JMIR Publications

ABSTRACT

Background:

Sleep disorders are experienced by up to 40% of the population but their diagnosis is often delayed by the availability of specialists.

Objective:

We propose to use search engine activity in conjunction with a validated online sleep questionnaire to facilitate wide-scale screening of prevalent sleep disorders.

Methods:

Search advertisements offering an online sleep disorder screening questionnaire were shown on the Bing search engine to those who indicated an interest in sleep disorders. People who clicked on the ads and completed the sleep questionnaire were identified as at risk for one of four common sleep disorders. A Machine Learning algorithm was applied to previous search engine queries to predict their suspected sleep disorder, as identified by the questionnaire.

Results:

A total of 397 users consented to participate in the experiment and completed the questionnaire. Of those, 132 had sufficient past query data for analysis. Our findings show that diurnal patterns of people with sleep disorders are shifted by 2-3 hours compared to controls. Past query activity is predictive of sleep disorders, reaching an Area Under the Receiver Operating Curve of 0.62-0.69, depending on the sleep disorder.

Conclusions:

Targeted ads can be used as an initial screening tool for people with sleep disorders. However, search engine data is seemingly insufficient as a sole method for screening. Nevertheless, we believe that evaluable online information, easily collected and processed with little effort on part of the physician and with low burden on the individual, can assist in the diagnostic process and possibly drive people to seek sleep assessment and diagnosis earlier than they currently do.