Acute Respiratory Distress Identification via Multi-Modality Using Deep Learning
Bibliographic record
Abstract
Medical instruments are essential in pediatric intensive care units (PICUs) for measuring respiratory parameters to prevent health complications. However, the assessment of acute respiratory distress (ARD) is still conducted through intermittent visual examination. This process is subjective, labor-intensive, and prone to human error, making it unsuitable for continuous monitoring and early detection of deterioration. Previous studies have proposed solutions to address these challenges, but their techniques rely on color information, the performance of which can be influenced by variations in skin tone and lighting conditions. We propose leveraging multi-modality data to address these limitations. Our method integrates color and depth data using deep convolutional neural networks with a late feature fusion scheme. We train and evaluate our model on a dataset of 153 patients with respiratory illnesses, 86 of whom have ARD of varying severity levels. Experimental results demonstrate that multi-modality data combined with simple late fusion techniques are more effective with limited data, offering higher confidence scores compared to using color information alone. Our approach achieves an accuracy of 85.2%, a precision of 86.7%, a recall of 85.2%, and an F1 score of 85.8%. These findings suggest that multi-modality data provide a promising solution for improving ARD detection accuracy and confidence in clinical settings.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| 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".