Development of novel optical character recognition system to reduce recording time for vital signs and prescriptions: A simulation-based study

All user actions on the system were automatically logged into the cloud data server for this study to calculate the recording time. A paired Wilcoxon signed-rank sum test were used to compare the OCR group and the typing group. The median recording times for vital signs were similar between the groups (e.g., normal state, 21 seconds [Interquartile range, IQR, 17–26 seconds] in the OCR group vs. 23 seconds [IQR, 18–31 seconds] in the typing group; p= 0.11).

In contrast, the median recording times for prescriptions were significantly shorter in the OCR group (e.g., six medication lists, 18 seconds [IQR, 14–21 seconds] in the OCR group vs. 144 seconds [IQR, 112–187 seconds] in the typing group; p< .001).