First-step validation of a text message-based application for newborn clinical management among pediatricians
Bibliographic record
Abstract
BACKGROUND: Neonatal mortality is high in developing countries. Lack of adequate training and insufficient management skills for sick newborn care contribute to these deaths. We developed a phone application dubbed Protecting Infants Remotely by Short Message Service (PRISMS). The PRISMS application uses routine clinical assessments with algorithms to provide newborn clinical management suggestions. We measured the feasibility, acceptability and efficacy of PRISMS by comparing its clinical case management suggestions with those of experienced pediatricians as the gold standard. METHODS: Each pediatrician was randomly assigned six of twelve cases. Pediatricians developed clinical case management plans for all assigned cases and then obtained PRISMS suggested clinical case managements. We calculated percent agreement and kappa (k) statistics to test the null hypothesis that pediatrician and PRISMS management plans were independent. RESULTS: We found high level of agreement between pediatricians and PRISMS for components of newborn care including: 10% dextrose (Agreement = 73.8%), normal saline (Agreement = 73.8%), anticonvulsants (Agreement = 100%), blood transfusion (Agreement =81%), phototherapy (Agreement = 90.5%), and supplemental oxygen (agreement = 69.1%). However, we found poor agreement with potential investigations such as complete blood count, blood culture and lumbar puncture. PRISMS had a user satisfaction score of 3.8 out of 5 (range 1 = strongly disagree, 5 = strongly agree) and an average PRISMS user experience score of 4.1 out of 5 (range 1 = very bad, 5 = very good). CONCLUSION: Management plans for newborn care from PRISMS showed good agreement with management plans from experienced Pediatricians. We acknowledge that the level of agreement was low in some aspects of newborn care.
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 | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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".