The Well-Being Journal

Advancing the Science of Predictive Modeling

Madison Agee

Central to a successful population health management strategy is identifying, assessing and mitigating risk, since you want to be able to implement appropriate interventions for those individuals who will incur the highest healthcare costs. But how do you determine those individuals in your population who represent future risk? There are challenges around such identification, including:

  • High-risk individuals may not be participating in the formal healthcare system (through a lack of regular exams or other provider visits) which prevents insight from the physician.
  • Some individuals simply don’t present as high-risk today, but because of lifestyle or other factors, they could potentially be so in a year or two.
  • Because of financial reasons or a perceived lack of urgency, individuals could be delaying necessary care. This could lead to compounded risk and higher future costs.

Challenges such as these emphasize the importance of predictive modeling, which helps organizations identify and assess future risk and then use that insight to develop interventions that can proactively mitigate it. Given this valuable role, it’s important that such modeling is as robust as it can be. A study published earlier this year makes an important contribution to the field of predictive modeling, by advancing the science of such models with a more accurate framework.

Published by Population Health Management and authored by the Healthways Center for Health Research, “Predicting Health Care Cost Transitions Using a Multidimensional Adaptive Prediction Process” introduces a new method of predictive modeling called the Multidimensional Adaptive Prediction Process (MAPP). MAPP improves upon traditional predictive modeling, which uses a single model based on a limited and fixed set of variables and then applies that across an entire population.

In contrast, MAPP doesn’t rely on a single model – it instead draws from a collection of predictive modeling methods. Nor does it rely on a single set of covariates within a given model, instead allowing for a multitude of covariate combinations within each model. In this study, rather than be estimated on the entire population at one time, MAPP is estimated on four distinct cohorts of the population – low, medium, high and very high – each defined by total annual healthcare cost. By incorporating such a multi-faceted approach based on multiple models, covariate sets and cost cohorts, MAPP more explicitly accounts for the multi-dimensional, dynamic nature of a real-life population.

MAPP was tested on three years of administrative healthcare claims for approximately 25,000 people. A traditional predictive model was also estimated in order to yield a ”status quo” or reference modeling set of results. The two modeling approaches were then compared to see which one was more effective in predicting how individuals would move between cost categories from one year to another.

The study showed that, when compared to the traditional model, MAPP correctly identified 25 percent more individuals who remained in a high-cost cohort and 10 percent more individuals who transitioned from a lower-cost to a higher-cost cohort. Overall, MAPP more accurately identified $17.6 million of incurred healthcare costs.

The confirmation of MAPP as a more accurate methodology for predictive modeling has important applications. MAPP could improve traditional uses of predictive modeling, such as population risk adjustment, premium settings and targeted interventions designed to reduce costs. MAPP could also help health systems, providers and plans improve allocation and planning of their human, technology and physical resources, which could lead to lower cost of care and superior patient outcomes.

Topics: Health Plan & Health System Predictive Modeling Science and Research

New Research Introduces New Way to Gauge Efficacy of Well-Being Improvement Programs

Madison Agee

Organizations are searching for new ways to determine the efficacy of well-being improvement programs, a search that new studies from the Healthways Center for Health Research help to support. Published in Population Health Management, “Regional Economic Activity and Absenteeism: A New Approach to Estimating the Indirect Costs of Employee Productivity Loss”, introduces a new method for measuring the economic impact of work-related absences. Another recently published study makes an additional important contribution to the science of measuring the effectiveness of well-being improvement programs.

The study, “Extending Coarsened Exact Matching to Multiple Cohorts: An Application to Longitudinal Well-Being Program Evaluation within an Employer Population”, appeared in Health Services and Outcomes Research Methodology (HSORM). As with the regional productivity loss (RPL) study, this study expands upon an existing methodology and introduces a more robust and comprehensive measure useful for gauging the efficacy of well-being improvement programs.

The study focuses on a methodology known as Coarsened Exact Matching (CEM), which is used to remove imbalance (i.e., biases) between two groups and therefore create an “apples to apples” comparison of impact between them over time. To measure the effectiveness of a well-being improvement program, CEM compares two groups – those who participate in the program and those who do not but are of similar prospective risk – and systematically removes imbalance between the groups based on shared characteristics such as age, gender and disease status. This process enables an unbiased estimation of the program’s causal effect.

This “binary group” application of CEM for measuring the impact of well-being improvement programs is useful, but does not reflect the reality of these programs in which there is usually a wide spectrum of participation levels within a population. The recent HSORM study expanded the scope of CEM beyond the traditional binary group application to determine whether CEM could be an effective method for quantifying causality among multiple groups with different levels of program participation.

The study was able to show that the new multi-category specification of CEM accounted for and removed more bias than the traditional binary group application. Thus, multi-category CEM was found to produce a more comprehensive and robust measure of the impact of well-being improvement than the traditional application.

In addition to showing the validity of a multi-category CEM application, the study also demonstrated that higher levels of participation within a well-being improvement program led to a larger improvement in overall well-being. Well-being among non-participants improved 0.57 points, while well-being improved 1.32 and 1.48 points among the low- and high-intensity participants, respectively.

Together with the RPL study, these two studies make important contributions to the scientific literature and provide employers with new methodologies for measuring the impact of their well-being improvement programs.

Topics: Measure Wellness Methodology Science and Research ROI

Three Reasons Health Systems Need to Master Care Transitions Now

Sophie Leveque

The concept of care transitions in health systems is nothing new – it’s been an ongoing concern and challenge for hospitals to address for a long time. But a unique confluence of legislative and market-driven forces are now putting new pressures on health systems to evolve the way they view and execute care transitions. Penalties for readmissions, emerging payment methods, new delivery models, and the overall shift from a fee-for-service to a fee-for-value environment are some of these powerful drivers behind the shift. As a result of this perfect storm of forces, we’re seeing health systems moving from a historically laser-focused view on logistics (e.g., how do you physically move a patient to a skilled nursing facility?) to a much more comprehensive role in the overall process, execution and follow-up that a care transition entails.

However, making this kind of tidal shift in such a critical part of healthcare delivery isn’t going to be easy, especially for health systems with firmly entrenched processes and procedures. Yet hospitals that don’t realize the urgency of the need to master care transitions face significant risk and also forgo the upside that comes with doing care transitions well.

Following are three reasons why health systems need to stress the necessity of mastering care transition improvements as soon as possible:

  1. The very definition of “care transition” is changing. Historically, a care transition might have just dealt with how a hospital transported a discharged patient from its environment to another one, but now a care transition can refer to a much broader spectrum of activity and coordination. It entails any movement patients make between healthcare practitioners and settings as their conditions and health needs change during the course of a chronic or acute illness. As a result, care transition demands broader thinking: where did your patients come from? Where are they going next? Do they have a personalized discharge plan? Do they understand their medication plan, and will they adhere to it? Care transition now requires a multi-disciplinary care coordination team.

  2. New financial pressures mean that readmissions are costlier than ever. According to one analysis, one single readmission doubles the cost of a beneficiary stay of episode, which makes readmission expensive on its own. There are also new – and growing year-over-year– federal fines for readmission, which means health systems have an immediate financial interest in figuring out how to better manage care transitions beyond the traditional acute-care facility.

  3. Poor care transitions lead to negative behaviors and outcomes that drive up costs. There are a number of causes that can create poorly executed care transitions, such as lack of resources or electronic uniformity. Regardless of what’s behind a bad care transition, it can engender negative behaviors, including fragmented and uncoordinated care, non-compliance, and a breakdown of communication, all of which can lead to costly results like patient and provider dissatisfaction and inferior outcomes.
We all recognize that the current state of reactive, episodic care is simply not sustainable. That’s why hospitals should immediately address how they handle care transitions, employing a much more holistic approach that will help them stay ahead of this pivotal point in the healthcare industry.  

To find out how you can help transform your health system with a better, more sophisticated approach to care coordination, view our recent webinar recording, “Carrots and Sticks: Why Hospitals Need to Master Care Transitions Now”.

New Methodology Helps Organizations Better Measure the Impact of Absenteeism

Madison Agee

New studies have shown some of the positive outcomes associated with well-being improvement programs among employers, such as improvements in overall well-being and individual well-being elements, higher productivity, lower rates of absenteeism, and gains in job performance. And now, recently published research helps organizations that are looking to better measure the impact of these programs. A new study authored by the Healthways Center for Health Research expands upon existing, widely accepted methodologies and provides organizations with a more comprehensive and robust way to gauge the impact of their well-being improvement programs.

The study “Regional Economic Activity and Absenteeism: A New Approach to Estimating the Indirect Costs of Employee Productivity Loss”, was published in Population Health Management and introduces a new method for measuring the economic impact of work-related absences. Called the Regional Productivity Loss (RPL) method, the new method expands upon the most commonly used and widely accepted method, the Human Capital Approach (HCA). The study showed that measuring the impact of workplace absenteeism using the RPL method resulted in materially higher cost estimates than would have been found via the HCA method (34 percent higher for two smaller employers and 51 percent higher for a larger employer).

For decades, the HCA method has been the most widely accepted measure for helping employers quantify the economic impact of workplace absenteeism, but the method has some significant weaknesses. To address these deficiencies, Healthways researchers developed the RPL model, which has three significant advantages over the HCA method:

  • Measures lost output and not simply lost wages. The RPL method recognizes that employees are expected to generate value for an employer above and beyond their hourly wage — otherwise, how would an organization be profitable?
  • Accounts for labor replacement for the absent employee. The RPL method acknowledges that when an employee is absent, a co-worker often steps in to cover the workload.
  • Extends the impact of lost productivity to the regional level. The RPL method takes into account the “ripple” effect of workplace absenteeism, by measuring the impact of a single employer’s workplace absenteeism on businesses that interact with that employer, such as vendors and customers, as well as organizations that interact with those businesses.

Because of these advantages over the HCA method, the RPL method more comprehensively calculates the economic impact of workplace absenteeism and thus better conveys the value of programs aimed at reducing absences, such as well-being improvement programs. This is especially true in industries where employees are highly skilled or trained and not easily replaced if they are absent.

In an upcoming article, we’ll take a look at another study authored by the Healthways Center for Health Research that also makes an important contribution to the science of well-being improvement program measurement.

Topics: Science and Research