and financial data across their total enterprise – and trigger actions upon it, no matter the size, data incompatibility or platform complexity. Visit http://effyhealthcare.com.

1BI Insider; Types of Enterprise Data; June 2, 2011; http://bi-insider.com/posts/types-of-enterprise-data-transactional-analytical-master/; accessed September 28, 2017.

The views, opinions and positions expressed within these guest posts are those of the author alone and do not represent those of Becker's Hospital Review/Becker's Healthcare. The accuracy, completeness and validity of any statements made within this article are not guaranteed. We accept no liability for any errors, omissions or representations. The copyright of this content belongs to the author and any liability with regards to infringement of intellectual property rights remains with them.

© Copyright ASC COMMUNICATIONS 2017. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.

 

Top 40 Articles from the Past 6 Months