Evaluation of community health worker's performance at home-based newborn assessment supported by mHealth in rural Bangladesh
Bibliographic record
Abstract
BACKGROUND: In low to middle-income countries where home births are common and neonatal postnatal care is limited, community health worker (CHW) home visits can extend the capability of health systems to reach vulnerable newborns in the postnatal period. CHW assessment of newborn danger signs supported by mHealth have the potential to improve the quality of danger sign assessments and reduce CHW training requirements. We aim to estimate the validity (sensitivity, specificity, positive and negative predictive value) of CHW assessment of newborn infants aided by mHealth compared to physician assessment. METHODS: In this prospective study, ten CHWs received five days of theoretical and hands-on training on the physical assessment of newborns including ten danger signs. CHWs assessed 273 newborn infants for danger signs within 48 h of birth and then consecutively for three days. A physician repeated 20% (n = 148) of the assessments conducted by CHWs. Both CHWs and the physician evaluated newborns for ten danger signs and decided on referral. We used the physician's danger sign identification and referral decision as the gold standard to validate CHWs' identification of danger signs and referral decisions. RESULTS: The referrals made by the CHWs had high sensitivity (93.3%), specificity (96.2%), and almost perfect agreement (K = 0.80) with the referrals made by the physician. CHW identification of all the danger signs except hypothermia showed moderate to high sensitivity (66.7-100%) compared to physician assessments. All the danger signs assessments except hypothermia showed moderate to high positive predictive value (PPV) (50-100%) and excellent negative predictive value (NPV) (99-100%). Specificity was high (99-100%) for all ten danger signs. CONCLUSION: CHW's identification of neonatal danger signs aided by mHealth showed moderate to high validity in comparison to physician assessments. mHealth platforms may reduce CHW training requirements and while maintaining quality CHW physical assessment performance extending the ability of health systems to provide neonatal postnatal care in low-resource communities. TRIAL REGISTRATION: clinicaltrials.gov NCT03933423 , January 05, 2019.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.021 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.003 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 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 teacher head, 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".