JMIR Publications

ABSTRACT

Background:

Mental disorders are prevalent during adolescence. Among the digital phenotypes currently being developed to monitor mental health symptoms, typing behaviour is one promising candidate. However, few studies have directly assessed associations between typing behaviour and mental health functioning, and whether this relationship differs between genders.

Objective:

Here, we tested whether various features of typing behaviour derived from keystroke metadata were associated with mental health functioning and whether these relationships differed between gender.

Methods:

Participants were 934 adolescents from waves 1 and 2 of the Future Proofing study who undertook two typing tasks on their smartphone through the Future Proofing App. Common keystroke timing and frequency features were extracted across tasks. Mental health symptoms were assessed using the Patient Health Questionnaire- Adolescent Version (PHQ-A), the Children’s Anxiety Scale-Short Form (CAS-8), the Distress Questionnaire 5 (DQ5), and the Insomnia Severity Index (ISI). Bivariate correlations were used to test whether keystroke features were associated with mental health functioning. The false discovery rates of p-values were adjusted to q-values. Machine learning models were trained and tested using independent samples (i.e., 80% train 20% test) to identify whether keystroke features could be combined to predict mental health functioning.

Results:

Keystroke timing features showed a weak negative association with mental health functioning across participants. When split by gender, females showed weak negative relationships between keystroke timing features and mental health functioning, and weak positive relationships between keystroke frequency features and mental health functioning. The opposite relationships were found for males (except for dwell). Machine learning models using keystroke features did not predict mental health functioning.

Conclusions:

Keystroke features are weakly associated with mental health functioning, with important gender differences. Keystroke metadata should be collected longitudinally and combined with other digital phenotypes to enhance their clinical relevance.