Differentiating Between COVID-19 and Tuberculosis Using Machine Learning and Natural Language Processing
Bibliographic record
Abstract
Over 10 million people around the world are affected by tuberculosis (TB) every year, making it a major global health concern. With the advent of the COVID-19 pandemic, TB services in many countries have been temporarily disrupted, leading to a potential delay in the diagnosis of TB cases and many cases going under the radar. Since both diseases sometimes present similarly and generally affect the lungs, there is also a risk of misdiagnosis. This study aims to analyse the differences between COVID-19 and TB in different patients, as a first step in the creation of a TB screening tool. 180 COVID-19 and 215 TB case reports were collected from ScienceDirect. Using Natural Language Processing tools, the patient’s age, gender, and symptoms were extracted from each report. Tree-based machine learning algorithms were then used to classify each case report as belonging to either disease. Overall, the cases included 252 male and 117 female patients, with 26 cases not reporting the patient’s sex. The patients’ ages ranged from 0 to 95 years old, with a median age of 41.5. There were 33 cases with missing age values. The most frequent symptom in the TB cases was weight loss while most COVID-19 cases listed fever as a symptom. Of all algorithms implemented, XGBoost performed best in terms of ROC AUC (86.9 %) and F1-score macro (78%). The trained model is a good starting point, which can be used by medical staff to aid in referring potential TB patients in a timely manner. This could reduce the delay in TB diagnosis as well as the TB death toll, especially in highly infected countries.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 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".