>Reduced-Dimensional Radial Basis Neural Network for Monitoring Haemodialysis
Bibliographic record
Abstract
Efficiency of haemodialysis is determined by calculating adequacy. Current practice utilizes invasive procedures, such as the periodic measurement of blood urea nitrogen levels for monitoring haemodialysis. Medical informatics has not been used to study haemodialysis. Here an algorithmic approach is presented to calculate adequacy using generalised radial basis function neural networks (GRBFN). Previous work by the authors has shown the performance of a GRBFN when compared to the DDQ method. Table I. Comparison between UN removal calculated by DDQ and that predicted by GRBFN. Next, adequacy was measured using those quantities that are non-invasive. Table II. Comparison between UN removal calculated by DDQ and that predicted by the 2 GRBFN architectures (NEW GRBFN inputs – Time, Weight; OLD GRBFN inputs – Bun, Time, Weight). Time Calculated UNRemoval- DDQ Predicted UN Removal (OLD GRBFN) Predicted UN Removal (NEW GRBFN ) % PE (OLD GRBFN) % PE (NEW GRBFN) 0 35.08 ± 3.33 34.48 ± 0.48 34.72 ± 0.07 1.70 1.02 60 34.00 ± 3.04 31.48 ± 0.31 31.60 ± 0.03 7.41 7.06 90 28.54 ± 2.72 28.44 ± 0.23 28.48 ± 0.07 0.34 0.23 120 25.88 ± 3.72 25.56 ± 0.25 25.64 ± 0.01 1.23 0.94 150 22.38 ± 1.14 21.83 ± 0.19 21.89 ± 0.03 2.46 2.20 180 20.56 ± 4.09 19.66 ± 0.14 19.70 ± 0.03 4.37 4.21 210 18.68 ± 1.88 17.04 ± 0.15 17.07 ± 0.08 8.80 8.63 240 15.60 ± 3.98 13.40 ± 0.06 13.40 ± 0.02 14.16 14.16 This study presents a better and more convenient algorithmic procedure that provides the physician with a better guide to the prescription of haemodialysis.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| 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".