Assessment and validation of the Community Maternal Danger Score algorithm
Bibliographic record
Abstract
BACKGROUND: High rates of maternal mortality in low-and-middle-income countries (LMICs) are associated with the lack of skilled birth attendants (SBAs) at delivery. Risk analysis tools may be useful to identify pregnant women who are at risk of mortality in LMICs. We sought to develop and validate a low-cost maternal risk tool, the Community Maternal Danger Score (CMDS), which is designed to identify pregnant women who need an SBA at delivery. METHODS: To design the CMDS algorithm, an initial scoping review was conducted to identify predictors of the need for an SBA. Medical records of women who delivered at the Federal Medical Centre in Makurdi, Nigeria (2019-2020) were examined for predictors identified from the literature review. Outcomes associated with the need for an SBA were recorded: caesarean section, postpartum hemorrhage, eclampsia, and sepsis. A maternal mortality ratio (MMR) was determined. Multivariate logistic regression analysis and area under the curve (AUC) were used to assess the predictive ability of the CMDS algorithm. RESULTS: Seven factors from the literature predicted the need for an SBA: age (under 20 years of age or 35 and older), parity (nulliparity or grand-multiparity), BMI (underweight or overweight), fundal height (less than 35 cm or 40 cm and over), adverse obstetrical history, signs of pre-eclampsia, and co-existing medical conditions. These factors were recorded in 589 women of whom 67% required an SBA (n = 396) and 1% died (n = 7). The MMR was 1189 per 100,000 (95% CI 478-2449). Signs of pre-eclampsia, obstetrical history, and co-existing conditions were associated with the need for an SBA. Age was found to interact with parity, suggesting that the CMDS requires adjustment to indicate higher risk among younger multigravida and older primigravida women. The CMDS algorithm had an AUC of 0.73 (95% CI 0.69-0.77) for predicting whether women required an SBA, and an AUC of 0.85 (95% CI 0.67-1.00) for in-hospital mortality. CONCLUSIONS: The CMDS is a low-cost evidence-based tool that uses 7 risk factors assessed on 589 women from Makurdi. Non-specialist health workers can use the CMDS to standardize assessment and encourage pregnant women to seek an SBA in preparation for delivery, thus improving care in countries with high rates of maternal mortality.
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 | 0.043 | 0.142 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.010 | 0.004 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.003 | 0.001 |
| Open science | 0.002 | 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".