Adding Explainability to Machine Learning Models to Detect Chronic Kidney Disease
Bibliographic record
Abstract
Chronic Kidney Disease is a common term for multiple heterogeneous diseases in the kidneys. It is also known as Chronic Renal Disease. Chronic kidney disease (CKD) has a gradual loss of glomerular filtration rate (GFR) over three months. The patient does not observe any significant symptoms in the earlier stage of CKD, and it is not identifiable without clinical tests like urine and blood tests. Patients with CKD would have a higher chance of developing heart disease. CKD is a progressive and often irreversible process of renal function decline, which may reach an endpoint of end-stage renal failure, requiring renal replacement therapy. It is critical to diagnose progressive CKD at an early stage and predict patients prone to developing the disease further for timely therapeutic interventions. As such, researchers have expended enormous efforts in the development of novel biomarkers that may identify subjects with early CKD at risk of progression. In this study, we have developed an explainable machine learning model to predict chronic kidney disease by implementing an automated data pipeline using the Random Forest ensemble learning trees model and feature selection algorithm. The explainability of the proposed model has been assessed in terms of feature importance and explainability metrics. Three explainability methods; LIME, SHAP, and SKATER have been applied to interpret the developed model and to compare the explainability results using Interpretability, Fidelity, and Fidelity-to-Interpretability ratio as the explainability metrics.
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 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 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".