A comparative study of explainable machine learning models with Shapley values for diabetes prediction
Bibliographic record
Abstract
Over the years, numerous machine learning models have been developed, leading to successful applications across various fields. This study uses a large dataset related to type 2 diabetes prediction from the Centers for Disease Control and Prevention (CDC) in the United States. The dataset with 70692 samples has 21 input features and one output (non-diabetes or diabetes). In addition to health indicators like Body Mass Index (BMI), blood pressure, and cholesterol level, the features include socioeconomic factors (e.g., income, education) and lifestyle factors such as diet and physical activity. This paper aims to study how these features influence diabetes risk. 80% of the dataset is used for training and 20% for testing. Six machine learning models, as well as the Multivariate Adaptive Regression Splines (MARS) model, were used in the investigation. A detailed comparison of the performance of these models is given. Shapley values explain the nature of various machine learning models using visualization by color graphs to demonstrate the reliability of different machine learning models. This paper shows how Shapley values can improve their explainability and interpretability on diabetes prediction. We leverage the SHapley Additive exPlanations (SHAP) scores to provide information about the relative importance of each predictive feature, and these results shed light on the relationship between the features and the risk of developing type 2 diabetes. • Use a large dataset with 70692 samples and 21 input features in machine learning for type 2 diabetes prediction. • Present detailed discussions on the Multivariate Adaptive Regression Splines (MARS) model. • Show good prediction performance for six machine learning models and the MARS model. • Use SHapley Additive exPlanations (SHAP) scores to provide information about the relative importance of each predictive feature. • Improve the explainability and interpretability of the machine learning model.
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 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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".