Model-interpreted outcomes of artificial neural networks classifying immune biomarkers associated with severe infections in ICU
Bibliographic record
Abstract
Introduction: Millions of deaths worldwide are a result of sepsis (viral and bacterial) and septic shock syndromes which originate from microbial infections and cause a dysregulated host immune response. These diseases share both clinical and immunological patterns that involve a plethora of biomarkers that can be quantified and used to explain the severity level of the disease. Therefore, we hypothesize that the severity of sepsis and septic shock in patients is a function of the concentration of biomarkers of patients. Methods: In our work, we quantified data from 30 biomarkers with direct immune function. We used distinct Feature Selection algorithms to isolate biomarkers to be fed into machine learning algorithms, whose mapping of the decision process would allow us to propose an early diagnostic tool. Results: We isolated two biomarkers, i.e., Programmed Death Ligand-1 and Myeloperoxidase, that were flagged by the interpretation of an Artificial Neural Network. The upregulation of both biomarkers was indicated as contributing to increase the severity level in sepsis (viral and bacterial induced) and septic shock patients. Discussion: In conclusion, we built a function considering biomarker concentrations to explain severity among sepsis, sepsis COVID, and septic shock patients. The rules of this function include biomarkers with known medical, biological, and immunological activity, favoring the development of an early diagnosis system based in knowledge extracted from artificial intelligence.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".