PARTNERED WITH
INEFFICIENCY INSIGHTS WITH NAVINA.AI
Why Physicians Spend Hours Pre-Charting—and How Navina Solves It
I'm well into my third year of residency, and I still haven't figured out how to streamline pre-charting and documentation. There's just too much to review in too little time. The fear of "missing something" never goes away.
This is especially true for complex patients who've seen five specialists across three health systems since their last visit, or who've had two hospitalizations with overlapping care teams. Piecing together that fragmented timeline takes real work. And when I'm writing my note, I'm constantly backtracking, jotting something down, then jumping back into the chart to verify a detail, then returning to finish the sentence.
It's maddening. And I like to think I'm efficient!
The data confirms what most of us already feel: physicians spend roughly half of their time on EHR and administrative tasks rather than direct patient care. Much of that happens after hours, the infamous "pajama time" devoted to finishing charts.
The stakes are even higher under value-based care.
What worries me most is what happens when I'm managing my own panel and my own risk-based contracts. Under value-based models, outcomes and financial performance hinge on precise documentation and accurate capture of diagnoses. I need comprehensive visibility into each patient's health journey.
But I’m left piecing together fragmented information from disparate systems with no single source of truth. Diagnoses fall through the cracks. Documentation gaps lead to underreported HCCs, inaccurate RAF scores, and unrealized shared savings. For physicians assuming downside risk, that's a direct hit to the financial incentives that value-based care is built on.
Primary care physicians dealing with high visit volumes and increasing value-based accountability are especially exposed. Multispecialty groups face complex RAF reporting and care coordination demands. And care teams shoulder the burden of closing gaps and ensuring documentation integrity.
So, we face two bottlenecks:
Fragmented patient data that's hard to find, reconcile, and trust.
Documentation burden that spills into after-hours work and fuels burnout.
Both undermine our ability to deliver high-quality care and succeed in value-based models.
Insights
Root Cause Analysis: 5 Whys
The 5 Whys process in root cause analysis involves repeatedly asking "Why?" five times to drill down into the root cause of a problem by exploring the cause-and-effect relationships underlying the issue.
The problem: Clinicians spend excessive time on pre-charting and documentation.
Why?: Pre-charting and documentation require hunting through multiple disconnected sources for patient information, with constant backtracking to verify details and piece together the clinical narrative.
Why?: Patient data lives in multiple siloed systems (EHR, claims databases, health information exchanges, unstructured notes, PDFs, labs, medications, and prior documentation) with no unified view or single source of truth.
Why?: Healthcare IT infrastructure evolved organically over decades, with different vendors, health systems, and payers building systems independently to meet their specific operational needs, resulting in limited interoperability between platforms.
Why?: True data interoperability has been technically and organizationally challenging to achieve, requiring coordination among competing vendors, standardization of data formats, and alignment of incentives across multiple stakeholders.
Why (root cause)?: The healthcare data infrastructure evolved to solve operational and financial needs first, with clinical workflow becoming a secondary consideration. Rebuilding integrated systems requires massive coordination and investment across an entire ecosystem.
Impact Analysis
Impact analysis is the assessment of the potential consequences and effects that changes in one part of a system may have on other parts of the system or the whole.
Patient: Receives fragmented, potentially incomplete care when their physician doesn't have full visibility into their health journey. Critical diagnoses or medication changes from other specialists may be missed, leading to duplicative testing, adverse drug interactions, or gaps in chronic disease management. Experiences longer wait times as their physician scrambles to piece together their chart before or during the visit. Ultimately, they may receive lower-quality care despite having excellent insurance and seeing multiple specialists, simply because information doesn't flow seamlessly between providers.
Clinician or Provider: Spends half of their working hours on administrative tasks rather than patient care, with much of this time occurring after hours during "pajama time." Faces professional frustration from knowing they might be missing critical information but lacking the time or tools to find it. Under value-based contracts, physicians bear financial risk for documentation gaps that lead to underreported HCCs and inaccurate RAF scores, directly undermining their compensation. The constant cognitive load of hunting through fragmented records contributes significantly to burnout—repeatedly cited in studies as a major factor in physician dissatisfaction and early retirement. We're forced to choose between thoroughness (spending more time we don't have) and efficiency (accepting we might miss something important).
System: Perpetuates massive inefficiency across the entire healthcare delivery chain. Organizations employing more administrative staff than clinicians just to manage data fragmentation, driving up operating costs without improving outcomes. Under value-based care arrangements, health systems and practices miss out on shared savings and quality bonuses due to incomplete documentation and missed diagnosis capture. The downstream costs are staggering: preventable hospitalizations from missed follow-up, duplicative testing, medication errors from incomplete reconciliation, and care coordination failures. For providers assuming downside risk, these gaps translate directly into unrealized revenue and financial losses, making value-based models unsustainable.
Solution: Navina.ai
If you review my root cause analysis, the only practical and realistic solution is the one that addresses Why #1 and Why #2. That is, a tool that automatically reconciles fragmented data, surfaces it at the point of care, and integrates into existing workflows.
This is what Navina is doing.
Navina is an AI copilot designed to tackle both bottlenecks I described:
Fragmented patient data
Documentation burden
Navina pulls information from everywhere (EHR, claims, health information exchanges, unstructured notes, PDFs, labs, medications, and ambient transcripts) and reconciles it into a single, coherent view. It integrates directly into the EHR, so there's no context-switching or opening another application. It lives where we already work.
Instead of me hunting through five different tabs to piece together a patient's timeline, Navina does that work automatically. During the visit, it records the encounter in real time and turns it into documentation, flagging suspected diagnoses and risk coding opportunities that are tied directly to source documents. That means I can verify everything quickly without the constant backtracking I described earlier.
What sets Navina apart from ambient-only scribes is that it fuses real-time conversation with historical clinical data. A recent study by Navina's medical team found that ambient transcription alone produced only 40.4% documentation completeness for chronic disease management, but when combined with historical data (labs, comorbidities, medications), completeness more than doubled to 82.9%. Critical markers like HbA1c trends and blood pressure history live in the chart, not in the room. Ambient-only tools miss them!
The data suggests it's actually working. A study by Phyx Primary Care found that physicians using Navina saw a 40% reduction in chart review time. The American Academy of Family Physicians reported that physicians using Navina saved an average of 9 minutes per visit in prep time and experienced a 45% increase in feeling prepared for the encounter.
And there's a 49% increase in identified diagnoses that weren't previously documented. Under value-based care models, those missed diagnoses translate directly into underreported HCCs and lost revenue. Surfacing them prospectively—during the visit, not at year-end chart review—means more accurate risk adjustment and better care.
The root cause—decades of fragmented system development—requires systemic reform that's not happening anytime soon. But tools like Navina show we don't have to wait for the system to change to make meaningful progress.
By breaking down data silos, reducing the cognitive burden of pre-charting and documentation, and giving physicians real-time visibility into patient data, Navina addresses the realities we physicians experience every single day.
About this post: This is a sponsored deep dive with Navina. The framework and conclusions, however, are my own. As a reminder, I only partner with companies solving real problems I'd write about anyway, and Navina's approach to fragmented patient data and documentation burden fits that bar. As always, my goal is to give you a transparent breakdown of what works, what doesn't, and why it matters for patients, physicians, and the health system. If you or your company would be interested in a partnership like this, click here.
FROM HUDDLE+
Why Most AI in Healthcare Treats Symptoms, Not Root Causes
AI is everywhere in healthcare right now—scribes, prior auth tools, “clinical copilots”—but most of what we’re rolling out is designed to make a dysfunctional system run a little faster, not to fix the dysfunction itself. We’re pouring time, money, and attention into tools that optimize around fee‑for‑service, prior auth, and documentation bloat instead of asking whether those constraints should exist in the first place.
That might feel like progress day to day, but it has a cost. The more “efficient” we make bad processes, the harder it becomes to build or justify truly transformative AI that could redesign workflows, payment, and staffing from the ground up. At some point we have to ask: are we reducing friction, or just deepening the grooves of a system we already know is broken?
👉 Full breakdown in my latest Huddle+ article here.
FROM HUDDLE UNIVERSITY
AI & Healthcare Utilization — Now Live
If you’ve been trying to separate AI hype from reality, this course is built for you.
AI & Healthcare Utilization walks through real‑world use cases across hospitals, physician groups, and payers—how AI is actually being used to reduce waste, improve flow, and support better care, with concrete ROI numbers and frameworks you can apply in your own setting.
I dig into where AI meaningfully changes utilization (and where it doesn’t), which vendors are solving real problems vs adding noise, and what it takes to go from pilot to system‑wide adoption without burning out your clinicians or blowing up workflows.
👉 Course is live—enroll in “AI & Healthcare Utilization” here.
CONSULTING
Work in clinical trials?
I’m looking to connect a fellow Huddle who’s building in the clinical trials space with people who work in it.
Specifically:
Folks involved in clinical trial operations
People responsible for patient identification and recruitment
Research coordinators, PI/Co‑Is, clinical research office leaders, or vendor partners who help sites fill studies
If you’re in that world—or know someone who is—and are open to a short conversation to share how your team actually runs patient recruitment today, just reply to this email and I’ll connect you.
I work with healthcare companies and startups who want an honest, physician‑level read on their strategy, product, and go‑to‑market—rooted in how care is really delivered, not just how it looks in a slide deck. Interested? Click here.
