Signal Quality Estimation of Impedance Pneumography Signals in the NICU Using a Frequency-based Approach *
Bibliographic record
Abstract
As a standard of care in the Neonatal Intensive Care Unit (NICU), infants' vital signs are monitored continuously via wired devices. These often interfere with skin-to-skin contact, patient care, and pose increased risks of skin damage, infection, and tangling around the body. We designed an ongoing study to evaluate the feasibility, accuracy, and safety of wireless vital sign monitoring in the NICU. Vital signs were simultaneously acquired using the wired, standard of care bedside monitor and a novel, wireless, wearable sensor (ANNE Arc). Data from 25 NICU infants were recorded for 8 hours a day, over 4 consecutive days. Previously, we found strong accuracy for wireless heart rate (HR) monitoring, but poor performance for respiratory rate (RR). However, RR measurements derived from impedance pneumography can be erroneous in the presence of movement artifacts and increased noise. Thus, we developed an algorithm to continuously estimate the signal-to-noise ratio (SNR) across wired and wireless impedance recordings, using the Fast Fourier Transform (FFT). Across 72 recording sessions, we found the impedance signal from the wireless sensor had a lower SNR (median SNR of -1.83 dB [IQR: -5.83-1.92]), than the wired reference device (median SNR of 2.12 dB [IQR: -2.14-6.33]). We examined the mean absolute error (MAE) and margin of error (MoE) between paired wired and wireless RR values as a function of the SNR of both systems. The agreement between the wireless and wired RR signals increased during periods of high SNR. The MAE achieved ≤ 10 bpm when wired SNR was ≥ 4 dB and wireless SNR was ≥ 10 dB; for the same SNRs, the MoE ≤±25 bpm. Thus, we showed that the SNR of raw impedance measurements could be used to assess the reliability of RR values displayed on clinical patient monitors.Clinical relevance- This algorithm provides a means of quantifying the signal quality of thoracic impedance measurements acquired from neonates, and assigning confidence to RR values displayed on clinical monitors.
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 | 0.002 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 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 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".