Equitable access to health care is more than just about geographical coverage. It depends on the healthcare system’s ability to identify risk early, intervene intelligently, and sustain those interventions across the most clinically and socially complex populations.
This is why many value-based care (VBC) models struggle. Underserved Medicaid and Medicare populations frequently experience a disproportionate burden of chronic diseases, behavioral health challenges, transportation barriers, food insecurity, language gaps, and disconnected care journeys. Once patients present in the emergency department or experience an avoidable admission, the opportunity for lower-cost, lower-acuity care is often less possible.
The challenges are well understood – most organizations are still operating with lagging data, subsequent incomplete visibility into contract performance, and limited ability to connect contractual risk with clinical action in real time. As healthcare continues shifting toward value-oriented reimbursement models, equitable care delivery increasingly depends on infrastructure capable of turning population-level data into timely, actionable clinical and operational decisions.
One Provider’s Experience
A large provider organization that serves roughly 141,000 Medicaid and Medicare patients recently confronted this reality. Nearly 45% of its patients managing diabetes were also navigating multiple comorbidities, creating a population vulnerable to acute exacerbations, hospitalizations, and readmissions.
The organization faced significant operational headwinds common to many serving underserved communities. Payer data often arrived months late, making it difficult to understand why contracts were under-performing or which patients were trending toward acute episodes before costs escalated. The organization was effectively trying to manage complex value-based risk arrangements while looking backward through incomplete data.
Unfortunately, this dynamic is not unique; across healthcare, providers serving high-risk populations are frequently asked to manage increasingly sophisticated contracts without the same actuarial visibility historically available to payers. The result is reactive care management instead of proactive intervention, particularly for populations where earlier outreach can make the greatest difference. Actuarial AI and predictive intelligence can help alter VBC’s trajectory by offering a more comprehensive, forward-looking framework.
Traditional Predictive Models Aren’t Up to the Challenge
Traditional predictive models often focus narrowly on utilization forecasting or retrospective reporting. The next generation of actuarial AI systems is beginning to amalgamate claims data, contract logic, demographics, utilization trends, and clinical workflows into a more operationally useful framework. Instead of simply identifying what happened, these systems can help organizations understand what is likely to happen next, and where intervention opportunities exist before costs spike.
The Importance of Operationalizing Insight
Risk presents heterogeneously across communities, age groups, languages, comorbidity profiles, and care access patterns; a one-size-fits-all intervention strategy inevitably leaves gaps. Predictive intelligence that can stratify risk dynamically across diverse patient populations allows providers to target outreach more precisely and allocate finite care management resources where they can have the greatest impact. This reduces costs as well as the friction that prevents appropriate care from happening proactively.
Much like with the technology that has preceded it, we’ve learned that AI adoption in healthcare only succeeds when it streamlines and is integrated into existing workflows rather than creating new administrative burdens. Physicians are not resistant to tools that help them, just to those that add unnecessary steps to already compressed processes and cluttered workdays. Organizations most likely to improve outcomes for vulnerable populations will not necessarily be the ones with the most sophisticated dashboards, but the ones capable of operationalizing insight directly into care delivery. If AI can surface which patients are at risk for avoidable admissions, identify the clinical and social drivers contributing to that risk, and simplify the pathway for intervention, then providers can act earlier and more impactfully.
Actuarial AI in Action
The experience of the provider organization mentioned earlier offers a practical example. After implementing actuarial AI tools, they were able to analyze utilization patterns and contract performance in real time, uncovering insights that traditional reporting had obscured. While initial payer data suggested pediatrics and OB were driving readmissions, deeper analysis identified hypertension as a leading root cause of avoidable hospital utilization. That insight materially changed their intervention strategy.
The system launched a hypertension management initiative specifically targeting Medicaid and Medicare patients with complex comorbidities, embedding prompts into clinical workflows and expanding outreach to previously unengaged patients within its risk contracts. Multi-lingual engagement campaigns helped convert previously disconnected patients back into care.
The organization moved from reacting to adverse events after they occurred to identifying risk trajectories earlier enough to intervene. That is the promise of combining actuarial AI with VBC infrastructure: strengthening the system’s ability to consistently deliver appropriate care at scale.
Transparency and Trust Are Critical Ingredients
There is a growing tension between regulated clinical AI and the informal use of ungoverned AI tools across healthcare environments. Across the industry, leaders agree that black-box outputs cannot become the foundation for clinical, operational, or financial decision-making.
For AI-driven VBC models to meaningfully support underserved populations, providers must understand how risk is being calculated, how interventions are prioritized, and how recommendations align with real-world patient needs. Otherwise, the industry risks replicating existing inequities inside more sophisticated systems.
The Future of Equitable Care
The future of equitable care delivery will depend on whether healthcare organizations can unify clinical intelligence, actuarial rigor, and operational execution into a single framework that supports both outcomes and sustainability. Healthcare already possesses enormous volumes of claims, utilization, demographic, and clinical information. The problem has been the inability to synthesize and operationalize that information quickly enough to change patient trajectories while there is still time to act. Actuarial AI and predictive intelligence are beginning to close that gap.
As VBC continues to evolve, the organizations best positioned to improve equity may be the ones that can transform data into earlier intervention, precise outreach, and more informed clinical decisions, not just for the easiest patients, but for the populations that healthcare has historically struggled to serve well.
About Najib Jai, MD,
Dr. Najib Jai, MD, is the Chief Operating Officer of Arbital Health. His career evolved from supporting value based care (VBC) models through private equity investing to joining Oak Street Health to lead specialty care strategy, improving outcomes for patients with complex, multimorbid conditions. He later co-founded Conduce Health, pioneering the first multi-specialty VBC platforms that match the right specialist with the right patient, considering their social drivers of health. Through predictive modeling and innovative contracting structures, his work improved care coordination and outcomes for high-risk populations. Now at Arbital Health, Dr. Jai continues to influence the industry by embedding clinical and operational insight into its Actuarial AI infrastructure, which enables payers and providers to identify the highest-risk members and their emergent needs to drive positive outcomes at scale.
