JMIR Publications

ABSTRACT

Background:

Patient-generated health data (PGHD) are important in the management of several diseases. Although there are limitations, information can be obtained using a wearable device, and time-related information, such as exercise time or sleep time, can also be obtained. Fitbits can be used to acquire sleep onset, sleep offset, total sleep time (TST), and wakefulness after sleep onset (WASO) data, although there are limitations regarding the depth of sleep and satisfaction; therefore, the patient's subjective response is still important information that cannot be replaced.

Objective:

To use PGHD related to time, such as sleep, it is necessary to understand the characteristics of the time response recorded by the user; therefore, the characteristics of the user's time perception were analyzed by comparison with wearable data.

Methods:

Sleep data were acquired for 2 weeks using a Fitbit. Participants' sleep records were collected daily through chatbot conversations while wearing the Fitbit, and the 2 sets of data were statistically compared.

Results:

In total, 736 people aged 30-59 years were recruited, and the sleep data of 550 people who wore Fitbit and responded to the Chat for more than 7 days on the same day were analyzed. Research participants tended to respond to sleep-related times on the hour or 30-min increments, and each participant responded within the range of 60-90 min from the value measured by the Fitbit. However, on average for the participants, the chat responses and the Fitbit data were similar within a difference of approximately 15 min. Regarding sleep onset, the answer was 8 min 33 s±60 min later than that of the Fitbit data, and with respect to sleep offset, the answer was 6 min 39 s±58 min earlier. The participants' actual sleep time (AST) was similar to that obtained by subtracting the WASO from the TST measured by the Fitbit. The AST was 13 min 09 s±86 min longer than the time WASO was subtracted from the Fitbit TST. On days when the participants reported good sleep, they responded 19 min±89min longer on the AST than the Fitbit data. However, for each sleep, the probability that the participant’s AST was within ±30 min of the Fitbit TST-WASO was 55.7%, and the probability that it was within ±60 min was 76.3%.

Conclusions:

The chatbot sleep response and Fitbit measured time were similar on average and the study participants had a slight tendency to perceive a relatively long sleep time if the answered quality of sleep was good. However, on a participant-by-participant basis, it was difficult to predict participants’ sleep duration responses with the Fitbit data. Individual variations in sleep time perception significantly affect patient response related to sleep, revealing the limitations of objective measures obtained through wearable devices. Clinical Trial: KCT0004297