[upbeat music] Here's why the first paper matters.
Right.
An invited perspective by Noppawit Ayamtrakul, Charat Thongprayoon, and Wisit Chungpasitporn.
Their diagnosis is a mismatch.
Our patients come with years of labs, medications, biopsies, dialysis records, and transplant history scattered across systems, and we have minutes to pull it together.
They point out that up to three-quarters of the world's population lacks good access to kidney care and that in a US survey, work hours and the electronic record were the top reported drivers of nephrologist burnout.
Preach.
They organize the fix around the visit.
Before it, AI that summarizes the referral packet, triages referrals, and maybe one day rebuilds a patient's whole kidney journey as one timeline.
During it, an ambient scribe that listens and drafts the note.
After it, AI that drafts patient replies, prior authorization letters and appeals, suggests diagnosis codes, and flags missing documentation.
The appeal letter one is my favorite.
So we'd have robots writing denials and robots writing appeals.
An arms race with a human signing at the bottom.
Now, their central idea is a useful one.
And they say start with three workflow jobs: pre-visit chart summaries, in-basket and message drafts, and administrative paperwork.
Why those three?
Nothing goes out, gets submitted, or gets acted on until a clinician checks it.
That's their safety net.
So what's the evidence it actually works?
[upbeat music] Here's why the first paper matters.
Right.
An invited perspective by Noppawit Ayamtrakul, Charat Thongprayoon, and Wisit Chungpasitporn.
Their diagnosis is a mismatch.
Our patients come with years of labs, medications, biopsies, dialysis records, and transplant history scattered across systems, and we have minutes to pull it together.
They point out that up to three-quarters of the world's population lacks good access to kidney care and that in a US survey, work hours and the electronic record were the top reported drivers of nephrologist burnout.
Preach.
They organize the fix around the visit.
Before it, AI that summarizes the referral packet, triages referrals, and maybe one day rebuilds a patient's whole kidney journey as one timeline.
During it, an ambient scribe that listens and drafts the note.
After it, AI that drafts patient replies, prior authorization letters and appeals, suggests diagnosis codes, and flags missing documentation.
The appeal letter one is my favorite.
So we'd have robots writing denials and robots writing appeals.
An arms race with a human signing at the bottom.
Now, their central idea is a useful one.
And they say start with three workflow jobs: pre-visit chart summaries, in-basket and message drafts, and administrative paperwork.
Why those three?
Nothing goes out, gets submitted, or gets acted on until a clinician checks it.
That's their safety net.
So what's the evidence it actually works?
The rest of this transcript — segmented and speaker-labeled, so you land on the exact moment something was said
Search every transcript — by keyword, by phrase, or by meaning, across every show Radar indexes
Trends — what is surging across podcasts, measured against its own baseline
Alerts — when a name you follow appears in a newly indexed episode
No account is needed to search Radar.