The Truven Health Blog

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

Three examples of how performance improvement opportunities were hiding in this health system’s data

By Truven Staff/Monday, October 16, 2017

Like most health systems, Indiana University Health System (IU Health) leaders knew they had large amounts of valuable data stored throughout the organization. The challenge for the largest health system in Indiana was how to use the often-segmented data to quickly identify opportunities for cost controls and financial decision making, especially at the regional level.

To meet this challenge, the system pulled together a results-driven group called the Profitability & Utilization Support Hub (PUSH), made up of experts in revenue cycle, supply chain, clinical operations, labor analytics and more. The team’s charter: Make data-driven recommendations that could eventually drive operational and financial improvements.

The PUSH group began to identify opportunities by leveraging a comprehensive comparative database. The robust and detailed benchmarks allowed the team to see where their organization stood compared to peers.

Here are just three examples of how the team incorporated performance benchmarking to fuel its recommendations:

#1  Reducing above-average telemetry usage

The group proactively found that telemetry usage at one of the system’s hospitals was 70 percent higher than the comparison group median. The PUSH team recommended a review of the hospital’s electronic medical record order set and staffing ratios, which led to changes. The hospital’s telemetry utilization was reduced to the comparison group median within three months.

#2  Increasing oncology patient volume

The health system had recently converted one of its hospitals into an outpatient facility offering emergency department (ED) and oncology services. Using comparison data, the team discovered an imbalance between oncology patient levels and staffing levels. Leadership acted quickly and launched a campaign to increase oncology patient and provider volumes to align with staffing levels.

#3  Boosting ED capacity

The chief financial officer of an IU Health hospital asked the PUSH group for guidance to figure out why ED visits were declining even though staff reported full capacity. The data showed the hospital was efficiently using its available space — treating 20 more ED patients per day than the comparison peer average — but it had six fewer treatment spaces. Based on that insight, the hospital received approval to expand to accommodate 25 more visits per day.

If you’d like more information on how the health system achieved these remarkable results, please reach out to us


Measuring the potential impact of a new palliative care service line

By Truven Staff/Monday, October 16, 2017

When you discover your mortality rates for stroke, pneumonia and heart failure aren’t where they need to be, what do you do?

The quality team at Carson Tahoe Health, a health system based in northern Nevada and eastern California, recently faced that challenge — and knew they had to answer two key questions: why is this happening and what can we do about it?

After a concentrated chart review, the health system discovered that the majority of patients who died in their care were at the end stages of their diseases.

Recent studies had pointed to the implementation of palliative care as a way to improve patient care and lower mortality rates. So to test the theory in their own environment, Carson Tahoe Health decided to roll out an inpatient care protocol in which hospitalists refer patients with end-of-life issues to a palliative care physician.

Comparing outcomes to determine progress

Using a clinical performance monitoring and benchmarking solution, the quality team was able to analyze several metrics, focusing on heart failure and chronic obstructive pulmonary disease (COPD) diagnosis-related groups in end stages of the diseases.

They tracked two groups of patients: those who participated in the palliative care protocol and those who did not. That way, cost, utilization, readmission, length of stay and other comparisons could be made.

The health system gained some key insights on the value of palliative care:

To see if they could move the dial even further on care improvement, the health system built and analyzed population reports to review the potential return on investment for an outpatient palliative program.

Informing the next step

With the new data and reports in hand, the health system proposed an outpatient palliative care service line to its board of directors, and the board approved it. Now Carson Tahoe Health offers a palliative care/heart failure chronic disease management clinic that sees patients within five days of discharge.

Seeing progress

After implementing the palliative care initiatives, the health system’s 30-day inpatient mortality rates for acute myocardial infarction, heart failure, COPD, pneumonia, stroke and coronary artery bypass graph surgery began trending lower than the national average.

They plan to expand palliative care services to other chronic end-stage disease groupings in the future.

If you’d like more information on how the health system achieved these results, please reach out to usYou can also read the full case study here.

How one health system closed care gaps and achieved improved ACO scores

By Truven Staff/Wednesday, September 27, 2017

As accountable care organizations (ACOs) for the Medicare Shared Savings Program (MSSP) know all too well, just one instance of a patient missing a follow-up visit to a clinic can change that person’s risk score. And those scores are ultimately important for demonstrating the MSSP goals of increasing quality of care while decreasing costs.

Cincinnati-based Mercy Health Select faced that challenge head on. Already one of the top ACOs in the US, Mercy Health Select wanted to do even more to close gaps in care and potentially improve the system’s ACO scores. Better scores would mean better care for patients and could help the system earn greater shared savings from the MSSP affiliation, too.

First, tackling a common issue: Different EHR systems

The Mercy Health organization started with a typical challenge for ACOs: Not all of the affiliated physicians in the network used the same electronic health record (EHR) system. That made it difficult to quickly consolidate information about at-risk patients across facilities.

That’s why Mercy Health Select opted to leverage technology that allowed the system to combine and mine the disparate sources of both clinical and claims data. The platform they chose also ran analytics on the data — to identify and prioritize the most at-risk, high-cost patients for follow-up communications.

Then, solving for speed

Of course, the timeframe for producing this kind of information is critical, too. If care coordinators wait too long to reach out to an at-risk patient who has not had a recommended cancer screening, for example, the ability to impact the individual’s health decreases.

So Mercy Health Select again used technology to update EHRs and patient risk scores within 24 hours. The new structure means clinicians can click on a link in a patient’s chart and see gaps in care right away — fueling fast intervention when necessary.

Solidifying the connection

Implementation of the new approach is paying off for Mercy’s ACO. With more gaps in care closed and more at-risk patients likely on the road to better health, the organization boosted its ACO score to 97.1 percent. That score is nearly 6 percent higher than the average1, and something all ACOs may aspire to achieve. After all, with that kind of improvement in score and patient care, ACOs are setting themselves up to earn greater shared savings.

If you’d like more information on how the health system achieved this result, please reach out to usYou can also read the full case study here

1 Muhlestein D, McClellan M, Saunders R. (2016, September 9) Medicare Accountable Care Organization Results For 2015: The Journey to Better Quality and Lower Costs Continues [Blog Post], retrieved from http://healthaffairs.org/blog/2016/09/09/medicare-accountable-care-organization-results-for-2015-the-journey-to-better-quality-and-lower-costs-continues/


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

How a Data Scientist Thinks about Risk Stratification

By Anne Fischer/Tuesday, October 25, 2016

“Risk”. It’s a word we hear every day in the healthcare industry. We want to avoid risk, we want to predict risk, we want to find patients that are high risk. We want to risk stratify populations (organize people into a set number of mutually exclusive tiers of increasing risk).

My recent blog posts have centered around the concept of Population Health. Clearly the idea of risk is particularly important in this world, where the goals are to keep well individuals healthy, avoid poor outcomes for those that are already sick, and minimize costs. Understanding, assessing, and predicting risk are all essential to this effort.

But what is “risk”? If you asked a physician, an insurer, and an average Joe on the street to describe “high risk” from a healthcare perspective, you would likely get very different answers. A physician might describe someone with high risk of developing a disease, high risk of a serious disease complication, or high risk of mortality. An insurer might describe someone at risk for a high amount of spending in the immediate future. The average Joe might describe someone at high risk for impairment/inability to function in daily life. Understanding the context-appropriate definition of risk is the first step toward building analytics to support risk analysis. And the appropriate definition is always dependent on the real world application.

Even when the application is understood, there is still considerable work to be done to identify the appropriate data and characteristics that lead to poor outcomes. Consider a discharge nurse who sees hundreds of patients a month as they prepare to depart from the hospital. Most knowledgeable hospital staff are aware that the most experienced discharge nurses will be able to tell you, with a high degree of accuracy, who is likely to show up back in the hospital in the near future. Multiple studies have tried to quantify the drivers of this type of “nurse’s intuition”. How do they know?

In 1964, United States Supreme Court Justice Potter Stewart used the now infamous phrase: “I know it when I see it” to describe his threshold test for obscenity in the case of Jacobellis v. Ohio. A discharge nurse might say much the same thing when asked to describe a patient at high risk for readmission. I know it when I see it. Characteristics such as illness burden, past behavior, social situation, self-care ability, home support, and others are often referred to, but the reality is that it’s the entire picture, and often a bit of an ambiguous “gut feeling” thrown in for good measure.

So how does Data Science fit into this picture? Our challenge as Data Scientists is to turn “I know it when I see it” into a measurable mathematical formula, so that everyone “knows it” even without seeing it in person. It involves extensive experimentation with different data sources, variables, and modeling techniques, as well as building in the capability for models to evolve and learn over time. At Truven Health Analytics, my team is exclusively focused on developing and testing new models, using various kinds of data that are readily available to us. In future blogs, we’ll describe some of these models including risk of developing diabetes and risk of admission. Truven Health, an IBM Company, now is positioned to move deeply into this space and develop these types of risk models by bringing together traditionally disparate data sources, clinical knowledge, and cutting edge modeling techniques.

Anne Fischer
Senior Director, Advanced Analytics