Quality improvement spreadsheets and AI privacy: what a GP clinical audit sheet gives away in ChatGPT or Claude.
Practices run quality improvement work from spreadsheets: an export of every patient with diabetes, their latest results and whether they are due for review. The practice manager or a nurse uploads the sheet to ChatGPT or Claude to find the overdue patients, chart the results or fix a formula. The sheet is a clinical register for a whole cohort, with identifiers. This page marks a routine audit sheet and shows how the same work is done on Ermos inside the practice.
The quality improvement spreadsheet
Exported from the clinical software by the practice manager or a nurse to plan recalls and track quality measures, then shared by email, which is how it reaches an AI tool.
| A | B | C | D | E | F | G | H | |
|---|---|---|---|---|---|---|---|---|
| 1 | Patient | DOB | Indigenous status | HbA1c % | eGFR | Smoker | Last review | Note |
| 2 | Walter Kaminski1 | 14/05/19482 | Neither3 | 7.64 | 524 | Ex5 | 03/11/20266 | Memory assessment pending7 |
| 3 | Lionel Achterberg1 | 07/07/19612 | Neither3 | 8.44 | 714 | Yes5 | 14/02/20266 | Recent NSTEMI. Alcohol.7 |
| 4 | Rosalind Mbeki1 | 22/01/19702 | Neither3 | 9.84 | 644 | No5 | 02/09/20256 | Overdue. Lost job, cannot afford strips.7 |
| 5 | Darren Coolwell1 | 09/11/19752 | Aboriginal3 | 10.24 | 414 | Yes5 | 18/06/20266 | Renal referral declined.7 |
| 6 | Mei-Ling Cartwright1 | 30/03/19832 | Neither3 | 6.94 | 984 | No5 | 12/10/20266 | Pregnancy planning.7 |
| 7 | Giorgos Lambrou1 | 15/08/19522 | Neither3 | 7.14 | 384 | Ex5 | 05/05/20266 | Wife has dementia; he is her carer.7 |
| 8 | Natalie Oyelaran1 | 01/12/19902 | Neither3 | 11.44 | 1024 | No5 | 20/01/20266 | Eating disorder history. GP only.7 |
| 9 | Ahmad Rahimi1 | 28/02/19662 | Neither3 | 8.04 | 594 | No5 | 11/08/20266 | Interpreter, Dari.7 |
An invented spreadsheet. All patients are fictional. Hover or tap any highlighted item for the analysis; the full list is below.
What leaves the practice
- 1Patient names
A name on a list titled for diabetes is already a diagnosis. The names were collected in providing a health service, so they are held as health information under section 6FA. Privacy Act guide.
Frontier Models (ChatGPT, Claude) Transmitted to the provider, generally offshore on personal plans Ermos Edge Stays on your instance in Australia; leaves only inside a permitted excerpt, per question, to the named provider Ermos Dominion Stays on the unit in your office - 2Dates of birth
With the names, enough to identify each patient with certainty. Privacy Act guide.
Frontier Models (ChatGPT, Claude) Dates of birth for the whole cohort transmitted Ermos Edge Stays on your instance in Australia; leaves only inside a permitted excerpt, per question, to the named provider Ermos Dominion Stays on the unit in your office - 3Aboriginal and Torres Strait Islander status
Racial or ethnic origin is sensitive information under section 6(1) of the Privacy Act. Privacy Act guide.
Frontier Models (ChatGPT, Claude) Sensitive information about ethnic origin transmitted Ermos Edge Stays on your instance in Australia; leaves only inside a permitted excerpt, per question, to the named provider Ermos Dominion Stays on the unit in your office - 4HbA1c and kidney results
Laboratory values against every named patient in the cohort. Health information, which is sensitive information. Patient data guide.
Frontier Models (ChatGPT, Claude) Sensitive health information transmitted; on consumer tiers it can train future models Ermos Edge Stays on your instance in Australia; leaves only inside a permitted excerpt, per question, to the named provider Ermos Dominion Stays on the unit in your office - 5Smoking status
A health behaviour against each name. Patient data guide.
Frontier Models (ChatGPT, Claude) Smoking status transmitted Ermos Edge Stays on your instance in Australia; leaves only inside a permitted excerpt, per question, to the named provider Ermos Dominion Stays on the unit in your office - 6Last review dates
When each patient was last seen, and which ones have dropped out of care.
Frontier Models (ChatGPT, Claude) Dates show who has dropped out of care, though not why Ermos Edge Stays on your instance in Australia; leaves only inside a permitted excerpt, per question, to the named provider Ermos Dominion Stays on the unit in your office - 7The notes column
Free text with the most candid detail: a lost job, an alcohol history, an eating disorder kept to the GP, a carer at home. The column most likely to cause harm. Patient data guide.
Frontier Models (ChatGPT, Claude) Candid notes about money, alcohol and an eating disorder transmitted Ermos Edge Stays on your instance; a permitted excerpt may go to the named Australian provider, which keeps nothing Ermos Dominion Stays on the unit in your office - 8The review formula
A date test with no patient information in it. The formula can be shared; the sheet it sits in cannot.
Frontier Models (ChatGPT, Claude) A formula with no patient data in it Ermos Edge Not about where data goes Ermos Dominion Not about where data goes - 9Other tabs and file properties
The workbook carries a second tab covering every chronic disease patient, plus any hidden columns, comments and properties such as the author. Uploading the file sends all of it.
Frontier Models (ChatGPT, Claude) Every tab, hidden column and comment travels with the file Ermos Edge Stays on your instance in Australia; leaves only inside a permitted excerpt, per question, to the named provider Ermos Dominion Stays on the unit in your office
What happens in Frontier Models (ChatGPT, Claude)
- The whole document is transmitted to the provider’s servers. On personal plans the user cannot choose where it is stored or processed, and for the major providers that has generally meant outside Australia, under that country’s legal process. Some business plans offer storage in Australia, but the provider still receives the content.
- On consumer tiers, prompts can be retained and used to train future models.
- The provider’s staff and systems can reach the content under the provider’s own policies.
- Once sent, the practice no longer controls it. Retention and deletion happen on the provider’s terms.
The same document on Ermos
Ermos Dominion
The document is drafted on a unit in your office, from your own templates and the patient record. Every marked item stays on the unit, which keeps working with the internet switched off. Nothing in it is transmitted to an AI provider, so there is no disclosure to analyse: the confidentiality work is the same as for your file server.
Ermos Edge
Your documents, the index and your access boundaries stay on your own instance in an Australian data centre. When a staff member asks for this draft, only their question and the excerpts they are permitted to see go to a named Australian provider, who is contractually barred from keeping the content or training any model on it. Nothing is processed outside Australia.
| Frontier Models (ChatGPT, Claude) | Ermos Edge | Ermos Dominion | |
|---|---|---|---|
| Where the document is processed | Provider servers, generally offshore on personal plans | Your instance in an Australian data centre; answers generated in Australia | The unit in your office |
| Who can read it | Provider staff and systems, under policy | Your staff, within the boundaries you set. The named Australian provider processes only permitted excerpts, under contract, and keeps nothing | Your staff only |
| Is it kept | On the provider’s terms | Kept on your instance; the provider is barred from retaining it | Stays on the unit |
| Can it train a model | On consumer tiers, yes | No, by contract | Only your own unit learns from it, on your hardware |
Part of AI data leakage in general practitioner (GP) practices. See how this works in practice: Care plans on Ermos.
Common questions
Do ChatGPT and Claude use the information in a quality improvement spreadsheet?
Is it safe to upload a quality improvement spreadsheet to ChatGPT or Claude if we delete the name column?
Can I upload a quality improvement spreadsheet to ChatGPT or Claude instead of pasting it?
How can a GP use AI for a quality improvement spreadsheet without sending it to ChatGPT or Claude?
Is a quality improvement export covered by the Privacy Act?
Would a breach of this sheet be notifiable?
Can we de-identify the sheet first?
See Dominion answering from your own documents.
A demonstration takes 30 minutes, uses no client data, and comes with no obligation.
Book a demo