Healthcare and life sciences
Your hospital’s own AI.
Patient file summaries and admin help, with records that stay in the hospital.
Admitted for a planned hip operation 1. Two changes since admission: a new blood thinner 2 and a fall risk flag from the nursing notes 3.
- 1Admission note
- 2Medication chart
- 3Nursing notes
Illustrative
- Tasks to start with. A Test Lab takes one.
- 3
- Its Formula
- HLM
- To roll back to the last release, by design
- 60 s
- Eigna Local. Data never leaves.
- Local
The work that cannot leave
Patient records are the most sensitive data there is. They stay where they are, and every draft needs a clinician’s approval.
- Patient records
- Clinical notes
- Letters and coding
- Referrals
Where it runs, for healthcare
Eigna Local
Data never leaves.
On the hospital’s own servers.
Training runs on a GPU we rent in a region you approve: an encrypted snapshot goes there for each run and is deleted after it. Where nothing may leave your network, it runs on your own GPU.
The first expert
Three tasks to start with.
Summaries, letters and decisions approved by clinicians and staff.
File summaries
The summary a clinician needs, with every line linked to the record.
Admitted for a planned hip operation 1. Two changes since admission: a new blood thinner 2 and a fall risk flag from the nursing notes 3.
- 1Admission note
- 2Medication chart
- 3Nursing notes
Learns from · Summaries your clinicians approved.
Letters and admin
Letters, coding and forms in the hospital’s own wording.
A draft in your letter template, with the diagnosis, the procedure and the follow up 1. The follow up date comes from the outpatient booking 2.
- 1Discharge summary
- 2Outpatient booking
Learns from · Letters your doctors signed.
Sorting referrals
Sends each referral to the right clinic, and hands the unclear ones to a person.
Cardiology outpatients, routine 1. The letter mentions chest pain on exertion, which your triage rules hand to a person 2.
- 1Referral letter
- 2Triage rules, cardiology
Learns from · Referrals your triage team sorted.
The proof we will measure
A metric, a baseline and a sealed test, agreed before we start.
The target is set with you before the Test Lab starts. If the expert does not beat your baseline, you keep the report.
17.8%
Our first training run cut forecast error 17.8% against its base model. It is not yet ahead of a simple last value baseline, and we publish that too.
Rules in plain words
What the rules ask, and what every release gives you.
- 01
Records stay in the hospital
With Eigna Local the model runs on the hospital’s own servers.
- 02
A person signs off
Summaries, letters and referrals are drafts until a clinician approves them. Nothing learns without approval.
- 03
A record of every release
A named owner, a Model Deed and a release record. Designed to support your compliance work, not to replace it.
Healthcare and life sciences
Records stay in the hospital.
The model runs on the hospital’s own servers, and every summary, letter and referral stays a draft until a clinician approves it.
Healthcare: questions and answers
Does it make clinical decisions?
No. It drafts summaries, letters and referral sorting for a clinician to approve. Unclear cases go to a person.
Where do patient records go?
Nowhere. With Eigna Local the model runs on the hospital’s own servers, and training can run on your own GPU.
How do we start?
With one admin task, such as discharge letters, in a Test Lab on your own data. If it does not beat today’s process, you keep the report.
Test Lab
Request a Test Lab for healthcare.
One task, your data, a sealed setup, about four weeks. If the expert beats your baseline, the test set becomes your first release gate. If not, you keep the report.
- RouteThrough hospital IT partners and health integrators.
- Watch forStrong need, long approval cycles. Admin and summaries come before anything clinical.
- ReplyWithin two working days, from a founder.
