Welcome to the MedMetrics Blog

The MedMetrics blog provides comments and insights regarding the world of Workers’ Compensation, principally, issues that are medically-related. The blog offers viewpoints regarding issues affecting the industry written by persons who have long experience in the industry. Our intent is to offer additional fabric, perspective, and hopefully, inspiration to our readers.

Search The MedMetrics Blog

Tuesday, December 13, 2016

Power-down WC Medical Costs by Identifying Comorbidities Early and Often

by Karen Wolfe

It just makes sense. When an injured worker has an underlying medical condition, recovery is compromised in one way or another. The case will be more complex and it is likely to have a longer duration, higher severity scores, and cost more. A recent article published by Denise Johnson in Claims Journal describes how identifying comorbidities early can help control Workers' Comp claim costs.[1]

Common comorbidities
Johnson identifies common comorbidities to watch for including obesity, diabetes, hypertension, and depression. Certainly these are the most common conditions that impact claims, yet there are many more.

For instance, a pregnant injured worker will require careful medical management. Pregnancy should be considered a comorbidity and managed closely. Other examples include HIV, hepatitis C, cardiac disease, and chronic pulmonary disease. The important thing is to identify the comorbid conditions in claims so they are monitored carefully and referred to nurse case management early. Nevertheless, discovering underlying comorbidities can be hit or miss.

Diagnoses in the data
Comorbid diagnoses can be found in the data--usually. Treating doctors can include the comorbid diagnosis in the list of diagnoses on the bill, but sometimes they do not. They might consider a general health problem irrelevant to a Workers' Comp claim, yet it might be critical.

Timing in the data
Reviewing diagnoses in a claim by the date they were added can be revealing. A diagnosis such as diabetes or obesity can appear weeks after the injury occurred and well into the treatment process. Moreover, when in the course of treatment a diagnosis appears can be enlightening and deserves attention.

Some comorbid conditions appear late in the data because they are newly discovered or the treating doctor becomes aware of them during the course of treatment. An example is discovering a diagnosis for a mental disorder in the data long after the actual injury.

A diagnosis of a mental disorder might result from delayed or unsuccessful recovery and the patient acts out in frustration. Or the late diagnosis might imply previously unrecognized psycho-social factors. Nevertheless, the data should be monitored continually to tag any diagnosis that creeps into the claim picture at any point.

Pre-emptive information
When comorbid, or any apparently unrelated diagnosis appears later in a claim, it could be a pre-emptive signal of poor response to treatment or even impending litigation. Monitoring the data continually to uncover new diagnoses is essential to avoid missing subtle issues.

Smart data
Data can be made smarter by the format and mechanism in which it is presented to those managing the claim. The manner in which diagnostic data is portrayed for claims reps and medical managers can be not only informative, but actionable. An example is portraying all diagnoses by the date they were added to the claim in bills. Such views can disclose subtleties about what is occurring in the treatment process and inform those managing the claim of ensuing problems.

Early intervention
Identifying comorbidities and other troublesome conditions in claims using predictive analytics and continuous data monitoring leads to early intervention and best results. For additional perspectives on this topic, please see, "Analytics-informed Early Intervention Drives Best Outcomes". [2]
Karen Wolfe is the founder and President of MedMetrics®, LLC, a Workers’ Compensation, analytics-informed medical management and technical services company. MedMetrics offers online apps and alerts that link analytics to operations, thereby making them actionable and measureable. We don’t do medical management. We make your medical management more powerful. karenwolfe@medmetrics.org

[1] Johnson, D. Experts Say Identify Comorbidities Early to Control Workers’ Comp Claims Costs. Claims Journal. 09-14-2016. http://www.claimsjournal.com/news/national/2016/09/14/273487.htm?_lrsc=bc8326a7-6188-4d5c-a372-994cffa2ecd5
[2] Wolfe, K. Analytics-informed Early Intervention Drives Best Outcomes. http://medmetrics.blogspot.com/2016/11/analytics-informed-early-intervention.html

Tuesday, November 8, 2016

Analytics-Informed Early Intervention Drives Best Outcomes

by Karen Wolfe

Early medical management intervention in Workers’ Compensation drives better outcomes. When a problem is discovered early, finding a positive solution is quicker, easier, and more effective. Moreover, predictive analytics-informed early intervention is even more powerful.

Past is prologue
Even though early medical management intervention is known to work, it is not always pursued aggressively. To be most effective, knowing what to look for in open and active claim data is key. 

The past is a preface to the future. Analyzing historic data to identify the kinds of conditions that have been costly to the organization reveals what to look for going forward. Some conditions are generally known. Examples are comorbidities that accompany injuries and certain problematic or severe injury or illness types. Yet, other less obvious, but troublesome conditions and preemptive situations must be teased out of the data using predictive analytics methodologies.

Predictive analytics
Predictive analytics is a methodology used to identify historic claim conditions that are likely to be troublesome in future claims. Conditions in claims that have led to high costs and poor outcomes in the past are isolated. Once the conditions are pinpointed a system is designed to continually monitor the data going forward and to notify adjusters and medical case managers when those conditions occur.

Continuous data monitoring
A practical method for uncovering problematic claims is to electronically monitor the data to reveal dicey conditions as they occur. Technology is used to find the claims that bear high risk conditions whenever they occur throughout the course of the claim. All claims are monitored continuously, so nothing is missed. Even subtle claim migration is exposed.

Data monitoring for conditions discovered through predictive analytics is powerful. Yet, the next step is also essential. Organizations that implement an analytic process for identifying risky claims early stand to overlook the entire benefit unless they also structure procedures for intervention. Importantly, the appropriate persons must be notified immediately and they must carry out the organization’s recommended procedures.

Claims adjusters are often alerted first. However, when medical case managers are alerted as well, the two can execute intervention procedures collaboratively. Claims adjusters may neglect to refer to medical case management as early as they could. But when the automatic referral to medical case management is made simultaneously by the system, that issue is eliminated.

Collateral opportunity
When claims adjusters receive an alert of adverse conditions developing in a claim, they know reserves should be adjusted. Predictive analytics can also inform adjusters of the probable ultimate medical reserve amount for that claim based on history, thereby making reserving easy, timely and accurate.

Measured success
A bonus advantage of an early intervention process informed by predictive analytics is the ability to objectively measure success. At claim closure, costs and other outcomes can be measured and compared with those for similar claims in the past. The savings effects of early problem identification and intervention by claims reps and medical case managers are posted for constituents as objectively measured savings.

Simply stated, early intervention is more effective than later intervention. Damage control is far more achievable. The problems have not yet morphed into catastrophic or irreversible states. Predictive analytics-informed systems and data monitoring can be established to automate tagging problem conditions in claims as they occur. Those who will intervene early are alerted. Finally, reporting objective measurements of success is the payoff.

Karen Wolfe is the founder and President of MedMetrics®, LLC, a Workers’ Compensation, analytics-informed medical management and technical services company. MedMetrics offers online apps and alerts that link analytics to operations, thereby making them actionable and measureable. We don’t do medical management. We make your medical management stronger. karenwolfe@medmetrics.org


Tuesday, October 4, 2016

How to Make Frontline Workers Smarter

by Karen Wolfe

Concern has been expressed in the Workers’ Comp industry about its aging workforce. Workers, especially claims reps with years of experience are retiring in greater numbers leaving a semi-vacuum in their place. This leads to a pressing need for training and providing tools that will help workers make smart decisions well before they earn seniority. Analytics is one of the tools that can make workers smarter.

Most people say they want analytics. Yet, many are not sure what analytics is or what benefits will be gained. Some anticipate operational disruption and fear the cost, neither of which is necessarily well-founded. Whether it is because of lack of knowledge or fear of change, many still hold back. To learn more about how analytics and how it can impact medical management in Workers’ Comp, please read, “Making the Most of Analytics to Improve Medical Outcomes”[1] 

Why analytics?
The reason for implementing analytics of any variety is to gain knowledge about the organization by analyzing its data. The knowledge gained should be actionable knowledge, meaning it supports intelligent action and decisions while enlightening the way forward.

Learning more about the business provides information for decision support which can be applied in an organization from long term planning to transactional decision-making by frontline workers. Transactional decision support at the operational level is where knowledge gained from analytics makes workers smarter.

Transactional decision support
Analytics-informed transactional decision support is linking knowledge gained through analytics with operations. Analytics will have no impact on the organization, its clients, or its workers unless the information is driven to, and acted upon at the operational level. Moreover, the information must be presented to workers in a fashion that guides them to appropriate action.

The way workers receive information determines how the knowledge gained through analytics is acted upon. In other words, the system designed to deliver appropriate knowledge to the right workers at the right time is crucial. Information designed to generate action can be delivered at the right time in the form of electronic alerts. But alerts must contain all the information needed to take appropriate action, the correct action.

Smart information delivery
For example, alerts transmitted to claims reps prompting them to adjust medical reserves in a claim must contain all the information necessary for adjusting reserves accurately. Claim background information as well as the conditions found through claim data monitoring that generated the alert should be portrayed for them. Importantly, to enlighten claims reps further, the alert should display the probable ultimate medical reserve amount for the claim based on predictive analytics.

Similarly, information should be delivered to others in the organization who would benefit from the knowledge in managing the claim. The conditions that initiated the alert to claims reps regarding the need for medical loss reserve adjustment are often appropriate for nurse case management involvement as well. The system designed for information delivery can automatically notify nurse case managers along with claim reps, thereby coordinating initiatives leading to early claim resolution.

Consistent response
Analytics-informed transactional decision support transmitted to the operational level accrues additional benefits. Not only are frontline workers smarter, but responses are more timely and consistent leading to credible measures of savings.

Measures of savings
Continuing the example of using predictive analytics to alert for medical loss reserving, even more value can be gained. Objective medical savings can be calculated at claim closure based on reserve projections and real-time proactive claims handling by claims reps and coordinated medical intervention by nurses. Early intervention by informed workers will lead to measurable savings that can be communicated to clients and other constituents.

Smarter workers
Frontline workers can be made smarter and more efficient through technology. Driving information gained from predictive analytics to the transaction level makes workers more accurate and efficient. Even minimally experienced workers given the right information at the right time will make accurate and timely decisions. Moreover, experienced workers will elevate their accuracy and efficiency, thereby saving time and money for the organization while improving claim outcomes.

Karen Wolfe is the founder and President of MedMetrics®, LLC, a Workers’ Compensation, analytics-informed medical management and technical services company. MedMetrics offers online apps and alerts that link analytics to operations, thereby making them actionable and measureable. karenwolfe@medmetrics.org

[1] Making the Most of Analytics to Improve Medical Outcomes. WellComp Managed Care Services.

Wednesday, September 7, 2016

How to Develop Analytics-Informed Operational Solutions

by Karen Wolfe

A recent article published by Safety National summarizes a panel discussion from WCI’s 2016 Workers’ Compensation Educational Conference. The panel’s message reiterated that Workers’ Compensation is a data-driven industry and now massive data is available that can be used to improve experience and outcomes.[1]

Data as driver
Certainly the Workers’ Comp industry has generated loads of data and it will provide operational solutions going forward. Everyone seems to agree, data will drive improved performance and outcomes. In fact many believe big data will bring significant change to the way organizations work. But few are saying exactly how to make that happen.

Actionable data
Much is said about data and what it will do, but little is said about how to make data actionable. The article states, “A large benefit of this data is that we have a better opportunity to get great benchmarks.[2]” Yes, but even when benchmarks are identified, what will they do? How will benchmarks impact operations? Benchmarks by themselves cannot change process or outcomes. Data alone will never deliver operational solutions. It’s all about how the data is regrouped and repurposed, then how the new information is delivered to those who will actually affect the change.

Plan design
Years ago, a bridge teacher said repeatedly, “A bad plan is better than no plan at all.” The same applies to developing actionable data and operational solutions. The first and most important initiative is to develop an overall design or plan. What data is available and what information is needed? What results are needed? Who will receive the information and what will be done with it? How will the information be acknowledged and what accountability will be implemented? The plan should be comprehensive and detailed, applying considerable resources.

Identify and Collect
The plan should identify the data needed and where it can be found. What data will likely inform the desired results? Collect, organize, and integrate the data according to the plan. As a part of this process, anticipate the need for data cleansing. Incorrect or incomplete data will not lead to the desired result and unfortunately, much of the data in the Workers’ Comp industry is wanting in this regard.

Data quality
One of the unfortunate facts in the Workers’ Comp industry is that its data, while abundant, is widely inaccurate and incomplete. Such data will not lead to solutions, but to frustration, delay, and often, project termination. Know in advance the data will need cleansing and strengthening. Include this function and the necessary resources to fortify and enrich the data in the plan design.

Execute the plan by integrating, organizing, and analyzing the data. Derive the desired information from the data, including benchmarks and other noteworthy facts about claims, processes, and outcomes. There is no limit to the possibilities, and adequate time and resources must be applied to this phase. So prioritize.

Halfway there
Don’t stop now. This is only the halfway point. Now operations must be informed so that solutions are realized.
Develop the mechanisms that will automatically deliver the right information to the
right persons at the right time.
Moving the newly-found information quickly and easily to those doing the work is the only way to impact operations, processes, and outcomes.
Current information
When the information reaches the appropriate persons, it should be as current as possible. Delayed or dated information may be inaccurate and need validating before acting upon it. Worse, if those receiving the information do not trust its validity, they will not act on it at all, thereby diminishing the entire project.
Easy does it
Those who receive the information should find it easy to receive and to act upon. This is how the work of those in the trenches is elevated and improved, thereby fostering operational solutions and improved outcomes. Moreover, collateral information supporting accurate decision-making should be portrayed along with the analytics-derived information.
Management’s job is to make sure the operational goals of the project are achieved and they stay in place. One way to incorporate accountability is to create a programmatic audit trail. Generate an electronic record that details what information was sent, to whom it was sent, and regarding what. At any point, management can spot-check the process.
Measuring success
As with any major project, success must be monitored and measured. Corrections and improvements can be implemented. The easiest way to measure success is to compare performance before and after project implementation. Carve out elements of process and outcomes and measure the difference before and after implementing analytics-informed solutions.
Analytics-Informed operational solutions are powerful. Implementing them appropriately will lead to efficiency, accuracy, profitability, and significantly improved outcomes, but only if the planning, execution, and commitment is considerable.

Karen Wolfe is the founder and President of MedMetrics®, LLC, a Workers’ Compensation, analytics-Informed medical management and technical services company. MedMetrics analyzes the data and offers online products that link analytics to operations, thereby making them actionable and measureable. karenwolfe@medmetrics.org

Friday, July 8, 2016

The Secret Power of the NPI

by Karen Wolfe

This is a David and Goliath story. It’s about how the seemingly insignificant NPI code can fight medical fraud and positively impact effective Workers’ Comp medical management. Many in the industry consider the NPI irrelevant. Yet it is a powerful factor in medical management and medical fraud detection.

The NPI is the National Provider Identifier assigned by CMS (Centers for Medicare and Medicaid) to individual medical providers and organizations that deliver medical services. It is required on bills for Medicare and Medicaid. Individual medical providers and medical groups must include their NPI on all bills submitted. 

If the NPI is required for Medicare and Medicaid reimbursement, it follows probably all medical doctors have a NPI number from CMS that uniquely identifies them. The problem is that many Workers’ Compensation payers do not ask for the NPI, do not require it, and even when the NPI is available, do not record it or transfer it to the next level. 

State requirement
Some, but not all states require the NPI on Workers’ Comp bills. However, even if it is added to the bill, it often goes no further.

Why bother?
The value of the NPI is that it uniquely identifies individual medical doctors. It carves out individual treating physicians in groups, organizations and facilities. Without the NPI associated with individuals, all those in a group are lumped together under the organization’s NPI or, worse, the entity’s Tax ID. This matters. The assumption is all members of the group practice exactly the same. But they do not.

Distinguish individuals
The ability to parse individuals from groups in the data is essential to fair performance analysis. Individual differences evidenced in the data can be distinguished, even when associated with a group with individual NPI’s. This is essential to creating quality preferred provider networks and directories. It is also indispensable for leveraging the data to create a teaching platform for improving provider performance in Workers’ Compensation.

Behavior change
Physicians should be given the opportunity to see themselves portrayed in graphic reports comparing their performance to others like them. By nature, they are high achievers and they want to show well. The graphic presentations are targets or guides for improvement. 

Simply paying attention to a treating doctor in this objective manner will result in behavior change!  Using the comparative data is invaluable, however, success depends on accurately identifying individuals in the data using the individual NPI.

Another valuable use of the NPI is to assign medical specialties to individuals. Professional specialties can be obtained electronically from CMS databases using the NPI. Specialty is yet another data element missing in much of the bill review and claim system data. If the NPI number is available, specialties can be derived. 

Specialties are important so that treating doctors are grouped with other doctors who are similarly prepared and licensed. The argument from doctors that they only treat the more difficult cases is nullified when they are compared only to others in their specialty. The best example is pain management specialists who really do treat the more difficult cases. Their performance should always be compared to other pain specialists.

Fraud by NPI
Unfortunately, there are those who twist the positive aspects of the NPI for fraudulent purposes. Close examination of the data reveals less reputable medical doctors and other providers obtain multiple NPI numbers, using them in different locations or situations to deliberately obfuscate the data.

When multiple NPI numbers are fraudulently used, the door is open to undetectable duplicate billing. Systems cannot recognize overall performance for the individual because their performance is fragmented across multiple NPI’s. In order to accurately analyze performance for an individual, all treatment incidences should be combined for one practitioner, thereby creating a critical mass of data for that individual.

Much ado
While some will think the focus on NPI is much ado about nothing, it is not. Individual NPI numbers on all medical bills is essential. Payers should insist on it. In fact, reimbursement should be withheld until the correct information is included on the bill as is done in Medicare. 

Impact on medical management
Treating doctors not only drive direct medical costs, but also indemnity costs, return to work, and disability ratings at the end of the claim. They can also influence legal involvement. Consequently, finding the best doctors and avoiding the bad ones is crucial. 

The way to determine who should be included in quality medical provider networks is to analyze past performance based on the data. The only way to accurately analyze performance is to identify individual treating doctors in the data and evaluate their performance across multiple claims based on the relevant performance factors. Correct NPI numbers included on medical bills are essential.

What to do
Workers’ Compensation payers must require correct individual NPI numbers on all medical bills. This is not an outrageous demand and does not add to costs. However, it does require attention to the matter. The benefits are too great to miss this simple, yet powerful opportunity.

The simple little NPI is a powerful element in Workers’ Compensation medical management. It is the David that can effectively and affordably fight the medical fraud Goliath.

Karen Wolfe is the founder and President of MedMetrics®, LLC, a Workers’ Compensation, analytics-Informed medical management and technical services company. MedMetrics offers online apps that link analytics to operations, thereby making them actionable and measureable. karenwolfe@medmetrics.org


Thursday, June 23, 2016

Make Your Data a Work-in-Process Power Tool

By Karen Wolfe

Heard recently, “Our organization has lots of analytics, but we really don’t really know what to do with them.” This is a common dilemma. Analytics (data analysis) are abundant, they are presented in annual reports and published in colorful graphics. Too often the effort ends there. Nice information, but how does it change operational flow, claim outcomes and profitability?

Obviously, the basic ingredient for analytics is data. After that comes skill, ingenuity, and creativity. Business intelligence and knowledge are severely limited without data. Fortunately, the last thirty years have been primarily devoted to data gathering.

Data evolution
Over the past thirty years or more, all industries have evolved through several phases in data collection and management. Main frame and mini-computers produced data and with the inception of the PC in the 80’s, data gathering became the business of everyone. DOS systems were clumsy and there were significant restrictions to screen size and data volume.

Recall the Y2K debacle caused by limiting  the year to two characters instead of four. The two digit year was made necessary in early computing because of restricted capacity.

Happily for the data gathering effort, progress in technology has been rapid. Advancement was enhanced first by local and wide area networks, then by the Internet along with ever more powerful hardware and lower costs. Data gathering has been overwhelmingly successful.

Big data
Now we have truckloads of data, often referred to as Big Data. In fact, a new industry has developed around understanding and managing huge data volumes. Once Big Data is corralled, analytic possibilities are endless. 

The Workers’ Compensation industry has also collected enormous volumes of data. Now, much is being done in the industry to actualize the analytics to produce knowledge that support reductions in costs and improved outcomes.

Imbed analytic intelligence
The best way to apply analytics in Workers’ Compensation is to create ways to translate and deliver intelligence to the operational front lines, to those who make critical decisions daily. Knowledge derived from analytics cannot change processes or outcomes unless it is imbedded into the work of adjusters, medical case managers, and other key personnel. These professionals make decisions that affect the course of claims and they need electronic knowledge tools to assist them.

Consulting graphics for guidance is cumbersome, interpretation is uneven or unreliable, and the results cannot be verified. Therefore, intelligence must be made easily accessible and easy to interpret and apply. Front line decision-makers need online tools designed to support decisions and direct actions.

Electronic monitoring
To effectively imbed analytic intelligence into operations, all claims data must be continuously monitored electronically. Data in claims must be monitored continuously so the system can identify claims that contain conditions cautioned by the analytics. The interpreted information is then linked to operations.

By electronically monitoring all claims for high risk events and conditions informed by analytics, high risk and migrating claims cannot slip through the cracks.

Personnel can be alerted of all claims with risky conditions identified through analytics. Additionally, the analytic delivery system should automatically document itself.

The system that is developed to deliver analytic knowledge to operations should automatically self-document. That is, it should keep its own audit trail to record to whom the intelligence alert was sent, when, and why.

Without self-documentation, the analytic delivery system lacks authenticity. Those who receive the information cannot be held accountable for whether or how they acted on it. When the system automatically self-documents, those who have received the information can be commended for, or held accountable for their part. Management is able to review current status at any time.

A system that is self-documenting can also self-verify, meaning results of delivering analytics to operations can be measured. Claim conditions and costs can be measured. Moreover, further analyses can be executed to measure what analytic intelligence is most useful, in what form, and importantly, what action responses generate best results.

The analytics-informed knowledge delivery system monitors all claims data, identifies claims that contain risk elements, and creates knowledge tools for front-line workers. The data becomes a work-in-process information and decision-support tool while analytics are linked directly to outcomes and savings are objectively measured.

Karen Wolfe is the founder and President of MedMetrics®, LLC, a Workers’ Compensation, analytics-Informed medical management and technical services company. MedMetrics offers online apps that link analytics to operations, thereby making them actionable and measureable. karenwolfe@medmetrics.org


Monday, May 23, 2016

7 Reasons You Really, Really Want WC Medical Analytics

by Karen Wolfe
In a recent post, Joe Paduda stated, “The workers’ comp, and, for that matter, the entire property and casualty insurance industry, is chronically systems-poor.  While other industries view IT as a strategic asset, continually investing billions in IT, WC/P&C considers IT an expense category to be mined for pennies to add to earnings per share.”[1]

As one who has worked on the vendor IT side of the Workers’ Comp industry for decades, I know for a fact Joe is exactly right. Nevertheless, both inside and outside change is impacting the industry—compliance requirements and how IT is perceived, financed, and implemented.

Moreover, customers are demanding more usable information. So as a way of advancing the perception part of medical analytics, seven reasons are offered here to whet the appetite for analytics-informed medical management

Analytics-informed medical management means collecting, integrating, and analyzing all relevant current and historic data to gain insights that will improve performance and outcomes. The following are a few very good reasons to invest in analytics.

1.    Look forward, not backward
An unfortunate, but persistent perception of business intelligence and data analysis is that reports are for looking at the past—how many claims, the trend in slips and falls, or how much money was spent last quarter. Interesting, but not actionable.

Much greater advantage can be gained from analyzing the data to understand what is happening now in order to improve procedures going forward. Identify cost drivers and develop prompt, appropriate, and consistent actions to redirect the organization.

2.    Find meaning in your data
The industry has been diligently collecting data for years, yet little attention has been paid to what the data might reveal. Analytics looks at the data to derive meaning, suggest direction, and empower informed decision-making.

Corporate leaders are often victims of their own denial, assuming all important information is known and current processes are the best they can be. Rarely is that actually the case and analytics can be eye-opening.

3.    Deliver intelligence to those who need it
Analytics can be used to evaluate medical provider performance, for instance, and deliver the information in real time to those who are directing care. Since poorly performing providers are guaranteed to add cost and complexity to claims, analytics used in this manner will directly impact efficiency, cost, and outcome.

Similarly, information about untoward events and conditions in claims delivered to operations concurrently will add efficiency and improved outcomes.

4.    Standardize procedures
A rule-based approach can be used to monitor data and create alerts of high risk conditions and events that occur in claims. Doing so inserts credibility, consistency, and comprehensiveness into the medical management process. Moreover, when standard procedures and actions are established to respond to specific alerts, the entire process can be measured for organizational improvement, cost-savings, and outcome success.

5.    Data as a work-in-process tool
Data can be a working tool. Analytics can be structured to concurrently tag data items that portend risk and cost in claims, then alert the person who can take action. Front line workers will gain decision support information in time to intervene effectively and usually avoid irreversible damage.

6.    Discover unexpected opportunities
When analytics are employed, newly discovered information or conditions understood differently can reveal opportunities. Interventions, priorities, and procedures might be restructured, streamlined, or enhanced. New products or delivery methods may also be realized and developed.

7.    Ensure the organization’s competitive advantage
Having implemented standard and consistent methodologies, improved outcomes are demonstrated objectively for clients and prospects. Proof of value generates confidence in operations and outcomes, a much easier sell.

The forgoing seven reasons to invest in medical analytics are not by any means all-inclusive, nor are they exhaustive in their portrayal. Much more can be said and gained by implementing medical analytics. The data ingredients are available and waiting.

The general tenor in the industry is to continue business as usual, but doing so has not produced desired results. Nor will it. As Paduda points out, IT in the WC/P&C industry is exceedingly underappreciated and underfunded.

Therefore, a  little creativity may be required to obtain what is needed. Outsourcing to a company that uniquely provides Workers’ Compensation medical analytics is one approach. Fees can be sized to the organization, thereby making it affordable. Being analytics-poor is no longer an option.

Paduda, J. Who’s running your company. 05/20/2016 http://www.joepaduda.com/2016/05/whos-running-company/#sthash.LJIERvyq.dpufv

Karen Wolfe is the founder and President of MedMetrics®, LLC, a Workers’ Compensation, analytics-Informed medical management and technical services company. MedMetrics analyzes and scores medical provider performance and offers other online apps that link analytics to operations, thereby making them actionable. karenwolfe@medmetrics.org

Thursday, April 28, 2016

Everyone Wants Analytics--Whatever That Is...

by Karen Wolfe

It seems everyone in Workers’ Compensation wants analytics. At the same time, a lot of confusion persists about what analytics is and what it can contribute. Expectations are sometimes unclear and often unrealistic. Part of the confusion is that analytics can exist in many forms.

Analytics is a term that encompasses a broad range of data mining and analysis activities. The most common form of analytics is straightforward data analysis and reporting. Other predominate forms are predictive modeling and predictive analytics.
Most people are already doing at least some form of analytics and portraying their results for their unique audiences. Analytics represented by graphic presentations are popular and often informative, but they do not change behavior and outcomes by themselves.

Predictive modeling
Predictive modeling uses advanced mathematical tools such as various configurations of regression analysis or even more esoteric mathematical instruments. They look for statistically valid probabilities about what the future holds within a given framework. In Workers’ Compensation, predictive modeling is used to forecast which claims will be the most problematic and costly from the outset of the claim. Predictive modeling is the most sophisticated and usually the most costly predictive methodology.

Predictive analytics
Predictive analytics lies somewhere between data analysis and predictive modeling. It can be distinguished from predictive modeling in that it uses historic data to learn from experience what to expect in the future. It is based on the assumption that future behavior of an individual or situation will be similar to what has occurred in the past.

Credit score
One of the most well-known applications of predictive analytics is credit scoring used throughout the financial services industry. Analysis of a customer’s credit history, payment history, loan application, and other conditions is used to rank-order individuals by their likelihood of making future credit payments on time. Those with the highest scores are ranked highest and are the best risks. That is why a high credit risk score is important to purchasers and borrowers.

Similarly, Workers’ Compensation claim data can be collected, integrated, and analyzed from bill review, claims system, utilization review, pharmacy (PBM), and claim outcome information to score and rank-order treating physicians performance. Those with the highest rank are the most likely to move the injured worker to recovery more quickly and at the lowest cost.

Making analytics predictive
Both predictive modeling and predictive analytics deal in probabilities regarding future behavior. Predictive modeling uses statistical methods and predictive analytics looks at what was, is, and therefore, probably will be. For predictive analytics, it is important to identify relevant variables that can be found in the data and take action when those conditions or events occur in claims.

Industry research
One way to find critical variables is to review industry research. For instance, research has shown when there is a gap between the date of injury and reporting or the first medical treatment, something is not right. That gap is an outlier in the data that predicts claim complexity.

Data search
Another way to identify key variables is to search the data to find the most costly cases and then look for consistent variables among them. Each book of business may have unique characteristics that can be identified in that manner.

Importantly, predictive analytics can be used concurrently throughout the course of the claim. The data is monitored electronically to continually search for outlier variables. When predictive outliers occur in the data, alerts can be sent to the appropriate person so that interventions are timely and more effective.

For example, to evaluate medical provider future performance, select data elements that describe past behavior. Look at past return to work patterns and indemnity costs associated with providers. If a provider has not typically returned injured workers to work in the past, chances are pretty good that behavior will continue.

Where to begin
For organizations looking to implement analytics, those who have already made the plunge suggest starting by taking stock of your organization’s current state. “The first thing you need to know is what is happening in your population,” says Rishi Sikka, M.D., senior vice president of clinical transformation for Advocate Health Care in Illinois. “Everyone wants to do all the sexy models and advanced analytics, but just understanding that current state, what is happening, is the first and the most important challenge.”

Best results
It is important to note, that the accuracy and usability of results will depend greatly on the quality of the data analyzed. To get the best and most satisfying results from predictive analytics, cleanse the data by removing duplicate entries, data omissions, and inaccuracies.

Analytics-informed medical management
For powerful medical management informed by analytics, identify the variables that are most problematic for the organization and continually scan the data to find claims that contain them. Then send an alert. Structuring the outliers, monitoring the data to uncover claims containing them, alerting the right person, and taking the right action is a powerful medical management strategy.

Karen Wolfe is the founder and President of MedMetrics®, LLC, a Workers’ Compensation, analytics-Informed medical management and technical services company. MedMetrics analyzes and scores medical provider performance and offers other online apps that link analytics to operations, thereby making them actionable. karenwolfe@medmetrics.org