> ## Content Index
> Fetch the complete content index at: https://nephspace.com/llms.txt
> Use this file to discover other available public pages before exploring further.

# Start AI with the paperwork, not the prescriptions, a Kidney360 piece argues
- URL: https://nephspace.com/ai-practice-kidney360/
- Published: 2026-10-02T00:24:00.000Z
- Updated: 2026-10-04T19:23:31.000Z
- Description: Three Mayo Clinic authors map where AI could save time before, during and after a visit. Their first picks are chart summaries, message drafts and admin documents, though the evidence for those uses is still thin.
- Author: Dr Wael Hussein
- Tags: Other, #story, #has-audio, #education-ai, #opinion, #full-story, Stories

### The argument

A nephrologist inherits years of labs, medications, imaging, biopsies, dialysis runs and outside records, then gets a short visit to make sense of them. Add notes, messages, coding and prior authorizations. This invited perspective from Mayo Clinic says the point of AI here is not speed for its own sake. It is to protect the clinician's attention for judgment and conversation.

The authors draw a useful line. Clinical AI estimates risk, spots patterns and suggests treatment. Workflow AI gathers information, drafts documents and routes tasks. They argue the second kind is the safer place to start.

### Key points

- Before the visit: AI summaries of referral packets, help with triage, and future tools that rebuild a patient's kidney history as a single timeline and flag gaps.
- During the visit: ambient AI scribes. A randomized outpatient trial they cite found modest drops in documentation time and better clinician well-being. It also found clinically significant note errors that doctors had to fix. Much nephrology reasoning, such as volume status or a dialysis prescription, often goes unsaid, so the scribe's note must stay an editable draft.
- In dialysis: use of an anemia-dosing model's recommendations was associated with 12.6 fewer hospitalizations per 100 person-years in an observational study.
- After the visit: suggested codes, draft orders, patient replies, education materials, prior-authorization requests and appeal letters.

Their three near-term priorities are pre-visit chart synthesis, drafting replies to patient messages and administrative documents. The burden is high and the risk is lower, because a clinician checks every draft before anything is sent or acted on. Their advice for rollout: pick one workflow, design it with nurses, patients, informatics and compliance, and measure the baseline before counting time saved, errors and overrides.

### Why it matters

It is a measured, practical road map. Responsibility stays with the treating clinician. Anything that could change a dialysis prescription, medications, immunosuppression, a transplant decision or escalation needs that clinician's confirmation. Oversight should scale with the cost of an error.

### Caveats

It is an opinion piece with 10 references and no new data. The authors admit the evidence is still limited for the very uses they recommend first, and they call for pragmatic trials against usual care. There are no cost figures, no vendor names and no time-saved numbers for scribes beyond "modest." The dialysis outcome examples are observational. They also list the failure modes: summaries that leave things out, drafts with inappropriate advice, inaccurate paperwork, automation bias and bad records amplified by AI.

Industry ties: none disclosed by the authors.

*Context, not from the paper:* the three dialysis tools it cites have Fresenius Medical Care links. Fresenius Medical Care is the legal manufacturer of the Anemia Control Model, the EuCliD paper was written by Fresenius Medical Care researchers, and the hospitalization-risk study by Chaudhuri and colleagues lists Fresenius authors and Fresenius-funded medical writing. NephSpace's editor, Dr. Wael Hussein, serves on the Fresenius Medical Care US Home Medical Advisory Board.

---

**The source:** Aiumtrakul N, Thongprayoon C, Cheungpasitporn W. Artificial Intelligence in Nephrology Practice: Practical Pathways to Improve Efficiency. Kidney360\. 2026 (ahead of print). doi:10.34067/KID.0000001424 [Read the original](https://journals.lww.com/kidney360/fulltext/10.34067/kid.0000001424~artificial-intelligence-in-nephrology-practice-practical?ref=nephspace.com)

**🎧 Listen:** [Weekly · Oct 2](https://nephspace.com/weekly-oct-2/), from 24:31; also in [Deep Dive · Two Desks](https://nephspace.com/two-desks/), from 01:22.

*Physician-led, AI-assisted. Dr. Wael Hussein chooses every item NephSpace covers and reviews and edits every story before it is published. The first draft was written in our own words with AI (Claude, by Anthropic) from the full text of the paper and checked against our reading notes; Dr. Hussein then reviewed and edited it. For education and information only, not medical advice. Please talk to your own physician or care team about your health. Clinicians: read the original before changing practice. See our* [*disclaimer*](https://nephspace.com/disclaimer/) *and* [*disclosures*](https://nephspace.com/disclosures/)*. Spotted an error?* [*Tell us*](mailto:hello@nephspace.com?subject=Correction)*.*