Deep Learning–Based Detection and Analysis of Pulmonary Tuberculosis Using Structured Clinical Data for Enhanced Diagnostic Accuracy
Bibliographic record
Abstract
This study introduces a deep learning framework to diagnose and identify pulmonary tuberculosis (TB) based on structured clinical data and imaging data to increase the precision of diagnostic outcomes. Using sophisticated neural networks, such as 3D ResNet-50 or algorithms to automate the process of detecting chest radiographs, the proposed system separates active and non-active cases of TB. The deep learning model demonstrated a high area under the ROC curve (AUC) of 0.96 and higher levels of diagnostic accuracy when compared with experienced radiologists in the context of performance evaluation. The system was found to have a sensitivity of 90 percent and specificity greater than 81 percent, which is captured by a strong confusion matrix (number of true positives: 432; number of false positives: 71; number of false negatives: 29; number of true negatives: 502). Model output was supported by the temporal trend analysis showing a reduction in TB incidence in upper-burden areas. Human-interpretable lesion localization facilitates clinical application further, providing a convenient and safe means to receive a fast and accurate diagnosis of TB to manage the current epidemic and a patient.
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 | 0.002 | 0.072 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.002 | 0.004 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".