health plans Archives | Page 2 of 2

Supervised vs. Unsupervised Machine Learning: Using The Right Tool For The Job

It’s Veda’s philosophy that any new technology tools we utilize are not meant to wholly replace human engagement. We believe that technology should help elevate humanity. With a focus on performing meaningful work, people can achieve their highest value. Technology should help people help people.

As a Data Science as a Service (DSaaS) company, Veda leverages scientific principles within our unique AI and machine learning systems to perpetually clean, correct, and monitor evolving provider and facility data. A lot of companies claim to offer accurate provider data, but none are as committed to using science to solve deeply entrenched provider data problems.

Dr. Bob Lindner describes supervised vs. semi-supervised learning

At Veda, we use AI systems including natural language processing (NLP), supervised, and unsupervised learning components that can be leveraged to solve a wide array of payer data challenges depending on what tool is right for the job. No matter what, we start by understanding the problem—not by applying a method.

A lot of companies claim to offer accurate provider data, but none are as committed to using science to solve deeply entrenched provider data problems.

The Roles of Supervised and Unsupervised Learning

Supervised Learning

Veda utilizes supervised learning because it doesn’t require “perfect” sources of data— it can make use of the good parts of any data source and knows how to ignore errors. With supervised learning, a data scientist is watching and helping train a model with all the healthcare nuances and industry-specific language, etc. to make the model a good one.

We’ve measured individual sources of data for years—including attestation— and haven’t found any at 90% or above yet. Supervised learning is incredibly accurate with the data we have access to today. The benefit is the highest accuracy which is flexible and not dependent on a single data source.

Unsupervised Learning

We also use unsupervised learning for offline data exploration and research to learn more about a dataset, to help design better machine learning features for supervised learning systems. That’s because unsupervised learning separates big collections of data into groups on its own. The benefit of unsupervised learning is its ability to pick out patterns in the data.

Unsupervised learning separates big collections of data into groups on its own. Some will claim that unsupervised learning, alone, is superior to supervised learning because of the lack of human intervention. However, most algorithms require the user to specify upfront how many groups they want the data separated into. So no matter what data is being grouped, one would have to delineate exactly how many groups are wanted ahead of time and the exact number of groups the data is sorted into regardless of whether the groups match up well with the data. This requires the user to have upfront knowledge of exactly what labels and groups they need.

But the biggest pitfall of unsupervised learning is that there’s no labeled training data, which means there’s no actual measurement of how well it’s working and placing the items into the correct groups. And with no way of knowing how well it’s working, it’s impossible to depend on unsupervised learning as a primary method for accuracy.

The Right Tool For the Job

Supervised and unsupervised learning are tools, and just as you wouldn’t remodel your kitchen and only use a saw, you shouldn’t only use one kind of machine learning model.

Veda’s technology and approach to data challenges are fundamentally different from other provider data technology companies in that we focus on fully automating both the static information and the more challenging temporal information about a provider—data that changes at varied rates over time, like practice address, phone, and group affiliation. Our patented systems do not require manual outreach to providers, rather they rely on data created by providers throughout their established workflows. This increases data accuracy by reducing human error while also decreasing provider abrasion. Validating millions of temporal data elements in real-time requires Veda’s full automation system and could not be solved manually.

Above all, we believe that AI and machine learning are the best ways to solve the provider data quality problem because:

These techniques do not require us to know how accurate our sources of data are ahead of time—the machine figures out how to tell good data from bad
AI makes the most of imperfect and changing data
They do not require provider participation—we use data they already create in their day-to-day workflows, so no need to persuade providers to take additional action
It works—we have scientifically tested attestation along with “source of truth” modeling, and Veda’s approach has the highest measured accuracy of any approach in the industry.

Read more about Veda’s approach to AI and data science with Dr. Bob Lindner’s blog post, Artificial Intelligence, ChatGPT, and the Relationship Between Humans and Machines.

Fierce Healthcare: OutCare Health partners with Veda to deliver LGBTQ+ affirming provider list to payers

Fierce Healthcare covered Veda’s partnership with OutCare Health on September 21, 2023.

Veda, a data automation startup serving payers, has partnered with OutCare Health to help patients and payers identify queer-affirming providers.

OutCare Health, a nonprofit advocating for queer health equity, is known for OutList—what it calls the most comprehensive directory of LBGTQ+ affirming providers. Veda will incorporate those data into the information it offers to payer clients.

Open Enrollment: Tips for Enhancing Provider Directory Accuracy

Prepare for Open Enrollment with Directory Accuracy

Provider directory accuracy leads to a positive experience for health plan members. But often overlooked is the importance of directory accuracy during open enrollment when both existing and prospective members are making choices for the upcoming year. Read on for open enrollment tips.

open enrollment tips person questioning health insurance

According to a recent eHealth survey, “Coverage for preferred doctors is a bigger consideration than affordable monthly premiums.” In fact, “31% of respondents say finding a plan that covers their preferred doctors or hospitals is their number one priority when choosing a plan.”

Inaccurate and incomplete directory information misrepresents health plan coverage, the leading priority for members during open enrollment. It also establishes an erroneous benchmark of user experience for enrollees — a first impression with your members should start on a good footing.

open enrollment tips person at computer deciding on health insurance

With nearly half of Americans considering a change to their health plan during open enrollment, your plan could gain a competitive advantage by clearly demonstrating the breadth of accurate and comprehensive provider information in your directory. Furthermore, accurate directories will only continue to enhance the member experience once they choose a plan and begin contacting their newest practitioners.

Open enrollment is right around the corner, but it’s not too late to make targeted changes that have the greatest impact on the member’s experience. Veda’s automation tool makes thousands of suggested changes to your directory in less than 48 hours.

With nearly half of Americans considering a change to their health plan during open enrollment, your plan could gain a competitive advantage by clearly demonstrating the breadth of accurate and comprehensive provider information in your directory.
Value Penguin

Open Enrollment Tips for Provider Data Improvements

Here are three open best practices and recommendations to quickly and strategically improve directory accuracy before November 1, 2023—and what to plan for in 2024 and beyond.

Make Segments: In lieu of whole directory changes, start small. Segment the directory with open enrollment priorities in mind. Veda recommends segmenting by market or specialty.
Be Specific: Target the high-impact data elements within a segment to get the needed results before open enrollment. Think provider level data such as clearing out deceased or retired providers or location level like updated addresses.
Act Confidently: Grab the highest impact, highest confidence recommendations. Bonus: Implementing mass maintenance of high confidence scores can automate directory fixes eliminating administrative burdens almost immediately.

Armed with a directory diagnostic, you can confidently address critical directory errors resulting in improved directory accuracy.

Ready, Set, Go: Get a Provider Directory Diagnostic Snapshot

Veda will diagnose your directory data, giving you a snapshot of your directory with fixes that can be enacted quickly. Armed with a directory diagnostic, you can confidently address critical directory errors resulting in improved directory accuracy.

We’re ready when you are.

Contact Veda for your Provider Directory Diagnostic Snapshot.

Quantym Diagnostic open enrollment get a data diagnosis

Six Questions to Ask Your Provider Data Vendor

The most impactful data vendors ensure top-quality data is being provided to their health plan clients. Data vendors can bring both value and collaboration to health plans’ business. A solid understanding of the vendor’s capabilities, methodology, and process can help you quickly build trust and maximize your ROI— or not.

Whether your health plan is currently working with a data vendor or hopes to do so in the future, these are the questions Veda’s data science team encourages you to talk to your partners about to get the most out of your data. Plus, we included Veda’s answers to the questions.

How often is data being refreshed?

Provider data is not “set it and forget it.” Providers change facilities, offices move locations, phone numbers are updated, etc. Without consistent updates, there is a risk of data being inaccurate. What was once correct can quickly become void when a clinic moves next door.

VEDA’S ANSWER: Veda optimizes results for each provider every 24 hours.

How do you perform entity resolution and resolve data conflicts?

Entity resolution is the foundation of all data processing, and poor entity resolution can affect results for locations, network adequacy, and provider details. One challenge in provider data is that the information about a provider is not static, and evolves over time—location, phone, specialty, etc.

VEDA’S ANSWER: Veda’s patented technology performs entity resolution in a way that specifically accounts for this data drift over time.

What sources are being used?

Knowing where source data comes from will help ensure you’re sourcing everything you need and nothing you don’t. Rather than crawling some websites for information that may already be inaccurate, using many sources means the data can be cross-referenced for quality.

VEDA’S ANSWER: Veda curates data from over 300,000 unique sources (including our proprietary data and multiple credentialing sources, such as NPPES, CMS, DEA, and State Licensing Boards).

How many active providers are included in data sets?

Data sets should include active providers. Sure, having more providers and large numbers in a roster seems like a win but if the roster is full of inactive or even deceased providers you’re risking a poor member experience. Garbage in, garbage out.

VEDA’S ANSWER: Organizations using Veda’s provider data can access profiles of every active provider in the U.S.—over 3.5 million.

How do you measure the performance of your data model?

Once you are certain you’re measuring the right outputs, identify the key metrics that support your accuracy KPIs: Aspects such as frequency of measurement, sample sizes, methodology, etc.

VEDA’S ANSWER: Veda’s solution accurately separates data into training and test sets for statistical modeling. This is essential to avoid overfitting and production performance “surprises” from the data.

How is success defined and how is it measured?

Are you measuring your performance like your patients and regulators are? We believe everyone needs to think more rigorously about what “correct” provider data means. Attested data is not the same as correct data.

VEDA’S ANSWER: The best measurement for accurate provider data? Patients should be able to make an appointment with a provider, using the data available to them, on the first try.

Ready to partner with a data quality vendor who is the authority on accuracy? Contact Veda.

Why Attestation Isn’t Sufficient for Quality Provider Data

Veda solves attestation problems by harnessing the power of AI and machine learning to automate manual data-gathering and validation processes

Attestation is necessary for compliance, but it fails to deliver quality provider data. At Veda, we’ve spent years measuring and monitoring the accuracy of attested data and its impact on quality—it just falls short. Attestation isn’t sufficient to achieve quality provider data.

Attested data sources are updated slowly through manual workflows that are susceptible to human error, and some providers never update information at all. It doesn’t work well and requires providers to act outside their busy days just to attest. It’s abrasive and providers dislike the process.

The risk of error, and patient dissatisfaction, is high when attested data is the source. Take one recent “secret shopper” example from a senator in Oregon. His staff made over 100 calls to make an appointment with a mental health provider for a family member with depression at 12 Medicare Advantage insurance plans in six states. The callers could only get an appointment only 18% of the time. That means more than eight in 10 mental health providers listed in provider directories were inaccurate or weren’t taking appointments.

Attesting is so burdensome that smaller or private practices—like many in the psychiatric workforce—do not participate in health plan networks because of the administrative burden.

At Veda, we work to achieve member satisfaction and ease the administrative burden as our definition of accuracy is the same as health plan members—”Can I easily find the phone number to call and make an appointment with [X Doctor] at [X Location]?”

A Better Way to Source Quality Provider Data

There is enough existing data to solve provider data accuracy problems, within current workflows, without relying on doctors to attest. We use the data providers generate every day, curated from over 100,000 unique sources, optimizing results for each provider, every 24 hours.

At Veda, we work to achieve member satisfaction and ease administrative burden as our definition of accuracy is the same as health plan members—”Can I easily find the phone number to call and make an appointment with [X Doctor] at [X Location]?”

Veda’s solutions are unique and proprietary. We employ rigorous scientific validation methodology to ensure we have optimal data for every provider in the U.S. on-demand, every day. Our comprehensive data set includes over 50 key data elements including demographic information; specialty & credentialing details; practice locations & group affiliation information; as well as contact information appropriate for making appointments. All without the attestation that isn’t sufficient for quality provider data.

Access To Comprehensive and Accurate Provider Data

We offer three unique products to address provider data challenges.

Velocity Process Automation automates the manual effort of provider roster updates. Velocity applies predetermined business rules to unstructured and disorganized roster files to quickly compare incoming data to an existing directory, validate it against external data sources, and enhance it with critical missing data elements
Quantym Data Quality Scoring analyzes entire provider directories, addressing the most at-risk data fields and identifying areas that may affect overall quality metrics.
Vectyr Data Curation offers access to ready-to-query data to help manage overall provider and directory accuracy by filling gaps in missing or incorrect information with complete provider profiles. We provide these profiles for providers of multiple types, including physicians, nurses, allied health professionals, behavioral health specialists, pharmacists & dental providers.

The Impact of Bad Healthcare Data

The information included in provider directories changes often and the scope of required information keeps expanding. Practices move, physicians change practices, and contracts between practices and health plans expire. According to a report from CAQH and AMA, between 20% and 30% of directory information changes annually.

Yet, no single party is the exclusive keeper of this information. Some of the information is governed and controlled by the practice, such as contact information and the roster of clinicians who practice there. Other data, such as whether a clinician is accepting new patients under a specific plan, can be owned by the practice, the health plan, or in some instances, shared by both parties.

Only when data is accurate, timely and contextually relevant, can we make actionable decisions that positively impact patients.

In the health plan space, we saw that bad data was driving claims fallout, bad patient interactions, and sanctions. It was also impacting members of health plans who weren’t able to find the right doctor to access care, like in the case of the secret shopper experiment above.

Compliance is table stakes, which is why Veda doesn’t stop at getting the data right for the sake of CMS audits. Only when data is accurate, timely, and contextually relevant, can we make actionable decisions that positively impact patients.

In October 2022, CMS asked for public input in creating a national directory; a system in which it would collect information from providers and compile it into a single directory maintained by CMS. While an important undertaking, officials note there are many unanswered questions such as managing information for Medicare and private payers.

Luckily, provider directory problems are being solved right now by Veda’s innovative technology. Veda’s offerings are ushering in a new day where data is not a burden to doctors, nor an obstacle to patients. Innovative solutions already exist to connect individuals to the healthcare they so desperately need. All without the need for taxpayer dollars or the use of valuable CMS resources that could be dedicated to other deserving initiatives.

Our solution can mitigate the manual lift from multiple sources, and streamline the workflow with guaranteed accuracy and turnaround.

Having different authoritative sources depending on the data contributes to the difficulty of health plans and practices in keeping information accurate. Our solution can mitigate the manual lift from multiple sources, and streamline the workflow with guaranteed accuracy and turnaround.

The Veda Approach to Provider Data Quality

Attestation-free: We don’t ask doctors to use portals or rely on attestation to validate.
Evidence-Based Data: We utilize doctors’ current data usage to build evidence where they practice. The result? No human error and real-time updates.
Higher-standard for Accuracy: Our definition of accuracy is the one members care about—”can you actually see this provider at this location?”
Proven Methodology: Our roots are in science. We leverage the scientific method to understand and optimize performance.
Unique, Patented Technology: Proprietary solution backed by five existing patents and more pending.
Performance Amplification: Option to layer in your existing data—claims + live call audits—to optimize platform processing.

Guaranteed Outcomes

Speed and accuracy outcomes are defined in our SLAs and brand-defining for Veda. We stand by our data, unlike any others in the market.

Ready for high-quality provider data that is attestation-free? Request a free data assessment from Veda.

The Impact of Provider Data on Star Ratings

Medicare Advantage plans saw the largest-ever decline in Star Ratings in 2023. How can provider directory accuracy boost your Star Ratings?

As Open Enrollment began last fall, Medicare Advantage payers saw a big hit to their 2023 Star Ratings. While some plans managed to weather the ratings storm, some saw drastic changes. In 2022, 68% of Medicare Advantage plans who offer drug coverage had a Star Rating of four or more. That metric dropped 25% for the 2023 ratings with only 51% of Medicare Advantage plans boasting a four or more.

“It’s estimated a Medicare Advantage plan with 100,000 members could lose $15 million in revenue with that lost .5 star.”

With 38 measures to assess the quality of care delivered to Medicare Advantage with prescription drug coverage members, the Star Rating System is administered by the Center for Medicare and Medicaid Services (CMS) and serves as a benchmark for the industry. Maintaining a high Star Rating is essential for health plans to reach enrollment goals as members use the ratings to compare and choose between plans in a competitive marketplace. The highest-rated five Star plans are able to market and sell their Medicare Advantage plans outside the standard enrollment, giving them an advantage when obtaining new members. Not to mention, the ratings also determine the size of the bonuses plans can receive from CMS—any plan rated four Stars or above receives a 5% quality bonus from CMS and has their payment benchmark increased.

What happened with the 2023 Star Ratings?

The steep decline in Medicare Advantage Star Ratings in 2023 was attributed to many factors including fading pandemic flexibilities and members feeling dissatisfied with their plan.

The value of member experience in Star measurement significantly increased in 2023 as member satisfaction played a much more dominant role than they have in previous years. Just how important is member satisfaction when the CMS Medicare Current Beneficiary Survey is also looking at details like cost of care, health disparities, and the number of tests performed? A Gartner study stated member experience metrics represent 57% of an individual health contract’s overall Medicare Advantage Star Rating.

Business impacts for loss in Stars

Projected earnings for insurers take a big hit when Star Ratings drop. Lower-rated plans hope to avoid a drop in enrollment as members compare plans and look for the highest Stars. The competition can be fierce for plans that are looking to hang on to their current members. We know members are comfortable making a change as 22% of those who select a Medicare Advantage plan switch health insurance plans in the next year. Losing members, and enrolling new ones, is costly to plans.

“A Gartner study stated member experience metrics represent 57% of an individual health contract’s overall Medicare Advantage Star Rating.”

Another significant source of income for Medicare Advantage plans is the quality bonuses paid by CMS. MA plans will receive an estimated $10 billion in bonus payments in 2022, according to an analysis by the Kaiser Family Foundation. Losing out on those bonuses will lower overall earnings and projections for the following years.

An uphill Star Ratings battle on tap for 2024

The outlook for next year’s ratings doesn’t look much better for payers. Maintaining and improving Star Ratings is set to become more difficult with the Tukey Outlier Deletion methodology that begins with the 2024 Star Ratings. According to CMS modeling, about 16% of plans could lose at least a half of a star in 2024. It’s estimated a Medicare Advantage plan with 100,000 members could lose $15 million in revenue with that lost .5 star.

How can Veda help health plans boost their Star Ratings?

If your health plan saw your Star Rating drop or are looking to hang onto your current rating, now is the time to get prepared for October’s open enrollment and future ratings. Veda has found accurate provider data is tied to high Star Ratings and existing customers have seen a lift due to their improvements in the directory quality and roster processing.

Veda can directly address two sections of the CMS Medicare Current Beneficiary Survey with our platform’s Smart Automation and access to our national provider database. Accurate provider data from Veda impacts key aspects of the survey, such as:

1. Ease of access to care: How simple is it for your members to find the information they need to obtain?

a. In the last 6 months, how often did you get an appointment for a check-up or routine care as soon as you needed?

b. In the last 6 months, when you needed care right away, how often did you get care as soon as you needed?

2. Quality of member experience: Inability to find a doctor leads to poor member experience.

a. In the last 6 months, how often did you get an appointment to see a specialist as soon as you needed?

b. In the last 6 months, how often was it easy to get the care, tests or treatment you needed?

“If your health plan saw your Star Rating drop or are looking to hang onto your current rating, now is the time to get prepared for October’s open enrollment and future ratings.”

Put yourself in the member’s shoes, imagine a scenario where you are searching for a specialist that is in-network, within 20 minutes of your home, and is accepting new patients. Inaccurate address information in a directory makes the provider you choose seem closer than they actually are. When you finally get an appointment, you find it’s two hours away. Maybe on this journey, you dialed incorrect phone numbers or weren’t even given an updated list of doctors as a new specialist started last month and hadn’t been put into the directory yet.

Put simply: Quality provider directory information means easy appointment booking for members. No more endless phone calls searching for a provider nearby and no more wondering if a surprise bill will arrive due to an out-of-network provider visit. When provider directory challenges are addressed, members and health plans both win.

What else can Veda’s provider data do?

Veda’s technology helps ensure payers meet or exceed CMS compliance benchmarks. Health plans can keep enrollment and Star Ratings in good standing, all while reducing data processing time by 98% and improving data accuracy to 95% or higher.

Prepare for future Star Ratings with a free data assessment from Veda.

Optimal and Proven Provider Data from Veda

What makes Veda’s data so great?

Healthcare provider data can be riddled with inaccuracies—just ask anyone who uses network directories to find an in-network specialist or view clinics in a 10-mile radius. The Centers for Medicare & Medicaid Services (CMS) Medicare Advantage (MA) online provider directory reviews between September 2016 and August 2017 found that 52.2% of the provider directory locations listed had at least one inaccuracy.

Health tech companies have attempted to solve provider data inaccuracy problems with a number of products, platforms, and integrations. No solutions have been able to ultimately offer a better experience for members where it matters: the ability to easily book an appointment armed with accurate information.

Many solutions in the market focus on gathering all data sources available to identify providers but don’t have the ability to clean up those databases so they have only current and accurate information. A patient might find a doctor in a directory but if the location and coverage information was wrong, they still can’t make an appointment.

Enter Veda’s latest offering: Vectyr Data Curation. Vectyr offers the most up-to-date, comprehensive, and accurate source of provider data on the market. Vectyr’s database uses more than 100,000 unique sources to create an optimal collection of provider information. The data is continuously monitored, validated daily, and backed by our accuracy guarantees.

Prove It

How does Veda back up claims of accuracy and completeness? For one, our team of data scientists behind the development of Vectyr has the clout and expertise needed for intensive data modeling. From creating ground-breaking machine learning code to researching at the largest particle physics laboratory in the world, the best in science and technology are found at Veda. Here is how Veda employs a different approach than other data companies on the market:

Automation: Veda fully automates static and temporal data, boosting accuracy and reducing provider barriers. This validation process is automated in real-time, a fundamental advantage for healthcare companies seeking effective data structure.
Performance Measurement: Veda’s team of scientists carefully monitors the data’s success rate, creating statistical models, sample sizes, and methodologies to consistently guarantee accuracy. This process ensures specialty and data demands are evaluated and performing at the highest level.
Data Reconciliation: As temporal data evolves, Veda’s entity resolution process follows. Our technology accounts for data drifts over time, so our entity resolution is calibrated to recognize correct data from the abundant sources available today. New data is always cleansed and standardized, then consolidated within a database to eliminate duplicates.
Test Outcomes: Even with 95%+ accuracy, Veda doesn’t rely on automation to do all the work. The Veda team inspects all aspects of delivered data, including quality, delivery methods, bugs, and errors with a continuous monitoring process. By continually auditing and testing our data fields to confirm they are the competitive, current, and optimal quality we know reasonable coverage is reached.

Coverage, Precision, and Recall are numbers reported and recorded by the science team.

Coverage: What is the fraction of the data that isn’t blank?

Precision: When we do have an answer, how often is it right?

Recall: If we should have an answer, how often do we actually have it?

“Anyone can make an API. They are flashy, they can help operations, they can automate processes. But if your API is pulling in duplicative, inaccurate, and just plain bad information it’s useless,” says Dr. Robert Lindner, Chief Science & Technology Officer at Veda. “With our science backing, Veda’s data is guaranteed accurate and with flexible query so data delivery is where, when, and how users need it.”

Veda’s data is currently being used by top health plans for the correction and cleansing of their directories. Now, customers, new prospects, and new channel partners have direct access to Veda’s best-in-class provider information based on their nuanced business use case.

Vectyr has profiles on more than 3.5 million providers who have an NPI 1 number—including MDs, DOs, RNs, social workers, DDS, and pharmacists.

What can health plans do with Veda’s data?
Staying atop changing information ensures provider directories are always accurate. This is no small feat as 20-30% of all provider directory information changes annually. With Vectyr, health plans can offer a better experience for members and providers by:

Expanding network offerings: Members need both provider options and location access to get the care they need. Using Veda’s data can help health plans identify providers they aren’t currently contracted with and fill geographic or provider gaps in their network.
Sourcing correct providers for referrals: Providing accurate and on-the-spot information for in-network referrals relieves administrative burdens and eliminates frustrating hours spent searching for answers.
Quick credentialing: Credential providers faster and deliver faster onboarding and credentialing support with data that’s updated every 24 hours and guaranteed accurate.

What’s possible with optimal provider data?
There are immediate benefits to using Veda’s data. Health plan members will no longer wonder if their doctor of choice accepts their insurance or where the closest allergist to their home is. Hours of phone calls and administrative burdens are eliminated for both the member and the health plan. And, most importantly, health plans can trust Veda’s rigorous scientific validation methodology to ensure they have the optimal data for every provider in the country, on-demand, every day.

When health plans have access to optimal data, it means members have access to optimal data and that results in a markedly better customer experience.

More about Vectyr Data Curation

Star Systems Meet Star Ratings: Using Science and Imagination to Solve Healthcare’s Most Complex Data Problems

What the heck does astrophysics have to do with provider data quality?

With an entire science department dedicated to solving complex data issues, science is at the very core of Veda’s existence. After all, our Chief Science & Technology Officer and Co-founder, Dr. Bob Lindner, began his career in astrophysics.

After taking a leap from the academic world and into political data analysis, Bob and co-founder Meghan Gaffney realized the potential of provider data automation. [READ Q&A WITH DR. BOB LINDNER]

The commitment to the scientific method and investment in science is what sets Veda apart from other data and healthcare tech companies—and what led to a robust science department with an impressive five IP and automation patents.

But you might be thinking: what exactly does this background in galaxy-staring, particle-measuring, and the expansive universe have to do with ensuring health plans’ provider directories are accurate?

The answer lies in wholeheartedly embracing the scientific method and Veda’s mission: We blend science and imagination to arrive at solutions for our customers. In fact, Bob argues one would not be able to tackle provider data problems accurately and reliably without a science department.

In the healthcare industry, data changes rapidly, some sources of data claim to be sources of truth but may in fact not be accurate, and data can be a heavily manual process. The only way to uncover the truth is with a careful and accurate measurement process.

Science meets imagination with Veda’s Science Team

Here is an expert from Dr. Lindner on problem-solving at Veda:

There are two kinds of main prediction problems. One where the answer to any given problem is self-evident. You can look at it and immediately know what the answer is. You give this problem a fast feedback loop and design your system to get the right answer based on immediate feedback from engineers. Outside of healthcare, an example is image classification. Is there a smiling person in this picture or not? You can look at an image and immediately tell.

A different kind of problem that we’re faced with every day at Veda is if the answer you’re trying to predict is not self-evident by a trained user in the field. For example, does this provider work at this address? It may look like a reasonable address and provider name but you don’t know if it’s accurate just by looking at it.

The only way to know if the system is working is to be very disciplined with the art of measurement and calibration. You must have a good set of test data that you trust that was collected in a way that was very tightly controlled. And you have to trust you are training your models on the data in a way that’s not overfitting because when your system gets used in production you don’t know—aside from that measurement in comparison to your training data set—if it’s working or not. You have to trust in science fully because if you do that part wrong, by using a biased training set or too narrow of a sample, there are errors that are invisible until you actually try to use the data. It can be a devastating effect. If you have a 10-digit number that says it’s the phone number of a provider, and you can’t call every phone number, how do you know it’s correct? You must have faith in the process. And the process to have faith in is the scientific method.
Dr. Robert Lindner

Provider data is complex and vast just like data in the field of astrophysics. However, provider data is nuanced and complicated in ways that even monitoring billions of stars is not.

The challenges with provider data are more complex than say, finding the largest thing in the universe, because the information included in directories changes often and the scope of required information keeps expanding. Practices move locations, physicians change practices, and contracts between practices and health plans expire. Multiple industry reports state between 20% and 30% of directory information changes annually.

Having different authoritative sources depending on the data contributes to the difficulty for health plans and practices in keeping information accurate.

So yes, provider data is more complicated to monitor than the stars but the Veda science department, using the scientific method day in and day out, can solve complex provider data problems faster and more accurately than anyone else. We start by understanding problems deeply before pairing them with an appropriate model and AI technology.

Before you select a healthcare data vendor, ask yourself, why don’t they have a science department backed by patented IP?

Get your provider data assessed by Veda.

How Smart Automation Brings The Healthcare Ecosystem Closer To True Interoperability

Most of the public discourse on interoperability has been centered around EHR vendors and clinical data, in large part because the Office of the National Coordinator for Health Information Technology (ONC) is requiring that these vendors make an expanded set of personal health data available by October 2022. However, EHR data represents just a fraction of the massive amounts of data that are constantly being harvested in healthcare. And ONC’s mandate represents just one of many interoperability scenarios.

“WHILE THE LACK OF INTEROPERABILITY IN HEALTHCARE CREATES ENDLESS BARRIERS, STAKEHOLDERS ACROSS THE SYSTEM TRULY NEED AI SOLUTIONS TO HELP THEM CONNECT THE DOTS WHEN IT COMES TO BOTH RECEIVING DATA, SHARING THEIR OWN DATA WITH OTHER ENTITIES, AND MINING ALL DATA FOR MEANINGFUL INSIGHTS.”

Given the industry’s host of disparate IT systems—layered on top of its tendency to customize technology platforms—there are myriad examples of how extremely challenging it is to derive value, produce accurate insights, and achieve connectivity from healthcare data. And the fact that all of these different systems are unable to communicate with one another and properly exchange information is one of the healthcare industry’s most critical issues.

True interoperability is the long-term goal for the industry—some would go so far as to say it’s the golden ticket for delivering patient-centered care. But like other major initiatives intended to address the inefficiencies of the healthcare system, such as value-based care, we are still far from a universal solution. In the meantime, providers, payers, and other key stakeholders are hungry for solutions that will help them connect their existing legacy IT systems and enable them to share data across systems. Fortunately, companies like Veda now offer relief through Smart Automation solutions that can be implemented both in the near term and the future.

Common interoperability issues

The ultimate reason to strive for global interoperability is to improve patient care and make it easier for all stakeholders to navigate healthcare’s messy data environment. While strides in sharing health data have been made, there are still many hurdles to jump.

“THE NEW PROVISIONS OF THE 21STCENTURY CURES ACT ARE DESIGNED TO IMPROVE HEALTHCARE’S IT ECOSYSTEM IN THE LONG RUN, BUT IN REALITY, IT’S UNLIKELY THAT ANY SINGLE PIECE OF LEGISLATION WILL BE ABLE TO SOLVE ONE OF THE MOST COMPLEX AND LONG-STANDING CHALLENGES IN THE INDUSTRY.”

As mentioned, the most universally acknowledged and long-standing interoperability problem in the healthcare system is around electronic health records (EHRs) data-sharing. Today, approximately 90% of hospitals and physician practices use EHRs. But even when two hospitals have the same EHR vendor, it’s so common for hospitals to customize their systems that in the end, oftentimes neither hospital is able to fully “talk to” each other and easily share information. Many in the industry have set their sights on Health Level 7 (HL7) as a universal solve for this problem—it makes sense that using a standard language would improve data sharing. However, while HL7’s goal is to function as a bridge between modern healthcare systems, it’s also being customized by healthcare organizations, much like EHR platforms.

Although it receives less attention, for payers, the provider roster data processing problem is just as significant of a problem as the EHR data sharing issue, especially now that the No Surprises Act (NSA) is being implemented. It’s so complex an issue that many industry insiders have deemed it unsolvable. More often than not, insurers’ member-facing provider directories are outdated and riddled with errors and inaccuracies. Patients could go through as many 40 entries in a directory before they actually find a provider who can address the health issue they’re experiencing and who is in their geography. Not to mention that it can take up to 6 weeks for new provider information to get updated in the directories. This creates a significant barrier to patients seeking care, one that would never be tolerated or left unsolved by a retailer. If a consumer went on a website like GrubHub, for example, and the first 40 restaurants that came up in their search results weren’t in their delivery area—GrubHub would likely be out of business.

“VEDA’S AUTOMATION IS PARTICULARLY ATTRACTIVE BECAUSE IT CAN DO ALL OF THIS WITHOUT REQUIRING AN ORGANIZATION TO OVERHAUL ITS EXISTING IT INFRASTRUCTURE”

The reason this issue exists is that health plans are continuously processing enormous amounts of provider data that’s not being shared through a common platform between both payers and providers. Payers are ultimately receiving human-generated, messy, and incomplete data spreadsheets from providers, formatted in many different templates. Updates to the roster data can take weeks on end to process, end up costing millions of dollars a year, and still have accuracy rates as low as 60%. This is a problem, as health plans rely on this data to make updates to their directories, along with impacting how providers are paid.

Automation: A solution with both short- and long-term potential

The new provisions of the 21stCentury Cures Act are designed to improve healthcare’s IT ecosystem in the long run, but in reality, it’s unlikely that any single piece of legislation will be able to solve one of the most complex and long-standing challenges in the industry. Given the state of the healthcare ecosystem and the growing number of data sources, AI solutions like Veda’s will be as crucial for achieving data connectivity in the future as this seminal piece of legislation and others that will come after it.

And in the near term, prior to legislative format consolidation, stakeholders across the system (including payers) need AI solutions to help them connect the dots when it comes to both receiving data, sharing their own data with other entities, and mining all data—regardless of its origin—for meaningful insights. Veda’s automation is particularly attractive because it can do all of this without requiring an organization to overhaul its existing IT infrastructure or communicate in a standard language like HL7. The technology is able to sit between disparate systems and act as a translator for the data coming out of each. (Not to mention the major cost efficiencies achieved through automating rote manual tasks that do not require a human brain to execute with accuracy.)

This same automation that helps healthcare organizations function in the absence of true interoperability offers many more benefits. Through Veda’s technology, customers also gain the ability to more easily address compliance at both the federal and state levels, achieve both cost savings and productivity gains, reduce backlog, increase data quality to further cut costs downstream, and more. Existing Health plan customers see improvements across Medicare star ratings (specifically fields related to ease of access to care and quality of member experience), reduce their overall risk exposure (i.e., from sanctioned providers, poor claims system quality, or violations of the NSA), and streamline referral management.

The future of interoperability

Complex, messy data, which is pervasive throughout the entire healthcare ecosystem, creates equally complex issues–not just from a data processing and analysis perspective, but across the whole system. Data sharing and the struggle to achieve interoperability are some of the most difficult and important challenges in the healthcare industry.

Schedule a demo to see how Veda’s science-driven approach can help you optimize data for your organization.

For key stakeholders in the space, waiting on legislation may not be ideal, and as mentioned, there’s ultimately not likely to be a one-size-fits-all approach to achieving interoperable health information exchange. Smart automation is exactly what healthcare organizations need to overcome the lack of data integration across industry systems and bridge data connectivity gaps, both now and in the future.

Are You in Compliance? What Health Plans Need To Know About The No Surprises Act

The No Surprises Act (NSA), which is a part of the Consolidated Appropriations Act of 2021 (Public Law 116-260), went into effect at the beginning of this year, on January 1, 2022. The goal of this law is to protect consumers from unexpected medical bills arising from circumstances beyond their control. In an effort to ensure a patient knows what providers are available within their health plan network, one of the provisions of the NSA requires health plans to update their provider directories more frequently (you can review the law in full here).

Three months into the year, we’re now at a point where it’s important for any health plans to ensure that they are updating their provider directories in 48 hours or less, as the law mandates, or be working towards a solution that can meet these critical timing requirements.

WHAT ARE THE PROVIDER DIRECTORY REQUIREMENTS IN THE NO SURPRISES ACT?

The “No Surprises Act” will require all provider directory updates to be processed quickly. This is a pivot from the manual processing and attestation that health plans have traditionally incurred

Update databases and new directory information: All provider directory updates will need to be processed within 2 business days of receipt of changes
Quarterly database quality audits: Validate provider data in databases and directories at least every 90 days

PENALTIES FOR NON-COMPLIANCE OF THE NO SURPRISES ACT

There are mechanisms for enforcement in place at both the state and federal levels. In Q1 2022, CMS began to levy fines for “coverage determination appeals and grievances” (42 C.F.R. § 422.105(a)) and an uptick in fines for non-compliance is likely down the road. Now is the time to assess if you’re in compliance with the new mandates and understand the potential risk they have for your business.

BUILDING YOUR COMPLIANCE CHECKLIST

Assessing your situation today: To understand what changes your health plan may still need to make, we recommend that you ask and answer the following questions:

What are your goals for processing provider data? Obviously meeting the 48-hour requirement should be the topline goal, but some plans may have variations on this goal based on the number of covered lives under their purview and the geographies they cover (some may want for example, to make updates within a 24-hour window).

What process(es) do you have in place for updating provider info? How does your plan deal with messy data coming from provider organizations? Are these processes documented, or is the organization reliant on employees with historical knowledge?

What process(es) do you have in place for verifying the accuracy of provider info? Are there documented procedures for communicating with providers, and are these mechanisms effective? What’s in place to manage providers who are submitting “bad” data?

What are the data points that you currently verify? Thinking beyond basic data such as first name, last name, and specialty… you will want to make sure your plan is also able to track individual and group NPIs, organizational tax identification numbers, whether providers are accepting new patients, and more.

How quickly are you currently able to make provider directory updates? If the answer is weeks, which is often the case for large, national plans, it’s important that new processes be put in place as soon as possible.

What process(es) do you have in place for helping members that are having difficulty navigating your provider directory? The entire purpose of the NSA is to shield consumers from “bad” bills, and to overall improve their experience with the healthcare system. A system that your plan is part of.

How often are you cleaning your provider data in aggregate? In addition to processing regular data updates, what processes are in place to keep your database clean as a whole, and to ensure that “old” data is verified at regular intervals?

USING AUTOMATION TO IMPROVE YOUR SITUATION

Most plans have historically used manual processes—human hands on keyboards—to update provider directories. But with the NSA’s 48-hour requirement in effect, manual processes are unlikely to remain effective, and automation truly is needed. Before bringing in an automation solution, however, you should get educated about their capabilities.

Understand what automation can and cannot do. Automation cannot completely solve the global interoperability problem. What some of the more sophisticated platforms can do, however, is sit between disparate systems and act as a translator.
Assess the situation and set realistic goals. Under current manual processes, how long does it take to make provider updates, on average? What percentage of the updates are accurate? What types of issues does your plan most commonly experience with the data you receive (is it missing column headers and or containing blank fields in Excel files, providers listed at the wrong practice locations, or something else entirely)? The answers to these questions will vary from plan to plan, as will the goals for improvement.
Understand the range of automation solutions available. Not all automation solutions are created equal. Some require a “rip and replace” approach that health plans may find disruptive to existing IT infrastructure, but other solutions can co-exist with current systems. Solutions also vary in terms of the type of data they can automate—your plan should seek out those that are sophisticated enough to deal with the inherent messiness of human-generated data. Finally, you should look for an automation partner that provides human support in addition to technology.

THE ONLY TOOL AVAILABLE THAT ALLOWS FOR COMPLETE PROVIDER DIRECTORY COMPLIANCE

Veda is the only solution on the market today that makes it possible for plans to fully comply with the provider directory provision of the NSA. And we can do it in 24 hours. Our smart automation platform offers the fastest provider roster & delegated network processing available, with guaranteed accuracy thresholds.

Our platform performs multiple functions that increase efficiency and accuracy for provider data processing. Key features include:

Intake: automate manual workflows
Validate: stop bad data from entering your system
Enhance: simplify audits with cleaner data
Compare: integrate to quickly update your database

Learn more about Veda’s automation solutions and why six of the top 10 health plans trust Veda with their automation.

The most up-to-date, comprehensive, and accurate source of data. Your organization can access profiles of every active provider in the U.S.—over 3.5 million.

See how we’ve helped leading healthcare organizations achieve significant cost savings, improve data accuracy, and enhance patient care. Here, you will find our results, research, reports, and everything else our scientists are testing in the Veda Lab – no lab coat required.

Stay up-to-date on industry trends and discover a wealth of resources on provider data management, roster automation, and AI.

At Veda we understand that every data point is an opportunity to improve the healthcare experience. And we can see the potential when data is no longer a barrier.

Veda solutions

For health plans

health plans