AI-assisted Documentation
Conditions
Keywords
AI, documentation, Effectiveness
Brief summary
Background There is currently no research evidence from randomized trial settings on the effectiveness of AI-assisted documentation. The aim of this study is to provide evidence regarding cost-effectiveness, professional experience, and patient experience. Design Physician consultations participating in the study are randomized into AI-assisted and traditional documentation groups in a 1:1 repeated crossover design. The goal is to include approximately 1,000 consultations per group. Methods Professionals will be asked to provide their own assessment of potential time savings, and the time spent on documentation will be measured using technical data from the documentation tools (cost-effectiveness). Additionally, professionals will complete baseline and follow-up surveys (professional experience), and patients will be sent a survey following the consultation (patient experience).
Detailed description
The study will include all acute and non-acute visits for the enrolled clinician. The study excludes sector-specific work and specialized consultations, such as maternity clinics, memory clinics, intellectual disability consultations, as well as non-Finnish-language consultations and interpreter-assisted consultations. The system has been primarily designed to monitor discussions between two individuals, and therefore, consultations where a guardian or companion accompanies the patient are also excluded from the study.
Interventions
OTHERAI assisted documentation
This study will use Gosta Aide AI-assisted documentation platform
Sponsors
University of Helsinki
Western Uusimaa Welbeing Services county
Helsinki University Central Hospital
Study design
Allocation
NA
Intervention model
CROSSOVER
Primary purpose
HEALTH_SERVICES_RESEARCH
Masking
NONE
Intervention model description
Single-arm repeated crossover design
Eligibility
Sex/Gender
ALL
Healthy volunteers
Yes
Inclusion criteria
* Clinician practices at a site in Western Uusimaa wellbeing services county where AI-assisted documentation tool is available
Exclusion criteria
* none The study will include all acute and non-acute visits for the enrolled clinician. The study excludes sector-specific work and specialized consultations, such as maternity clinics, memory clinics, intellectual disability consultations, as well as non-Finnish-language consultations and interpreter-assisted consultations. The system has been primarily designed to monitor discussions between two individuals, and therefore, consultations where a guardian or companion accompanies the patient are also excluded from the study.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Time saved using AI-assisted documentation | From enrollment until the of study (approx two months). | The documentation platform will measure time used for documentation of the appointment for both AI-assisted and regular documentation. For each appointment separately, from the moment the patient leaves the appointment until the documentation is finished and saved to the patient records. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Clinician satisfaction questionnaire | At the end of the study (expected two months) | Clinicans will report their satisfaction by assessing the effect of AI tool to quality of documentation. The questionnaire includes three questions answered in 1-5 likert scale where 1 worst and 5 best outcome. The questions are How has AI affected time used in documentation? (1 = IIncreased the time spent on documentation significantly, 5 = Decreased the time spent on documentation significantly) How has AI affected the quality of documentation? (1 = Decreased the quality of documentation significantly, 5 = Increased the quality of documentation significantly) How has AI affected patient safety? (1 = Significantly compromised patient safety, 5 = Significantly improved patient safety) |
| Clinician satisfaction by Net Promotor Score (NPS) | At the end of the study (expected two months) | Clinicans will report their satisfaction (regarding AI tool) by NPS. The question is stated Would you recommend AI assisted documentation to your colleague? and is assessed in scale 0-10 where 0 means would not recommend and 10 is would recommend extremely highly. |
| Clinician satisfaction by willingness to continue with the tool | At the end of the study (expected two months) | Clinicans will report their satisfaction by assessing whether they would like to continue with the AI-tool or using regular method. The question is stated In future, would you prefer to do clinical documentation with the now used AI-based tool or as you were doing previously without the AI-based tool? (With AI-tool/Without AI-tool) |
| Subjective time saving in documentation due to AI-assisted documentation | Assessed once a day after the days appointments and records have been completed through study completion, expected 2 months.. | Each clinician will give their subjective assessment the time saved or wasted due to AI tool per appointment (in minutes) after each day through study completion (approximately two months). |
| Patient satisfaction by Patient Enablement Instrument (PEI) | Immediately after the randomized appointment | Patient satisfaction will be assessed after each appointemnt using PEI questionnaire. The patients who visit a participating clinician will receive a questionnaire including PEI once after each of their appointment. Score ranges between 0-12 and higher score indicates better outcome for the patient. |
| Patient satisfaction by The Patient Satisfaction Questionnaire Short Form (PSQ-18) | Immediately after the randomized appointment | Patient satisfaction will be assessed after each appointment using PSQ18 questionnaire. The patients who visit a participating clinician will receive a questionnaire including PSQ18 once after each of their appointment. Score ranges from 18 to 90 and higher score indicates worse patient experience. |
| Patient satisfaction by Net Promotor Score (NPS) | Immediately after the randomized appointment | Patient satisfaction will be assessed after each appointemnt using NPS. The patients who visit a participating clinician will receive a questionnaire including NPS once after each of their appointment. The scale is 0-10 where 0 is would not recommend the appointment at all and 10 would highly recommend the appointment. |
Countries
Finland
Outcome results
None listed