Not provided
| ID | Type | Description | Link |
|---|---|---|---|
| UWMSN | Nursing | Admin | Other Identifier | UW Madison | |
| Protocol Version 5/15/26 | Other Identifier | UW Madison |
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
The goal of this clinical trial is to learn whether using Ambient Artificial Intelligence for nursing staff documentation in an inpatient setting will reduce the time spent in flowsheet documentation and enhance nurse staffing wellbeing.
Participants will use Ambient Listening AI software to draft documentation in discrete fields.
This pragmatic trial is being conducted to test the effectiveness of Artificial Intelligence Driven Ambient Listening software on reducing time in flowsheet documentation among Registered Nurses (RNs) and nursing assistants (NAs) in an inpatient setting. The Ambient AI software uses Automated Speech Recognition technology with Large Language Models to automatically generate discrete flowsheet values from nurse-patient conversations in real-time. The clinical trial is an examination of the impact and usability of this implementation on the workload and well-being of nurses involved in the rollout of the software pragmatic Electronic Health Record embedded design integrated into clinical workflows and the health system IT infrastructure.
Not provided
Not provided
Not provided
Not provided
| Label | Type | Description | Intervention Names |
|---|---|---|---|
| Ambient Listening Group 1 | Experimental | The hospital unit will be randomized and all nursing staff within the unit will have access to start using Ambient AI at week 8. |
|
| Ambient Listening Group 2 | Experimental | The hospital unit will be randomized and all nursing staff within the unit will have access to start using Ambient AI at week 11. |
|
| Ambient Listening Group 3 | Experimental | The hospital unit will be randomized and all nursing staff within the unit will have access to start using Ambient AI at week 14. |
|
| Name | Type | Description | Arm Group Labels | Other Names |
|---|---|---|---|---|
| Artificial Intelligence | Other | Ambient AI software intervention is implemented into the nursing staff workflow. The software incorporates Automated Speech Recognition technology with Large Language Models to generate clinical documentation in real-time |
| Measure | Description | Time Frame |
|---|---|---|
| Change in Active Time Spent in Flowsheets per shift hour | To assess a change in nursing staff documentation time, the change active time spent in flowsheets per shift hour with the use of the Ambient Listening tool versus usual documentation will be reported. | Baseline to 22 weeks |
| Measure | Description | Time Frame |
|---|---|---|
| Change in Active Time Spent in Flowsheets per patient per shift | To assess nursing staff documentation burden, the change in active time spent in flowsheets per patient shift will be reported. | Baseline to 22 weeks |
| Change in the number of clicks or taps in Flowsheets |
Not provided
Inclusion Criteria:
Exclusion Criteria:
Not provided
Not provided
Not provided
Not provided
Not provided
| Name | Role | Phone | Extension | |
|---|---|---|---|---|
| Ann Wieben, PhD, RN | Contact | 6082651029 | wieben@wisc.edu | |
| Jann Pfaff, PhD, RN | Contact | jpfaff2@uwhealth.org |
| Name | Affiliation | Role |
|---|---|---|
| Ann Wieben, PhD, RN | University of Wisconsin, Madison | Principal Investigator |
| Jann Pfaff, PhD, RN | University of Wisconsin, Madison | Principal Investigator |
| Facility | Status | City | State | ZIP | Country | Contacts |
|---|---|---|---|---|---|---|
| UW Health - East Madison Hospital | Recruiting | Madison | Wisconsin | 53718 | United States |
| PubMed Identifier | Type | Citation | Retractions |
|---|---|---|---|
| 41625485 | Background | Afshar M, Baumann MR, Resnik F, Hintzke J, Sullivan AG, Wills G, Lemmon K, Dambach J, Ann Mrotek L, Quinn M, Abramson K, Kleinschmidt P, Brazelton TB, Leaf MA, Twedt H, Kunstman D, Patterson B, Liao F, Rasmussen S, Burnside ES, Goswami C, Gordon J. A Pragmatic Randomized Controlled Trial of Ambient Artificial Intelligence to Improve Health Practitioner Well-Being. NEJM AI. 2025 Dec;2(12):10.1056/aioa2500945. doi: 10.1056/aioa2500945. Epub 2025 Nov 26. | |
| 40959192 |
Not provided
Not provided
We plan to share the majority of our research documentation including the Study Protocol, Statistical Analysis Plan, Informed Consent Plan, Analytics Code, data dictionary, and de-identified survey and interview/focus group results data.
We will make the IPD information available in early 2027 once we have completed our analysis and are ready for publication. It will be available indefinitely.
We will provide a publicly accessible GitLab link where all study materials can be downloaded
Not provided
Not provided
| ID | Term |
|---|---|
| D001185 | Artificial Intelligence |
| ID | Term |
|---|---|
| D000465 | Algorithms |
| D055641 | Mathematical Concepts |
Not provided
Not provided
The stepped wedge design involves staggered implementation of an intervention across different hospital units over multiple time periods, allowing all nursing staff within these units to eventually receive the intervention.
Not provided
Not provided
Not provided
Not provided
To assess nursing staff documentation burden, the change in the number of clicks or taps in flowsheets will be reported. |
| Baseline to 22 weeks |
| Change in Amount of Overtime Charting | To assess nursing staff documentation burden, the change in time spent documenting after end time of assignment will be reported. | Baseline to 22 weeks |
| Change in Clinician Worklife Survey (Mini-Z) Score | Professional Wellbeing will be assessed with the Mini Z 3.0, a 10 item tool (plus one open-ended question) designed to quickly assess clinician burnout, stress, satisfaction, and work-life drivers such as workload control, teamwork, and electronic health record (EHR) related stressors. The Mini Z survey is scored by summing responses to the first 10 items, each rated on a 1-5 Likert scale, producing a total score ranging from 10 to 50. Higher scores indicate better worklife conditions, with scores of 40 or above reflecting a "joyful" workplace. | Baseline to 22 weeks |
| Change in Mini-Z Subscale Scores: Supportive Work Environment | Professional Wellbeing will also be assessed with Mini Z subscales. One Mini-Z subscale measures supportive work environment with 7-items (scores range from 7-35, higher scores indicate more supportive environment). | Baseline to 22 weeks |
| Change in Mini-Z (3.0) Subscale Scores: EHR Stress | Professional Wellbeing will also be assessed with Mini Z subscales. One Mini-Z subscale measures EHR stress (scores range from 3-15, higher scores indicate more manageable EHR stress). | Baseline to 22 weeks |
| Change System Usability Scale (SUS) | The SUS is a 10-item scale that assesses perceived usability of a system, in this case, the Abridge Ambient Listening Tool. It yields a single score that can range from 0-100 with higher scores indicating higher system usability. | 11 weeks to 22 weeks |
| Background |
| Afshar M, Resnik F, Baumann MR, Hintzke J, Lemmon K, Sullivan AG, Shah T, Stordalen A, Oberst M, Dambach J, Mrotek LA, Quinn M, Abramson K, Kleinschmidt P, Brazelton T, Twedt H, Kunstman D, Wills G, Long J, Patterson BW, Liao FJ, Rasmussen S, Burnside E, Goswami C, Gordon JE. A Novel Playbook for Pragmatic Trial Operations to Monitor and Evaluate Ambient Artificial Intelligence in Clinical Practice. NEJM AI. 2025 Sep;2(9):10.1056/aidbp2401267. doi: 10.1056/aidbp2401267. Epub 2025 Aug 28. |