Development of an Innovative Digital Data Collection System for Routine Mental Health Care Delivery in Rural Haiti
Bibliographic record
Abstract
INTRODUCTION: Effective digital health management information systems (HMIS) support health data validity, which enables health care teams to make programmatic decisions and country-level decision making in support of international development targets. In 2015, mental health was included within the Sustainable Development Goals, yet there are few applications of HMIS of any type in the practice of mental health care in resource-limited settings. Zanmi Lasante (ZL), one of the largest providers of mental health care in Haiti, developed a digital data collection system for mental health across 11 public rural health facilities. PROGRAM INTERVENTION: We describe the development, implementation, and evaluation of the digital system for mental health data collection at ZL. To evaluate system reliability, we assessed the number of missing monthly reports. To evaluate data validity, we calculated concordance between the digital system and paper charts at 2 facilities. To evaluate the system's ability to inform decision making, we specified and then calculated 4 priority indicators. RESULTS: The digital system was missing 5 of 143 monthly reports across all facilities and had 74.3% (55/74) and 98% (49/50) concordance with paper charts. It was possible to calculate all 4 indicators, which led to programmatic changes in 2 cases. In response to implementation challenges, it was necessary to use strategies to increase provider buy-in and ultimately to introduce dedicated data clerks to keep pace with data collection and protect time for clinical work. LESSONS LEARNED: While demonstrating the potential of collecting mental health data digitally in a low-resource rural setting, we found that it was necessary to consider the ongoing roles of paper records alongside digital data collection. We also identified the challenge of balancing clinical and data collection responsibilities among a limited staff. Ongoing work is needed to develop truly sustainable and scalable models for mental health data collection in resource-limited settings.
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 | 0.010 | 0.018 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
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".