Dataset Information

Smartphone keyboard dynamics predict affect in suicidal ideation.

ABSTRACT: While digital phenotyping provides opportunities for unobtrusive, real-time mental health assessments, the integration of its modalities is not trivial due to high dimensionalities and discrepancies in sampling frequencies. We provide an integrated pipeline that solves these issues by transforming all modalities to the same time unit, applying temporal independent component analysis (ICA) to high-dimensional modalities, and fusing the modalities with linear mixed-effects models. We applied our approach to integrate high-quality, daily self-report data with BiAffect keyboard dynamics derived from a clinical suicidality sample of mental health outpatients. Applying the ICA to the self-report data (104 participants, 5712 days of data) revealed components related to well-being, anhedonia, and irritability and social dysfunction. Mixed-effects models (55 participants, 1794 days) showed that less phone movement while typing was associated with more anhedonia (β = -0.12, p = 0.00030). We consider this method to be widely applicable to dense, longitudinal digital phenotyping data.

SUBMITTER: Knol L

PROVIDER: S-EPMC10705661 | biostudies-literature | 2023 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Smartphone keyboard dynamics predict affect in suicidal ideation.

Knol Loran L Nagpal Anisha A Leaning Imogen E IE Idda Elena E Hussain Faraz F Ning Emma E Eisenlohr-Moul Tory A TA Beckmann Christian F CF Marquand Andre F AF Leow Alex A

medRxiv : the preprint server for health sciences 20231129

While digital phenotyping provides opportunities for unobtrusive, real-time mental health assessments, the integration of its modalities is not trivial due to high dimensionalities and discrepancies in sampling frequencies. We provide an integrated pipeline that solves these issues by transforming all modalities to the same time unit, applying temporal independent component analysis (ICA) to high-dimensional modalities, and fusing the modalities with linear mixed-effects models. We applied our a ...[more]

PMID: 38076837

Similar Datasets

Project description:BackgroundTransgender people are at a high risk of suicidal ideation, suicide attempts, and deaths. Among transgender individuals, 77% and 41% engage in suicidal ideation and suicide attempt in their lifetime, respectively, which exceeds the general population rates (9.2% and 2.7%, respectively). Traditionally, suicide risk factors have been studied over a long period between measurements, making it difficult to understand the short-term variability in suicide risk. Mobile phone apps offer an opportunity to understand the immediate precursors of suicidality through the assessment of behaviors and moods in real time. This is the first study to use a mobile phone app (TransLife) to understand the short-term risk factors for suicide among transgender individuals.ObjectiveThis study aims to beta test the usability of an evidence-informed mobile health (mHealth) suicide prevention phone app, TransLife. The primary aims are to obtain preliminary data on user engagement and satisfaction with the app, and to assess the feasibility of completing ecological momentary assessments (mood logs) within the app.MethodsWe used qualitative methods and an exploratory research approach that combined naturalistic app use, focus groups, and semistructured phone interviews. The focus group was informed about the development of the prototype. We conducted a 3-week evaluation to determine engagement and obtain detailed user feedback about the app. After participation in the pilot, phone-based, semistructured, and audio-recorded exit interviews were conducted with the research participants.ResultsIn total, 16 transgender individuals participated in this study. On average, users logged in 4 (SD 2.7) times a week and spent approximately 5 (SD 3.5) minutes on the app per log-in. A total of 6 major themes emerged in this study. These themes focused on the app's functionality, satisfaction with using the app, perceived ease of use, perceived safety of providing personal data within the app, trusting the app enough to share personal feelings, and features that make this app engaging. These themes suggest that TransLife is an engaging, useful, and acceptable mHealth intervention. Participants reported that the app was easy to use and understand, supported mental self-care, promoted self-awareness, and helped them identify triggers of negative moods.ConclusionsThe results of this pilot study indicate that TransLife is an engaging, acceptable, and potentially effective mHealth intervention. Transgender participants reported many advantages of using TransLife, such as being able to track their mood, connecting to the community, and accessing local resources. This study provides initial support for the acceptability and usability of TransLife as an mHealth intervention designed for the transgender community.

Dataset Information

Smartphone keyboard dynamics predict affect in suicidal ideation.

Publications

Smartphone keyboard dynamics predict affect in suicidal ideation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets