Analysis of Suspected Factors in Tuberculosis Cases in Semarang City Using a Logistic Regression Model
Bibliographic record
Abstract
Tuberculosis (TB) is one of the world's deadliest infectious diseases, with Indonesia being among the countries with the highest TB burden. Semarang City, as an urban area with a dense population, faces significant challenges in controlling TB, particularly among vulnerable populations. This study identifies significant risk factors influencing TB incidence in Semarang City using a binary logistic regression model. Descriptive analysis reveals an imbalance in the data, with the majority of patients categorized as "not indicated for TB." Chi-Square tests show that variables such as shortness of breath, persistent fever for more than one month, diabetes mellitus, and household contact are significantly associated with TB incidence. The logistic regression model demonstrates overall significance (G statistic = 275.13; p-value = 1.23×10−55), with shortness of breath and diabetes mellitus emerging as major risk factors based on odds ratio interpretation. However, the model's performance in detecting the "indicated for TB" category is very low (Precision 36.36%; Recall 2.05%; F1-Score 3.88%), despite an overall accuracy of 87.25%. The poor performance in the "1" category and the Pseudo R2 value of 7% are likely related to data imbalance, where the number of cases in the "1" category is much smaller than in the "0" category, leading to bias toward the majority class. Additionally, the distribution of predictor variables that do not provide sufficient information to distinguish the "1" category from the "0" category further contributes to the model's limited ability to explain data variability overall.
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 | 0.004 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
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".