CMS released a Framework for Health Equity 2022–2032, signaling a proactive approach to understanding and addressing the influence of social determinants of health (SDoH). This initiative aims to evaluate the impact of SDoH and formulate a strategic plan for individuals facing obstacles in accessing healthcare services. The CMS Health Equity framework calls upon all stakeholders within the healthcare system to reevaluate their programs and incentive structures, considering factors that can be modified to tackle unmet social needs. Additionally, it explores strategies for linking individuals with the necessary services once data related to their health risks has been collected.

This blog post highlights CMS’s Priority One, the importance of standardized data collection, and the transformative power of machine learning in healthcare.

CMS’s Priority 1: Expand the Collection, Reporting, And Analysis of Standardized Data

The Centers for Medicare & Medicaid Services (CMS) has recognized the pivotal role of data in achieving health equity. Their Priority One initiative focuses on expanding the collection, reporting, and analysis of standardized data.

Health Equity, a term we often hear, refers to the absence of disparities in health and healthcare among different groups. Achieving health equity means that everyone has the opportunity to attain their highest level of health. It’s a noble goal, but how do we get there? The answer lies in data.

At the core of Priority One lies SPADE, which stands for “Standardized Patient Assessment Data Elements.” SPADE comprises seven essential elements:

1. Patient Assessment: Gathering comprehensive information about the patient.
2. Race and Ethnicity: Understanding the patient’s racial and ethnic background.
3. Preferred Language: Identifying the language a patient is most comfortable communicating in.
4. Need for an Interpreter: Assessing whether an interpreter is required for effective communication.
5. Health Literacy: Gauging the patient’s ability to comprehend health-related information.
6. Transportation: Examining the accessibility of transportation for patients.
7. Social Isolation: Identifying instances where patients may be socially isolated.

To understand healthcare disparities, CMS wants more data beyond contact details, like race, age, ethnicity, and income. However, making this data collection voluntary is problematic because of member distrust and difficulties in obtaining accurate data, especially for Medicaid members. While the intent is good, members may not share information, placing the burden on plans to find alternative ways to collect risk data.

The Role of Machine Learning in Reporting & Analysis

So, how do we make sense of all this data? This is where machine learning steps in. Machine learning algorithms can analyze SPADE data, extracting valuable insights and patterns.

1. Enhancing Data Completeness

Machine learning can validate the meaningfulness of data by comparing Z codes (structured data) with textual data. This ensures that the information collected is both accurate and relevant.

2. Predictive Analytics

By harnessing historical data, machine learning enables healthcare professionals to predict patient behaviors and health outcomes. For example, it can forecast how individuals from a specific area might fare health-wise in the next decade based on their social determinants of health (SDOH).

3. Empowering Population Health Management

Healthcare isn’t just about individual patients; it’s also about entire populations. By aggregating and analyzing SPADE data, healthcare providers can:

1. Tailor services: Identify which services are most needed by a population.
2. Allocate resources: Efficiently allocate resources based on specific population needs.
3. Foster collaboration: Encourage collaboration among hospitals, local bodies, and communities to address health disparities.

How Persivia Can Help with Priority 1:

Persivia’s advanced AI-driven platform offers a comprehensive solution for healthcare organizations. It seamlessly collects and consolidates data from a multitude of patient sources, including clinical records, insurance claims, Health Information Exchanges (HIEs) and Admission, Discharge, and Transfer (ADT) systems, patient-reported information, device data, behavioral data, and Social Determinants of Health (SDOH) data.

The key feature of this platform is its ability to create a dynamic, continuously updated longitudinal patient record. This record provides a holistic view of each patient’s medical history, interactions with the healthcare system, personal circumstances, and more. It serves as a valuable foundation for a wide range of applications.

Once this comprehensive patient record is established, the platform leverages the power of artificial intelligence (AI). Sophisticated machine learning algorithms are applied to ensure data completeness and accuracy. By analyzing this enriched data, the platform generates intelligent insights. These insights can be harnessed for various purposes, with a primary focus on enhancing population health management.