Enhancing Diabetes Prediction Based on Pair-Wise Ensemble Learning Model Selection
Bibliographic record
Abstract
Diabetes, a multifaceted health condition, presents significant challenges in terms of early diagnosis. This has sparked an interest in investigating the efficacy of two-combination ensemble learning (EL) techniques, which have shown potential in heightening the precision of predictions. Although methodologies such as logistic regression (LR), K-nearest neighbors (KNN), naive bayes (NB), support vector machine (SVM), decision tree (DT), and random forest (RF) have been promising when applied in isolation, their collective strength through an ensemble approach is not comprehensively studied. This investigation fills this research void by evaluating different integrations of these methodologies to construct solid predictive systems for diabetes using the pima indian diabetes dataset (PIDD). This approach employs ensemble learning, a strategy that amalgamates several analytical models to improve the reliability of predictions. By strategically synthesizing models like LR, KNN, NB, SVM, DT, and RF, this study aims to utilize the unique advantages that each model offers. Among these combinations, the SVM+RF, KNN+DT, and SVM+DT configurations stand out, delivering impressive accuracy rates of 84 %, 84 %, and 83 % respectively on tests. The effectiveness of the SVM+DT combination is further highlighted through receiver operating characteristic (ROC) curve analysis, showing extraordinary discrimination power with the highest area under the curve (AUC) score reaching 0.9. When comparing these results to findings from contemporary research, the innovative combinations proposed here-namely, SVM+DT, KNN+DT, and SVM+RF-provide enhanced performance, surpassing recent models by margins of 6 %, 6 %, and 4.4 % accordingly. These results underline the advantage of integrating a variety of classifiers to amplify the accuracy of diabetes predictions.
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 | 0.003 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| 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".