Investigating Awareness and Acceptance of Digital Phenotyping in Dhaka’s Korail Slum: Qualitative Study
Bibliographic record
Abstract
Background: Digital phenotyping (DP), the process of using data from digital devices, such as smartphones and wearable technology to understand and monitor people's behavior, health, and daily activities, has shown significant promise in mental health care within high-income countries. However, its application in low- and middle-income countries (LMICs) is limited, particularly among impoverished populations such as slum residents. objectives: This study investigates the awareness, knowledge, acceptance, and implementation of DP, including willingness to share data, and concerns regarding privacy and data security, among residents of Dhaka's Korail slum, one of Bangladesh's largest and most densely populated informal settlements. Understanding awareness, acceptance, and privacy concerns surrounding DP in these settings is critical for its effective implementation. Methods: We conducted 8 focus group discussions with 79% (30/38) of female participants (mean age 37, SD 13.7 years). Participants included 20 individuals diagnosed with serious mental disorders and 18 caregivers. The focus group discussions also included a section explaining what DP is. Results: Smartphone ownership was reported by 45% (17/38) of the participants, while 92% (35/38) of the participants had access to a smartphone through family members. There was a general lack of awareness about DP among the participants. Initially, 92% (35/38) of participants had no prior knowledge of DP, but after receiving an explanation, they acknowledged its potential applications and benefits. Participants recognized the use of DP for health monitoring, particularly in managing mental health conditions. Participants expressed willingness to share certain types of data, particularly phone usage and location data, provided that content-level information remained private. Despite these perceived benefits, significant concerns about privacy and data security emerged. Participants expressed fears about the potential misuse of their personal information, with some feeling resigned to the idea of already being constantly monitored. Trust in DP tools emerged as a critical factor for adoption, highlighting the need for transparent data protection policies and user control over data sharing. Additionally, participants emphasized the importance of adapting DP tools to local contexts, including cultural considerations and technological literacy. Conclusions: While DP presents a promising avenue for mental health support in underserved urban populations, its adoption in LMIC slum settings requires targeted educational initiatives, robust privacy safeguards, and community involvement to ensure trust and usability. DP tools should be adapted to fit the cultural context of the target population, possibly involving modifications to the types of data collected or the way data are interpreted. While DP holds potential to improve mental health care in underserved communities, addressing barriers related to awareness, privacy, culture, and usability is crucial. Focusing on educational initiatives, robust data protection, cultural adaptation, user-friendly design, and community engagement, DP can become a valuable tool in bridging the mental health care gap in LMICs.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.009 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.005 | 0.005 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".