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
ACTRN12625000769482p
Ethics application status
Submitted, not yet approved
Date submitted
21/05/2025
Date registered
21/07/2025
Date last updated
21/07/2025
Date data sharing statement initially provided
21/07/2025
Type of registration
Prospectively registered

Titles & IDs
Public title
Early delirium detection and prediction in hospitalised patients through analysis of clinical signs and behaviours.
Scientific title
Clinical and behavioural analysis for early prediction and diagnosis of delirium in a hospital setting
Secondary ID [1] 314489 0
None
Universal Trial Number (UTN)
Trial acronym
Linked study record

Health condition
Health condition(s) or problem(s) studied:
Delirium 337535 0
Condition category
Condition code
Mental Health 333897 333897 0 0
Other mental health disorders

Intervention/exposure
Study type
Observational
Patient registry
False
Target follow-up duration
Target follow-up type
Description of intervention(s) / exposure
This research will collect data on the clinical and behavioural patterns linked to delirium in hospitalized patients. All consecutive individuals with and without a current diagnosis of delirium admitted as inpatients in the acute and sub-acute services of St Vincent’s Hospital Melbourne will be considered for recruitment to this prospective, longitudinal observational study. First Nations peoples over 50 years of age, and other individuals over 65 years of age, will be eligible for inclusion from the following SVHM study sites: St Vincent’s Hospital Melbourne Inpatient Services (IPS), Bolte Wing (SVHM), and St George’s Hospital, Kew.

Once recruited, patients will continue to receive standard medical care from the treating team in addition to their participation in the study. To effectively monitor participants, re-identified data will be collected from both wearable devices and the hospital database system. The wearable device used in this study is developed by Verisense Health and is a wrist-worn sensor designed to capture continuous physiological and activity-related data. Participants will be asked to wear the device continuously, including while sleeping, for uninterrupted data collection. The device may be temporarily removed for activities such as showering, bathing, or during medical procedures—particularly radiation-based procedures or any intervention where the attending technician advises removal. In all such cases, participants will be reminded to reapply the device as soon as the procedure is completed to maintain consistent data capture.

Unique patient IDs will be created for each participant, and their wearable information and clinical information will be linked to these IDs to facilitate continuous monitoring and recording of relevant data. The wearable device will track physiological indicators including skin temperature, heart rate variability, sleep stages from movement, blood volume changes, sympathetic arousal metrics, and levels of physical activity.

From the hospital database, re-identified demographic information including age, gender, past clinical history (including previous admissions and comorbidities), and current clinical information relevant to delirium risk (e.g., blood test results, fluid and food intake, bowel movements, medication usage, other laboratory test results, and vital signs) will be collected. Observed signs and indications of delirium, such as agitation and any positive results from the 4AT assessment, will also be documented. The 4AT will be administered by trained clinical staff at least every 72 hours and also upon any observed behavioural change suggestive of delirium.

The presence or absence of delirium will be determined based on clinical diagnoses documented in the patient’s medical records by the treating clinicians. These diagnoses will generate timestamped ground truth labels, marking the onset and resolution of delirium episodes. The timestamped labels will be aligned with the wearable sensor data and associated clinical information to create a comprehensive dataset for training and evaluating AI models developed for delirium prediction.

Participants will be observed for the duration of their hospital admission or up to a maximum of 30 days from admission, whichever is shorter. Machine learning and deep learning models, including Support Vector Machine (SVM), Linear Discriminant Analysis (LDA), Decision Tree, Random Forest, Gradient Boosting, Artificial Neural Networks (ANNs), Long Short-Term Memory (LSTM), and Transformer models will be developed to analyse the data. These models will be compared using standard performance measures such as accuracy, precision, recall, and F1 score to determine the most effective approach for predicting delirium.
Intervention code [1] 331115 0
Early Detection / Screening
Comparator / control treatment
Validated clinical tools and formal clinical diagnoses will serve as the reference standard for evaluating the AI models developed in this study. Specifically, the 4AT (4 A’s Test), a validated screening tool for delirium, will be administered to all participants as part of the daily clinical routine and additionally upon any observed behavioral changes suggestive of delirium. These assessments will be conducted by trained clinical staff during the participant’s inpatient stay. In addition, formal clinical diagnoses of delirium made by treating clinicians and documented in the patient’s medical record—including ICD-coded hospital data—will be used to generate timestamped ground truth labels marking the onset and resolution of delirium episodes. These labels will be aligned with the wearable sensor data and associated clinical information to create a comprehensive dataset for training and evaluating the AI models. This approach ensures that AI predictions are assessed against established clinical references collected within the same timeframe as the wearable data.
Control group
Active

Outcomes
Primary outcome [1] 341550 0
Accuracy of delirium onset prediction by AI techniques compared to 4AT clinical assessment.
Timepoint [1] 341550 0
Everyday from baseline till 30 days or till the patient is admitted at St Vincent's Hospital Melbourne, whichever is of lesser duration.
Secondary outcome [1] 447909 0
Precision of delirium onset prediction by AI techniques compared to 4AT clinical assessment
Timepoint [1] 447909 0
Everyday from baseline till 30 days or till the patient is admitted at St Vincent's Hospital Melbourne, whichever is of lesser duration.
Secondary outcome [2] 448380 0
Recall of delirium onset prediction by AI techniques compared to 4AT clinical assessment
Timepoint [2] 448380 0
Everyday from baseline till 30 days or till the patient is admitted at St Vincent's Hospital Melbourne, whichever is of lesser duration.
Secondary outcome [3] 448381 0
F1 Score of delirium onset prediction by AI techniques compared to 4AT clinical assessment
Timepoint [3] 448381 0
Everyday from baseline till 30 days or till the patient is admitted at St Vincent's Hospital Melbourne, whichever is of lesser duration.
Secondary outcome [4] 448382 0
False Positive Rate of delirium onset prediction by AI techniques compared to 4AT clinical assessment
Timepoint [4] 448382 0
Everyday from baseline till 30 days or till the patient is admitted at St Vincent's Hospital Melbourne, whichever is of lesser duration.
Secondary outcome [5] 448383 0
Classification of hypoactive states of delirium using AI techniques
Timepoint [5] 448383 0
Everyday from baseline till 30 days or till the patient is admitted at St Vincent's Hospital Melbourne, whichever is of lesser duration.
Secondary outcome [6] 448384 0
Classification of hyperactive states of delirium using AI techniques
Timepoint [6] 448384 0
Everyday from baseline till 30 days or till the patient is admitted at St Vincent's Hospital Melbourne, whichever is of lesser duration.

Eligibility
Key inclusion criteria
Inpatients admitted to acute and sub-acute services of SVHM study sites (1. St Vincent's Hospital Melbourne (SVHM), 2. Bolt Wing (SVHM), 3. St George's Hospital, Kew)

People 45 years of age or greater in case of First Nations peoples, and 65 years of age or greater for other individuals

Inpatients with/without a current diagnosis of delirium

Inpatients diagnosed with dementia, as documented in their medical history or based on clinical evaluation, who are at risk for delirium

Inpatients without a history of dementia

Inpatients capable of and willing to wear the wearable device on their wrist

Inpatients, or their legal representative, must be able to provide informed consent to participate in the study (Inpatients not capable of providing informed consent may also have a legally authorized representative (for example, a next-of-kin, guardian, or medical treatment decision-maker) who can give consent on their behalf).
Minimum age
45 Years
Maximum age
No limit
Sex
Both males and females
Can healthy volunteers participate?
No
Key exclusion criteria
Inpatients less than 45 years of age in case of First Nations peoples, and less than 65 years of age for other individuals

Individuals unable to provide informed consent; if a legally authorized representative (e.g., next-of-kin, guardian, or medical treatment decision-maker) also cannot provide consent on their behalf

Inability to wear the wearable device

Patients admitted under the direct care of mental health services or subject to an assessment or treatment order under the Mental Health and Wellbeing Act (Vic) 2022

Estimated to be admitted for less than one week

Patients under palliative care services or otherwise imminently approaching end-of-life

The treating team decides that it is not in the patient’s interest to participate in the study and/or might be detrimental to the patient

Study design
Purpose
Natural history
Duration
Longitudinal
Selection
Random sample
Timing
Both
Statistical methods / analysis

Recruitment
Recruitment status
Not yet recruiting
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)
VIC
Recruitment hospital [1] 27967 0
St Vincent's Hospital (Melbourne) Ltd - Fitzroy
Recruitment postcode(s) [1] 44159 0
3065 - Fitzroy

Funding & Sponsors
Funding source category [1] 319030 0
University
Name [1] 319030 0
RMIT University
Country [1] 319030 0
Australia
Primary sponsor type
University
Name
RMIT University
Address
Country
Australia
Secondary sponsor category [1] 321495 0
None
Name [1] 321495 0
Address [1] 321495 0
Country [1] 321495 0

Ethics approval
Ethics application status
Submitted, not yet approved
Ethics committee name [1] 317639 0
St Vincent's Hospital Melbourne Human Research Ethics Committee
Ethics committee address [1] 317639 0
Ethics committee country [1] 317639 0
Australia
Date submitted for ethics approval [1] 317639 0
28/02/2025
Approval date [1] 317639 0
Ethics approval number [1] 317639 0

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

Contacts
Principal investigator
Name 141654 0
Dr James Mahon
Address 141654 0
St. Vincent's Hospital Melbourne, 41 Victoria Parade, Fitzroy, VIC - 3065
Country 141654 0
Australia
Phone 141654 0
+61 491721361
Fax 141654 0
Email 141654 0
Contact person for public queries
Name 141655 0
Dr Priya Rani
Address 141655 0
RMIT University, Building 12 Level 11 Room 13-2, 124 La Trobe St, Melbourne , VIC - 3000
Country 141655 0
Australia
Phone 141655 0
+61 0410784111
Fax 141655 0
Email 141655 0
Contact person for scientific queries
Name 141656 0
Dr Priya Rani
Address 141656 0
RMIT University, Building 12 Level 11 Room 13-2, 124 La Trobe St, Melbourne , VIC - 3000
Country 141656 0
Australia
Phone 141656 0
+61 0410784111
Fax 141656 0
Email 141656 0

Data sharing statement
Will the study consider sharing individual participant data?
No


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.