Machine Learning-Based Detection of Fetal Respiratory Patterns: A CNN-LSTM Approach for Enhanced Perinatal Monitoring
Bibliographic record
Abstract
Prenatal monitoring is crucial for assessing fetal health.Fetal health is typically evaluated using parameters such as fetal heart rate, fetal breathing movements, fetal body movements, and fetal tone.Fetal breathing movement, defined by periodic contractions of the fetal diaphragm, reflects pulmonary maturity and central nervous system development, making its accurate detection essential for early identification of fetal distress and developmental abnormalities.Conventional techniques such as ultrasound and cardiotocography are commonly used but are hindered by limited temporal resolution, maternal motion artifacts, and poor sensitivity to subtle respiratory variations.To address these limitations, a hybrid CNN-LSTM framework is developed to classify fetal respiratory episodes as normal, irregular, or distress patterns using high-resolution acoustic signals.Wavelet-based preprocessing eliminates baseline drift and power-line interference, convolutional layers extract spatial features, and LSTM networks capture temporal dependencies.Residual connections improve gradient propagation, and attention mechanisms enhance focus on critical signal segments, enabling robust classification in noisy biomedical environments.The model achieves 95.2% accuracy with sensitivity and specificity above 94%, demonstrating strong clinical relevance.A key innovation lies in the integration of residual connections and attention mechanisms within a CNN-LSTM pipeline for fetal respiratory signal analysis, a novel configuration not previously applied in this context.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".