Machine Intelligence in the Pharmacy
Conditions
Brief summary
Pharmacists currently perform an independent double-check to identify drug-selection errors before they can reach the patient. However, the use of machine intelligence (MI) to support this cognitive decision-making work by pharmacists does not exist in practice. This research is being conducted to examine the effectiveness machine intelligence (MI) advice on to determine if its impact on pharmacists' work performance and cognitive demand.
Interventions
BEHAVIORALNo MI Help
Participants will complete the medication verification task without any MI help
BEHAVIORALInterpretable MI
Participants receive interpretable machine intelligence assistance to complete the medication verification tasks.
BEHAVIORALUninterpretable MI
Participants receive uninterpretable (i.e., black-box) machine intelligence assistance to complete the medication verification tasks.
Sponsors
National Library of Medicine (NLM)
Corey Lester
Study design
Allocation
RANDOMIZED
Intervention model
PARALLEL
Primary purpose
OTHER
Masking
NONE
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
1. Licensed pharmacist in the United States 2. Age 18 years and older at screening 3. PC/Laptop with Microsoft Windows 10 or Mac (Macbook, iMac) with MacOS with Google Chrome or Firefox web browser installed on the device 4. Screen resolution of 1024x968 pixels or more 5. A laptop integrated webcam or USB webcam is also required for the eye tracking purpose.
Exclusion criteria
1. Eyeglasses with more than one power (bifocals, trifocals, progressives, layered lenses, or regression lenses) 2. Cataracts, intraocular implants, glaucoma, or permanently dilated pupil 3. Require a screen reader/magnifier or other assistive technology to use the computer 4. Eye surgery (e.g., corneal) 5. Eye movement or alignment abnormalities (lazy eye, strabismus, nystagmus)
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Cognitive effort | 1 day - Single study visit | Difference in cognitive effort measured by duration of fixation and fixation count |
| Decision accuracy | 1 day - Single study visit | Difference in detection rate measured by number of medication verification errors |
| Trust change | 1 day - Single study visit | Difference in trust as measured by visual analog scale will be calculated based on AI advice accuracy. Participants will indicate their level of trust in the AI advice after every trial on a scale from 1-100, with higher scores indicating greater levels of trust. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Reaction time | 1 day - Single study visit | Difference in task time measured by the number of seconds from starting the task to accepting or rejecting a medication image |
Countries
United States
Outcome results
None listed