Risk adjustment & quality measurements for optimized CMS reimbursements

Risk adjustment in healthcare, also known as ‘case-mix management,’ administered by the Centers for Medicare & Medicaid Services (CMS), is a program that aims to answer “How would the performance of various units compare if hypothetically they had the same mix of patients?” as defined by the National Quality Forum.¹

This model is used to adjust payments of Medicare Advantage Organizations (MAOs) to determine the expected healthcare costs of the Medicare patients, also known as, enrollees, based on disease factors and demographic characteristics.²

How does risk adjustment in healthcare work?

A risk-adjusted rate for a facility is calculated as the following:

Risk-adjusted rate = (observed rate / expected rate) * reference population rate

What is the ‘observed rate,’ in risk adjustment healthcare?

(The observed rate is the number of patients with the measure focus / by the number of patients in the target population.)

The target population will reflect the patient characteristics of the measured entity – the clinician or facility – and the observed rate will determine the performance of the measured entity in that target population.

What is the ‘expected rate’ in risk adjustment healthcare?

(The expected rate is also the number of patients with the measure focus / by the number of patients in the target population.)

Here, the expected rate is the performance of all the measured entities in the reference population (e.g. Medicare fee-for-service) on that target population.

What is the ‘reference population’ rate in healthcare?

In the reference population rate, the target population will reflect the enrollee’s characteristics of the reference population, and the performance of all the measured entities in the reference population on that population.

Another way to calculate the risk-adjusted rate for a facility is the following:

(Risk-adjusted rate/reference population rate) = (observed rate / expected rate)

The result is often to as the ‘risk standardize ratio.’

For example, the observed-to-expected rate ratio for a facility is 1:4, which interprets the provider’s performance as 40 per cent higher than what is expected for the particular provider’s patient population. The risk-adjusted rate will assume that the provider would have performed at the same relative performance had the same patient population as the reference population.

What are the risk adjustment quality scores and patient satisfaction measures as per HEDIS?

The Healthcare Effectiveness Data and Information Set (HEDIS) measures designed by the National Committee for Quality Assurance (NCQA), is a popular set of performance measures in the US-managed healthcare sector.

HEDIS includes measures for physicians, Preferred Provider Organization (PPOs), and other Medicare Advantage organizations

An incentive for many health plans to collect HEDIS data is a CMS requirement that health maintenance organizations (HMOs) submit Medicare HEDIS data in order to offer HMO services for Medicare patients, also known as enrollees, under the program called Medicare Advantage.

Importance of ‘High Data Quality’ in your risk adjustment for healthcare payers

The data submitted for risk adjustment must be of top quality; including other parameters:

• The data must be retrieved in a reliable way
• Data must be valid for their purpose
• Data must be sufficiently comprehensive
• The data collected are the recent ones
• The data collected are as complete
• Documentation of the data sources.

How can an Analytic Approach to Risk Adjustment help MA organizations?

Selecting the correct AI-based risk adjustment coding solution is imperative because conventional models can lead to missing important diagnosis codes and even worst, you may end up validating and submitting non-compliant HCC codes to the CMS.

Optimized patient data, will make it easy for HMOs to contact patients in the target group and notify them about the importance of preventative screenings. The same approach to patient outreach can be used to encourage patients to take measures when needed the most and improve care quality.

The key to success with this approach to patient care is real-time data, which can be achieved using an NLP-powered chart review and retrospective audit solutions.

Click to know more about HEDIS Measurement Year 2022 & HEDIS Measurement Year 2023.

Godspeed!