A study by the management consulting firm of McKinsey, “The New Growth Game: Beating the Market with Digital and Analytics” revealed that companies using digital analytics generate on average 50% more revenue than those not using these analytics.  Digital analytics also provides practical solutions for high-growth industries such as life sciences and healthcare by providing granular insights into customer behavior and purchase trends.

 Increased Data Accuracy

Increased data accuracy is another reason why providers should invest in digital analytics as it will provide accurate data insights that can be utilized for decision making purposes; lead qualifying activities; market segmentation; and prospecting campaigns.

In light of the significant benefits resulting from the use of digital analytics, it is no surprise that healthcare providers are swiftly converting to make use of this technology.

 Insights into Patient Behavior

The number of people in the United States who suffer from chronic diseases is skyrocketing. This increased demand on providers can equate to more pressure on them, especially financially. To make sure they meet the needs of their patients, healthcare providers can employ digital analytics to gain insights into their patients’ behaviors and needs and leverage those insights to spearhead chronic illness.

 Collecting Data is Not enough

Collecting data is not enough. They need to know how to analyze it and use it for their benefit. The right digital analytics can help them understand their patients better; identify potential new services; predict trends; and improve conversion rates on their website.

The right analytics can help providers answer questions like: What is happening with our website traffic?  How many people are calling in for appointments? What is happening with our ad campaigns? The answers to these questions requires a specific skill set in analytics.

 More Efficient Services

Analytics helps healthcare providers in making their services more efficient and effective.

Metrics such as conversion rates; average visit duration; and call bounce rates can assist healthcare providers to identify improvements to their services. Furthermore, analytics can be used to monitor the effectiveness of advertisement campaigns and how it affects the overall revenue and business performance.

Reference:

1. A Look at Challenges and Opportunities of Big Data Analytics in Healthcare https://www.mckinsey.com/~/media/McKinsey/Business%20Functions/Marketing%20and%20Sales/Our%20Insights/The%20new%20growth%20game/The-new-growth-game-Web.pdf

In recent years, most people in the healthcare industry have heard of HCCs (Hierarchical Condition Categories).  HCCs are conditions and diseases that are grouped together into categories by body system or disease process to measure the health status of a patient.  In medical coding, this is known as Risk Adjustment.  The current Center for Medicare & Medicaid Services (CMS) HCC model includes nearly 10,000 ICD-10 codes that map to 79 HCC Categories.

CMS utilizes HCCs to reimburse Medicare Advantage plans based on the health status of their enrollees. The plan pays for the predicted healthcare costs of a patient or population of patients.  Costs are estimated based on the demographical profile and  the health status of the patient.   The data that is utilized to determine health status is based on the diagnoses codes from billed claims and medical records which are collected by physician offices, hospital inpatient visits, and outpatient settings.

In order to categorize HCC data, we need to look at qualitative text data that is usually present in medical coding and survey methodologies.¹   HCCs are dependent  upon the assigned risk scores from ICD-10 coding and demographic information and in order to determine those costs a RAF (Risk Adjustment Factor) score is calculated for that patient.

Insurance companies use algorithms to predict the cost of care for patients. For example, a patient with few serious health conditions could be expected to have average medical costs for a given period of time.  However, a patient with multiple chronic conditions would be expected to have higher utilization of services and a corresponding higher rate of health care costs. ²

How does AI factor into HCCs?

The term AI (Artificial Intelligence) is becoming a more commonplace and recognized term.  AI utilizes machine learning to simulate human processes.  Using ,  AI makes human processes more efficient. As AI relates to HCCs, machine learning natural language processing, disease detection algorithms, and suggestion scoring are terms for the technical processes that are  utilized to identify otherwise unfound data in a patient’s history that help assist in determining the RAF score.

At the end of the day, many companies are limited by time and resources when analyzing and optimizing RAF scores.  An established patient may have a new diagnosis for this current year, but it is possible that the prior year’s diagnoses have progressed and should be coordinated to a new non-progressed diagnoses and be recaptured. This over-time look at the patient’s history creates opportunities that would have been previously missed.

Natural Language Processing is one of the must-have tools for disease discovery. By leveraging the natural language processing for chart abstraction, we improve the efficiency of identifying underlying disease burden ³  

The Future of HCCs

HCCs are the future of better health management.  Medical coding professionals should be sure they stay up to speed on the latest advancements in coding in order to ensure that the level and intensity of the services provided to patients is aligned with the reimbursement. CMS has some great HCC software that ensures appropriate diagnosis codes are reported for the patient.  Companies that utilize natural language processing software have introduced new tools that can discover insights previously locked in unstructured data like surveys in the form of PDFs and text notes. ⁴  

As we move forward, let’s consider the complete picture of the risk adjustment factors and how the HCC score reduces the need to request additional medical details and audits of claims. If you want to know more about reimbursements and HCCs or you currently participate in a value-based reimbursement model. Let us know and we can help you get a handle on high-quality care and sustainable profits.

1. https://www.tandfonline.com/doi/abs/10.1080/01930826.2015.1105035
2. https://www.aafp.org/family-physician/practice-and-career/getting-paid/coding/hierarchical-condition-category.html#:~:text=Hierarchical%20condition%20category%20(HCC)%20coding%20is%20a%20risk%2Dadjustment,health%20care%20costs%20for%20patients.&text=Along%20with%20demographic%20factors%20(such,adjustment%20factor%20(RAF)%20score.

So how do we navigate this new landscape?  Financial markets, hospitals, and the hospitality industry have been hardest hit with some of the most radical disruptions we have seen in decades. How can we continue to find innovation and opportunity in this extremely difficult environment?

Learn How to Digital Partner Differently

What exactly is the meaning of to digital partner differently? This means going all in.  Grab the cameras, set up the lights, it’s GO time!  People have been learning very rapidly how to digital partner better.  Years ago, interviews were constrained to being in person and in the same room.  Businesses spent millions of dollars traveling to meet clients and today we are holding these same meeting from our phones and tablets from our home office.  Now is the time to innovate around the pandemic to create those much-needed digital partnerships.  Offer things that no one else in the industry is offering perhaps by adding some flair to your training offerings.  Create a new service that is even more digitally driven than your competitors.  Automate your customer ending processes and show them what you know.  Partner with a company that offers something exciting like introductory videos or adds soothing background music to your virtual webinars.  We could all use it.  Make your company stand out with digital partnerships that are different.

Launch Now

Great companies can be born as a result of disruptive events, for example, Uber, Groupon, and Slack, that fall into this category.  Look at the changes in the real estate marketplace where a prospective buyer can access a completely virtual tour of a home and meet with their client  over a Zoom meeting.  The need no longer exists to even step foot into the home.  Many transactions are occurring without ever visiting the property and thus becoming a completely virtual experience.

Where do we get the confidence to trust these services?  I think that it is from knowing that someone smarter than us innovated and created a process around something that assists in our life progression.  We hope that they have thought out all of the bugs and errors along the way.

This means that we have the potential opportunity to find those bugs and address those errors in a way that is more meaningful today than perhaps previously thought.  Can you find the gaps?  Today, some might say we have a bigger voice because everyone has been upgraded or downgraded (depending how you look at it) to the same video-enabled internet platform.  Here, in the digital arena, we are on a level playing field and as we approach the issues.  There is no better time than now to humbly innovate in the industries most impacted by the crisis. Spend the time now!  Launch something that the future will need and thank you for it!

Do More with Less

Can we increase operational efficiency without spending another $10,000-$20,000 on a product or service for the year?  I’m sure we can do this.  Drill down into your existing team and focus on the technologies that are already in use.  Help everyone become more efficient. For example, have your administrative support team member or Excel Analyst host a virtual training class and invite the entire team.  Have your analyst guru instruct everyone how to addresses problems in Excel and perhaps how to model data to answer specific questions about their projects.  Share this information far and wide.   Repeat, repeat, repeat and hope that the team recalls some specifics of the training and brings that learning into their own processes.

Are you utilizing Microsoft Teams or Slack?  Are you actually using Teams for the complete project setup and project management or are you just using Team to communicate like Skype?  Microsoft Teams is a very powerful collaboration tool and integrates many facets of a solid project management or workflow foundation.  Having colleagues working within those boundaries, although difficult, allows for a more fluid and easier project administration.  It fosters centralization and conversations around the work product which makes things easy to find and reference later.

Balance Your Short-Term Versus Long-Term Needs

As we continue to search for solutions to the problems that a company encounters, we should always consider the ways in which we can reduce risk without adding additional overhead and ensure that our team adapt to the ever-changing needs of the crisis.  Setting goals for the business, much like setting personal goals, requires strategy, tactics and communication in order to make it a reality.  Set your sights for a one-year goal on business operations. How do we envision our organization to be operating one year from now?  At first, this question may seem nuanced and this question should be asked every year as part of a progress check to determine the reasonableness of that future vision.

What must be kept in mind is how we can change the current state which involves thinking about the systems that are currently in place. Those systems may have been flushed out and work really well or they might not be working well.  The job of innovators on the team is to determine how things can work better.

Don’t Make Small Problems Bigger Than They Are

Finally, do not make problems bigger than they need to be.  Solve for the immediate need of the client or supervisor and make sure not to put the task off until it is too late which could result in a missed deadline.  Ask those tough questions now while you have the time to solve the problem. Think about what you are doing and don’t forget to be present in the problem solving.  Sometimes the only thing stopping us from solving the problem is being fully present in the moment of solving that problem.  Be a good team member by being the change agent that you would want to see in others.

References

1. The Digital Transformation Playbook: Rethink Your Business for the Digital Age By. David L. Rogers.
2. Scaling New Heights: A Toolkit for SME’s Preparing for Post-COVID-19 Business By. Craig

Today, many applications are utilizing machine learning, but we don’t always know how or to what capacity.  How do we integrate machine learning at our business?  How do we get from A, not using any supplemental machine learning tools to B, full integration and adoption?

Although not widely realized or known, many tools we utilize every day already integrate many facets of machine learning, we just don’t see it.  The algorithms behind intelligent search, suggestions on Netflix, Social Platform Censorship, and even Microsoft PowerPoint, are all powered by machine learning.  Most of the time when you see a PowerPoint referencing A.I.  What you really want to know about is the machine learning. So, what’s the difference between machine learning and AI?

Artificial Intelligence is more of a buzzword these days, you can buy a domain and claim to use AI in a presentation, but in all honestly, there’s probably a good amount of fluff mixed in. Many claim to use AI but have minimal achievements.  In application development, especially with AI and Data Science, we can often put the cart before the horse.  Most AI today is a pitch in a slide deck.  More recently, we’ve seen models as a series of regressions or neural networks, attempting to solve some really complex decision-making issues.  But at the enterprise business level these tools have a long way to go to reach unencumbered adoption.

The reality is that in order for AI to be true and robust, it would need to enable in-the-moment decision making with an influx of new data all the time.  The entire artificial intelligence module must be embedded at every layer of the company’s ecosystem.  To be truly effective, it would have to live in the Operating System (OS) of your computer, your e-mail, your devices, and company work product. It would have to integrate back with cloud services in real-time and analyze potentially terabytes of data in seconds. It would need a feedback system that tells it whether it did a good job or not, and some serious looks at how often re-training of the models is necessary.

Today, this is not only possible, it’s frequently happening at every level of the industry.  However, many tools that sit on top of those big players simply don’t have the in-depth subject matter expertise to solve the problem.  Maybe the model is too broad, or maybe the data isn’t internally consistent, it might not get you the answers you need when you need them.  Don’t get me wrong it’s here already but more so for the bigger market players than the niche consulting or legal firms.

While looking at these products and tools there’s a few things we should especially look out for, and questions to ask:

• Vet the Executive Team: Evaluate startups and review backgrounds. Look for technical expertise and many years of statistics and data science background. Bonus points for specializations in certain fields and certifications that are specific to you.
• Is it internally consistent? Ask some basic technical questions, and some tough ones. There are AI products that are totally bogus out there.  Talk to the vendors about where they get the data they use in the models, what models and techniques they use, and how they validate the model.  What would you check in our data to ensure the models work the same?
• Consider the fit within the organization. Can all the people at my organization use the tool, or is it specific to a select few “power users”? It’s not enough to just ask someone in the tech team if this will solve our problems, you need a team if you want it to work for a team. Start slow, with a use case. Some early adopters and supporters who share in your frustration may help bring the solution to life and assist in implementation. You need allies.
• Will the product evolve with the organization?

Now more than ever the importance of explaining business outcomes hits home for me.  Next time you see a company saying they do AI, ask them questions, make them prove it.

Ask about these processes to ensure that the data your next tool plans on integrating is being used in a way that makes sense to the business.  Where does your data live?  How will this tool extract it and how frequently?

Finally, are the models robust enough to actually get you an answer?  Many models out there are broad in nature and only provide probabilities.

The HIPAA Right of Access Initiative was created to support patients’ rights to timely and affordable access to their health records.

The HIPAA Privacy Rule protects individual’s rights to access their health information under 45 CFR §164.524.  Generally, the HIPAA Privacy Rule requires:

“HIPAA covered entities (health plans and most health care providers) to provide individuals, upon request, with access to the protected health information (PHI) about them in one or more “designated record sets” maintained by or for the covered entity.”¹

The “designated record set” is defined at 45 CFR §164.501 to include:

“…a group of records maintained by or for a covered entity” that includes medical and billing records; enrollment, payment, and claims adjudication data; and case or medical management record systems data.²

HIPAA generally requires covered entities to provide access to medical records within 30 days of a patient’s request and also specifies what fees providers can charge.³

 OCR Enforcement

Department of Health and Human Services (HHS) Office of Civil Rights’ (OCR) enforcement of this initiative began in 2019.  Bayfront Health St. Petersburg paid $85,000 to the HHS OCR after failing to provide records to a mother for her minor daughter in a timely manner.⁴

In September of this year, the OCR resolved its 20^th enforcement with an $80,000 settlement.

Children’s Hospital & Medical Center (CHMC) failed to provide a mother:

“with timely access to her minor daughter’s medical records. CHMC provided some records but did not provide all of the requested records to the parent’s multiple follow-up requests.”⁵

The OCR also recently announced four additional enforcements totaling $232,000 in settlements in addition to corrective action plans, and one civil money penalty of $100,000.⁶  These we not related to a parent/minor relationship.

 The OCR Not Backing Down

In the HHS press release, OCR Director Lisa J. Pino is quoted as saying:

“OCR will continue its enforcement actions by holding covered entities responsible for their HIPAA compliance and pursue civil money penalties for violations that are not addressed.” ⁷

The most recent enforcements include individual doctors, medical groups, and specialty treatment centers.   As patients file complaints, if they feel they have not been given timely access, enforcements will not be limited to large organizations.  Individual providers and small groups alike are subject to the Privacy Rule.

All providers should have a plan to ensure they meet the 30-day limit to provide the medical records to ensure they are in compliance with the HIPAA Right of Access Initiative.

Resources:

1. https://www.hhs.gov/hipaa/for-professionals/privacy/guidance/access/index.html
2. https://www.ecfr.gov/current/title-45/subtitle-A/subchapter-C/part-164/subpart-E/section-164.501
3. https://www.ecfr.gov/current/title-45/subtitle-A/subchapter-C/part-164/subpart-E/section-164.524
4. https://www.healthcareitnews.com/news/first-hipaa-right-access-case-gets-settled-ocr
5. https://www.hhs.gov/about/news/2021/09/10/ocr-resolves-twentieth-investigation-in-hipaa-right-of-access-initiative-with-settlement.html
6. https://www.hhs.gov/about/news/2021/11/30/five-enforcement-actions-hold-healthcare-providers-accountable-for-hipaa-right-of-access.html
7. https://www.hhs.gov/about/news/2021/11/30/five-enforcement-actions-hold-healthcare-providers-accountable-for-hipaa-right-of-access.html

Data problem? Analytics? Regulations? Data privacy? Humanity? Coffee and talk?  You can reach me at jleventhal@kohlerhc.com or 312.933.2752.

Josh Leventhal is an expert in healthcare data and analytics and is Managing Director with Kohler HealthCare. He has over 15 years of hands-on experience in healthcare data and analytics solving problems for providers, payers, and life science organizations.  Josh started his career in management consulting analyzing data for the largest joint defense litigations in the country before applying his skills and expertise at local startups to assist the Medicaid a managed care organization and medical research industries.  His experiences as a consultant, product manager and developer allow him to work effectively with both business and technology stakeholders.

The National Institute of Health (NIH) defines benchmarking as  “a strategic and analytical process of continuously measuring an organization’s products, services and practices against a recognized leader in the studied area for the purpose of improving business performance.”¹

Nearly every KHC client asks, “How is our performance compared to your other clients?  Do you have a benchmark for that?”  Hospitals and other providers have troves of data and a seemingly endless way of measuring their organization’s performance.  The other day, I worked through a limited dataset live with a compliance officer and in one hour and we identified five new metrics for observation services.  However, clients always want to know how they compare to others in order to measure success.

When making the leap directly to an external benchmark to determine if you perform better or worse than a peer, the context is overlooked.  Every company and situation is unique and external benchmarks do not contain enough information to determine if the data that supports the metric was determined in a manner that is consistent with how the company will utilize it that benchmark.

When considering a benchmark, there are key questions to help determine if it is meaningful to you:

1. What is the source of data? Self-reported data is subjective as different respondents may interpret questions or data points differently.
2. What is the lag time between data collection and reporting? Is a benchmark that is reported in June based on data from the prior year helpful or even relevant?
3. What key factors were considered in developing the benchmarks?  Payer mix?  Payer contract terms?  Geographic location?   Provider specialty?
4. What industry or market circumstances might be reflected in the data that does or does not apply to my organization?
5. What is not included in the benchmark?

I was recently digging through the Centers for Medicare and Medicaid Services (CMS) Part D Prescriber Provider Utilization and Payment (PUF) Data to find some contextually relevant benchmarks for a client.  The data is accompanied by a 28-page methodology document that outlines what is included and what is NOT included in the various data sets.²  Although there was a sufficient amount of data available, what was not included impacted any benchmarks in such a way that they were no longer meaningful.

I have also found that a significant amount of time is spent justifying the benchmark and explaining why it does not consider the specifics to the internal organization.  Importantly, benchmarks do not help identify the impact of changes made to the organization.

Operationally, it is more effective to measure the current performance against the desired results.  External benchmarks can be used to provide guideposts as to what the desired result is and a month over month analysis against an internal benchmark can demonstrate performance improvement in relevant areas based on the organization’s individual and unique context and goals.  This also considers the reality that the team that performs the work drives productivity, quality, and the final outcome.

Our auditing clients frequently request comparative error rates.  As each audit has a specific goal and each organization has different coding policies; coding team responsibilities; and physician involvement; comparative error rates can only be utilized as a high-level guideline to help establish what the desired result should be for that organization.

Consider physician compensation as another example.  HFM Magazine’s Summer 2021 issue has an article by Stuart Schaff, “We must stop relying so heavily on benchmark tables to set physician pay.” This statement succinctly explains why external benchmarks expose a hospital to risk because the hospital faces “difficulties not only in foreseeing the changes in benchmark data” and also details how the benchmarks generally used in physician compensation are based on a voluntary response and are self-reported.   Mr. Schaff instead proposes a physician compensation model that accounts for the physician’s specialty and other aspects of the physician’s work and pay.

In KHC compliance and litigation work, opposing experts frequently lose when we are able to explain why the analytics are not relevant to the case.  A few good examples are when are when an opposing expert used lower prices from 2018 to reprice claims from nearly a decade earlier, using Medicaid volumes from geographic locations with a lower Medicaid population to attempt to prove fraud or comparing nursing home ratings in one state to another to establish performance metrics.  In each of these examples, the benchmarks that were used were not of the same context as the measurement against which they were compared.

As one that lives in data, benchmarking is an analytics tool that I use daily as part of my work.  However, time must be spent refining the benchmark calculation to ensure that it is within the context of the problem.  Frequently, as I spend more time refining the calculation, I’m able to identify more than one benchmark that needs to be measured in order to measure against the goal.

Resources:

1. National Institutes of Health, Office of Management: https://ors.od.nih.gov/OD/OQM/benchmarking/Pages/benchmarking.aspx.
2. Medicare Fee-For Service Provider Utilization & Payment Data Part D Prescriber Public Use File: A Methodological Overview, https://www.cms.gov/Research-Statistics-Data-and-Systems/Statistics-Trends-and-Reports/Medicare-Provider-Charge-Data/Downloads/Prescriber_Methods.pdf.

Data problem?  Analytics?  Regulations?  Data privacy?  Humanity?  Coffee and talk?  You can reach me at jleventhal@kohlerhc.com or 312.933.2752.

Josh Leventhal is an expert in health and is Managing Director with Kohler HealthCare.  He has over 15 years’ hands-on experience in healthcare data and analytics solving problems for providers, payers and life science organizations.  Josh started his career in management consulting analyzing data for the largest joint defense litigations in the country before using his skills and expertise at local startups to assist the Medicaid managed care organization and medical research industries.  His experiences as a consultant, product manager and developer allow him to work effectively with both business and technology stakeholders.

This is well evidenced by the actions of the Department of Justice (DOJ).  In 2017, the DOJ created a specific Data Analytics Team within their Health Care Fraud Unit.¹  In addition to analyzing trends within healthcare, the Data Analytics Team also provides the offices of the U.S. Attorney with analytics support, including case specific support.  Furthermore, the DOJ leadership has continued to express how the role of data analytics in developing cases.

The DOJ has expressly said that it analyzes data submitted to Medicare to identify fraud.  Acting Assistant Attorney General Brian M. Boynton explained in his remarks to the Federal Bar Association that the DOJ “has increasing been undertaking sophisticated analysis of Medicare data to uncover potential fraud schemes that have not been identified by whistleblower lawsuits, as well as help analyze and support the allegations that we do receive from such suits.” ² (emphasis added)

Identifying Potential Fraud with Data

Government agencies have access to a trove of data submitted by providers and pharmaceutical and device manufacturers and are comparing these disparate data sets to identify potential fraud, with a focus on outliers.

1. Medicare Parts A, B, C, and D, including DME, home health, SNF and hospice.
2. Medicaid data, including prescription claims.
3. Medicare and Medicaid provider and beneficiary information.
4. Open Payments.

These data can be utilized to identify potential fraud both within a dataset and across data sets.  Over the past few years, I have seen an increase in the sophistication of the analytics by governmental agencies and which often times results in larger cases.

Some recent examples from my experience, as well as cases announced by the DOJ:

1. Physicians that bill an uncommon code more often than normal, including unusually high amounts of a particular DME or drug, can be identified using claims data.
2. Ancillary service providers (e.g., labs, pharmacies) that receive a large portion of referrals form certain physicians or set of physicians can be identified using claims data and provider information.
3. Providers that provide care to patients that do not live geographically close by and providers that do not practice close to a frequently used lab can be identified using claims, provider and beneficiary information.
4. Providers that diagnose and prescribe differently from other providers for the same patient can be identified using claims data.

Recently, the DOJ announced criminal charges against 14 defendants for alleged participation in a COVID-19 exploitation scheme involving telehealth and laboratory testing.³  You can view a simple infographic about the scheme here: https://oig.hhs.gov/documents/root/368/covid-takedown-2021-scheme-508.pdf.

Having experience with these types of allegations, specifically in analyzing claims and other data as it relates to lab referrals for testing, I understand how claims, beneficiary and provider data likely played a role in identifying outliers.  Further, unrelated data was likely used to identity the flow of money between the various parties.

What this means for the Compliance Department?

As part of an effective compliance program, compliance programs should leverage the data they have to proactively identify potential fraud. The DOJ’s Evaluation of Corporate Compliance Programs Guidance (ECCP) provides guidance to prosecutors on evaluating compliance programs.  Imporantly, the guidance includes evaluating “Data Resources and Access” to ensure that the Compliance Departments “have sufficient direct or indirect access to relevant sources of data.” ⁴

Compliance programs can leverage analytics to sift through their own claims data to identify high-risk areas.  The Office of Inspector General’s (OIG) Audit Work Plan is an good place to start for high-risk areas identified by the Government.⁵  Compliance programs should review the targets of the Audit Work Plan and dig into the relevant regulations to determine how data can be mined in order to be proactive.

Dashboards with KPIs can be developed that measure and identify risk. Investing in an analytics project that utilized modern technology will streamline this process so that the Compliance Department can focus on investigating and mitigating the risk instead of focusing on data challenges.  Scripts can be developed to pull new data in as it becomes available, cleanse it, and then harmonize it with other data.  Data visualization tools provides quick dashboarding and an opportunity for further analysis to determine what might be driving risk for further investigation.

I also believe that with an effective analytics program measuring the correct KPIs and resources focused on investigating and mitigating risk, the Compliance Department transitions from a cost-center to a revenue generator through the protection of past and future revenue.

Reflections

As one who has been known to “geek out” in data from time to time, I enjoy seeing analytics continue to play a major role in compliance.  I also appreciate that analytic tools have become robust enough that the analysis of disparate data sets is becoming more accessible.

While data is a good foundation to help prove a hypothesis, one must recognize that data does not provide context.  It does not inherently explain why there is an outlier or why there is a trend.  The context within the industry is important in order to understand if the outlier really is an outlier.  A good example is trending and identifying outliers related to COVID-19.  Normal curves and averages do not exist as benchmarks, therefore, what might seem like average could be considered high, even though not an outlier.

Providers may not be well-positioned to act on their data.  Although tools are better, analyzing disparate data is a challenge within itself.  By linking disparate data together, one can derive more meaning from the analytics.  The most time-consuming part of any data project is data engineering, which I lovingly call the art of cleansing, harmonizing and herding data cats.  However, this is a rabbit hole to be explored in a future article.

Resources

1. DOJ Fraud Section Year in Review 2017: https://www.justice.gov/criminal-fraud/file/1026996/download
2. Acting Assistant Attorney General Brian M. Boynton Delivers Remarks at the Federal Bar Association Qui Tam Conference https://www.justice.gov/opa/speech/acting-assistant-attorney-general-brian-m-boynton-delivers-remarks-federal-bar
3. DOJ Announces Coordinated Law Enforcement Action to Combat Health Care Fraud Related to COVID-19: https://www.justice.gov/opa/pr/doj-announces-coordinated-law-enforcement-action-combat-health-care-fraud-related-covid-19
4. U.S. DOJ ECCP: https://www.justice.gov/criminal-fraud/page/file/937501/download
5. OIG Audit Work Plan Fiscal Year 2021: https://oig.ssa.gov/audits-and-investigations/audit-work-plans/audit-work-plan-fiscal-year-2021

Data problem?  Analytics?  Regulations?  Data privacy?  Humanity?  Coffee and talk?  You can reach me at jleventhal@kohlerhc.com or 312.933.2752.

Josh Leventhal is an expert in healthcare data and analytics and is Managing Director with Kohler HealthCare.  He has over 15 years of hands-on experience in healthcare data and analytics solving problems for providers, payers and life science organizations.  Josh started his career in management consulting analyzing data for the largest joint defense litigations in the country before applying his skills and expertise at local startups to assist the Medicaid a managed care organization and medical research industries.  His experiences as a consultant, product manager and developer allow him to work effectively with both business and technology stakeholders.

A recent Office of Inspector General (OIG) review of Medicare Advantage (MA) companies found that during 2016, the 162 MA organizations received $9.2 billion “from diagnoses that were reported only on chart reviews and HRAs, and on no other service records.”¹  Of these 162 organizations, 20 received 54% ($5 billion) of the payments while accounting for only 31% of MA beneficiaries.

The Centers for Medicare and Medicaid Services (CMS) risk-adjusts capitated payments based on beneficiaries’ diagnosis codes.  MA organizations report beneficiaries’ diagnosis codes based on service provided to the beneficiary to CMS’ MA encounter data system and the Risk Adjustment Processing System.  There are two primary sources for MA organizations to identify diagnoses used for risk adjustment:

1. Chart reviews are an MA organization’s review of a medical record to identify diagnosis codes that a provider did not submit or submitted in error.
2. Health Risk Assessments (HRAs) occur when a health care professional collects information from the beneficiary about their health in order to diagnose a beneficiary and identify gaps in care.

The diagnosis codes are then translated into HCCs that are used for the basis of payments to MA organizations.

The OIG found that the HCCs based on chart reviews and HRAs were not always supported by services documented in the medical record:

HCCs generated by diagnoses reported only on chart reviews and HRAs included serious illnesses, such as diabetes and heart disease. However, there were no service records directly demonstrating that beneficiaries who had a chart review and/or HRA received treatment for these serious health diagnoses.

The OIG further identified that for the 20 companies, $3.4 billion (68%) of their total $5 billion in payments on HCCs based only on chart reviews and HRAS were on 12 of the 101 possible HCCs, as identified in the chart from their report as displayed below.

The OIG recommended that CMS should provide oversight to these 20 MA organizations and perform “periodic monitoring to identify MA companies that had a disproportionate share of risk-adjusted payments from chart reviews and HRAs.”

Providers and MA organizations should pay close attention to the findings and establish procedures to ensure that risk-adjusted diagnosis codes are supported by services documented in the encounter notes.

At KHC, we advise our clients to establish and HCC coding workflow that integrates the doctor and an HCC coder, in order to ensure that all diagnoses are supported and that HCCs are appropriately captured.  This workflow is supported by data mining and analytics to identify high risk areas and monitor the success of the HCC program.  We recommend our clients consider the following:

1. Analyzing data available from the Medicare Advantage (MA) plans, such as Open HCC Lists and MA websites, to calculate and monitor HCC recapture rates.  This data can also be used to identify and schedule patients with open HCCs.
2. Monitoring volumes of frequently miscoded diagnosis codes/HCCs (e.g., heart attack or active stroke within office), especially those on the OIG’s list above.
3. Monitor diagnosis codes submitted on encounters by providers that cannot assign risk adjusted diagnosis codes.
4. Monitor the volume of diagnosis codes that are unspecified, as the medical record may support a higher level of specificity.
5. Use patient measurements taken during an office visit and recorded in the medical record, such as body mass index (BMI), to identify inappropriate diagnosis codes (e.g., cannot be morbidly obese if BMI is low).

Resources

1. Office of Inspector General report, “Some Medicare Advantage Companies Leveraged Chart Reviews and Health Risk Assessments To Disproportionately Drive Payments”: https://oig.hhs.gov/oei/reports/OEI-03-17-00474.pdf

Data problem? Analytics? Regulations? Data privacy? Humanity? Coffee and talk?  You can reach me at jleventhal@kohlerhc.com or 312.933.2752.

Josh Leventhal is an expert in healthcare data and analytics and is Managing Director with Kohler HealthCare. He has over 15 years of hands-on experience in healthcare data and analytics solving problems for providers, payers, and life science organizations. Josh started his career in management consulting analyzing data for the largest joint defense litigations in the country before applying his skills and expertise at local startups to assist the Medicaid a managed care organization and medical research industries. His experiences as a consultant, product manager and developer allow him to work effectively with both business and technology stakeholders.

It’s not that our leaders were ignoring the power of data, however, the pandemic has revealed the truly meaningful benefits of investing in the resources and the infrastructure that is required for a strong data analytics team.  We have leveraged data analytics in the healthcare world in the following ways:

Patient Engagement

The modern model of patient engagement consists of utilizing a patient portal for scheduling visits, messaging the doctor, prescription refills and virtual visits.  One aspect of technology that has notably improved in recent months is the amount of real-time data being passed between the patient and doctor through the patient portal.  Because at times, in-person results and updates were  not possible, the importance of utilizing and engaging with the patient portal were critical for patient care.

Corporate Agility

Last year, some healthcare providers learnt lessons the hard way when COVID hit the nation. Pivoting quickly by learning and implementing  strategies from other the organizations was essential in providing patient care.  From a workforce perspective,  internally transitioning into more collaborative tools like Microsoft Teams and video conferencing solutions provided the platform for sharing information for decision-making.

Leverage Technology

As the organization’s employee needs change in collaboration with the ever-changing needs of the patient, we have always been faced with addressing these challenges by using the technology we have around us. The fundamental directives moving forward should be to understand how we can leverage technology further and reshuffle priorities well into 2022. Knowing and harnessing the power and understanding the technology we implement allows us to answer question:  “Can we do this?” with a Yes answer.  The  answer of “Let me go check.” should no longer applies in the environment of today. e

Dynamic Strategies

Are your leaders making decision on whims and their gut feelings? What if you knew the facts before making those assumptions?  Things change and so should our business strategies. Strategies should align with the organizations plans but also be open enough to adjust and consolidate those decisions and commitments in a way that is flexible and dynamic.

It’s as important as ever to make sure your business is optimized and structured according to your improved decision-making processes.  Make sure the structures are clear and streamlined in an effort to expedite the process and resolve issues that need to be addressed.

1.     Not understanding data sources and how they work together (mixing data sources).

Data is one of the most valuable resources in the digital age.  However, not understanding how data is collected and processed can have a negative impact on the rest of your marketing efforts.

The most common mistakes made in data analysis are:  the mixing data sources (i.e. combining customer data from different channels) and not understanding how to filter or separate the good data from the bad data (i.e. using ineffective filters or separating irrelevant information).

2.      Not analyzing the data correctly because of insufficient understanding of statistical concepts.

Statistics is an important field of study for any data scientist or business analyst.  It’s necessary to know how to analyze data correctly so as not to misinterpret the results.

I will discuss two common mistakes that people make when analyzing data and the ways to avoid them.  The first mistake is not understanding statistical concepts such as a p-value means or a confidence interval.

The second mistake is misinterpreting the results.  For example, if you are trying to determine whether a company’s marketing campaign led more people to buy their product and the target cities in question are unknown, then the analysis will be misinterpreted because you are analyzing the wrong population.

3.      Too much focus on inputs and not enough on output.

Data is only useful if it is utilized in a way that has an impact on the outcome.  There needs to be a balance between using data and creating data that can be useful.

Data without proper analysis or interpretation will not result in any value and instead will just serve as expensive noise.  Data can be used for many different things; it may even be able to generate more data points that we would have never been able to produce ourselves.

4.      Ignoring visualization techniques (e.g., dashboards) for presenting insights to clients, stakeholders – those who have the power to adopt change.

Many people might not know that data visualization is the process of transforming information into something visual that can be understood at a glance.  Presenting insights in the form of visuals helps people better understand the data.

As data becomes more and more voluminous, it becomes difficult for humans to comprehend it all without the use of some type of visualization technique.  Data visualization techniques can help us detect patterns and trends in data and generate insights that we would otherwise never notice.

The most common types of visualizations include: charts; graphs; diagrams; maps; infographics; and illustrations.  These are quite effective tools as they relay more information in less time and with fewer words than if they were written on paper or spoken aloud verbally.

5.      Gaining insights from only one perspective or angle of analysis.

The only data perspective that people are aware of is their own.  By looking at the world through only their lens, individuals cannot develop an accurate understanding of the whole picture.  There are many ways in which people can gain a better understanding about a topic.  They can read other people’s perspectives; they can be exposed to new experiences and they can be given access to different types of data.  This is why there is a need for more perspectives when it comes to data analytics.