Evaluation of machine learning–driven automated Kleihauer‐Betke counting: A method comparison study
Bibliographic record
Abstract
INTRODUCTION: The Kleihauer-Betke (KB) test is the diagnostic standard for the quantification of fetomaternal hemorrhage (FMH). Manual analysis of KB slides suffers from inter-observer and inter-laboratory variability and low efficiency. Flow cytometry provides accurate quantification of FMH with high efficiency but is not available in all hospitals or at all times. We have developed an automated KB counting system that uses machine learning to identify and distinguish fetal and maternal red blood cells (RBCs). In this study, we aimed to evaluate and compare the accuracy, precision, and efficiency of the automated KB counting system with manual KB counting and flow cytometry. METHODS: The ratio of fetal RBCs of the same blood sample was quantified by manual KB counting, automated KB counting, and flow cytometry, respectively. Forty patients were enrolled in this comparison study. RESULTS: Comparing the automated KB counting system with flow cytometry, the mean bias in measuring the ratio of fetal RBCs was 0.0048%, with limits of agreement ranging from -0.22% to 0.23%. Using flow cytometry results as a benchmark, results of automated KB counting were more accurate than those from manual counting, with a lower mean bias and narrower limits of agreement. The precision of automated KB counting was higher than that of manual KB counting (intraclass correlation coefficient 0.996 vs 0.79). The efficiency of automated KB counting was 200 times that of manual counting by the certified technologists. CONCLUSION: Automated KB counting provides accurate and precise FMH quantification results with high efficiency.
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) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 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".