Investigating the accuracy of neural networks for blood pressure prediction in the ICU
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This paper reports on research which investigates the viability of artificial neural networks, used in an ICU environment, for predicting both systolic and diastolic blood pressure up to 1 h ahead. In this environment, patients often receive pharmacological intervention to increase or decrease blood pressure. The physiological state of an ICU patient is therefore quite different to a hyper or hypotensive patient outside hospital, suggesting that predicting blood pressure in this environment is more challenging The work investigates whether building neural network architectures with multivariate input data is capable of predicting blood pressures in this environment. Our work uses skin temperature and heart rate readings in addition to systolic and diastolic blood pressure. Two types of neural network are explored are explored in this paper: an encoder-decoder long short-term memory architecture and, separately, a convolutional neural network architecture. The top-performing configuration, when using a 70 %–30 % train-test split of data, is a convolutional neural network model. This predicted systolic and diastolic blood pressures for a patient with an error of approximately 3 . 4 % . These results are at the same level of accuracy as work on blood pressure prediction outside the ICU environment. Our work shows that neural networks are a viable tool for short term prediction of arterial blood pressures in an ICU 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.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| 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 it