Risk analytics uses data and predictive modeling to help insurers better understand risk, price policies accurately, and manage claims effectively. By identifying high-risk claims and focusing resources on proactive resolution, insurers can lower costs, reduce premiums and claims, gain a competitive advantage, and increase market share. While predictive models have limitations, when used correctly they provide rapid insight to help triage incidents, settle claims sooner, and achieve better outcomes.
Harnessing The Power Of (Claim Risk) Analytics Published Captive Review Sept 09paulmarshall
Risk analytics is revolutionizing the processes and tools employed by insurers to more quickly and accurately market, price and underwrite their products. Ad¬ditionally, these tools have the potential to enhance an insurer’s ability to manage claims more effectively. With improved management, insurers can lower overall costs, reduce premiums, reduce claims, gain competitive advantage and, ultimately, increase their market share. Through advances in technol¬ogy and data availability, many insurers are already benefiting from the use of data analytics and predictive modeling capabilities to better understand and identify risk.
Measuring Risk - What Doesn’t Work and What DoesJody Keyser
The topics for this webinar include:
The Problem – Why your method may be a “management placebo” and why that is the biggest risk you have Problems that many methods ignore – and problems some methods introduce What Does Work – Studies reveal some methods show consistent, measurable improvements on the forecasts and decisions of managers
Examples of Real Improvements
Overview of Applied Information Economics (AIE) Process Common Objections to quantitative methods and the misconceptions behind them
Questions & Answers
Harnessing The Power Of (Claim Risk) Analytics Published Captive Review Sept 09paulmarshall
Risk analytics is revolutionizing the processes and tools employed by insurers to more quickly and accurately market, price and underwrite their products. Ad¬ditionally, these tools have the potential to enhance an insurer’s ability to manage claims more effectively. With improved management, insurers can lower overall costs, reduce premiums, reduce claims, gain competitive advantage and, ultimately, increase their market share. Through advances in technol¬ogy and data availability, many insurers are already benefiting from the use of data analytics and predictive modeling capabilities to better understand and identify risk.
Measuring Risk - What Doesn’t Work and What DoesJody Keyser
The topics for this webinar include:
The Problem – Why your method may be a “management placebo” and why that is the biggest risk you have Problems that many methods ignore – and problems some methods introduce What Does Work – Studies reveal some methods show consistent, measurable improvements on the forecasts and decisions of managers
Examples of Real Improvements
Overview of Applied Information Economics (AIE) Process Common Objections to quantitative methods and the misconceptions behind them
Questions & Answers
There Is A 90% Probability That Your Son Is Pregnant: Predicting The Future ...Health Catalyst
Predictive: Relating to or having the effect of predicting an event or result. Analytics: The systematic computational analysis of data or statistics. Together they make up one of the most popular topics in healthcare today. But predictive analytics is a means to an ends, and there is little good in predicting an event or result without a strategy for acting upon that event, when it happens. If, as the Robert Wood Johnson Foundation recently published, 80% of healthcare determinants fall outside of the healthcare delivery system as we traditionally define it, should we focus our predictive analytics on the traditional 20% of traditional healthcare delivery, or broaden our focus to the 80% that includes social and economic factors, physical environment, and lifestyle behaviors? What if our predictive models reveal to us that the highest risk variable to a patient’s length of life and quality of life is their economic status? Can an accountable care organization and patient centered medical home realistically do anything to reduce that risk, in reaction to the predictive model? Given the current availability and type of data in the healthcare ecosystem, and our organizational ability or inability to realistically intervene, where should we focus our predictive and interventional risk management strategies? There is enormous potential value in the application of predictive analytics to healthcare, but, in contrast to predicting the weather, credit risk, consumer purchasing habits, or college dropout rates, the data collection, and social and ethical complexities of applying predictive analytics in healthcare are significantly higher. This session will explore some of the less technical, more human interest and philosophical issues, associated with predictive analytics in healthcare, including the speaker’s experience prior to healthcare, in the US Air Force, National Security Agency, and manufacturing.
Microsoft: A Waking Giant in Healthcare Analytics and Big DataDale Sanders
Ten years ago, critics didn’t believe that Microsoft could scale in the second generation of relational data warehouses, but they did. More recently, many of these same pundits have criticized Microsoft for missing the technology wave du jour in cloud offerings, mobile technology, and big data. But, once again, Microsoft has been quietly reengineering its culture and products, and as a result, they now offer the best value and most visionary platform for cloud services, big data, and analytics in healthcare.
Break All The Rules: What the Leading Health Systems Do Differently with Anal...Dale Sanders
This was my attempt to capture the intangible differences between leaders and followers in data driven healthcare. It should be noted that the organizations listed are not necessarily Health Catalyst clients. This slide deck is not intended to market or advertise Health Catalyst, but rather highlight leadership in analytics, wherever it exists.
Predicting the Future of Predictive Analytics in HealthcareDale Sanders
This is the latest version of a slide deck that discusses some of the less technical, but very important issues, related to the effective use of predictive analytics in healthcare.
Legal Firms and the Struggle to Protect Sensitive DataBluelock
Survey results from the 2016 IT Disaster Recovery Planning and Preparedness Survey | Bluelock commissioned with ALM to asses the current state of the legal industry's IT disaster recovery (DR) preparedness, pressures and confidence.
Legal Firms and the Struggle to Protect Sensitive DataKayla Catron
Survey results from the 2016 IT Disaster Recovery Planning and Preparedness Survey | Bluelock commissioned with ALM to asses the current state of the legal industry's IT disaster recovery (DR) preparedness, pressures and confidence.
The term “Big Data” emerged from Silicon Valley in 2003 to describe the unprecedented volume and velocity of data that was being collected and analyzed by Yahoo, Google, eBay, and others. They had reached an affordability, scalability and performance ceiling with traditional relational database technology that required the development of a new solution, not being met by the relational data base vendors. Through the Apache Open Source consortium, Hadoop was that new solution. Since then, Hadoop has become the most powerful and popular technology platform for data analysis in the world. But, healthcare being the information technology culture that it is, Hadoop’s adoption in healthcare operations has been slow. In this webinar, Dale Sanders, Executive Vice President of Product Development will explore several questions:
Why should healthcare leaders and executives care about this technology?
What makes Hadoop so attractive and rapidly adopted in other industries but not in healthcare?
Why is Big Data a bigger deal to them than healthcare?
What do they see that we don’t and are we missing the IT boat again?
How is the cloud reducing the barriers to adoption by commoditizing the skilled labor impact at the local healthcare organizational level?
Forecasting operational risk losses for CCAR poses a number of challenges, not least of which is uncertainty about the best methodology for modeling the relationship between a bank’s future losses and the macroeconomic environment.
Practical and Succinct Solutions to Coding - Select Data, Inc. RachelBuckleySelect
Discussing increasing numbers of Complexities in Home Health that challenge reimbursement and the financial and quality outcomes bottom line;
Exploring Regulatory Issues and Agency Finances
Making Connections Between Coding, the POC, and Keeping Your Reimbursement;
Looking at Potential Impending Audits and Queries and their Impact;
and ICD-10…Will you be ready or will you be one of the agencies expected to have significant delays in payment?
How to Choose the Best Healthcare Analytics Software Solution in a Crowded Ma...Health Catalyst
There’s a new trend in the healthcare industry to adopt analytics software solutions to help organizations achieve clinical and financial success. Because of the high demand for analytics, there are many players touting their ability to delivery comprehensive solutions. With so many options available, health systems need to be able to cut through the marketing hype to find tools that provide the best value for their needs. Key solutions include an enterprise data warehouse and analytics software applications (from foundational to discovery to advanced). Other considerations include the organization’s readiness for cultural change, the total cost of ownership required, and the viability of the company providing the technology.
Healthcare Best Practices in Data Warehousing & AnalyticsDale Sanders
This is from a class lecture that I gave in 2005. Rather dated, but 95% of content is still very relevant today, which is a bit unfortunate. That's an indication of how little we've progressed in the healthcare domain.
There Is A 90% Probability That Your Son Is Pregnant: Predicting the Future ...Health Catalyst
In this webinar, which is geared for managers and executives, Dale Sanders provides a new version of a very popular lecture he presented at this year’s Health Analytics Summit in Salt Lake City. Attendees will gain an understanding of:
What to expect from predictive analytics as it relates to human behavior
A general overview of predictive analytics models, and the contexts in which those various models should and should not be used
The scenarios in which predictive models in healthcare are effective and when they are not, given that 80% of population health outcomes are determined by socio-econonic factors, not healthcare delivery
The relationship between predictive analytic accuracy and topics of data management such as data quality, data volume and patient outcomes data
The use of predictive analytics to identify patients who are on a trajectory for poor, as well as good, outcomes
How current predictive analytics strategies are overlookng the cost of intervention and “Return on Engagement”, ROE— the cost per unit of healthcare improvement for patient populations
The cultural, philosophical, and legal conundrums that predictive analytics will create for healthcare, notably healthcare rationing
The success of predictive analytics will not be defined by the simple risk stratification of patient populations for care management teams. Success will depend on the costs of intervention to reduce the risks that are identified by predictive analytics, which boils down to this two-part question: Now that we can predict a patient’s risk for a bad healthcare outcome, “What’s the probability of influencing this patient’s behavior towards a better outcome?” And, “How much effort and cost will be required for that influence?”
Improving Healthcare Risk Assessments to Maximize Security BudgetsMatthew Rosenquist
Healthcare is undergoing major changes
that are being driven by medical, consumer,
IT, and security trends. While these trends
deliver compelling benefits to healthcare
organizations, workers, and patients, they
also carry significant privacy and security
risks. Healthcare organizations are seeing an
escalation in the frequency and impact of
security compromises, driving a corresponding
increase in healthcare privacy and security
regulation at the national and local levels.
This paper looks at how healthcare organizations can better optimize and focus their
privacy and security efforts and budgets
through risk assessments designed to
identify, characterize, and address the most
serious threats and the agents behind them.
Advantages of Regression Models Over Expert Judgement for Characterizing Cybe...Thomas Lee
Expert Judgment is the foundation of many risk assessment methodologies. But research is robust on the inaccuracy of Expert Judgment with regards to rare events—and large data breach events are rare. Regression models, which are a statistical characterization of cross-company historical events are substantially more accurate than expert judgment or even models with expert judgment as a foundation.
There Is A 90% Probability That Your Son Is Pregnant: Predicting The Future ...Health Catalyst
Predictive: Relating to or having the effect of predicting an event or result. Analytics: The systematic computational analysis of data or statistics. Together they make up one of the most popular topics in healthcare today. But predictive analytics is a means to an ends, and there is little good in predicting an event or result without a strategy for acting upon that event, when it happens. If, as the Robert Wood Johnson Foundation recently published, 80% of healthcare determinants fall outside of the healthcare delivery system as we traditionally define it, should we focus our predictive analytics on the traditional 20% of traditional healthcare delivery, or broaden our focus to the 80% that includes social and economic factors, physical environment, and lifestyle behaviors? What if our predictive models reveal to us that the highest risk variable to a patient’s length of life and quality of life is their economic status? Can an accountable care organization and patient centered medical home realistically do anything to reduce that risk, in reaction to the predictive model? Given the current availability and type of data in the healthcare ecosystem, and our organizational ability or inability to realistically intervene, where should we focus our predictive and interventional risk management strategies? There is enormous potential value in the application of predictive analytics to healthcare, but, in contrast to predicting the weather, credit risk, consumer purchasing habits, or college dropout rates, the data collection, and social and ethical complexities of applying predictive analytics in healthcare are significantly higher. This session will explore some of the less technical, more human interest and philosophical issues, associated with predictive analytics in healthcare, including the speaker’s experience prior to healthcare, in the US Air Force, National Security Agency, and manufacturing.
Microsoft: A Waking Giant in Healthcare Analytics and Big DataDale Sanders
Ten years ago, critics didn’t believe that Microsoft could scale in the second generation of relational data warehouses, but they did. More recently, many of these same pundits have criticized Microsoft for missing the technology wave du jour in cloud offerings, mobile technology, and big data. But, once again, Microsoft has been quietly reengineering its culture and products, and as a result, they now offer the best value and most visionary platform for cloud services, big data, and analytics in healthcare.
Break All The Rules: What the Leading Health Systems Do Differently with Anal...Dale Sanders
This was my attempt to capture the intangible differences between leaders and followers in data driven healthcare. It should be noted that the organizations listed are not necessarily Health Catalyst clients. This slide deck is not intended to market or advertise Health Catalyst, but rather highlight leadership in analytics, wherever it exists.
Predicting the Future of Predictive Analytics in HealthcareDale Sanders
This is the latest version of a slide deck that discusses some of the less technical, but very important issues, related to the effective use of predictive analytics in healthcare.
Legal Firms and the Struggle to Protect Sensitive DataBluelock
Survey results from the 2016 IT Disaster Recovery Planning and Preparedness Survey | Bluelock commissioned with ALM to asses the current state of the legal industry's IT disaster recovery (DR) preparedness, pressures and confidence.
Legal Firms and the Struggle to Protect Sensitive DataKayla Catron
Survey results from the 2016 IT Disaster Recovery Planning and Preparedness Survey | Bluelock commissioned with ALM to asses the current state of the legal industry's IT disaster recovery (DR) preparedness, pressures and confidence.
The term “Big Data” emerged from Silicon Valley in 2003 to describe the unprecedented volume and velocity of data that was being collected and analyzed by Yahoo, Google, eBay, and others. They had reached an affordability, scalability and performance ceiling with traditional relational database technology that required the development of a new solution, not being met by the relational data base vendors. Through the Apache Open Source consortium, Hadoop was that new solution. Since then, Hadoop has become the most powerful and popular technology platform for data analysis in the world. But, healthcare being the information technology culture that it is, Hadoop’s adoption in healthcare operations has been slow. In this webinar, Dale Sanders, Executive Vice President of Product Development will explore several questions:
Why should healthcare leaders and executives care about this technology?
What makes Hadoop so attractive and rapidly adopted in other industries but not in healthcare?
Why is Big Data a bigger deal to them than healthcare?
What do they see that we don’t and are we missing the IT boat again?
How is the cloud reducing the barriers to adoption by commoditizing the skilled labor impact at the local healthcare organizational level?
Forecasting operational risk losses for CCAR poses a number of challenges, not least of which is uncertainty about the best methodology for modeling the relationship between a bank’s future losses and the macroeconomic environment.
Practical and Succinct Solutions to Coding - Select Data, Inc. RachelBuckleySelect
Discussing increasing numbers of Complexities in Home Health that challenge reimbursement and the financial and quality outcomes bottom line;
Exploring Regulatory Issues and Agency Finances
Making Connections Between Coding, the POC, and Keeping Your Reimbursement;
Looking at Potential Impending Audits and Queries and their Impact;
and ICD-10…Will you be ready or will you be one of the agencies expected to have significant delays in payment?
How to Choose the Best Healthcare Analytics Software Solution in a Crowded Ma...Health Catalyst
There’s a new trend in the healthcare industry to adopt analytics software solutions to help organizations achieve clinical and financial success. Because of the high demand for analytics, there are many players touting their ability to delivery comprehensive solutions. With so many options available, health systems need to be able to cut through the marketing hype to find tools that provide the best value for their needs. Key solutions include an enterprise data warehouse and analytics software applications (from foundational to discovery to advanced). Other considerations include the organization’s readiness for cultural change, the total cost of ownership required, and the viability of the company providing the technology.
Healthcare Best Practices in Data Warehousing & AnalyticsDale Sanders
This is from a class lecture that I gave in 2005. Rather dated, but 95% of content is still very relevant today, which is a bit unfortunate. That's an indication of how little we've progressed in the healthcare domain.
There Is A 90% Probability That Your Son Is Pregnant: Predicting the Future ...Health Catalyst
In this webinar, which is geared for managers and executives, Dale Sanders provides a new version of a very popular lecture he presented at this year’s Health Analytics Summit in Salt Lake City. Attendees will gain an understanding of:
What to expect from predictive analytics as it relates to human behavior
A general overview of predictive analytics models, and the contexts in which those various models should and should not be used
The scenarios in which predictive models in healthcare are effective and when they are not, given that 80% of population health outcomes are determined by socio-econonic factors, not healthcare delivery
The relationship between predictive analytic accuracy and topics of data management such as data quality, data volume and patient outcomes data
The use of predictive analytics to identify patients who are on a trajectory for poor, as well as good, outcomes
How current predictive analytics strategies are overlookng the cost of intervention and “Return on Engagement”, ROE— the cost per unit of healthcare improvement for patient populations
The cultural, philosophical, and legal conundrums that predictive analytics will create for healthcare, notably healthcare rationing
The success of predictive analytics will not be defined by the simple risk stratification of patient populations for care management teams. Success will depend on the costs of intervention to reduce the risks that are identified by predictive analytics, which boils down to this two-part question: Now that we can predict a patient’s risk for a bad healthcare outcome, “What’s the probability of influencing this patient’s behavior towards a better outcome?” And, “How much effort and cost will be required for that influence?”
Improving Healthcare Risk Assessments to Maximize Security BudgetsMatthew Rosenquist
Healthcare is undergoing major changes
that are being driven by medical, consumer,
IT, and security trends. While these trends
deliver compelling benefits to healthcare
organizations, workers, and patients, they
also carry significant privacy and security
risks. Healthcare organizations are seeing an
escalation in the frequency and impact of
security compromises, driving a corresponding
increase in healthcare privacy and security
regulation at the national and local levels.
This paper looks at how healthcare organizations can better optimize and focus their
privacy and security efforts and budgets
through risk assessments designed to
identify, characterize, and address the most
serious threats and the agents behind them.
Advantages of Regression Models Over Expert Judgement for Characterizing Cybe...Thomas Lee
Expert Judgment is the foundation of many risk assessment methodologies. But research is robust on the inaccuracy of Expert Judgment with regards to rare events—and large data breach events are rare. Regression models, which are a statistical characterization of cross-company historical events are substantially more accurate than expert judgment or even models with expert judgment as a foundation.
Transforming Insurance Risk Assessment with Big Data: Choosing the Best PathCapgemini
Insurers are realizing that big data has the potential to create competitive advantage. There is a gold mine of information residing across the large volumes of data available in multiple sources and disparate formats, if only it can be efficiently mined to support key operational decisions and improve the customer experience. Commercial risk assessment is data intensive and ripe for the incorporation of real-time external data. In this paper, we explore the ways commercial insurers can gain accurate and comprehensive risk assessments when underwriting policies by using big data.
Insurance today is considered both as a form of security and investment. It gives a sense of assurance to its client- the courage to mitigate unforeseen mayhem in life. But with the influx of fraudulent activities and felony across various industries, the insurance sector stands to be no exception. One of the ways that miscreants try to get money from insurance companies is through Insurance Claims Fraud
One of the fastest growing concerns on insurers’ enterprise risk agenda is model risk
management. From being a phrase that primarily actuaries and other modelers used, “model risk” has become a major focus of regulators and the subject of intense activity and debate at insurers. How model risk management has evolved from ad hoc efforts to its currentproactive stage is an interesting story. But more interesting still is
what we believe could be its next stage – generating measurable business value.
A brief and clear argumentation in favour of the personalisation approach in risk management procedures in large companies.
Taken from "Making better risk management decisions" by J. Birkinshaw and H. Jenkins.
This presentation provides a brief insight into the need to undertake an analytics project, particularly as it pertains to claims management and fraud. To this end the presentation will touch on the general challenges confronting the property and casualty insurance industry, as well as the challenges and lessons learnt from early adopters of business intelligence. In the face of these challenges analytics holds the potential to generate substantial value as evidenced by several short case study examples. The presentation concludes with a look at the issue of fraud as it pertains to the industry and some of the metrics that are influenced by it.
The presentation draws extensively, and focuses on, the work and viewpoints from industry participants including; Accenture, IBM, Ernst & Young, Strategy Meets Action, Ordnance Survey, Gartner, Insurance Institute of America, American Institute for Chartered Property Casualty Underwriters, International Risk Management Institute and John Standish Consulting. References are included on each slide as well as on the “References” slides at the end of the presentation.
Beyond the secular forces that we describe in our Future of Insurance series1, more immediate and cyclical issues will be shaping the insurance executive agenda i n 2 016 .2 Commercial insurers (including reinsurers) face tough times ahead with underwriting margins that are being pressured by softening prices and a potentially volatile interest rate environment.
Property & Casualty: Deterring Claims Leakage in the Digital AgeCognizant
For property and casualty insurers, the persistent and vexing problem of claims leakage can be effectively curtailed by applying digital technology with cutting-edge clarity.
1. Risk Analytics and Claims: An Ounce of Prevention Is Worth a Pound of Cure
Written by: Mary Chmielowiec and Paul Marshall, PointRight, Inc.
Published in:
Captive Review Magazine July 2009
Risk analytics is revolutionizing the processes and tools employed by insurers to more
quickly and accurately market, price, and underwrite their products. Additionally, these tools
have the potential to enhance an insurer’s ability to mange claims more effectively. With
improved management, insurers can lower overall costs, reduce premiums, reduce claims, gain
competitive advantage and, ultimately, increase their market share. Through advances in
technology and data availability, many insurers are already benefiting from the use of data
analytics and predictive modeling capabilities to better understand and identify risk.
What Is Risk Analytics?
Risk analytics is a quantitative method of examining data for the purpose of drawing
conclusions about the information. When coupled with predictive modeling, risk analytics has
the potential to answer very important questions about risk. The critical ingredient is data, which
must be gathered, scrubbed, aligned, indexed, and benchmarked to be useful in building
predictive models. Ultimately, the potential of data analytics is realized when the user gains rapid
access to answers for important questions such as, “What is the likelihood that this incident will
lead to a million dollar settlement?”
To illustrate the value of risk analytics, consider a healthcare facility that experiences a
patient fatality due to a fall. Too often, if that claim is not handled properly, the facility can
expect to payout the maximum allowed according to policy limits. However, if the claim is
handled properly (i.e. timely and proactively), the claim can be settled out of court for a fraction
of that cost. Unfortunately, healthcare systems can generate upwards of 100 incidents per month,
and available claims management resources do not extend beyond the constraints of full blown
2. lawsuits. Consequently, incident reports pile up and obscure the real risks. With risk analytics,
incidents can be rapidly and cost effectively analyzed. Then, “real” risk is identified sooner,
triaged appropriately, and dealt with proactively.
Logistically, it’s a simple process. The unique circumstances of each incident are
captured. The situation is analyzed in the context of like-facilities and resident health. This
provides the immediate insight necessary to gain perspective and focus resources accordingly.
Within the long term care industry, public access to OSCAR data, MDS assessments and survey
results provides for highly effective predictive modeling opportunities.
Advantages of Analytics
While a few risk managers are truly gifted with a sixth sense for risk, most are not. With
access to risk analytics, all claims managers can be equally and consistently equipped with the
tools and potential to greatly improve their performance. Risk analytics provides the critical
information needed to move forward with confidence and target attention on the high-risk
situations that will benefit most from a proactive stance. In addition to providing a virtual red,
yellow or green flashing light on each incident, risk analytics can provide a number of other
advantages:
1. Accelerate the acquisition of knowledge – “The quicker we can investigate, understand
and evaluate the claim, the quicker we can reach our decision points. Does the claim have value?
What is the potential value of this claim? Are we comfortable defending it at trial? Risk analytics
helps us tailor the investigations because if we can identify problem areas we can dig deeper and
perform more pointed and specific investigations. Any time we have access to critical
information about the facility, staffing levels, potential problem areas, etc. early in the claim
handling process we improve our chances of being able to evaluate the claim accurately and
2
3. resolve it in an optimal fashion...” explains Paul Hamlin, Founder and President of Hamlin and
Burton Liability Management, Inc. and expert in the field of claims management.
2. Place claims into proper context – Not all falls are created equal. The actual context of
individual claims may be quite different. For example, one facility’s data may demonstrate that
the fall was an anomaly that occurred despite having excellent protocols and risk management
practices, while the other facility’s data may reveal a true risk management weakness. This
knowledge advantage offers rapid discernment of the overall quality of care provided at one
facility versus another and can chart the course for improved negotiations with plaintiffs and,
ideally, lower overall settlements. “Risk analytics has allowed us to focus on critical claims by
gaining rapid clinical and analytical insight to help us put claims into a broader context and
obtain more favorable outcomes,” notes Jonathan Swann, Underwriter, CareSurance Nursing
Home Program at Lloyd’s. At a minimum, the information guides claims professionals and gives
them the wisdom to determine which claims to defend and which to settle, fast.
3. Lower claims administration costs – Claims managers who research files in the
traditional approach will spend 25 to 50 percent more time completing the legwork necessary to
obtain the data necessary to evaluate a claim. “Most data in the comprehensive risk analysis we
could find out on our own; but, it would take a tremendous amount of leg work and would be
done slowly, expensively and inconsistently,” says Paul Hamlin. If risk analytics can save an
insurer just five percent of total claims management expense, that impact could easily be
converted into a significant competitive advantage.
4. Detect fraud – Claims fraud is a multi billion dollar problem, and healthcare fraud is the
major contributor. While the reasons for this are many, the sad truth is that insurers can only
investigate a small percentage of suspected cases due to limited resources. Consequently, it’s
3
4. critical to rapidly evaluate every file to identify the likelihood of fraud and then focus
investigative resources accordingly. Failure to identify fraud raises claims cost, which increases
premiums for all insured. For insurers, even a minor improvement in the ability to detect fraud
can generate a significant return on investment.
5. Triage claims – By identifying underlying problems quicker, risk analytics gives the
insurer the clarity to identify real risk and fast-track the potentially large settlements at a much
earlier stage in the process. These cases, that are more likely to evolve into large settlements, are
instantly identified, designated a priority and handled appropriately.
As the application of risk analytics becomes more widespread in the claims handling
arena, new uses of these tools are expected. One application currently being explored is with
causation defense. To illustrate, assume a nursing home resident is afflicted with severe skin
breakdown that leads to an amputation of a lower extremity. Such a case is likely to result in a
lawsuit. To prepare for that possibility, the insurer can utilize predictive modeling to develop an
effective defense strategy. By processing the detailed circumstances of the case through a
sophisticated data analysis, the insurer can look at the medical condition of the resident and infer
what probability existed that that resident would have experienced severe skin breakdown
regardless of the facility’s quality of care or resident specific care plan.
Proceed With Caution
Any statically driven predictive modeling tool has limitations and the old adage, “garbage
in, garbage out” will always apply. While risk analytics and predictive modeling have
tremendous advantages to offer insurers and risk management organizations, the ultimate value
is derived when the experts interpret the information correctly and make the right decisions.
After all, there are many variables that go into each and every case that ultimately determine how
4
5. it is settled. Once a case proceeds to court, the deciding factor is the six or eight people in the
jury box. Just how they will decide is extraordinarily unpredictable. “There are precious few
variables that exist between the cases we win in trial and the ones we lose in trial,” says Paul
Hamlin.
Timing Is Everything
With the passage of time, the cost to settle any case may increase exponentially. Risk
analytics and predictive modeling provide the insurer and the defense team with rapid access to
the information needed to manage incidents proactively, triage claims effectively and settle
claims before that critical window of opportunity closes. It is simply an industry best practice
available for any insurer ready to harness the power of knowledge and technology and apply the
old adage “an ounce of prevention is worth a pound of cure”.
About the Authors:
Mary Chmielowiec is the Executive Vice President for Insurance and Paul Marshall is Director of Insurance
Business Development at PointRight Inc. PointRight Inc., formerly known as LTCQ, is based in Lexington, Mass.,
analyzes liability risks for the insurance industry using predictive models and underwriting decision support that
enable risk bearing organizations to more quickly and accurately analyze and manage the risks that shape their
bottom line. For more information, please call (781) 457-5820, email: paul.marshall@pointright.com or visit their
website at www.pointright.com.
5