Health plans are not short on data. Most have access to claims, clinical records, pharmacy information, and lab results covering their entire enrolled population. The real problem is that this data sits in disconnected systems, rarely surfacing as actionable insight until the measurement window is nearly closed, and almost never translates into coordinated action at the member level. Care gaps go undetected, outreach gets launched in Q4 as a last resort, and manual workflows limit how many members a team can actually reach.
AI is changing this equation, but only when it is connected to the right data infrastructure and the right interventions at the right time. Here are five ways health plans are using AI to close care gaps more effectively and what that means for HEDIS performance and Stars ratings.
1. Making fragmented health plan data actionable for gap closure
Most plans have the right data somewhere. The challenge is that it is spread across claims systems, EHRs, pharmacy feeds, lab results, and supplemental sources that rarely talk to each other. A member who completed a colorectal cancer screening at an out-of-network facility may still appear as an open gap in the plan's quality dashboard simply because the result never made it into the right system.
AI-powered platforms that unify clinical, claims, pharmacy, and lab data into a single model eliminate this problem at its root. Rather than chasing documentation gaps after the fact, plans get a real-time, member-level picture of what has been done and what has not. Galaxy by Innovaccer is built on this foundation, connecting disparate data sources so that every gap closure decision starts with a complete view of the member, not a partial one. Orlando Health is one organization that uses this unified data model to power real-time care decisions and personalized outreach across its network.
2. Scaling member outreach through smarter segmentation
No plan can reach every member with the same level of intensity, and trying to do so waste resources while producing diminishing returns. AI-powered segmentation changes the calculus. By analyzing clinical history, prior engagement patterns, social risk factors, and measure-specific data, AI can identify which members are most at risk of missing a measure and which outreach channels are most likely to produce a response.
This matters especially in Medicare Advantage, where a one-point Stars improvement can translate into tens of millions of dollars in Quality Bonus Payments. Plans that use AI to prioritize outreach around specific measures, such as colorectal cancer screening, kidney health evaluation, or hemoglobin A1c control, direct their resources toward the gaps most likely to move the needle rather than distributing effort evenly across a population that does not require it equally.
The results from AI-powered prioritization at the point of care are concrete. Optimus Healthcare Partners, a leading ACO, achieved a 27% improvement in quality gap closure for MSSP patients over a two-year period and a 16% improvement in documentation accuracy using Innovaccer's platform. That kind of sustained improvement does not come from manual outreach lists. It comes from AI surfacing the right member, at the right time, with the right clinical context already assembled.
3. Reaching members where they are, right at home
Identifying a gap is only half the problem. Closing it requires that a member actually completes the required service. For many Medicare Advantage populations, that is where traditional outreach breaks down. Transportation barriers, care deserts, work schedules, and low provider engagement all reduce the likelihood that a member will complete a screening through conventional channels.
At-home testing removes these barriers by bringing the test to the member rather than asking the member to come to a clinic. Ash, a leading at-home health testing platform expanding care to reach those most in need, has partnered with Innovaccer to integrate Ash's at-home gap closure solutions as a diagnostics infrastructure layer within Galaxy's MultiPoint Gap Closure™ platform, enabling health plans to manage testing programs across provider offices, community pharmacies, and member homes from a single workflow. Test results from Ash's programs, including A1C, FIT, and kidney health screenings, flow directly back into Galaxy's data layer, closing the loop between identification and documented closure.
According to Grand View Research, the global at-home testing market is expected to reach over $18 billion by 2030, reflecting a structural shift in how care is delivered and where members expect to engage with their health plan. For quality programs, this shift is an opportunity: members who have never responded to provider-based outreach often will engage when a kit arrives at their door with clear instructions and a simple return process.
4. Coordinating care across every channel simultaneously
The traditional gap closure model is sequential. A plan identifies a gap, sends a letter, waits, calls, waits again, and then considers alternative channels if nothing has worked. By the time a plan has exhausted this sequence for a large population, the measurement year is nearly over.
MultiPoint Gap Closure™ changes this by activating all channels simultaneously. If a member does not respond to a provider alert, a pharmacy outreach and a mailed kit are already in motion. If the kit goes unregistered after delivery, the member enters a targeted follow-up workflow. Every action is coordinated through one system, with a single view of what has been attempted and what remains open. This is the model Ash and Innovaccer have built together: Ash is now directly integrated within Galaxy's MultiPoint Gap Closure platform, enabling health plans to launch and manage testing programs not just across provider offices and community pharmacies, but critically, in member homes from a single, unified command center.
5. Building a gap closure engine that improves over time
The most durable advantage AI offers in gap closure is not speed. It is learning. Each measurement year produces a clearer picture of which member segments respond to which interventions, which measures are hardest to close through which channels, and which outreach sequences produce the highest completion rates. Plans that capture this intelligence in a connected platform carry those learnings forward into the next year, improving prioritization models and outreach sequencing without starting from scratch.
This is what separates an AI-powered gap closure program from a vendor relationship that resets annually. The model gets better because it is built on the same unified data foundation that powers risk adjustment, quality management, and member engagement simultaneously. Every interaction adds context. Every result, including at-home test completions, informs future decisions. Optimus Healthcare Partners saw this compounding effect directly: a 10% improvement in coding gap closure alongside quality gains that built over a two-year period, not a single measurement cycle.
Care gap closure at scale presents logistical challenges including staffing and channel, but even more so it is a data and coordination problem. AI addresses it by unifying the data, prioritizing the right members, reaching them through every available channel, including their front door, and carrying the intelligence forward year over year. For health plans looking to build a sustainable quality program rather than a reactive Q4 sprint, that is where the real opportunity sits.
To learn more about how Ash and Innovaccer power gap closure at scale, meet with the Ash team or request a Galaxy demo.
At-home testing market projection sourced from Grand View Research. Partnership details sourced from the Ash and Innovaccer press release, January 2026. Optimus Healthcare Partners outcomes sourced from the published Innovaccer case study, August 2025.
