The safety and scientific validity of this study is the responsibility of the study sponsor and investigators. Listing a study does not mean it has been endorsed by the ANZCTR. Before participating in a study, talk to your health care provider and refer to this information for consumers
Trial registered on ANZCTR


Registration number
Help: Registration number
ACTRN12626000868381
Ethics application status
Help: Ethics application status
Approved
Date submitted
Help: Date submitted
30/06/2026
Date registered
Help: Date registered
16/07/2026
Date last updated
Help: Date last updated
16/07/2026
Date data sharing statement initially provided
Help: Data sharing statement date
16/07/2026
Date results provided
Help: Date results provided
16/07/2026
Type of registration
Help: Type of registration
Retrospectively registered

Titles & IDs
Public title
Evaluating the use of generative AI to improve the quality and timeliness of junior doctor written discharge summaries in Australia: Exploratory blinded simulation study.
Scientific title
Evaluating the use of generative AI to improve the quality and timeliness of junior doctor written discharge summaries in Australia: Exploratory blinded simulation study.
Additional trial identifiers [1] 317740 0
MD430
Universal Trial Number (UTN)
Trial acronym
Related trial records

Health condition
Health condition(s) studied:
Health Services Research 342636 0
Public Health 342778 0
Condition category
Condition code
Public Health 338907 338907 0 0
Health service research

Intervention/exposure
Study type
Interventional
Description of the intervention or exposure

Delivered at home
3 junior doctors given AI-assistance using a Heidi Health subscription supplied by the company, accessed by desktop website. 2 junior doctors non-AI assistance. Each doctor given 20 records derived from the MIMIC-IV hospital admissions repository - a retrospective deidentified cohort of ICU admission in US hospitals specifically designed for research purposes containing full transcripts of all features of the admission including pathology, radiology, and other investigations, and referrals and reviews by consult teams. The records were randomly chosen from 400 downloaded records, allocated based on a weighted file size balance (which qualitatively reflected both the length and complexity of admissions).
AI-assistance participants were given no special training, only that provided to all first-time users via the Heidi Health scribe software.
AI-assisted all returned within the 30 day window. Human only participants given 2 extensions of 30 days each for completion at two follow ups due to non-return of summaries. Adherence was monitored by return of summaries to the pre-specified collection email address.
The Heidi discharge summary template was aligned to the ACSQHC template for digital presentation of hospital discharge summaries with no other instructions given in the prompts. Participants could attach the deidentified patient event to the template and generate, review, edit and finalise the script before returning it on identical standardised discharge summary template docx file which all participants (AI-asssist and human-only) used for their summary completion.
The study protocol included a Delphi method for managing assessment and any significant disagreements between assessors on the scoring of any one discharge summary. Delphi participants included 3 general practitioners, 2 hospital-based consultants and 2 senior registrars. A prespecified threshold of disagreement (>80% difference in scores on the two assessment tools) amongst reviewers was agreed as a trigger a review. Delphi participants were given drafts of the 100-point assessment rubric with the background of its creation in Australia. There were no amendments or changes to the agreed assessment process of both the assessment rubric and PDQI-9. Discussion regarding limitations of the use of US data and the limits of simulation were discussed prior to commencement, with no major disagreements on strategies to manage these issues. At completion of assigned assessments, no summaries had reached the 80% disagreement threshold triggering further summary review.
Intervention code [1] 334577 0
Other interventions
Description of the comparator or control
Non-generative artificial intelligence discharge summary writing. Participants given complete episode of care document in a notepad digital format: the same format as that used for the AI-assisted arm. They could copy and paste, search, and review each episode of care, then complete their summary on the prespecified identical discharge summary template provided by the research team.
Control group
Active

Outcomes
Primary outcome [1] 345977 0
Quality assessment marking rubric returned by each of seven expert consultant reviewers.
Timepoint [1] 345977 0
Within 30 days of allocation of discharge summary to each reviewer.
Secondary outcome [1] 463993 0
Quality Assessment
Timepoint [1] 463993 0
Within 30 days of allocation of discharge summary to each reviewer.
Secondary outcome [2] 463994 0
Timeliness
Timepoint [2] 463994 0
With 30 days of allocation to participants of the 20 randomly selected event summaries

Eligibility
Key inclusion criteria
Any junior doctor registered with AHPRA currently undertaking clinical appointment at an Australian public hospital
Minimum age
18 Years
Maximum age
No limit
Sex
Both males and females
Healthy volunteers
No
Key exclusion criteria
None

Study design
Purpose of the study
Educational / counselling / training
Allocation to intervention
Randomised controlled trial
Procedure for enrolling a subject and allocating the treatment (allocation concealment procedures)
central computer-generated randomisation codes using participant ID linked to email address for allocation
Methods used to generate the sequence in which subjects will be randomised (sequence generation)
computer generated random sequence
Masking / blinding
Blinded (masking used)
Who is / are masked / blinded?


The people assessing the outcomes
The people analysing the results/data
Intervention assignment
Parallel
Other design features
Phase
Not Applicable
Type of endpoint/s
Efficacy
Statistical methods / analysis
Power statistic of 80% using an effect size of 0.5 with alpha of 0.5 based on prior reported differences in other studies on documentation quality using generative AI

Recruitment
Recruitment status
Completed
Date of first participant enrolment
Anticipated
Actual
Date of last participant enrolment
Anticipated
Actual
Date of last data collection
Anticipated
Actual
Sample size
Target
Accrual to date
Final
Recruitment in Australia
Recruitment state(s)
ACT,NSW,NT,QLD,SA,TAS,WA,VIC

Funding & Sponsors
Funding source category [1] 322282 0
University
Name [1] 322282 0
Bond University
Country [1] 322282 0
Australia
Primary sponsor type
University
Name
Bond University
Address
Country
Australia
Secondary sponsor category [1] 325196 0
Commercial sector/Industry
Name [1] 325196 0
Heidi Health
Address [1] 325196 0
Country [1] 325196 0
Australia

Ethics approval
Ethics application status
Approved
Ethics committee name [1] 320798 0
Bond University Human Research Ethics Committee
Ethics committee address [1] 320798 0
Ethics committee country [1] 320798 0
Australia
Date submitted for ethics approval [1] 320798 0
01/04/2025
Approval date [1] 320798 0
15/04/2025
Ethics approval number [1] 320798 0
KL02349

Summary
Brief summary
Trial website
Trial related presentations / publications
Public notes

Contacts
Principal investigator
Name 151666 0
Dr Kieran Le Plastrier
Address 151666 0
Bond University, 14 University Drive. Robina. QLD. 4226
Country 151666 0
Australia
Phone 151666 0
+61 0428 727 222
Fax 151666 0
Email 151666 0
Contact person for public queries
Name 151667 0
Kieran Le Plastrier
Address 151667 0
Bond University, 14 University Drive. Robina. QLD. 4226
Country 151667 0
Australia
Phone 151667 0
+61 0428 727 222
Fax 151667 0
Email 151667 0
Contact person for scientific queries
Name 151668 0
Kieran Le Plastrier
Address 151668 0
Bond University, 14 University Drive. Robina. QLD. 4226
Country 151668 0
Australia
Phone 151668 0
+61 0428 727 222
Fax 151668 0
Email 151668 0

Data sharing statement
Will the study consider sharing individual participant data?
No
No IPD sharing reason/comment: Small n study making de-identification less reliable



What supporting documents are/will be available?

TypeCitationLinkEmailOther DetailsAttachment
Ethical approval    KL02349_BUHREC approval letter.pdf
Study protocol    MD A430 AI Discharge Summaries Ethics Protocol Application PROJECT PLAN 20032025 V3.docx


Results publications and other study-related documents

Documents added manually
TypeIs Peer Reviewed?DOICitations or Other DetailsAttachment
Basic resultsNo ANZCTR ResultsReportingTemplate .docx

Documents added automatically
No additional documents have been identified.