Time-Series Autoregressive Models for Point and Interval Forecasting of Raw and Derived Commercial Near-Infrared Spectroscopy Measures: An Exploratory Cranial Trauma and Healthy Control Analysis
Bibliographic record
Abstract
Cerebral near-infrared spectroscopy (NIRS) systems have been demonstrated to continuously measure aspects of oxygen delivery and cerebrovascular reactivity. However, it remains unknown whether the prediction of these cerebral physiologic signals into the future is feasible. Leveraging existing archived data sources, four point and interval-forecasting methods using autoregressive integrative moving average (ARIMA) models were evaluated to assess their ability to predict NIRS cerebral physiologic signals. NIRS-based regional cerebral oxygen saturation (rSO2) and cerebral oximetry index signals were derived in three temporal resolutions (10 s, 1 min, and 5 min). Anchored- and sliding-window forecasting, with varying model memory, using point and interval approaches were used to forecast signals using fitted optimal ARIMA models. The absolute difference in the forecasted and measured data was evaluated with median absolute deviation, along with root mean squared error analysis. Further, Pearson correlation and Bland–Altman statistical analyses were performed. Data from 102 healthy controls, 27 spinal surgery patients, and 101 traumatic brain injury patients were retrospectively analyzed. All ARIMA-based point and interval prediction models demonstrated small residuals, while correlation and agreement varied based on model memory. The ARIMA-based sliding-window approach performed superior to the anchored approach due to data partitioning and model memory. ARIMA-based sliding-window forecasting using point and interval approaches can forecast rSO2 and the cerebral oximetry index with reasonably small residuals across all populations. Correlation and agreement between the predicted versus actual values varies substantially based on data-partitioning methods and model memory. Further work is required to assess the ability to forecast high-frequency NIRS signals using ARIMA and ARIMA-variant models in healthy and cranial trauma populations.
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 | 0.005 | 0.006 |
| 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 | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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".