The revenue cycle is the engine that keeps a hospital running. Yet, many finance executives are not armed with the right information or the right tools to build a well-oiled machine. Given growing regulatory and financial pressures, the time is now to look under the proverbial "hood" and implement sustainable efficiencies that provide cost savings opportunities.
A 2009 report by Aberdeen Research found that the most effective way to manage rising operating costs and deliver high-quality care is to integrate disparate data sources and deploy business intelligence tools. The advanced business intelligence technology — data mining — allows healthcare systems to use their own data to proactively identify mistakes that lead to lost revenue, reduced cash flow, and unnecessary spending on manual processes.
Also known as predictive analytics, data mining uses statistical algorithms to identify relationships in data that make predictions about specific events, identify anomalies and target high-value actions that deliver the greatest and fastest return on investment.
Here are five ways in which data mining can enhance revenue cycle management.
1. Integrating hospital financial data is essential for data-driven business decision-making. The first step to applying data mining solutions to the revenue cycle is to aggregate and integrate fragmented hospital data sources (clinical, financial and patient) into one central repository called a data warehouse. The data warehouse will serve as the foundation for any and all data analytics, which drives evidence-based decision-making and supports higher-value care.
Data mining and data warehousing are gaining popularity in the healthcare industry because of the large volume of data stored in various systems and the need for data-driven business decisions. The data warehouse stores all the data points from the patient’s universe including account, claim, transaction, diagnosis, procedure, chargemaster, contract terms and readmissions details. These data must properly link on unique identifiers such as medical record numbers.
In a matter of minutes, the predictive models analyze years' worth of clinical and financial data to detect anomalies and trends and to identify revenue leaks from missed charges or payment variances. Because the model is customized to the individual hospital or health system, it can detect billing and reimbursement nuances specific to that facility, resulting in the greatest potential to identify missed revenue.
2. Automating functions of the revenue cycle increases revenue and staff productivity. The need for efficiencies and resource prioritization is critical to remaining competitive in a time where hospitals must do more with less. Data mining is the one technology that can more accurately and quickly automate follow-up processes across the revenue cycle, which leads to greater productivity — in some cases an increase of 150 percent — and, therefore, greater operating margins.
Conventional follow-up processes rely on cumbersome, manual steps where staffers must access patient data from various disparate systems in order to interpret and verify claims. Data mining technology automatically sifts through all billing, account, and clinical data 24/7 to flag as examples, missed charges, payment variances, denials, over charging, under coding and predictive follow up.
For charge integrity, data mining automates account categorization, identifies credit balance root-causes and recommends solutions. The process of automation can assist with finding lost revenue, improving compliance and increasing staff productivity to focus resources on difficult cases and revenue generating initiatives.
3. Real-time access to analytics reporting leads to proactive improvements. Traditionally, healthcare software is rules-based, retrospective and not driven from client-specific data, unfortunately resulting in the identification of problems and opportunities well after they have emerged. Reports generated from customized data mining algorithms incorporate all billing and patient data and provide intelligence that is both highly accurate and actionable. With one click of the mouse, staff can slice and dice all of their data down to the specific charge code or white blood cell count to identify root causes, trends, budget projections, patients likely to readmit, and productivity metrics with an extremely high degree of accuracy.
Armed with an analytics platform generated from data mining algorithms, a finance team from a 1,000-bed hospital learned for the first time that its contract management system missed $35 million in owed revenue over a two-year period. Staffers identified errors in the system by reviewing reports, but never before had the access to the data to confirm the scale or genesis of the significant breakdown in the contract management system. They have since discontinued use of the system and rely entirely on data mining technologies for the entire revenue cycle.
In another case, the algorithms identified that a specific payor was consistently reimbursing a provider at a rate lower than the agreed upon term of the contract. The hospital’s director of the revenue cycle shared the data-driven evidence with the payor and negotiated a more favorable contract rate overall given the insurer's error.
When armed with the right intelligence in a timely manner, finance teams can actually curb problems before they affect the bottom line.
4. Technology seamlessly monitors, tracks and reports on staff productivity. Hospitals are working with fewer and fewer resources, which means accurate and timely productivity reporting is key to ensuring proper resource prioritization. The key here is to measuring productivity correctly by having the right technology in place capturing and reporting on the information.
The first step is to shift from measuring account "touches" which is just tracking if a staff member did any activity on the account (e.g., a simple call, sending a follow up letter, etc.) to measuring volume of dollars resolved in a given time period.
In addition to measuring dollars collected an organization should also assign activities a score or points system — the more difficult the activity the higher the score. The model also allows for tracking and measuring of staff by hourly activities throughout the day. A hybrid of all three algorithmic approaches will result in the most effective way to measure staff productivity. Leveraging data mining and analytics is an efficient and effective way to measure dollars resolved, create and assign scoring logic, and track hourly activities.
5. Data mining provides the platform to help hospitals provide greater value care. A key advantage of data mining technology is that it can analyze data as well as serve as the infrastructure to capture, integrate and share critical intelligence between the business and clinical sides of a hospital. The data mining model can find patterns and correlations on specific patient populations to determine both outcomes and associated costs, ultimately revealing ineffective care and, therefore, wasteful spending that may be subject to reimbursement penalties or even denials.
For example, the data mining algorithms can predict which pneumonia patients are most likely to be readmitted and then identify care practices that can help prevent the readmission. Or, the analytics can be used first to identify and compare subsets of a Type 2 diabetes population, such as patients with the highest cost per visit versus those with the lowest cost per visit. Data mining can then pinpoint the practices (e.g., regular check-ups) that could prevent the need for higher-cost care.
Overall, data mining equips physicians with valuable clinical information they can use to make better decisions that result in more cost effective care — the end goal in this new age of value-based purchasing.
Mr. Merck leads the technical implementation teams at MethodCare. He brings 10 years of healthcare consulting and technology experience. Prior to joining MethodCare, Mr. Merck was with a national healthcare-consulting firm focused on revenue cycle improvement and patient flow solutions.
How to Collect More Often on Spine Cases
Webinar: How to Ensure a Profitable ACO Through the Revenue Cycle
A 2009 report by Aberdeen Research found that the most effective way to manage rising operating costs and deliver high-quality care is to integrate disparate data sources and deploy business intelligence tools. The advanced business intelligence technology — data mining — allows healthcare systems to use their own data to proactively identify mistakes that lead to lost revenue, reduced cash flow, and unnecessary spending on manual processes.
Also known as predictive analytics, data mining uses statistical algorithms to identify relationships in data that make predictions about specific events, identify anomalies and target high-value actions that deliver the greatest and fastest return on investment.
Here are five ways in which data mining can enhance revenue cycle management.
1. Integrating hospital financial data is essential for data-driven business decision-making. The first step to applying data mining solutions to the revenue cycle is to aggregate and integrate fragmented hospital data sources (clinical, financial and patient) into one central repository called a data warehouse. The data warehouse will serve as the foundation for any and all data analytics, which drives evidence-based decision-making and supports higher-value care.
Data mining and data warehousing are gaining popularity in the healthcare industry because of the large volume of data stored in various systems and the need for data-driven business decisions. The data warehouse stores all the data points from the patient’s universe including account, claim, transaction, diagnosis, procedure, chargemaster, contract terms and readmissions details. These data must properly link on unique identifiers such as medical record numbers.
In a matter of minutes, the predictive models analyze years' worth of clinical and financial data to detect anomalies and trends and to identify revenue leaks from missed charges or payment variances. Because the model is customized to the individual hospital or health system, it can detect billing and reimbursement nuances specific to that facility, resulting in the greatest potential to identify missed revenue.
2. Automating functions of the revenue cycle increases revenue and staff productivity. The need for efficiencies and resource prioritization is critical to remaining competitive in a time where hospitals must do more with less. Data mining is the one technology that can more accurately and quickly automate follow-up processes across the revenue cycle, which leads to greater productivity — in some cases an increase of 150 percent — and, therefore, greater operating margins.
Conventional follow-up processes rely on cumbersome, manual steps where staffers must access patient data from various disparate systems in order to interpret and verify claims. Data mining technology automatically sifts through all billing, account, and clinical data 24/7 to flag as examples, missed charges, payment variances, denials, over charging, under coding and predictive follow up.
For charge integrity, data mining automates account categorization, identifies credit balance root-causes and recommends solutions. The process of automation can assist with finding lost revenue, improving compliance and increasing staff productivity to focus resources on difficult cases and revenue generating initiatives.
3. Real-time access to analytics reporting leads to proactive improvements. Traditionally, healthcare software is rules-based, retrospective and not driven from client-specific data, unfortunately resulting in the identification of problems and opportunities well after they have emerged. Reports generated from customized data mining algorithms incorporate all billing and patient data and provide intelligence that is both highly accurate and actionable. With one click of the mouse, staff can slice and dice all of their data down to the specific charge code or white blood cell count to identify root causes, trends, budget projections, patients likely to readmit, and productivity metrics with an extremely high degree of accuracy.
Armed with an analytics platform generated from data mining algorithms, a finance team from a 1,000-bed hospital learned for the first time that its contract management system missed $35 million in owed revenue over a two-year period. Staffers identified errors in the system by reviewing reports, but never before had the access to the data to confirm the scale or genesis of the significant breakdown in the contract management system. They have since discontinued use of the system and rely entirely on data mining technologies for the entire revenue cycle.
In another case, the algorithms identified that a specific payor was consistently reimbursing a provider at a rate lower than the agreed upon term of the contract. The hospital’s director of the revenue cycle shared the data-driven evidence with the payor and negotiated a more favorable contract rate overall given the insurer's error.
When armed with the right intelligence in a timely manner, finance teams can actually curb problems before they affect the bottom line.
4. Technology seamlessly monitors, tracks and reports on staff productivity. Hospitals are working with fewer and fewer resources, which means accurate and timely productivity reporting is key to ensuring proper resource prioritization. The key here is to measuring productivity correctly by having the right technology in place capturing and reporting on the information.
The first step is to shift from measuring account "touches" which is just tracking if a staff member did any activity on the account (e.g., a simple call, sending a follow up letter, etc.) to measuring volume of dollars resolved in a given time period.
In addition to measuring dollars collected an organization should also assign activities a score or points system — the more difficult the activity the higher the score. The model also allows for tracking and measuring of staff by hourly activities throughout the day. A hybrid of all three algorithmic approaches will result in the most effective way to measure staff productivity. Leveraging data mining and analytics is an efficient and effective way to measure dollars resolved, create and assign scoring logic, and track hourly activities.
5. Data mining provides the platform to help hospitals provide greater value care. A key advantage of data mining technology is that it can analyze data as well as serve as the infrastructure to capture, integrate and share critical intelligence between the business and clinical sides of a hospital. The data mining model can find patterns and correlations on specific patient populations to determine both outcomes and associated costs, ultimately revealing ineffective care and, therefore, wasteful spending that may be subject to reimbursement penalties or even denials.
For example, the data mining algorithms can predict which pneumonia patients are most likely to be readmitted and then identify care practices that can help prevent the readmission. Or, the analytics can be used first to identify and compare subsets of a Type 2 diabetes population, such as patients with the highest cost per visit versus those with the lowest cost per visit. Data mining can then pinpoint the practices (e.g., regular check-ups) that could prevent the need for higher-cost care.
Overall, data mining equips physicians with valuable clinical information they can use to make better decisions that result in more cost effective care — the end goal in this new age of value-based purchasing.
Mr. Merck leads the technical implementation teams at MethodCare. He brings 10 years of healthcare consulting and technology experience. Prior to joining MethodCare, Mr. Merck was with a national healthcare-consulting firm focused on revenue cycle improvement and patient flow solutions.
More Articles on Revenue Cycle Management:
Strategies to Help Hospitals Break Even on MedicareHow to Collect More Often on Spine Cases
Webinar: How to Ensure a Profitable ACO Through the Revenue Cycle