Validation of a Costing Algorithm and Cost Drivers for Neonates Admitted to the Neonatal Intensive Care Unit
Bibliographic record
Abstract
Objective Neonatal intensive care units (NICUs) account for over 35% of pediatric in-hospital costs. A better understanding of NICU expenditures may help identify areas of improvements. This study aimed to validate the Canadian Neonatal Network (CNN) costing algorithm for seven case-mix groups with actual costs incurred in a tertiary NICU and explore drivers of cost. Study Design A retrospective cohort study of infants admitted within 24 hours of birth to a Level-3 NICU from 2016 to 2019. Patient data and predicted costs were obtained from the CNN database and were compared to actual obtained from the hospital accounting system (Coût par Parcours de Soins et de Services). Cost estimates (adjusted to 2017 Canadian Dollars) were compared using Spearman correlation coefficient (rho). Results Among 1,795 infants included, 169 (9%) had major congenital anomalies, 164 (9%) with <29 weeks' gestational age (GA), 189 (11%) with 29 to 32 weeks' GA, and 452 (25%) with 33 to 36 weeks' GA. The rest were term infants: 86 (5%) with hypoxic–ischemic encephalopathy treated with therapeutic hypothermia, 194 (11%) requiring respiratory support, and 541 (30%) admitted for other reasons. Median total NICU costs varied from $6,267 (term infants admitted for other reasons) to $211,103 (infants born with <29 weeks' GA). Median daily costs ranged from $1,613 to $2,238. Predicted costs correlated with actual costs across all case-mix groups (rho range 0.78–0.98, p < 0.01) with physician and nursing representing the largest proportion of total costs (65–82%). Conclusion The CNN algorithm accurately predicts NICU total costs for seven case-mix groups. Personnel costs account for three-fourths of in-hospital total costs of all infants in the NICU. Key Points
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 | 0.009 | 0.051 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.005 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.000 | 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".