Negative binomial mixed model neural network for modeling of pulmonary tuberculosis risk factors in West Java provinces
Bibliographic record
Abstract
Tuberculosis (TB) is still a major public health concern in many regions of the world, including Indonesia's West Java Provinces. Accurate TB risk factor prediction can enhance overall TB control efforts by directing focused therapies. In this study, utilizing a combination of Negative Binomial Mixed Models (NBMMs) and Feed-Forward Neural Networks (FFNNs), we offer a unique method for the predictive modeling of TB risk variables. A variety of sociodemographic, behavioral, and environmental factors that are known to be linked to TB are included in the dataset utilized in this investigation. To correct for overdispersion and include both fixed and random effects in the model, we first fitted an NBMM major problem in epidemiological investigations is modeling count data with overdispersion, and the NBMM component of the model offers a versatile and effective framework for doing so. Following that, we include an FFNN component in the model, which helps us to detect relevant predictive features and alter the model's weights accordingly. Backpropagation methods are used by the FFNN to adjust model parameters and enhance accuracy. The resulting Negative Binomial Mixed Model Neural Network (NBMMNN) model has a high accuracy value of up to 0.944. Our research suggests that the NBMMNN model outperforms conventional models that are frequently used to predict TB risk factors. By contrast to simpler models, the NBMMNN model can capture complicated and nonlinear interactions between predictors and outcomes. Additionally, the inclusion of random variables in the model enables us to take into account potential sources of variability in the data as well as unmeasured confounding. This work emphasizes the opportunity to enhance TB risk prediction and control efforts by integrating NBMMs with FFNNs. In West Java Provinces and other comparable contexts, the NBMMNN model might be a helpful tool for identifying and resolving TB risk factors, guiding targeted interventions, and enhancing overall TB control efforts.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.005 |
| Open science | 0.003 | 0.001 |
| 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".