As our Medicaid health plan clients tell us, reimbursement is a numbers game. State evaluations using the National Care Quality Alliance’s HEDIS and other endorsed measurements play a major role in reimbursement. But making measurable improvements to performance is a continuous struggle.
However, medication nonadherence is a driver of preventable healthcare costs, unnecessary hospitalizations, morbidity, and mortality. That said, one way to improve performance on measurements is by targeting interventions for nonadherence. The right artificial intelligence (AI) analytics program can target at-risk and noncompliant patients to boost adherence and reduce costs.
The Role of AI Analytics in Driving Change
In many health sectors, implementing data-driven changes can be challenging. But Medicaid health plans already have mounds of patient data. The key to unlocking that data and making it useful is artificial intelligence. In January 2018, Deloitte reported that the same AI and cognitive technologies used in our personal lives can also improve Medicaid programs.
“Given the size, scope, and cost of the Medicaid program, states and the federal government are constantly looking to improve health outcomes for Medicaid members and achieve greater program efficiencies,” Deloitte experts say. “Smart technologies could provide that possibility through the application of intelligent programs that can process vast amounts of data to understand patterns and make predictions about a member’s future health outcomes or health care utilization.”
So far, state Medicaid programs have been slow to adopt innovative technologies such as AI because many of these companies use outdated platforms — or what Deloitte calls “large, hard coded, and monolithic.”
But the good news is that Centers for Medicare & Medicaid Services (CMS) and state programs are requesting modular API and interoperable cloud solutions when replacing their old platforms. Just like consumer sites that continuously collect data on individuals to learn their preferences and serve relevant content, Medicaid AI systems can use machine learning to identify patients who are likely to be nonadherent and recommend targeted interventions.
Why Targeted Interventions Matter
Data consistently shows that a small number of patients contribute to the largest share of Medicaid expenses. They typically have three or more chronic illnesses and difficulty caring for themselves. They are also more likely to be nonadherent to their medications. Most estimates suggest that around 40-50 percent of patients with chronic illnesses are nonadherent. This pattern worsens their health and quality of life, necessitating even more healthcare and spending.
Targeted interventions selectively speak to this share of the patient population, using language they understand and interventions that address their needs. AI analytics are key to identifying high-risk groups and devising solutions.
The CMS Push for AI Analytics Innovation
If Medicaid plans overlook AI analytics as a tool to optimize their scores, they are doing so at their peril. CMS wants this innovation to happen, so it launched the CMS AI Health Outcomes Challenge in March 2019. Twenty-five participants advanced to Stage 1 of the challenge, with the final two winners announced in April 2021.
CMS describes the challenge as “an opportunity for innovators to demonstrate how AI tools – such as deep learning and neural networks – can be used to accelerate development of AI solutions for predicting patient health outcomes for Medicare beneficiaries for potential use in CMS Innovation Center innovative payment and service delivery models.”
For any Medicaid health plan, improving scores remains the ultimate goal. Because some of these scores reflect whether patient outcomes are genuinely improved by better adherence, finding ways to increase adherence rates has become imperative. In using AI and machine learning to improve adherence scores, Medicaid health plans can translate all their patient data into true patient care.
AllazoHealth is a healthcare AI solution that uplifts adherence by predicting individual patient behavior and specifying personalized interventions. Our mission is to be a leader in precision engagement and predictive analytics, revolutionizing how our healthcare clients improve the adherence of their patient populations.