Development and Pilot Implementation of Neotree, a Digital Quality Improvement Tool Designed to Improve Newborn Care and Survival in 3 Hospitals in Malawi and Zimbabwe: Cost Analysis Study
Bibliographic record
Abstract
Background: Two-thirds of the 2.4 million newborn deaths that occurred in 2020 within the first 28 days of life might have been avoided by implementing existing low-cost evidence-based interventions for all sick and small newborns. An open-source digital quality improvement tool (Neotree) combining data capture with education and clinical decision support is a promising solution for this implementation gap. Objective: We present results from a cost analysis of a pilot implementation of Neotree in 3 hospitals in Malawi and Zimbabwe. Methods: We combined activity-based costing and expenditure approaches to estimate the development and implementation cost of a Neotree pilot in 1 hospital in Malawi, Kamuzu Central Hospital (KCH), and 2 hospitals in Zimbabwe, Sally Mugabe Central Hospital (SMCH) and Chinhoyi Provincial Hospital (CPH). We estimated the costs from a provider perspective over 12 months. Data were collected through expenditure reports, monthly staff time-use surveys, and project staff interviews. Sensitivity and scenario analyses were conducted to assess the impact of uncertainties on the results or estimate potential costs at scale. A pilot time-motion survey was conducted at KCH and a comparable hospital where Neotree was not implemented. Results: Total cost of pilot implementation of Neotree at KCH, SMCH, and CPH was US $37,748, US $52,331, and US $41,764, respectively. Average monthly cost per admitted child was US $15, US $15, and US $58, respectively. Staff costs were the main cost component (average 73% of total costs, ranging from 63% to 79%). The results from the sensitivity analysis showed that uncertainty around the number of admissions had a significant impact on the costs in all hospitals. In Malawi, replacing monthly web hosting with a server also had a significant impact on the costs. Under routine (nonresearch) conditions and at scale, total costs are estimated to fall substantially, up to 76%, reducing cost per admitted child to as low as US $5 in KCH, US $4 in SMCH, and US $14 in CPH. Median time to admit a baby was 27 (IQR 20-40) minutes using Neotree (n=250) compared to 26 (IQR 21-30) minutes using paper-based systems (n=34), and the median time to discharge a baby was 9 (IQR 7-13) minutes for Neotree (n=246) compared to 3 (IQR 2-4) minutes for paper-based systems (n=50). Conclusions: Neotree is a time- and cost-efficient tool, comparable with the results from limited similar mHealth decision-support tools in low- and middle-income countries. Implementation costs of Neotree varied substantially between the hospitals, mainly due to hospital size. The implementation costs could be substantially reduced at scale due to economies of scale because of integration to the health systems and reductions in cost items such as staff and overhead. More studies assessing the impact and cost-effectiveness of large-scale mHealth decision-support tools are needed.
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 | 0.017 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".