Tag Archives: Healthcare Analytics

MIPS and the Business of Healthcare


Post by Vicki Harter, BA, RRT


Vice President, Care Transformation

At this year’s Healthcare Information and Management Systems Society (HIMSS) conference, representatives from the Centers for Medicare & Medicaid Services (CMS) held multiple sessions where they reinforced the message that the Quality Payment Program and value-based programs are moving forward. Jean Moody-Williams, deputy director of the center for clinical standards and quality at CMS said “As we build the program, our goal is to achieve a 90 percent participation rate by all clinicians. That includes small practices as well.”[1] Other CMS officials touted tangible results that value-based care has been delivering, such as a “17 percent reduction in hospital acquired conditions across all measures from 2010 to 2013, to savings of $37 million from providers participating in the advanced ACO Pioneer program.”[2]

As about nine out of ten providers are expected to fall under the Merit-Based Incentive Payment System (MIPS) track of the Medicare Access and CHIP Reauthorization Act (MACRA), many providers are asking themselves whether they should fulfill MIPS’ minimum requirements or strive for more. Said another way, should their organization strive to be a MACRA All-Star? Is it worth it to commit the effort and investment required to max out potential bonuses?

There are four main inputs to consider as you create your data-driven strategy for performing under MIPS. The first is the amount of Part B Reimbursements that you are expecting currently, how much you have received in the past, and how much you expect to receive in the future. That is going to drive your bonus potential as a practicing system, which is the second input to consider. Your bonus potential is going to help you understand the amount of resources that you have available to make the necessary changes in your care team. This third factor is critical in driving your organization’s MIPS strategy as you may decide to change the workflows of your nurses and physicians or add a data analyst to help you take care of the populations that are now transforming your practice. And finally, consider the amount of data analytics you have in your practice. In the past, where have you performed? Where do you stand to gain? How much of a gap do you have to close to become a MACRA All-Star?

Providers should think about these key inputs they will need to evaluate for their MIPS strategy. What is my Medicare Part B Revenue today? What impact does MACRA have on it? Do I need to get ahead of payment rates that will remain basically flat? How many resources will be impacted by MACRA reporting requirements this year, next year, in two years? Can I earn a bonus that makes a difference to my business?

If you’d like to continue the discussion, please send a note here.

[1] http://www.diagnosticimaging.com/articles/cms-seeks-make-macra-manageable-small-practices

[2] http://www.healthcarefinancenews.com/news/despite-some-good-parts-ahip-says-gop-healthcare-bill-concerning-insurers

MACRA Final Rule: Empowering Physicians and Health IT


Post by Corinne Stroum (Pascale)


Director, Program Management – Healthcare Analytics, Caradigm

It’s the moment that Medicare Part B clinicians and healthcare administrators have been waiting for. The final release of the MACRA Quality Payment Program! Health & Human Services released the rule amidst much publicity, a response to thousands of comments and industry feedback throughout the year.

I would summarize the theme of the final ruling as, “Empowering physicians to achieve the Triple Aim through choice and health IT”.  My colleague Dr. Brad Miller, who contributed to the ideas in this post, also said it well in this recent blog post: “CMS’ ultimate goal with MACRA is to move healthcare further to a system based on quality, and to accelerate the shift in how providers use technology to improve patient care and outcomes.” Here are some of our key takeaways on the final release:

  • Per the earlier “Pick your Pace” communique from acting CMS administrator Andy Slavitt, clinicians can still choose one of three participation pathways for Performance Year 2017:

      – Submit minimum data by March 2018 to avoid a negative payment adjustment

      – Submit partial data to earn neutral or minimal positive payment adjustment

      – Submit complete data to earn a moderate payment adjustment

  • Clinicians will not be scored on the Resource Use category until 2018. In the absence of Resource Use, the Quality category raises to 60% of the MIPS composite score for PY2017.

– Overall, while choosing which quality measures to choose will remain a challenge, by pushing out the Resource Use category until 2018, CMS is giving providers more time to analyze their data and intelligence to drive the necessary practice changes for improved Resource Use performance.  Identifying these areas for RU and enacting change represents a significant practice and workflow re-design effort for providers and this extra year represents a more realistic timeframe under which providers can adapt.

  • Clinical Practice Improvement Activities have been renamed to the simpler, “Improvement Activities” category.
  • CMS has provided much clearer guidance on how existing alternative payment models (APMs) will qualify for different categories:

 – As previously assumed, CMS established the quality reporting requirements for Medicare Shared Savings Plan (MSSP) Track 1 as sufficient for the Quality category.

– Medical Homes, and advanced APMs, will earn full credit for the Improvement Activities category; MSSP Track 1 and Oncology Care will receive points based solely on their APM participation.

  • Advancing Care Information requirements differ based on EHR edition:

– Patient-generated health data is an opportunity for those reporting prior to the 2017 edition to start learning from the copious amount of wearable and patient-reported data now in the marketplace.

  • CMS has supplied the healthcare public with fantastic, easy-to-use resources on the new CMS Quality Payment Program (QPP) site.  Users can select and export their a la carte activities or measures for easy tracking.

Taken together, these changes reflect the ability of healthcare organizations to choose how they adopt MACRA.  First, providers have been given a little more breathing room to gather their understanding and strategy for MACRA overall.  This helps with the widespread sentiment that providers were overwhelmed on how and what to report in the first year.  Second, there is a more gradual focus of scoring on smart fiscal skills and slowed rollout of large downward payment adjustments which aims to decrease overall MACRA performance and financial anxiety.  Finally, CMS motivates providers to get ahead of the rule by supplying incentive bonuses for underrepresented types of quality measures or for demonstrating advanced registry usage.

2017 represents a time for providers to get educated on MACRA’s subtleties, gather needed data and intelligence and develop go-forward strategies to effectively evolve with MARCA.  This includes the hefty task of experimenting and training their practitioners, support staff and their tools like software solutions needed to succeed in future years.  This means organizations now have an opportunity to get ahead of the requirements by creating a MACRA strategy in the remaining 2016 and beginning of 2017 to establish a flexible foundation for MACRA success.  More directly and simply, CMS has listened to providers and given them more space and time to develop practice responses and strategies to adapt to this brave new MACRA world.

 

 

 

Can MACRA and MIPS Move the Needle for Healthcare Analytics?


Post by Corinne Stroum (Pascale)


Director, Program Management – Healthcare Analytics, Caradigm

The Medicare and CHIP Reauthorization Act (MACRA) draft has become a novel I can’t put down. Its 962 digital pages tell a compelling story on the future of healthcare metrics. One narrative I follow in particular, is the next generation of quality measurement that shifts the focus of healthcare analytics to the reporting of patient outcomes.

In MACRA’s first year, most Medicare Part B clinicians will be eligible for the Merit-based Incentive Payment System (MIPS). MIPS will unify existing process-based quality measurement systems into one that promotes diversity of measure types and encourages providers to report on measures which it deems to have more impact.

Here are some examples of measure types that form the performance standards in MIPS:

    • Process measures – These are the most simple measures to report on such as whether a provider successfully completed something, such as an evidence-based best practice. This might take the form of an annual influenza vaccination for an at-risk patient. While process measures formed the meat of early healthcare quality metrics, they don’t tell the whole story.
    • Outcome measures – These measures get to the heart of clinical care by measuring how providers have influenced patient’s health. For example, has the patient’s depression index score gone down over a six-month period? Did an intervention prevent complications? Did a patient attain cancer remission?
    • Intermediate outcome measures – Some outcome measures look at the long term, which may take years to measure performance. Intermediate outcome measures are an important part of the story because they identify other clinical markers to indicate progress along the way. One example is the reduction of fasting blood glucose as part of a larger diabetes management plan.
    • Patient-reported outcome measures (PROs or PROMs) – Championed by organizations like PCORI, these measures are the window into the perspective of the patient: how does the patient feel about his/her health (such as the PROMIS survey) or how does the patient report the outcome of treatment?
    • Patient experience measures Cousins to PROMs, patient experience measures ask patients and caregivers about their perception of their care. The Consumer Assessment of Healthcare Providers and Systems (CAHPS) and Hospital Consumer Assessment of Healthcare Providers and Systems (HCAHPS) are well known experience measures.

The MIPS quality performance category offers opportunities to achieve bonus payments as well as prevent penalties. CMS will allocate points for quality measure performance depending on a “benchmark decile” – assigning providers level of achievement based on thresholds set during a baseline period. These deciles determine the points that the provider will receive. For measures already with overall high performance – those which CMS deems to be “topped-out” – it will be more difficult to obtain full points, incentivizing providers to explore new healthcare quality measures in which they can demonstrate excellence.

MIPS will require one outcome and high-priority measure as part of a standard submission. CMS deems high-priority quality measures as those which track appropriate use, efficiency, care coordination, or patient safety.   Additionally, CMS will score two bonus points for each additional outcome and patient experience measure and one point for each extra high-priority measure that a physician or group elects to report on.

In the first two years of MIPS, the Quality Performance score makes up about half of the performance score. In the following years, the Quality Performance score will balance out with the Resource Use score and clinicians should move from MIPS to advanced APMs. For the next two to three years, however, MIPS will move the needle on quality measurement. It will incentivize providers to report on impactful measures and measures that have not already “topped out”, and to store and transmit quality performance data electronically. This electronic data sets the stage for future victories in healthcare analytics: more data to work with, and more meaningful data.

I highly recommend beginning the process now to develop your MIPS strategy before the performance period begins in 2017. You shouldn’t underestimate the time needed to implement MIPS data and reporting requirements, identify the measures you can be successful in, and plan for how you will drive improved performance in those measures. If you’d like to talk about how Caradigm can help you with your MIPS Quality Measurement strategy, then please leave us a note here.

MACRA: Reporting for Quality’s Sake


Post by Brad Miller


Vice-President of Clinical Solutions, Caradigm

Now that we’ve had some time to think about the Medicare Access and CHIP Reauthorization Act (MACRA) and digest the details, a few high-level points stick out. First, it does away with Medicare’s Sustainable Growth Rate (SGR), which few physicians were in favor of due to the detrimental impact on services fees. Second, it consolidates and simplifies current reporting programs that were viewed by some as reporting for reporting’s sake– Physician Quality Reporting System (PQRS), Value-based Purchasing (VBP) and Meaningful Use (MU). For example, in the Merit-Based Incentive Payment System (MIPS) track of MACRA, providers only have to report on six measures, instead of the nine required in PQRS, and they also have greater flexibility in choosing what those six measures are. Third, and most importantly, CMS’ ultimate goal with MACRA is to move healthcare further to a system based on quality, and to accelerate the shift in how providers use technology to improve patient care and outcomes. CMS believes that based on its conversations with thousands of clinicians and patients, most providers have yet to acquire the right set of technology tools to make care and reporting more effective and coordinated.

Andy Slavitt, Acting Administrator for the CMS describes one the main drivers of MACRA:

“With many hours of observations, what became clear was that the combination of technology, regulation and measurement took time away from patients and provided nothing or little back in return. Among other things, physicians are baffled by what feels like the ‘physician data paradox.’ They are overloaded on data entry and yet rampantly under-informed. And physicians don’t understand why their computer at work doesn’t allow them to track what happens when they refer a patient to a specialist when their computer at home connects them everywhere.”[1]

So, how should providers start preparing for MACRA? The first thing they need to determine is whether they will qualify for the MIPS or Alternative Payment Model (APM) track. It can be a complicated determination because some organizations could be considering entering into programs (e.g. NextGen ACO) that would impact which track they will qualify for in the future. Next, they should assess their current ability to succeed in all of their value-based programs, including how they will meet the MIPS or APM reporting requirements in order to qualify for bonus payments. Although it feels like the proposed rule was just announced, providers should begin strategizing for MACRA now because the performance period scoring for MACRA begins in 2017.

At Caradigm, we are already working to stay ahead of MACRA. This includes evaluating and prioritizing the proposed measures in advance of the final rule. We are also collaborating with customers to understand their specific requirements and to determine if there are any synergies with their other initiatives and applications. Our overall approach is to build a data aggregation and analytic foundation that can be used to support multiple initiatives and reporting requirements. That foundation has to be robust yet nimble and efficient so organizations can scale programs and evolve rapidly to meet future iterations of requirements. We have architected our technical solutions to help technology support, rather than be a burden, on the progress of providers.

MACRA is a broad topic with lots of areas to explore and many implications for providers, so we will be discussing different parts of it regularly on this blog. If you’re interested in speaking about your quality reporting and MACRA needs further, then please send us a note here.

[1] Slavitt, Andy. “Datapalooza: MACRA, HER Reform and Working with Doctors – Not Against Them.” The Health Care Blog. May 12, 2016. Originally published: http://thehealthcareblog.com/blog/2016/05/12/datapalooza-macra-reforming-meaningful-use-and-working-with-doctors-not-against-them/

Expanding Your Population Health Data Foundation to Claims and Beyond


Post by Niranjan Sharma


Director of Engineering for Healthcare Analytics Platform & Applications, Caradigm

Healthcare is traditionally thought of as the care of patients by healthcare providers. Clinical data is generated during that care, and payers reimburse providers for the services rendered based on submitted claims. For providers engaging in population health, working solely with clinical data only tells part of the population health story. Most healthcare organizations are striving to derive more value and population insight by including claims and other types of data so that they can better stratify their populations, drive other analytics efforts, and improve care coordination among many activities. 

Payer Pic1

Siloed Data Challenges

Payer Pic2 v3

The challenge is that it is complicated to ingest, normalize and model different types of healthcare data. Healthcare organizations often have many disparate information systems, and many work with partners who in turn also have many disparate systems. Most providers are still working towards harmonizing all of their data so they can view a single picture of their populations and make the best use of it in a timely manner to meet their clinical and financial goals.

 

Harmonize Data, Analyze & Compute

Payer Pic3

One of Caradigm’s hallmarks as an enterprise population health company is that we are experts in healthcare data management infrastructure and processes. We help our customers remove the complexity and manual processes associated with data management through the Caradigm Intelligence Platform (CIP), an enterprise data warehouse designed specifically for healthcare. CIP enables organizations to harmonize their data, and then perform a rich array of analysis (e.g. predictive risk stratification, utilization), as well as computations on data (e.g. quality compliance, gaps in care, display last glucose results, display last PCP visit for a patient, etc.).

 

Modeling Claims Data Using Entities

Payer Pic5

 

Caradigm has a proprietary methodology that structures data as specific healthcare entities. On the outer ring in the diagram above are examples of core payer entities that we can introduce with our customers. Seeing payer data organized in this fashion is often eye opening because it provides a harmonious view of the care delivered to patients. What is even more exciting is when payer data is combined with clinical and other data to show a complete picture that can then feed other integrated applications.

 

Lighting Up Applications With Payer Data

  • Risk Management Analytics
  • Accountable Care Organization compliance
  • Gaps in Care
  • Gaps in Billing
  • Network Utilization Analytics
  • LOS Analytics
  • Post-Acute Care Analytics
  • PMPM Analytics
  • In-Patient Analytics
  • ED Visit Analytics
  • Ambulatory Visit Analytics
  • Drug Utilization Analytics
  • Conditions Analytics
  • Bundled Payments Analytics
  • EMR Only Analytics
  • Claims Only Analytics
  • Harmonized Data Analytics

The beauty of a complete and reusable data asset is that it can light up all kinds of analytics applications. You can forecast clinical and financial risk, identify gaps in care, and analyze utilization or network steerage in order to uncover opportunities for financial improvement.

The amount of data available in our industry is growing exponentially. It is time for healthcare organizations to augment their ability to harness all of that data and realize more value. If you would like to discuss how your organization can harmonize its data and better leverage claims data as part of population health efforts, then please send us a note here.

Moving Healthcare Analytics from Measurement into Management


Post by Corinne Stroum (Pascale)


Director, Program Management – Healthcare Analytics, Caradigm

Current hot topics in healthcare analytics include user-centric dashboards and self-service reporting. These provide users with information they need, but don’t necessarily provide them with the means to extract key insights or take action on their results. I consider this to be traditional measurement, but propose that healthcare analytics must evolve into a rich management tool alongside these new features. Let’s explore the key steps to achieving this management goal.

Analytics

Quantify Your Performance

Whenever a computer or device is in use in healthcare delivery, there is an opportunity to capture data. This is a natural starting point for either a measurement or management tool: both types of tools must empower users to build reports or identify key performance indicators (KPIs) from an authoritative source of data.

Know your Population

An authoritative data source is a great start, but a patient doesn’t leave a footprint in just a single system. Information about a patient spans many systems and the mash-up of this data from these sources is vital to producing meaningful and actionable analytics.

Incomplete data can lead to user distrust – “I see in system X that my patient has had this immunization; why doesn’t my report reflect that?” A complete view of the patient’s data, from all systems, enables deeper and more accurate insights.

Find the Signal in the Noise

An evolution from measurement to management relies on a user’s ability to explore the data on their own terms rather than with prepackaged KPIs. There are natural hierarchies within healthcare data that can aid users in this exploration. For example, a provider group is composed of individual practitioners, an inpatient facility has its departments, a grouping of diagnoses will narrow down into individual health issues and services, etc.

Exposing these natural hierarchies in a management tool helps users to uncover areas that warrant attention. For example, are particular classes of drugs having unexpected outcomes? Can a user spot a spike or drop in performance metrics for a single provider in a given facility? A user should be able to dig into data hierarchies and determine the factors affecting a particular metric.

Take Action

Recent advances in analytics allow users to look at metrics in real time, providing an opportunity to intervene and change the course of performance trends. Therefore, an analytics management tool should enable users to do something with their data, such as:

  • Identify quality compliance gaps and let users contact the provider to facilitate a necessary appointment or enroll patients into a campaign, which results in the patient being contacted by a care manager or receive a mailer reminding them of an important healthcare issue they should address
  • Show the user a utilization hotspot and enable him to export data from this report to assign and share amongst their colleagues
  • Provide opportunities to move insights into different applications, such as flagging patients who have not received a post-discharge outreach to ensure that a provider is performing appropriate due diligence (and tracking it in the appropriate application).

Measure Outcomes of your Actions

If an analytics application empowers a user take action, it certainly needs to measure the impacts of the interventions. It might report on the following:

  • On average, how long did it take between the user’s action and the desired result?
  • Are some users more successful at generating positive results?
  • If a user is given many actions as part of an intervention, which is most effective at achieving the desired result quickly?

In summary, healthcare analytics applications are no longer just for quantifying performance from a single source. They’re beginning to help users find meaningful signals in large amounts of data, enabling users to take action, and measuring outcomes of these interventions. These improvements are the key to evolving analytics applications from measurement to management. If you’re interested in discussing how Caradigm can help evolve your reporting and measurement efforts then send us a note here.

How to Get the Most Out of Population Health Analytics


Post by Sumeet Shrivastava


VP Engineering for Population Analytics, Caradigm

It seems like there is a constant buzz these days around healthcare analytics and their role in population health. It makes sense because in order to effectively manage a population of patients, healthcare organizations need to gain a variety of different insights. For example, they need to understand the clinical and financial risk of their population, define cohorts and prioritize patients to be enrolled in care management, evaluate how they are performing against quality measures, view patterns in utilization for financial improvement, etc. Analytics provide these insights.   

However, in order to get the most value from analytics, it’s important to understand how analytics are integrated with other population health strategies. Analytics shouldn’t be viewed as an independent activity because population health is a connected series of activities impacting the entire organization and requires a broad set of capabilities including data aggregation, analytics, care coordination and patient engagement and outreach.  It is also important to consider end user needs such as making it easy to access, visualize and take action. Let’s explore a few of the key success factors needed for population health analytics in more detail.

  • Quantity and quality of data: These elements are essential to light up any pop health analytics scenario. Across many organizations, I have seen implementations get delayed due to “bad data”, i.e. data that is not ingested in the format that is required to produce quality analytics, and later requires additional work to cleanse the data to be usable. A data aggregation solution should be designed to handle bad data and provide tooling to make it easier and faster to consume data from different and often non-uniform sources. While the data from different systems will be inherently non-uniform, data ingestion tooling and software should considerably shorten the process. Quantity i.e. completeness of data is also important because incomplete data dilutes the value of the insights presented. Incomplete data can skew or inflate insights, which then can make it challenging to formulate actionable strategies based on the information. 
  • Easy and real-time access: Once data has been aggregated and cleansed, it needs to be easily accessible, timely and in a format that can be used by both applications and by non-technical analysts. If it takes days or weeks to access analytics, then that time lag can render the data out- of-date.  Creating consistent and reusable data models along with self-service tools better ensures that queries are simple, maintainable and timely. 
  • Actionable insight: For analytics to make the greatest impact, they need to be actionable and integrated into clinician workflows. For example, gaps in care can be surfaced in an EMR so that a physician can close them while still in the presence of a patient. Also, if an analyst sees quality measures below where they should be, the analyst should be able to drill down to the provider and patient level so that additional action can be taken (e.g. enroll patient in a campaign or the analyst creates a task to prompt a clinician to take action). Analytics should also be surfaced within care management workflows as part of a longitudinal patient record so that all members of a care team have a more complete picture of patients, which can then be incorporated into the plan of care.
  • Flexible visualization engine: A picture is worth a thousand words. Users need to able to visualize the data in various formats – whether it is graphs, plots, trend lines, etc. An analytics engine should support different forms of visualizations that give users flexibility to derive value. 
  • Advanced analytics: To evolve beyond retrospective reporting and receive greater value from analytics, organizations need to leverage predictive and prescriptive analytics. Predictive analytics are essential for prioritizing resources as they forecast clinical risk, identify cost savings opportunities, likelihood of readmission, and can even identify which patients are likely to comply with a plan of care. Based on these predictions, prescriptive analytics can go one step further by suggesting interventions and identifying what actions should be taken to improve care for the patient.

Caradigm has taken a holistic approach to population health analytics since our inception.  We designed our enterprise data warehouse, analytics applications and workflow applications to work together, which makes each individual application more effective. Our analytics offering is unique because it can leverage virtually all of an organization’s data from disparate systems in real-time, apply best-of-breed algorithms to that data to derive insights, then surface that information directly within clinician workflows to drive action. If you’d like to discuss pop health analytics more, then please send us a note here. I look forward to continuing the discussion on analytics in an ongoing series of posts that will be coming from the Caradigm team. 

 

The Importance of Patient Motivation in Population Health Management


Post by Steve Shihadeh


Chief Commercial Officer, Caradigm

As healthcare organizations take on more financial risk for patient populations, they must gain a much deeper understanding of their patient population in order to drive better outcomes. Realizing the full potential of population health management is limited by finite care management resources as well as each patient’s willingness to participate in his or her own outcomes. By stratifying your patient population based upon predicted future risk that considers patient motivation, providers can identify and prioritize patients most likely to be positively impacted by targeted care planning and interventions.

Factoring patient motivation into the risk stratification of a patient population is one of the exciting ways that Caradigm is helping innovate population health management. Consider the following example of two patients that I have a deep understanding of – my mom and my dad.  Both have chronic conditions, and would be identified by most providers as patients that are high risk or could potentially move to a high risk stratification. Inside of an EMR, the two patients look very similar, but the truth is they should be viewed very differently by providers.

My mom is the ideal patient. She follows her physician’s instructions, fills her prescriptions promptly, schedules her follow-ups, and takes exercise classes as recommended. On the other hand, my dad presents as a more problematic patient because he doesn’t follow his doctor’s recommendations. He’s the opposite of my mom in terms of participating in self-care even though he also has a chronic condition that needs ongoing management.

For a provider, it is extremely valuable to factor in patient motivation when stratifying populations to identify and prioritize patients like my parents. Providers are more likely to have much better outcomes from interventions with motivated patients. Care teams can better assess which patients will benefit most from certain types of interventions, so that they can manage their limited time in order to receive the highest return on intervention.  I am not saying “only focus on motivated patients” but I am saying “working with motivated patients can have the biggest positive impact for all”.

I have been asked, “How in the world do you measure patient motivation?” It starts with being able to aggregate and leverage all of a provider’s data (e.g. clinical, claims, financial). Next, Caradigm applies sophisticated analytics to that data with help of our partner LexisNexis with MEDai Science who has been refining and perfecting the accuracy of how they calculate patient motivation for many years. The data plus analytics then enables deep population stratification and providers can use that information to streamline care management workflows as well as surface it at the point-of-care to guide decisions.

I’ll be participating on the Data Analytics and Practical Uses panel at the Becker’s Hospital Review CEO Strategy Roundtable on November 4th in Chicago, and would happy to continue the discussion at the event or after.