Trial Radar AI | ||
|---|---|---|
Clinical Trial NCT07493616 for Artificial Intelligence, Usability is not yet recruiting. See the Trial Radar Card View and AI discovery tools for all the details. Or ask anything here. | ||
One study matched filter criteria
Card View
AI-based Informational Assistant for Automated Point-of-care Documentation and Protocol Retrieval 25
Clinical Trial NCT07493616 is an observational study for Artificial Intelligence, Usability and is currently not yet recruiting. Enrollment is planned to begin on 1 July 2026 and continue until the study accrues 25 participants. Led by Willemijn Berkhout, this study is expected to complete by 1 December 2026. The latest data from ClinicalTrials.gov was last updated on 25 March 2026.
Brief Summary
Clinical rounds in the intensive care unit (ICU) involve substantial manual documentation. Retrieving the correct protocol text and structuring notes at the bedside is time-consuming and may contribute to variation in documentation quality. Modern artificial intelligence (AI) can help structure existing information and automate protocol look-ups within a restricted, manually selected document set.
The tool evaluated...
Show MoreOfficial Title
Evaluation of an AI-based Informational Assistant for Automated Point-of-care Documentation and Protocol Retrieval in the Intensive Care Unit
Conditions
Artificial IntelligenceUsabilityOther Study IDs
- 15243
NCT ID Number
Start Date (Actual)
2026-07-01
Last Update Posted
2026-03-25
Completion Date (Estimated)
2026-12-01
Enrollment (Estimated)
25
Study Type
Observational
Status
Not yet recruiting
Primary Outcome Measures
Secondary Outcome Measures
| Outcome Measure | Measure Description | Time Frame |
|---|---|---|
Implementation outcomes acceptability, appropriateness, and feasibility | The mean scores and standard deviations of the 5-point Likert scale (1 = strongly disagree, 2 = disagree, 3 = undecided, 4 = agree, 5 = strongly agree) closed-ended questions of the survey on the physicians' perspectives will be calculated. Standardised questionnaires AIM, IAM and FIM are used. | Before integration of the AI-based informational assistant and 4-, 8-, and 12-weeks after integration. |
| Outcome Measure | Measure Description | Time Frame |
|---|---|---|
Perceived time saved when using the AI-based informational assistant during ICU rounds | The mean scores and standard deviations of the 5-point Likert scale closed-ended questions of the survey on the physicians' perceptions on retrieval speed. | 12-weeks after integration of the AI-based informational assistant . |
Task-based efficiency, including time to (i) produce a structured rounds note and (ii) retrieve relevant protocol text | Timed predefined ICU round documentation tasks with and without AI-based informational assistant. Time difference will be calculated. | Before integration of the AI-based informational assistant and 12-weeks after integration |
Perceived usefulness, clarity, and trustworthiness | The mean scores and standard deviations of the 5-point Likert scale (1 = strongly disagree, 2 = disagree, 3 = undecided, 4 = agree, 5 = strongly agree) closed-ended questions of the survey on the physicians' perspectives will be calculated. | Before integration of the AI-based informational assistant and during the 12-weeks utilization. |
Adoption and use, including frequency of use, retention over time, and interaction patterns (e.g., number/type of edits, use cases, feature use) | Adoption will be determined by frequency of use (interactions per participant per week) and retention (continued use over time), expressed as counts and proportions. Fidelity will be determined by the misusage per participant, reported as counts and proportions. Adoption and fidelity will be aggregated at both participant and cohort level. Interaction logs will be used to characterize use patterns, including number and type of edits, use cases and feature usage. | During the 12-weeks utilization of the AI-based informational assistant. |
Technical output quality | Outputs is reviewed on accuracy, recall, precision, groundedness, contextual usefulness, and hallucination presence. Reported as counts and proportions. | Before integration of the AI-based informational assistant and during the 12-weeks utilization. |
Trust in the system, perceived workload, and task satisfaction | The mean scores and standard deviations of the 5-point Likert scale (1 = strongly disagree, 2 = disagree, 3 = undecided, 4 = agree, 5 = strongly agree) closed-ended questions of the survey on the physicians' perspectives will be calculated. Standardised questionnaires S-TIAS and NASA-TLX are used. | 12-weeks after integration of the AI-based informational assistant. |
Participation Assistant
Eligibility Criteria
Eligible Ages
Child, Adult, Older Adult
Eligible Sexes
All
- ICU physician (nurse practicioner, resident, or staff intensivist) at the Erasmus MC.
- Signed informed-consent for study participation.
- Physicians not expected to work on the ICU during the study period will not be approached.
Willemijn BerkhoutStudy Responsible Party
Willemijn Berkhout, Sponsor-Investigator, MSc, Erasmus Medical Center
No contact data.