Prediction of the infecting organism in peritoneal dialysis patients with acute peritonitis using interpretable Tsetlin Machines
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
Motivation: The analysis of complex biomedical datasets is becoming central to understanding disease mechanisms, aiding risk stratification and guiding patient management. However, the utility of computational methods is often constrained by their lack of interpretability, which is particularly relevant in clinically critical areas where rapid initiation of targeted therapies is key. Results: To define diagnostically relevant immune signatures in peritoneal dialysis patients presenting with acute peritonitis, we analysed a comprehensive array of cellular and soluble parameters in cloudy peritoneal effluents. Utilizing Tsetlin Machines, a logic-based machine learning approach, we identified pathogen-specific immune fingerprints for different bacterial groups, each characterized by unique biomarker combinations. Unlike traditional 'black box' machine learning models, Tsetlin Machines identified clear, logical rules in the dataset that pointed towards distinctly nuanced immune responses to different types of bacterial infection. Importantly, these immune signatures could be easily visualized to facilitate their interpretation, thereby allowing for rapid, accurate and transparent decision-making. This unique diagnostic capacity of Tsetlin Machines could help deliver early patient risk stratification and support informed treatment choices in advance of conventional microbiological culture results, thus guiding antibiotic stewardship and contributing to improved patient outcomes. Availability and implementation: All underlying tools and the anonymized data underpinning this publication are available at https://github.com/anatoliy-gorbenko/biomarkers-visualization.
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 | 0.000 | 0.000 |
| 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