Enhancing Pneumonia Diagnosis Through AI Interpretability: Comparative Analysis of Pixel-Level Interpretability and Grad-CAM on X-ray Imaging With VGG19
Bibliographic record
Abstract
Pneumonia is a leading cause of morbidity and mortality worldwide, necessitating timely and precise diagnosis for effective treatment. Chest X-rays are the primary diagnostic tool, but their interpretation demands substantial expertise. Recent advancements in AI have shown promise in enhancing pneumonia detection from X-ray images, yet the opacity of deep learning models raises concerns about their clinical adoption. Interpretability in AI models is vital for fostering trust among healthcare professionals by providing transparency in decision-making processes. This study conducts a comparative analysis of two interpretability methods, Pixel Level Interpretability (PLI) and Gradient-weighted Class Activation Mapping (GradCAM), in the context of pneumonia classification using VGG19 on X-ray datasets. The research includes an experiment involving three distinct X-ray datasets. VGG19 is applied to classify a query image, and both PLI and Grad-CAM are used to interpret the classification decisions. The study evaluates these interpretability methods across multiple dimensions: computational efficiency, diagnostic performance, explanation continuity, calibration accuracy, robustness to training parameters, and feedback from medical experts. Our findings aim to determine which interpretability technique offers a more clinically meaningful explanation, balancing computational feasibility and diagnostic reliability. This study contributes to the development of explainable AI in healthcare, supporting the integration of trustworthy AI systems in clinical environments for enhanced pneumonia diagnosis.
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 | 0.015 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 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".