Accepted for/Published in: JMIR Medical Informatics
Date Submitted: Jun 4, 2020
Open Peer Review Period: Jun 4, 2020 - Jul 7, 2020
Date Accepted: Aug 3, 2020
(closed for review but you can still tweet)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
The effect of artificial intelligence-based automated medical history taking system on patient waiting time in the general internal medicine outpatient setting: interrupted time series analysis
ABSTRACT
Background:
Use of automated medical history taking (AMHT) systems in the general internal medicine outpatient department (GIM-OD) is a promising strategy to reduce waiting time.
Objective:
We evaluated the effect of AI Monshin, an AMHT system, on waiting time in the GIM-OD.
Methods:
We retrospectively analyzed waiting time length in a Japanese community hospital GIM-OD (April 2017–April 2020). AI Monshin was implemented in April 2019. We compared the mean waiting time before and after the AI Monshin implementation. An interrupted time series analysis of the mean waiting time/month was conducted.
Results:
We analyzed 21,933 cases. The mean waiting time after the AI Monshin implementation (87.0 min, SD 55.1) was significantly shorter than before the AI Monshin implementation (89.5 min, SD 56.6), with an absolute difference of −2.5 min (P = .003; 95% CI, −4.0 to −0.9). In the interrupted time series analysis, whereas the underlying linear time trend was statistically significant (−0.6 min/month; P = .005; 95% CI, −1.0 to −0.2), level change (26.2 min; P = .43; 95% CI, −16.1 to 68.5) and slope change (−0.6 min/month; P = .23; 95% CI, −2.0 to 0.8) did not differ significantly. In a sensitivity analysis of data between April 2018 and April 2020, the mean waiting time after the AI Monshin implementation (87.0 min, SD 55.1) was not significantly different compared with that before the AI Monshin implementation (86.8 min, SD 53.9) with the absolute difference of +0.2 min (P = .84; 95% CI −1.6 to 2.0).
Conclusions:
AI Monshin reduced waiting time only to a very limited extent.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.