Trial Review

Please note that the ANZCTR website will be unavailable from 1:00pm until 2:30pm (AEST) on Thursday 5th June for website maintenance.
Please be sure to log out of the system in order to avoid any loss of data. Thank you and apologies for any inconvenience caused.

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
ACTRN12625000432415
Ethics application status
Approved
Date submitted
18/02/2025
Date registered
9/05/2025
Date last updated
9/05/2025
Date data sharing statement initially provided
9/05/2025
Type of registration
Retrospectively registered

Titles & IDs
Public title
AI scribe for clinical documentation
Scientific title
Improving Clinical Efficiency using AI scribe for Documentation (ICE-AID study): A retrospective-prospective cohort study.
Secondary ID [1] 313998 0
Nil
Universal Trial Number (UTN)
Trial acronym
ICE-AID study
Linked study record

Health condition
Health condition(s) or problem(s) studied:
Paediatric infections 337284 0
Neuro-developmental conditions 337286 0
paediatric neurological conditions including seizures 337287 0
Genetic conditions 337288 0
paediatric respiratory conditions e.g. asthma 337289 0
paediatric kidney diseases e.g. glomerulonephritis 337290 0
failure to thrive. 337291 0
Condition category
Condition code
Public Health 333227 333227 0 0
Health service research

Intervention/exposure
Study type
Interventional
Description of intervention(s) / exposure
The intervention is use of Artificial Intelligence (AI )scribe (Heidi Health AI scribe) by the clinicians, The study evaluates the impact of the AI scribe tool for medical documentaiton on various quantitave and qualitative outcomes related to improved clinical efficiency and quality of medical documentation.

Description of tool/ intervention: AI scribe tool works as a standalone tool in the browser. The AI tool uses microphone of the computer the doctor is working on. AI tool uses instantaneous cloud based transcribing technology from the audio input of the computer via the microphone in the room and does not record any encounter. The transription is then processed by the AI tool to produce the documentation of the clinical encounter and produce letters and correspondance so that the clinicians do not have to type these documents.

Type of documents will include the clinic notes in the outpatient and inpatient settings, letters for the general practitioners, letters to other health professionals, advocacy letters to NDIS, , letters to the school, letters explaining the condition of the child to the parents in simplified language that the consumers can understand.

Tool is online and the documents produced will be copied and pasted into the hospital electronic records. The tool will stay online only and not downloaded to the devices or the hospital computers.

Training: will be provided to the health professionals using the tool by the AI scribe project team and the vendor. Each health professional will have atleast one face to face session with the vendor or the AI scribe project team who are proficient in the use of the AI scribe tool. The face to face sessions will be usually for an hour though multiple sessions may be required for some health professionals to set up their specific letter templates. The training is delivered over the first month (onboarding month) with ongoing assistance and support by the project team and the vendor as required.

Intervention administration: General Paediatricians, paediatric subspecialists (all paediatric subspecialities including paediatric respiratory,paediatric neurology, cardiology, nephrology, immunology, rheumatology, palliative care), nurse practitioners and allied health professionals including speech pathologist, occupational physiotherapists, genetic counsellors.

Monitoring adherence: Adherence will be monitored uisng the AI scribe tool analytics provided by the vendor.

Post implementation preiod will start after the onboarding month. The data will be matched for each user in the pre and post implementation phase.
Intervention code [1] 330581 0
Treatment: Devices
Comparator / control treatment
This study compares pre and post intervention outcomes in the same cohort.

Preintervention phase: had the following hospital processes:
a) The clinicians use the IEMR for clinical notes (typed)

b) Dragon Medical system for dictating the letters back to referring GP or other health professionals. The letters are then typed by the medical transcriptionists sent by secure web transfer (electronic portal to GPs) and then also put in electronic medical records.. If a GP is not on the electronic secure web transfer system then the letters are mailed to the GP surgery.

Participants: The data of the same participants will be compared pre and post intervention.

Duration of data for pre-intervention phase: the same period as the period of the study in one year prior to the study. The data period will be different for different clinicians depending on their onboarding date. 6 months data in 2024 for the preintervention period will be the comparator in exactly the same months as for the trial period in 2025. Each clinician will be in the study for 6 months. So pre-intervention 6 months data compared to post intervention 6 months data.

The data in the proof of concept project for the first two months will not be considered as pre-intervention data, .The pre-intervention data will be the historical data prior to introduction of AI scribe.


Control group
Historical

Outcomes
Primary outcome [1] 340790 0
Any change in the time to clinician completion of clinical letter/document from the end of the clinical encounter compared to pre-implementation
Timepoint [1] 340790 0
Baseline data of 6 months prior to onboarding (in the same months in the previous year) ; 3 , 6, 12, 18 and 24 months post implementation.
Secondary outcome [1] 445079 0
Any change in patient satisfaction during clinical encounters.
Timepoint [1] 445079 0
1 month, 3 months, 6 months , 12 months , 18 months and 24 months after the onboarding month (first month of AI scribe use = onboarding month)
Secondary outcome [2] 445080 0
Any change in the quality of life measures for health professionals
Timepoint [2] 445080 0
1 month, 3 months, 6 months , 12 months , 18 months and 24 months after the onboarding month (first month of AI scribe use = onboarding month)
Secondary outcome [3] 445081 0
Perceived value of AI scribe by clinicians (User reflections survey)
Timepoint [3] 445081 0
at 1 month, 3 months, 6 months after onboarding month and then 6 monthly intervals till 24 months.
Secondary outcome [4] 445082 0
Any change in the ratio of letters to appointments in the pre and post implementation phase
Timepoint [4] 445082 0
at 1 month, 3 months, 6 months after onboarding month and then 6 monthly intervals till 24 months.
Secondary outcome [5] 445083 0
Cost-effectiveness of implementation of an AI scribe compared to pre-implementation due to savings within organisation from overtime expenditure and transcribing services cost.
Timepoint [5] 445083 0
at 1 month, 3 months, 6 months after onboarding month and then 6 monthly intervals till 24 months.
Secondary outcome [6] 445084 0
SUS score (system usability scale)
Timepoint [6] 445084 0
at 3 months after onboarding and also at 6 months (if feasible)
Secondary outcome [7] 445087 0
Modified PDQI9 (Physician document quality instrument) tool to evaluate the quality of the notes pre and post implementation
Timepoint [7] 445087 0
at 3 months after onboarding month and also at 6 months after onboarding (if feasible)
Secondary outcome [8] 445088 0
Focussed group interview to evaluate the subjective outcomes and themes in a qualitative framewok.
Timepoint [8] 445088 0
6 months after the onboarding month

Eligibility
Key inclusion criteria
All general paediatricians in the General Paediatrics department were included and rest of health professionals were selected based on the expression of interest invited from health professionals in the hospital with total number of AI scribe licences capped at 150 (based on calculation of available resources to support the onboarding of clinicians within the parameters and funding for the project)

Patient: Carers were included in the Patient's carer surveys if the patients had clinical encounter with a health professional using the AI scribe.
Minimum age
No limit
Maximum age
No limit
Sex
Both males and females
Can healthy volunteers participate?
No
Key exclusion criteria
There are no exclusion criteria for clinicians.

If a patient/carer declines consent for the clinician to use the AI scribe for their clinical interaction, that particular episode of clinical interaction will not be included in the study.

Study design
Purpose of the study
Educational / counselling / training
Allocation to intervention
Non-randomised trial
Procedure for enrolling a subject and allocating the treatment (allocation concealment procedures)
Methods used to generate the sequence in which subjects will be randomised (sequence generation)
Masking / blinding
Open (masking not used)
Who is / are masked / blinded?



Intervention assignment
Single group
Other design features
Phase
Not Applicable
Type of endpoint/s
Efficacy
Statistical methods / analysis
The data will be analysed with mixed methods approach using both quantitative and qualitative analyses techniques. The quantitative data will be analysed with Stata 17 statistical software. Statistical software R will be used to generate graphics in some instances. We will use means ± SD to describe the normally distributed continuous variables, median and interquartile ranges for the non-parametric variables and proportions with 95% confidence intervals to describe the categorical variables. Chi square and Fisher exact test as appropriate will be used to compare the categorical variables, Student’s t-test to compare normally distributed continuous variables and Mann-Whitney test to compare the non-parametric variables. Logistic regression analysis will be used to assess predictors for the completion of the medical notes and letters. Log transformation or other transformations will be used where appropriate. Survival analyses using cox-proportional hazard models will be used for assessment of time to completion of the medical letters and to evaluate the predictors for completion of the medical letters and for successful uptake of AI scribe by the users. In the current study, successful uptake of AI scribe will be defined as usage of AI scribe on an ongoing basis by the users beyond 3 months of introduction. Longitudinal regression data analyses will be used to evaluate the associated factors for change of outcomes over time.

Qualitative framework using thematic analyses will be used to analyze and identify themes for the qualitative data.

Recruitment
Recruitment status
Recruiting
Date of first participant enrolment
Anticipated
Actual
18/02/2025
Date of last participant enrolment
Anticipated
31/05/2025
Actual
Date of last data collection
Anticipated
28/03/2027
Actual
Sample size
Target
150
Accrual to date
100
Final
Recruitment in Australia
Recruitment state(s)
QLD
Recruitment hospital [1] 27656 0
Queensland Children's Hospital - South Brisbane
Recruitment postcode(s) [1] 43830 0
4101 - South Brisbane

Funding & Sponsors
Funding source category [1] 318504 0
Hospital
Name [1] 318504 0
Chief Executive Imagination Fund ; Children's Health Queensland
Country [1] 318504 0
Australia
Primary sponsor type
Hospital
Name
Queensland Children's Hospital
Address
Country
Australia
Secondary sponsor category [1] 320893 0
None
Name [1] 320893 0
Address [1] 320893 0
Country [1] 320893 0

Ethics approval
Ethics application status
Approved
Ethics committee name [1] 317109 0
Children’s Health Queensland Hospital and Health Service Human Research Ethics Committee
Ethics committee address [1] 317109 0
Ethics committee country [1] 317109 0
Australia
Date submitted for ethics approval [1] 317109 0
07/02/2025
Approval date [1] 317109 0
12/02/2025
Ethics approval number [1] 317109 0
HREC/25/QCHQ/115987

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

Contacts
Principal investigator
Name 140022 0
Dr vishal Kapoor
Address 140022 0
Department of Paediatrics, Queensland Children's Hospital, 501 Stanley Street, Queensland, Brisbane ; Post code 4101
Country 140022 0
Australia
Phone 140022 0
+61400889748
Fax 140022 0
Email 140022 0
[email protected]
Contact person for public queries
Name 140023 0
vishal Kapoor
Address 140023 0
Department of Paediatrics, Queensland Children's Hospital, 501 Stanley Street, Queensland, Brisbane; post code 4101
Country 140023 0
Australia
Phone 140023 0
+61400889748
Fax 140023 0
Email 140023 0
[email protected]
Contact person for scientific queries
Name 140024 0
vishal Kapoor
Address 140024 0
Department of Paediatrics, Queensland Children's Hospital, 501 Stanley Street, Queensland, Brisbane; Post code 4101
Country 140024 0
Australia
Phone 140024 0
+61400889748
Fax 140024 0
Email 140024 0
[email protected]

Data sharing statement
Will the study consider sharing individual participant data?
No
No IPD sharing reason/comment: There is no patient data



What supporting documents are/will be available?

No Supporting Document Provided



Results publications and other study-related documents

Documents added manually
No documents have been uploaded by study researchers.

Documents added automatically
No additional documents have been identified.