+1,1,1
Search

Blog


The Truven Health Blog


The latest healthcare topics from a trusted, proven, and unbiased source.


Risk of Hospitalization


By Therese Gorski/Tuesday, December 13, 2016

As Anne Fischer wrote in her last blog How a Data Scientist Thinks about Risk Stratification, in order to predict risk, we need to first determine what “risk” is being measured. One important risk is that of being hospitalized.  Risk of hospitalization or admission models have become more targeted, more personal and seemingly more prevalent. Further, they are very much in line with the goals of population health and the “quadruple aim” (improving patient care, reducing costs, improving the health of populations and improving the provider’s experience). If a person has proper ambulatory or outpatient care for a chronic disease, acute inpatient admissions related to that disease should be rare.

At Truven Health, we have been developing and maintaining risk models for decades. Many risk models, such as risk of cost, risk of mortality and risk of complications, are best used in aggregate within a population subset. This evaluation is typically done at a service line or patient group level, for example, all cardiovascular patients or all patients with a specific MS-DRG.

In today’s world of increasing interest in care management and targeted outreach, individual level risk models hold much promise.  These models evaluate and interpret risk for each individual patient. Several years ago, we started a journey to develop new targeted risk models – including risk of hospitalization – to meet this increasing business need. We focused on specific diseases with the intent to have high predictive accuracy overall but particularly at the “tails”, meaning we must perform well at identifying those who have a high likelihood of being admitted in the near future. Or, in data science terms, model performance was measured by its sensitivity, specificity and positive predictive value for all patients above a specific risk threshold, with an emphasis on high sensitivity (that is, reducing false negatives).

To start, we chose to focus on diabetes, congestive heart failure (CHF), asthma, and more recently chronic obstructive pulmonary disease (COPD). These conditions run the gamut for both prevalence and admission risk, with asthma being most prevalent and least likely to result in admission versus CHF, which is least common but most likely to result in admission. These are also chronic conditions that are typically managed, at some level, which also fit our criteria.

In addition to specific diseases, we also focused on identifying risk at one-, three- and six-month intervals so that a care manager can better understand the risk at hand and be able to prioritize accordingly. Further, we report risk across several categories including “all-cause admissions”, “potentially avoidable admissions” (largely defined by AHRQ) and risk of “related admissions” which represents conditions that are considered to be related to the main condition as defined by Truven Health. Finally, along with each model’s risk score, we provide the patient attributes that are driving the risk score, whether it be a recent hospitalization, level of disease severity or even age. We believe that this additional insight gives the care manager a bit more background on the patient, helping to explain why the patient may have an increased risk value.

These models have been notably successful in terms of their predictive accuracy and our work will continue as we expand the number of diseases and work with our clients to help make the information actionable. The general trend toward person specific risk versus risk in aggregate will only grow and will become more refined as we, and the industry in general, are able to obtain and incorporate more personalized information about people.

Therese Gorski
Senior Director, Advanced Analytics


Truven Health Risk Model Ranks High in Actuarial Evaluation


By John Azzolini/Monday, November 28, 2016

 

Healthcare payers today are facing the complexities of reform, increased competition, and budget constraints — all while dealing with pressures to reduce costs and improve member health. Managing health risk has become a necessity. But to manage risk, payers must first understand their population. To do this well, they need reliable, robust risk and cost of care models.

 

Last month, the Society of Actuaries (SOA) released a study showing that Truven Health Analytics’ cost of care model outperformed other risk models in 18 out of 22 measures. SOA’s Accuracy of Claims-Based Risk Scoring Models compared health risk-scoring models, building on their previous studies with similar objectives (the most recent was in 2007). In the medical claims category (predictions based only on medical claims data), the current study showed that, in 21 of the 22 measures, the Truven Health model was ranked either first or second. No other model came close to matching this performance. (See Table 1 for a summary of how Truven Health’s model ranked relative to the competition).

 

How the SOA Evaluates Risk Models

The SOA evaluated Truven Health Analytics’ cost of care model against six others:

 

  • ACG® System
  • Chronic Illness & Disability Payment System and MedicaidRx
  • DxCG Intelligence
  • HHS-HCC
  • Milliman Advanced Risk Adjusters
  • Wakely Risk Assessment Model

 

The SOA assessed all models on their ability to predict costs using the Truven Health Marketscan® commercial claims dataset of 1 million members, and used three methodologies to evaluate their precision: R-Squared, the mean absolute error statistics, and predictive ratios. All three methodologies measure the statistical difference between the prediction and the actual results. All models produced both a concurrent and prospective cost prediction and were evaluated using both a capped data set (where patient costs were capped at $250,000) and a non-capped data set.

 

The SOA evaluated the models’ predictive ability using a number of scenarios (total medical costs, simulated random groups, condition-specific predictions, patient cost). In the simulated random group scenario, the SOA created groups of 1,000 and 10,000 patients to simulate the application of the model to subgroups of the population.

 

Table 1: How the Truven Health Cost of Care Model Performed

The Truven Health model ranked first or second for its ability to predict costs in 21 of the 22 measures studied.

 

Scenario

Truven Health Model Ranking*

R-Squared

Mean Absolute Error

Non-Capped

Capped**

Non-Capped

Capped**

Total Medical Costs, Concurrent

2

1

2

1

Total Medical Costs, Prospective

1

1

1

1

Simulated Random Groups, Concurrent

2

3

1

1

Simulated Random Groups, Prospective

1

1

1

1

 

 

Predictive Ratios

 

 

Overall Condition Specific Prediction, Concurrent

 

1

 

 

Overall Condition Specific Prediction, Prospective

 

1

 

 

Very Low Cost Patients, Concurrent

 

1

 

 

Very Low Cost Patients, Prospective

 

1

 

 

Very High Cost Patients, Concurrent

 

1

 

 

Very High Cost Patients, Prospective

 

1

 

 

     * Compared with six other models.

** Capped at $250,000

 

Why Risk Models Are Important to Payers

Risk modeling is a very helpful tool for health plans and employers. It can provide valuable insights into member utilization patterns and risk– vital for benefit planning, disease management and wellness program management, and member communications. It can provide deep insights into provider performance, and aid in determining ideal reimbursement and premium rates. Such models are an integral part of a number of Truven Health databases and analytical tools. The SOA evaluation speaks to the high quality and reliability of the Truven Health solutions.

John Azzolini
Senior Consulting Scientist

Why Implement Data Mining in the Medicaid Fraud Control Unit?


By David Hart/Monday, October 24, 2016

 

In 2013, the U.S. Department of Health & Human Services (HHS) Office of Inspector General (OIG) promulgated a rule enabling Medicaid Fraud Control Units (MFCUs) to receive federal funding for their Medicaid fraud data mining efforts provided certain requirements were met.  The rule adds to the toolset that MFCUs have at their disposal for fighting Medicaid fraud and abuse.  But most MFCUs have been reluctant to begin data mining efforts due to concerns over increasing caseloads and expanding federal reporting obligations.

Many MFCUs are now evaluating whether to implement data mining programs. There are several potential benefits to consider for MFCUs contemplating data mining.

Potential benefits:

  • Identify potentially fraudulent providers not previously suspected
  • Identify types of fraud that cannot be systematically detected without data mining
  • Identify additional schemes for a provider already under investigation
  • Prioritize the best cases and reduce wasted time
  • Improve case presentation
  • Ensure a balanced case mix and review of all providers
  • Increase return on investment (ROI)

MFCUs can increase their identification of fraudulent providers, better prioritize cases, and effectively support prosecution efforts by applying best practices, critical success factors, and innovations to data mining efforts. 

Questions to think about when considering data mining:

  • Doesn’t the state Medicaid agency already do this work for the MFCU?
  • Will data mining increase MFCU workload?
  • Will there be evidentiary challenges?
  • Is the cost of data mining prohibitive?
  • Will the application and reporting process be burdensome?

For more than 35 years, Truven Health has used data mining to help clients uncover possible fraud, waste, and abuse, and some of our experience is summarized in a new white paper. To learn more about strategies for implementing successful data mining in a MFCU and guidance to the benefits and questions reviewed in this blog, click here.

David Hart, JD
Vice President, Client Services, State Government


A Data Scientist Thinks About Population Health Management


By Anne Fischer/Wednesday, August 24, 2016

(The Truven Health Advanced Analytics team is tasked with building new and differentiating analytic methods. Asked to explain some interesting new analytics that are important for managing populations, the Advanced Analytics team wanted first to explain how they’re thinking about Population Health Management.)

What is Population Health Management (PHM)? Much like the adage about the blind men and the elephant, Population Health Management can mean completely different things to different audiences. Hospital systems, practitioners, government, and private insurers all have different interpretations of what the term means. And, in fact, its implications are very different to each of these players.

For most health systems, PHM represents a complete paradigm shift from their traditional way of doing business. Think of it like this: Imagine you own an auto-repair business. Perhaps you have a single facility, perhaps a chain of facilities. You are generally responsible for fixing a car when it’s damaged, and perhaps also performing routine maintenance on that vehicle. Now imagine you are being told that:

  • You are no longer simply responsible for the car when it is in your shop, but you are responsible for the car’s general care and maintenance for its lifetime.
  • The insurance company is no longer paying for the specific services you provide, they are paying you based on the overall “health” of the cars that you service. You now need to know what happens to that car outside the walls of your facilities.
  • You are no longer simply repairing the car when it needs it, you are being paid to keep the car “healthy” and out of your repair shop.

Imagine how foreign that would seem. You have no information about the drivers of the car other than what you can gather publicly. You have no idea what kind of driving record a person has, what kind of routine maintenance they perform on their car (except that which happens to occur in one of your shops), or what kinds of roads they drive on. In short, you have no knowledge of what kind of risk they bring to the table.

Hospital systems are in this situation. Historically, they have not needed to know much about their patients outside of what occurs within their facilities. They don’t have much information on where their patients are seeking care outside of their facilities, what kind of preventive care they are taking, what their social determinants of health are, nor how risky each patient is in terms of lifestyle and overall health, and they don’t have any input to their patients’ health benefit programs.

Now imagine you are the auto mechanic. Your repair shop owner is now asking you to understand the entire spectrum of a given vehicle you are servicing. Perhaps your specialty is body work, but you have to start thinking about the gas mileage and the health of the exhaust system in every car you see. Similarly, practitioners – particularly those who are not primary care physicians and are not used to thinking about “the whole patient” – struggle with the concept of population health because their focus is typically on one patient and one problem at a time.

Taking the analogy further, imagine you are the auto insurer (payer). You have historically managed payment for all the expenses for a given driver (and adjusted your rates to that driver based on their record/perceived risk). However, in this analogy as a healthcare insurer, your ability to refuse coverage to someone is diminishing, and your ability to assess risk is out of date, given that all drivers seem to be getting progressively worse and consequently more expensive. You are eager to shift some of that payment risk to the auto mechanics who are far more “hands on” with the cars, but there is no framework in which to plan and agree to terms. Plus you are still expected to maintain the risk for random “Acts of Nature” such as trees falling on cars, lightning strikes, and accidents caused by others. You are used to thinking about risk stratification and management at the group level, less so at the individual level.

Finally, imagine that you are the civil engineer responsible for designing the infrastructure on which the cars travel. You design roads to accommodate certain volumes, speeds, and types of vehicles, and support laws to enforce speed limits and construction zones. (Besides being the largest healthcare payer, this is the other role government plays in healthcare.) But now you’re being asked to help understand and contribute to improving the overall “health” of the vehicles on your roads, to do this in a way that minimizes the frequency and scope of needed repairs, and to do it all on a reduced budget. Oh, and at the same time, you have to be thinking about how to ensure safe roadways and service for new kinds of cars – self driving, connected, and beyond. . .

So how can Truven Health help? Our job as the analytics specialists is to help provide the information needed to expand the view of patients, and to present the information so that it’s actionable. Providing information on the full spectrum of care, even for something as specific as a surgical patient receiving a joint replacement (as our Bundled Care consultants do), can be invaluable in helping facilities, practitioners and payers understand the downstream implications of the care that is delivered. Helping them understand which patients are at high risk for “collision” (such as our new Risk of Hospitalization models) can lead to timely, cost-effective interventions. Identifying which segments of the population could most benefit from management (such as our forthcoming population classification method) can help focus activities for guiding patients and members towards health and well-being. Bringing valuable analytics to life can only happen if we first understand where our clients are coming from, and second, where they need to go to continue to be successful.

In coming blog posts, I will offer insights into the work of data scientists and into the analytics we are developing to help our clients continue to be successful.

 

Anne Fischer
Senior Director, Advanced Analytics


Here’s What you Missed at AHIP Institute 2016


By Truven Staff/Wednesday, June 29, 2016

Last week, representatives from Truven Health Analytics, an IBM Company, and nearly 3,000 other healthcare professionals attended AHIP Institute 2016 in Las Vegas, NV to learn from health plan industry leaders, see the newest products and services, and get an idea of what’s ahead in healthcare.

Here’s what you missed from Truven Health at this year’s AHIP Institute:

  1. Some things just work well together: A Toast to Truven Health Analytics and IBM Watson Health - During the opening night reception, Truven Health Analytics and IBM Watson Health celebrated our new relationship: Truven Health is now a wholly owned subsidiary of IBM Watson Health.

  2. Custom LEGO® Bridge Build - Our booth included a custom LEGO bridge build to show how our portable analytics solution can bridge the gap between your enterprise data warehouse and the answers you need. Watch our video for more information on our portable analytics solution.

  3. Truven Health Concurrent Session: Bundled Payments: Evaluating the Opportunities for Your Business -  During our concurrent session on Thursday, June 16, Truven Health experts Kevin Ruane and David Jackson discussed the experiences of payers and providers in various stages of implementing bundled payments. They also reviewed methods used to determine preparedness, how to evaluate opportunities and risks, and key metrics for success. 

If you missed our session at AHIP Institute, the presentation will also be included in our upcoming AHIP webinar. Contact us to register.

Contact us for more information on AHIP Institute, or to find out more about our solutions. 


RSS