Development and Implementation of a Birth Forecasting Tool to Optimize Resources in Obstetrical Care During the COVID-19 Pandemic: Mixed-Methods Study
Bibliographic record
Abstract
Background: Medical resource allocation is important to ensure availability of care, especially in challenging circumstances like a pandemic. In fields of unpredictable care demand such as obstetrics, forecasting may help manage scarce resources. Objective: The development, validation, and implementation of a regional birth forecasting tool to support obstetrical staff planning in the Utrecht region during the COVID-19 pandemic. Methods: We combined predicted birth dates retrieved from Saltro, a large regional primary care laboratory, with data from the Dutch national perinatal registry (Perined) and Statistics Netherlands for model development. We created and implemented an HTML tool visualizing these forecasts, which were discussed during the regional acute obstetric health care network meetings. Six months after implementation, we assessed the impact of the tool using an evaluative stakeholder meeting. Results: We achieved a performance accuracy (R) of 0.45, 0.61, and 0.67 (all actual number of births within 95% CI) forecasting the number of births in the region, pooled in 1-, 2-, and 3-weekly bins, respectively. After presenting these findings to stakeholders, we implemented a forecasting tool using the 2-week bin model. The evaluative stakeholder meeting proved that the tool improved communication, awareness of health care need, and collaborations among health care providers in the Utrecht region. Additionally, stakeholders identified additional applications, such as communication with patients and training of obstetric health care providers. Conclusions: Implementation of a forecasting tool for the number of births based on available data across the health care system added value to obstetrical care by providing insight into care demand, and increasing communication, awareness, and collaboration between health care providers. Further research should aim at improving regional obstetric acute care by fostering data sharing in order to improve health care demand forecasts.
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 | 0.098 | 0.111 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.005 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| 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".