An Interpretable TabNet Deep Learning Approach for Kidney Disease Classification
Bibliographic record
Abstract
Chronic kidney disease (CKD) has emerged as a major public health problem, and early and accurate diagnosis is crucial. This study introduced an interpretable deep learning framework that uses the TabNet architecture for efficient CKD classification. The proposed approach includes comprehensive data preprocessing techniques including handling outliers using gaussian method, correcting skewness with the Box-Cox transformation, encoding categorical variables, scaling features, and addressing class imbalance using the Synthetic Minority Oversampling Technique (SMOTE). The TabNet model was trained on a refined dataset, using its inherent sequential attention mechanism to select features and facilitate learning. The model obtained outstanding results on all evaluation metrics, that include accuracy, precision, recall, F1-score, and AUC. The ROC curve, confusion matrix, and classification report all confirmed these results, indicating that there were no errors in classification. SHAP (SHapley Additive exPlanations) was employed to enhance the transparency and interpretability of the model. By using SHAP-based analysis, important features were identified as having a major impact on the model's predictions. Summary and beeswarm plots effectively illustrate both the extent and direction of each feature's effect. The results are consistent with established clinical knowledge, thereby validating the model's reliability, interpretability, and potential value in clinical decision-making.
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 | 0.001 | 0.000 |
| 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) | 0.003 | 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".