Devdatta Halbe, SVP, Engineering, Author at Ensemble Health Partners https://www.ensemblehp.com/blog/author/devdatta-halbe/ Your modern revenue cycle solution Thu, 06 Nov 2025 15:41:39 +0000 en-US hourly 1 https://www.ensemblehp.com/wp-content/uploads/2023/10/Logo-Chevron-80x80.png Devdatta Halbe, SVP, Engineering, Author at Ensemble Health Partners https://www.ensemblehp.com/blog/author/devdatta-halbe/ 32 32 Why Revenue Cycle Data Is a Key Differentiator https://www.ensemblehp.com/blog/why-revenue-cycle-data-is-a-key-differentiator/ Wed, 29 May 2024 13:44:00 +0000 https://www.ensemblehp.com/?p=14224 By mapping to outcomes, revenue cycle data models can yield swift, precise insights precisely when decisions matter most. … Read More

The post Why Revenue Cycle Data Is a Key Differentiator appeared first on Ensemble Health Partners.

]]>

What you need to know

Aggregating and normalizing data is time-consuming and costly for health systems — it requires preprocessing, mapping and translating millions of data points, which is resource intensive. The effort is worth it, however; in revenue cycle management, as in other areas, the efficacy of analytic models lies in data diversity — more variables and broader data sources enhance model completeness. By mapping to outcomes, RCM models can yield swift, precise insights precisely when decisions matter most.

Data is the lifeblood of artificial intelligence (AI), and high-quality, unbiased data is essential for building fair and ethical AI systems. But with the average person likely to generate more than one million gigabytes of health-related data in their lifetime, equivalent to 300 million books, this kind of massive amount of information can be difficult for health systems to analyze on their own.

In healthcare, 80% of data is unstructured, meaning that it traditionally needed to be manipulated or processed in order to be readable by machines. In today’s industry, AI and other technologies exist that can ingest this data and make meaning of it, but these advancements come at a cost. Hospitals, which in recent years have been working with narrow operating margins and focusing their energies on standing up EHRs to meet federal specifications, are left with a ton of rich, beneficial data that many can’t fully tap into without support.

What is the value of data for analysis?

In machine learning, models ingest a large volume of data from thousands of data points to detect patterns so that computers can make decisions without a person intervening.

Data is critical for many other functions, including deep learning, the subset of machine learning that spawned generative AI like ChatGPT. Deep learning is essentially machine learning at warp speed; relying on more data input, millions of data points to assess, and the use of neural networks, which provide layers of processing to support more complex representations of data.

Diversity is critical here; models that draw on diverse expertise, geographies and perspectives help to ensure a diversity of contexts and patterns within datasets. This will help to support robust LLMs that can prevent overfitting a model to a limited set of instances, while also incorporating a diversity of contexts and patterns through a broader range of data and insights.

The more variables that inform models, the more valuable their insights become. Historical data can and should be codified within artificial intelligence, drawing upon multi-system or facility perspectives. This helps to avoid an N=1 bias in model development during the training or evaluation of a model.

Hosting and analyzing this data can take so much processing power and translation that many hospitals usually can’t do it alone. But the energy to access this data is worth the effort, as valuable insights can be gleaned across the revenue cycle.

Where are the sources of revenue cycle data in RCM + how are they used?

To train and run these models, there must first be data for them to ingest. Structured data is explicit and can be readily processed by machines. It is easier to ingest but limited in nature. These data sources include:

  • Demographic information (e.g., age, gender)
  • Vital signs (e.g., height, weight, blood pressure, blood glucose)
  • Diagnostic, procedures and/or billing codes, medications and laboratory test results generally available in host system
  • Financial data elements such as billing, payments, denials and adjustments

Unstructured data sources require extensive tools to extract relevant information. Examples of unstructured revenue cycle data include:

  • Clinical data, including medical images, scanned labs and ECGs
  • Treatment data, including clinical notes and discharge summaries

The benefits of this data in RCM are massive. These datasets can be used to guide decisioning across various stages throughout the revenue cycle and improve reimbursement accuracy.

Front office:

  • Streamlined appointment scheduling, taking into consideration which providers are credentialed for which payers
  • Automated and optimized scheduling to boost utilization
  • Automated insurance verification and prior authorization retrieval prior to service
  • Virtual assistants managing patient communications regarding financial inquiries, payment plans and insurance-related questions to enhance the patient experience

Mid-office:

  • Thorough clinical documentation based on natural language processing during patient encounters
  • Automated coding and charge entry based on clinical data
  • Automated coding and charge audit for all accounts to ensure accurate reimbursement for services provided

Back office:

  • Denial prediction and prevention based on historical data for proactive interventions to prevent revenue loss
  • Automated billing and payment posting to reduce errors and accelerate reimbursements
  • Contract management and analytics to support underpayment recovery, improve reimbursement and support payer contract negotiations
  • Payer portfolio management to analyze and predict payer-specific trends, behaviors and patterns associated with reimbursement

What are key challenges in compiling revenue cycle data?

Gathering and harmonizing data from many different systems is a difficult ask across industries. Healthcare revenue cycle data, in particular, has unique barriers that make the creation of a centralized, holistic dataset a challenge.

Data heterogeneity and inconsistency

  • Challenge: Healthcare data comes from various systems, each with its own format, terminology and structure. Aggregating these disparate data sources can be like assembling a puzzle with mismatched pieces.
  • Solution: Implement robust data normalization techniques. Standardize terminology, map data elements to common ontologies and ensure consistent representation across systems. For true interoperability, the industry must align on standard data definitions. This means not just consistent terminology, data formats or exchange standards but a single set of these that can inform an industry-wide patient health dataset.

Lack of meta-information and quality for unstructured data

  • Challenge: Unstructured data (such as clinical notes, radiology reports, and free-text entries) lacks essential meta-information (context, source details) and also suffers from inaccuracies, missing values and biases. Extracting meaningful insights from unstructured data becomes challenging without proper context. The vast volume of clinical data is unstructured, requiring processing before any value can be extracted. This means that fundamentally valuable revenue cycle data is often inaccessible to the health systems that might benefit from it.
  • Solution: Generative AI can make sense of unstructured data to create content that can then be analyzed for patterns and other valuable insights. Develop tools for capturing relevant metadata during data entry. Leverage natural language processing (NLP) to extract context and enrich unstructured data. At the same time, implement data validation checks, address missing data and assess bias systematically. Regularly audit data quality and correct discrepancies. Each of these steps helps ensure that the datasets being used are not only accessible but accurate.

Lack of systems interoperability

  • Challenge: Standards such as HL7 and FHIR exist but lack of adherence is an issue. Without consistently enforced standards in place for technological systems — like electronic health records or pharmacy and lab databases — to easily share healthcare data electronically, the effort that it takes for a health system to be interoperable can create a barrier to information exchange.
  • Solution: Providers can overcome challenges of interoperability by integrating large language models (LLMs) with host/legacy systems and other systems of record, not only at a facility level, but across all locations and across all instances of EHRs. This will allow for system-wide datasets that follow industry standards and vendor-specific requirements for data management.

Regulatory compliance and privacy

  • Challenge: The Health Insurance Portability and Accountability Act (HIPAA) regulates the use of sensitive patient health information and prohibits its broad disclosure to those who do not need to access it. Any dataset containing protected health information (PHI) therefore must be built to align to these federal restrictions. Aggregating data while adhering to HIPAA regulations and ensuring patient privacy is critical.
  • Solution: Understand HIPAA’s permitted uses and disclosures. Obtain patient consent when necessary. Regularly review privacy policies and practices. Regarding data usage, ensure proper de-identification of patient data to protect privacy, and adhere to the minimum necessary standard, sharing only relevant information. Implement robust access controls, encryption and audit trails to secure patient data.

The bottom line

Robust AI models are informed by thousands of variables and consume billions of transactions. The more variables provided to inform models, and the greater the volume and variety of data available for consumption, the more complete and valuable models become — providing better and faster insights at the point of decision.

For many health systems, however, this type of processing power can be difficult to support in house; in these situations, a revenue cycle data partner can be an invaluable asset, not only to assist in processing the data but also to provide insight into normalized, holistic analyses from other organizations.

Revenue cycle data is only as valuable as the access an organization has to it. Data analysis requires persistent efforts from a diverse team of problem solvers as well as a robust, diverse dataset — ensure your organization has both available to it.

RELATED CONTENT

The post Why Revenue Cycle Data Is a Key Differentiator appeared first on Ensemble Health Partners.

]]> AI in Action: Revenue Cycle Management https://www.ensemblehp.com/blog/ai-in-action-revenue-cycle-management/ Thu, 11 Apr 2024 18:54:18 +0000 https://www.ensemblehp.com/?p=12924 There's great opportunity for AI in healthcare RCM where models can be fine-tuned to reduce friction and more accurately predict outcomes. … Read More

The post AI in Action: Revenue Cycle Management appeared first on Ensemble Health Partners.

]]>

What you need to know

Artificial intelligence (AI) holds great opportunity for the healthcare revenue cycle, and organizations are taking notice. One recent survey found that nearly 60% of healthcare organizations are considering using generative AI for revenue cycle management (RCM) operations. AI models can be fine-tuned to reduce friction across the revenue cycle and more accurately predict outcomes. For patients and staff, AI can help automate tasks, enhance accuracy and promote compliance.

The healthcare revenue cycle offers a labyrinth of processes, each with its own intricacies. Coding complexities, billing inaccuracies, claim denials and reimbursement delays can often create bottlenecks. These inefficiencies not only impact financial health but also directly affect patient care, causing delays and frustrations in the healthcare journey.

Optimizing the healthcare revenue cycle with AI

Luckily, artificial intelligence can lend support in these areas by:

  1. Automating administrative tasks: AI-driven solutions streamline coding and billing processes, significantly reducing manual efforts and error rates. By automating these tasks, institutions can expedite the revenue cycle and minimize discrepancies.
  2. Enhancing accuracy in claims processing: AI’s analytical capabilities can help minimize errors in claims processing, reducing denials and rework. This precision ensures smoother revenue flow and quicker reimbursements.
  3. Optimizing revenue with predictive analytics: AI algorithms can analyze historical data to predict and prevent barriers to efficient, complete revenue collection. This proactive approach aids in strategic planning and resource allocation, ensuring optimal financial outcomes.
  4. Engaging patients with AI-driven communications: By leveraging AI-powered platforms, institutions can provide patients with transparent billing information and promote compliance. This not only fosters trust but also reduces payment delays.

Here at Ensemble Health Partners, AI is deployed in ways both big and small in support of our partners. The Ensemble data lake maps over 25 billion transactions to outcomes, providing a continuous and growing stream of feedback and insights across our partners. Over the past decade, more than 5,500 AI models have been deployed, informed by 25,000+ variables.

AI in healthcare RCM at Ensemble Health Partners
Click to expand

This enables our partners to benefit from things like predictive analytics, intelligent prioritization of operator work queues and zero-touch automation to streamline processes and ensure providers get paid what they are owed.

A bright future for AI in healthcare RCM

The healthcare revenue cycle, which encompasses the entire lifespan of a patient’s account from appointment scheduling to payment, is a critical process for any organization. Artificial intelligence and generative AI stand to revolutionize not just healthcare’s clinical processes but also those of revenue cycle management.

Today’s AI innovations have the potential to address longstanding challenges and optimize RCM operations — if deployed thoughtfully and with consideration for the current limitations of this technology.

Having specific elements in place can help support AI transformation. These include:

  • Using aggregated, normalized data to build and train models
  • Building diverse models representing numerous geographies and perspectives, which can prevent overfitting a model to a limited set of instances
  • Deploying a clear correlation of inputs to outputs — in the revenue cycle, this might be transactions mapped to outcomes — in order to detect successful patterns
  • Smoothly integrating AI into RCM operations in order to infuse insights directly into workflows and streamline processes
  • Ensuring compliance with HIPAA and other security or privacy policies

Due to specialized knowledge, massive processing power and particular tools needed, building AI models and implementing them effectively can be a difficult undertaking for providers attempting to implement on their own. The right end-to-end RCM partner with experience incorporating AI into the revenue cycle can help to make the transition a seamless one.

The bottom line

AI’s integration into the healthcare revenue cycle brings with it the ability to automate tasks, enhance accuracy, provide predictive insights and engage patients. Exploring and strategically adopting AI solutions can redefine the financial landscape of healthcare institutions, paving the way for improved efficiency, accuracy and, most importantly, better patient outcomes.

Explore The Power + Potential of AI in the Healthcare Revenue Cycle to find out more about how artificial intelligence is being applied in RCM today and learn additional best practices for implementation. Get the whitepaper >>>

RELATED CONTENT

The post AI in Action: Revenue Cycle Management appeared first on Ensemble Health Partners.

]]> 8 Ways to Turn Big Data Into Big Benefits https://www.ensemblehp.com/blog/8-ways-to-turn-big-data-into-big-benefits/ Mon, 10 Oct 2022 19:55:16 +0000 https://www.ensemblehp.com/?p=9142 As the biggest producers of healthcare data, providers must learn how to transform healthcare experiences and outcomes for the better. … Read More

The post 8 Ways to Turn Big Data Into Big Benefits appeared first on Ensemble Health Partners.

]]>

With so much data in healthcare, how do you make it work for you?

Future-proofing your healthcare organization requires maximizing the benefits of your big data while mitigating the associated risks.

While providers are starting to come together to meaningfully share their data through models like Truveta, hurdles still exist. The timing of payor changes and regulatory updates are misaligned, existing standards are interpreted differently and poorly adopted, and several solutions are sitting on the shelf waiting for payors and providers who aren’t ready to use them.

As the biggest producers of healthcare data, providers must learn how to bring that product to market to transform healthcare experiences and outcomes for the better.

Below are eight ideas to start making progress with your data:

  • Start treating your data as an asset. Reframe your organization’s data strategy as something enterprise-wide, not something IT does.
  • Don’t let data become a distraction. Define use cases and ensure business cases and outcomes are clear before embarking on any initiative to monetize your data.
  • Don’t do recreational analytics. Focus your efforts on projects and initiatives that impact at least 20% of your revenue. Focus on solving value creation problems, not technology problems.
  • Get back to basics with your security strategy. Ensure your entire organization has a common understanding of how to share data. Define what you want to do with it early on, map it, and partner with your cybersecurity team to ensure the right safeguards are in place throughout all touch points.
  • Push for a national patient identifier. Accelerating innovation and adoption of digital health capabilities requires the ability to consistently and reliably identify and match patients to their health information.
  • Crawl, walk, run. Start with a clearly defined use case and get a coalition organized to tackle the problem collectively. We can’t tackle everything at once, but we can start making incremental progress toward a clearly defined vision with clearly defined value.
  • Maximize what’s already out there. Learn about the work being done to make progress toward interoperability through initiatives like HL7’s Gravity and Da Vinci projects. The vision is there, the parts are there, and now alignment on regulations is starting to come into focus.
  • Don’t try to figure this out alone. Find an experienced partner that has already walked the path. Getting data structured to provide analytics is hard, but actually using that information and making the answers real is even harder and takes a massive amount of orchestration. Leverage peers and partners to help execute on your strategy.

 

These materials are for general informational purposes only. These materials do not, and are not intended to, constitute legal or compliance advice, and you should not act or refrain from acting based on any information provided in these materials. Neither Ensemble Health Partners, nor any of its employees, are your lawyers. Please consult with your own legal counsel or compliance professional regarding specific legal or compliance questions you have.

RELATED CONTENT

The post 8 Ways to Turn Big Data Into Big Benefits appeared first on Ensemble Health Partners.

]]> Big Data in Healthcare: Know the Risks + Rewards https://www.ensemblehp.com/blog/hospital-leaders-are-in-the-business-of-big-data-know-the-risks-rewards/ Tue, 13 Sep 2022 09:02:00 +0000 https://www.ensemblehp.com/?p=8374 Being in healthcare management means you need to understand the complexity, risks and opportunities associated with running a data company. … Read More

The post Big Data in Healthcare: Know the Risks + Rewards appeared first on Ensemble Health Partners.

]]>

Being a hospital CEO, CFO, CIO or really chief anything, means you need to understand the complexity, risk and opportunity associated with running a data company (which, surprise, you do).

Data is central to everything in healthcare today. Electronic health records (EHRs) have given healthcare providers a platform to digitize and collect massive amounts of data. There are more than 2,300 exabytes1 of healthcare data in the digital universe – up 1,400% from 2013 and growing more than 30% each year.

But what is all this digital data doing for hospitals and patients? Not much (yet). Despite all the potential from this information, we’re only using less than 3% of it and the use of paper is still prevalent. Additionally, productivity is only increasing by 1-3% as a result.

97%

of healthcare data goes unused.

Nearly 90% of providers believe they can achieve better clinical benefits with digitized data.2 However, healthcare data is messy and normalizing it to make it valuable is a huge challenge.

A lot of data is unstructured free text; it’s coming from a lot of disconnected systems and there is a ton of variety – think patient demographics, doctor’s letters, lab results, medications, radiology, insurance and financial information. Additionally, each data type may include various kinds of metrics, such as age, date of birth and measurements, e.g., kg, g/ml. The challenge is to organize the data volume, metrics and measurements from all formats and sources and put it to work.3

As one healthcare leader stated, “It is hard, boring work done by incredibly smart people. There’s no magic solution.” But with more data comes more risk. Are you prepared?

You’ve already got the risk, now get the reward.

Did you know that there are 18x more healthcare data bytes in existence than stars in the observable universe? Every patient adds 80 million bytes of data and each hospital adds 50 quadrillion bytes per year. 

The rewards for big data in healthcare could be abundant when used correctly. The data monetization market in the U.S. could reach $68 billion in 2025,* so it’s essential to understand the risks and what to do next.

Risks of Big Data in Healthcare

While digital information has become an essential piece of healthcare, digital data proliferation has also opened doors for information security risks.

Data breaches or cyberattacks have increased significantly in the last year. In 2021, 45 million people were impacted by healthcare data breaches, which is 84% more likely than in 2018.4 The 2022 stats are already staggering just within the first six months – 337 healthcare data breaches occurred with over 19 million records breached.5  

Not only is a data breach bad for patients and healthcare organizations, but they’re also expensive. The average cost to remediate a breach is over $10 million, increasing 9% in one year; however, one health system’s price was nearly $113 million.6,7

All hospitals and health systems are at risk no matter their size, location or prominence. All hackers care about is getting your data – and they’re coming for it. Check out the Hospital Data Breach Playbook to ensure your healthcare organization is prepared for such an event.

Take a proactive and strategic big data and cybersecurity approach. Healthcare leaders must focus on proper management, cybersecurity and utilization of this massive amount of data to not only maintain their organization’s reputation but position it for future success.

Here are three ways to take control of your data:

Secure it

Have an enterprise data strategy in place and create a culture of preparedness.8

  • Include your cybersecurity team in everything your organization is doing. View this team as a critical partner in digital transformation, not a barrier. And involve your cyber (and legal) teams early in any data and innovation initiatives.
  • Stay ahead of regulations. Understand the rules of how data can and cannot be used and include in your data strategy, even as the proliferation of data outpaces regulatory guidelines.
  • Create a cybersecurity prevention and response plan. To prevent data breaches and mitigate risks of security threats, educate employees on prevention tactics since they are the first line of defense. For your response plan, map out all impacted areas like clinical and revenue cycle downtime, understand analog capabilities, identify support teams and create a data backup strategy.

Structure it

Make data and IT infrastructure investment a priority. Establish and organize an enterprise data warehouse for collecting, storing, analyzing and presenting your data to improve efficiencies and patient outcomes.3

  • Employ data models that are flexible and future-proof to ingest different types of data sources into the warehouse. Be sure your data warehouse includes the 5 Vs of big data analytics: volume, velocity, variety, veracity, value. Each one represents a big data characteristic that should be a part of the framework.
  • Start building your warehouse with structured data, like EHR data, followed by unstructured data, such as doctor’s letters and device data, and then add new data. Continue collecting data in real-time to further enable your team with accurate information to make quick decisions when needed, for example, when patients are sent home from the hospital and are monitored via mobile devices.
  • Create a user-friendly and interoperable system for end users with different skill sets, like researchers and providers, to collaborate, present, interpret and use the data.

Put it to work

 

Monetize your data (directly and indirectly).

  • Analyze your data to improve outcomes. Map your inputs to outputs to reduce variation in contracts and supplies, streamline authorization processes with payors and improve preventive and chronic care management.
  • Think beyond digitizing analog experiences to improve patient engagement. Don’t settle for patients typing their name on an iPad instead of writing it on the clipboard. Ask why patients need to fill in their name at all if their information and appointment time is already in your system. Instead of emailing someone to remind them of a scheduled appointment, text on their birthday to remind them to schedule their first annual mammogram.
  • Capitalize on the data’s inherent value. Properly de-identifying and sharing data can be a new revenue stream for providers and patients. Recently 20 innovative health systems came together to form Truveta, an organization designed to combine, normalize and leverage the massive amounts of data the systems managed to improve patient care, advance health equity and expedite research. Open Health launched a platform called PatientSphere allowing patients to monetize their health data by connecting companies or research institutions with patients who fit the criteria for different studies or analytics. This model uses blockchain technology to secure its data exchange, and this helps resolve data governance and privacy concerns seen elsewhere.

As the amount of healthcare data generated each year grows exponentially, so do the risks and opportunities associated with it. We have more information waiting to be organized than ever before in human history. Let’s use it to provide more access options to people in all communities. Let’s use it to make the practice of medicine more personal, more equitable, more human.

Ensure your partners are helping you prevent the risks and maximize the rewards of your data. Learn more about Ensemble’s commitment to information security, achieving the HITRUST Risk-based, 2-year Certification for our proprietary EIQ revenue intelligence platform and our flagship facility.

References:

  1. Fed Health IT
  2. HealthIT.gov
  3. Frontiers: Better Patient Outcomes Through Mining of Biomedical Big Data
  4. Claims Journal: Viewpoint: Recognize and Plan for Health Care Cybersecurity Risks
  5. Becker’s Health IT: 19M Health Records Compromised in the First Half of 2022
  6. Health IT Security: Average Healthcare Data Breach Costs Surpass $10M, IBM Finds
  7. Modern Healthcare: Scripps Health Cyberattack Cost the Company $113 Million
  8. HIMSS: Cybersecurity in Healthcare

*Prediction by Transparency Market Research.

RELATED CONTENT

The post Big Data in Healthcare: Know the Risks + Rewards appeared first on Ensemble Health Partners.

]]> Using AI and Physician Education to Bolster CDI Teams https://www.ensemblehp.com/blog/using-ai-and-physician-education-to-bolster-cdi-teams-2/ Thu, 09 Jan 2020 19:00:00 +0000 https://www.ensemblehp.com/2020/01/09/using-ai-and-physician-education-to-bolster-cdi-teams-2/ Savvy health systems are using AI and physician education to bolster their clinical documentation improvement (CDI) teams. … Read More

The post Using AI and Physician Education to Bolster CDI Teams appeared first on Ensemble Health Partners.

]]>

Savvy health systems are using AI and physician education to bolster their CDI teams — Join them with these 6 best practices

Many health system leaders see their organizations as locked in an adversarial contest with payers over reimbursement. Claims are often denied based on clinical indicators or the fact that complications or comorbidities were only documented once. These coding issues can lead to inadequate reimbursement, as payers will downgrade reimbursement if the claim lacks specificity.

At Becker’s 8th Annual CEO & CFO Roundtable in Chicago in November, Ensemble Health Partners hosted an executive roundtable to explore how clinical documentation improvement (CDI) best practices and physician education, as well as technologies like artificial intelligence, can enhance reimbursements. Ensemble Health Partners’ Jenna Jordan, senior vice president of health information, and Pieter Schouten, chief analytics officer, facilitated a wide-ranging discussion with session participants.

CDI and coding pitfalls are leading to reductions in hospital reimbursements

Many CDI professionals and medical coders are trained to only look for complications and comorbidities in a patient’s medical record, and then they stop. This is problematic for several reasons. If a complication is only documented once in the discharge summary, payers often will deny the claim. They want to see documentation of diagnosis and treatment throughout the patient’s stay.

Ms. Jordan explained, “Your CDI teams and coders must look at the entire medical record. If they don’t do this, you will fail on value-based outcomes and population health information. Once a payer sees one [major complication or comorbidity], you’re done with the reimbursement. But what about those additional diagnosis codes that show how sick the patient is?”

Organizations that do well on their Medicare Star ratings and risk-adjusted coding have CDI professionals that go beyond complications and look at potential patient safety events.

Another challenge is that payers often use clinical indicators that haven’t been adopted by hospitals. For Medicare, most health systems use sepsis-2 criteria for claims. Yet, Medicare Advantage and other commercial payers will deny those claims because they use sepsis-3 criteria. As a result, the healthcare organization receives an even lower payment even though the patient was treated for sepsis.

“Payers are denying claims just because you don’t meet what they consider to be their clinical indicators,” Ms. Jordan said. “It’s very important that your [health information management team] and CDI departments work together. If the clinical indicators aren’t there, you won’t get paid,”.

Physician education and involvement can help

Physicians must be educated about coding rules, documentation and variations in payers’ clinical guidelines. Ms. Jordan noted, “You won’t connect with doctors by telling them the hospital is seeking more revenue. You have to show them clinically what’s wrong with the patient charts.”

CDI queries to physicians must include clinical evidence. If a large number of queries comes back with “undetermined” responses, that’s a sign that the organization needs a physician education program.

“A CDI professional can tell you they are querying 35 percent of patients, but if they aren’t getting a response from the physicians, those queries are irrelevant,” Ms. Jordan said. “Who are the top doctors you are querying and why? How are they responding? This information will help you identify the financial impact of a physician education program.”

Including a physician advisor on the denials team can also help. Often physician-to-physician calls are more effective than inquiries from the CDI staff. Foreign physicians who aren’t licensed to practice in the United States can make good CDI physician advisors. They must be trained, however, on current clinical indicators and documentation guidelines.

Artificial intelligence can identify claims-related errors

Over the last year, Ensemble Health Partners has been applying technology to identify anomalies and errors in medical claims. Initially, the team took a rules-based approach. Now it is using artificial intelligence and applying it directly to areas like claims validation.

“If you use a rules-based system, it’s basically static. It looks for issues that resemble problems found in the past,” Mr. Schouten said. “Artificial intelligence is more advanced. You can explore completely new problems. We use a machine learning approach called the multi-armed bandit to find errors, particularly with DRG validation.”

6 best practices for bolstering CDI and increasing reimbursements

Ms. Jordan shared six best practices health systems can use to strengthen CDI departments:

  1. Confirm whether the CDI program is reviewing all inpatients. Many CDI initiatives exclude pediatrics and maternity cases. Ms. Jordan has worked with health systems where pregnancy complications are a major source of denials, yet the CDI team doesn’t review maternity patient cases.
  2. Require CDI teams to work on the weekend. Hospitals serve patients seven days a week. Unfortunately claims may never be reviewed for patients who come in on Friday and leave before Monday, if the CDI team only works Monday to Friday.
  3. Make sure the CDI team is on the floor, rounding and communicating with physicians. There is no sense in having CDI onsite if they never leave the office. CDI team members should be out on the floor.
  4. Consider a hybrid onsite/remote CDI model. It’s a good idea to always have a CDI professional onsite. One option is to rotate shifts. CDI team members can alternate between working onsite one week and then working from home the next. “When people work from home, they should have high levels of productivity. When they work onsite, they should focus on interacting with physicians or PAs,” Ms. Jordan said.
  5. Get a list of the top five denials for diagnosis-related group downgrades and the top five findings for code audits. This information allows organizations to develop prompts for physicians within the EHR.
  6. Take CDI to the next level beyond the financial impact. The CDI team should work with quality and focus on patient safety measures.

Conclusion

Dealing with payers is tougher than ever. It’s critical CDI specialists understand the coding rules and review the entire medical record clinically. Even if coders don’t have a clinical background, they can learn clinical indicators. Technology can also give healthcare organizations a leg up, as they strive to minimize denials.

As Ms. Jordan explained, “When you get denials, you have to fight them. You provided the services to patients and you deserve to get paid for them. Fight for every one of those denials, otherwise the payer will see you as an easy target.”

RELATED CONTENT

The post Using AI and Physician Education to Bolster CDI Teams appeared first on Ensemble Health Partners.

]]>