digitaltzar

Thank you!

Greatly appreciated!

Thank you!

Agreed, many reasons to admire them

:)

Thank you for these thoughts. I think billing inefficiencies caused by documentation make both hospitals and insures lose - one will get paid later, one will pay anyway, but the process is costly for patients who finance both, in the end of the day :(

Thank you so much! Lets explore! Could you please ping me at dmitry.k@wrkdn.com or let me know what is the best way to connect

My friend who works now as an engineer at Apple interviewed with Epic 6 years ago - he got a guidance from a fellow to make a few mistakes in test tasks to increase chance of getting a job offer, and it worked - he got the offer

Thank you, human stories like this made us passionate about solving this issue! Talked today to a behavioral health clinic that has 65 different payors, all with own set of billing rules and documentation standards!

The agents are LLM-based but for orchestration we use other ML methods

Thank you for the insights, I believe the challenge they have is related to CPT coding - not mistakes or errors, but the completeness' of clinical picture fro m the billing/insurance standpoint. A lot of this coding knowledge is tribal and resides in the head of clinicians. We can help, would greatly appreciate an introduction to your wife's colleagues at dmitry.k@wrkdn.com (Dmitry Karpov), thank you!

Very insightful, thank you! A comment on claim-amplifying customers - optimizing for the insurance payouts actually forces providers to adopt certain standards of compliance for medical records - here we are not talking about mistakes but about depth of CPT coding (the biggest for value-based care providers), etc. And it is not about claim but the underlying documentation of care

Now I understand your question. I can provide and example where a small documentation error may cause patient harm - wrong copy-pasting in a discharge note, copying from other personal medical record and accidentally pulling their diagnosis into the record, and then factoring this diagnosis by the other doctor in their treatment plan

Not with Epic, we work with Kipu and Athena for now

Not only US, e.g. the whole clinical world is now moving into AI-powered scribing of doctor visits, it really depends on the deployment model - where are LLMs, how they comply with local regulations. But access of AI to medical charts is a solved questions in general.

Great questions, indeed this is a kingdom of red tape. We realized that our fist users likely will be small providers but who currently lose $$ on denied/delayed claims. Talked to the first cohort of them - rehabs, allergy clinic, men's health clinic, nursing home, etc. We signed the first rehab just 2 weeks after meeting them because we offered to solve their problem in the same way as their 3rd party billing provider does (manually finds mistakes and circles them back to clinicians) for 2x lower price tag. Then we realize this is common situation for many rehabs.

For them it's a cost of doing business. Many of those claims will be paid after resubmissions (upon fixes the mistakes if it is possible) but the office operates with higher amount of working capital in this case

It's a rough journey, we are exploring how MCP makes it easier. Haven't met anyone who say that they like their EHR interface yet.

Thank you! We are at wrkdn.com

To start, we integrate with Kipu and Athena, just happened that our first clients are rehabs and clinics that use these 2.

Good point on the desire to stay in HR for the review workflow, this is our vision that could be achieved with widgets in specific EHRs but this is down the road. Once mistake is identified, we notify clinical professionals via standard communication like emails and also keep a dashboard with the list of 'topics' inside our portal.

Thank you!

1. It really depends on the clinical specialty, but the average is around 25% (e.g. 250M claims denied a year because of documentation mistakes). We work with rehabs where this ratio is above 50%

2. It's triple checking -tun the analysis twice and then verify the conclusion, 3+ separate agent calls