by Ivan Bradshaw
What is medical necessity?
Before jumping straight into resolving denials, we need to first define medical necessity. Medical necessity refers to the determination by an insurance company that a healthcare service or procedure is reasonable and necessary for the diagnosis or treatment of a patient’s medical condition. This judgement is supposed to be based on accepted standards of clinical practice.
Factors that cause medical necessity denials
Sometimes, when providers make a medical necessity request seeking approval to treat a patient, it is denied. Some common factors why payers deny medical necessity include:
Medical necessity denial can sometimes be preventable. By ensuring thorough documentation and adherence to the payer’s guidelines, providers give their medical necessity requests the best possible chance for approval by the payer. However, even when the rules are followed and clinical justification is solid, denials are not always entirely avoidable. Sometimes, factors such as insurance company policies and individual case complexities are cited in denying medical necessity.
AI helps prevent these denials
AI for claim denials helps prevent medical necessity denials by analyzing patient data, clinical documentation, and insurance guidelines to ensure that the proposed treatment plans align with established clinical criteria from the payer. AI looks for patterns in large datasets such as claims, EMR, or PMS and spots accounts that may be missing patient data, do not follow the payer’s guidelines, or have missing or incomplete clinical documentation to justify the request.
When AI finds inconsistencies in data patterns, it flags the account so billers, coders, and revenue integrity staff can review the account and address the items that have been surfaced by AI. It can be used to support accurate billing practices in a similar fashion.
Predictive analytics help even more
The use of ML-based models and techniques, can combine multiple models to improve predictive accuracy when predicting medical necessity denials. Temporal models can also be used to analyze longitudinal patient data and predict changes in medical necessity over time. This trending information allows providers to proactively anticipate potential issues and take preventive actions to avert the denials.
Appealing the denial
Even when you think the medical necessity request has been properly filed and it has been checked against all known criteria, sometimes denials still happen. At this stage, the provider needs to go to bat for the patient through the payer’s appeal process. This can be time-consuming and the work it takes to generate an appeal is not reimbursed.
The appeal submission includes additional documentation that justifies why the provider believes the recommended treatment would be in their patient’s best interest. Various types of medical records such as emergency department documentation, diagnostic test results, procedure documentation, consultation reports, progress notes, physician orders, clinical guidelines, and other sources can be submitted to support the appeal.
Automating appeals management
Automating the generation of appeal letters and supporting documentation based on denial reasons and relevant clinical data streamlines the appeals process and improves efficiency. Robotic Process Automation (RPA) can handle repetitive tasks involved in appeal generation, freeing up human resources for more complex tasks.
There are a couple of ways that automation can help reduce the administrative burden of appealing a medical necessity denial. By using AI and Large Language Models (or LLM), appeal letters can be automatically generated by providers. Once AI has created the initial letter, the provider does need to review it, and make appropriate edits. However, this automation saves a tremendous amount of time, and it can even provide scholarly citations by reviewing clinical sites on the internet to bolster justifications.
Another use case for AI in the appeals management process is for the gathering of supporting documentation based on denial reasons and relevant clinical data streamlines to improve the improves efficiency of the appeals process. Some larger organizations are beginning to experiment with Robotic Process Automation (RPA) to process repetitive, low risk tasks that are involved in appeal generation. RPA successfully performs these timeconsuming and tedious tasks and frees human resources to focus on researching and responding to more complex tasks.
Overcoming Medical Necessity Denials WhiteSpace Health
The WhiteSpace Health Platform interprets historical claims data using AI algorithms and identifies payer patterns, guidelines, and provider recommendations. Staff can then use the actionable insights generated by AI to resolve act and resolve denied claims with the steps that have been historically proven to have the highest probability of successful resolution. Here is a high-level explanation of how it works.
Find all the denials due to medical necessity. Group them together to work efficiently
AI in the platform looks for similar claims in historical data that were approved and paid. It consolidates the steps that lead to successful reimbursement and delivers guided steps so your team can always take the highest probability actions for resolving medical necessity denials.
Advantages of using AI for medical necessity denials
AI in the WhiteSpace Health Platform finds complex patterns in historical claims information and delivers guided steps to resolve medical necessity denials. Since appealing medical necessity denials is not a reimbursable activity, it is important to appeal denials quickly and effectively. AI supports successful appeals with historical evidence.
Even the newest employees can be immediately productive when they follow the guided steps provided by AI. This ensures even the most junior staff members can work quickly and effectively. And when appeals are overturned, patients can receive the care that is needed, and your organizational billings are enhanced.
About Ivan Bradshaw
Ivan Bradshaw is the vice president of product management at WhiteSpace Health. As a revenue cycle management executive with over 20 years of experience, Ivan is adept at building high-performance teamsand creating RCM solutions that stop revenue leakage, improve operational efficiency, and grow top-line performance.
Ivan.Bradshaw@whitespacehealth.com
2424 North Federal Highway, Suite 205
Boca Raton, FL 33431
