Accelerating Cough-Based Algorithms for Pulmonary Tuberculosis Screening: Results From the CODA TB DREAM Challenge
Bibliographic record
Abstract
Background: Open-access data challenges can accelerate innovation in artificial intelligence-based tools. In the Cough Diagnostic Algorithm for Tuberculosis (CODA TB) DREAM Challenge, we developed and independently validated cough sound-based artificial intelligence algorithms for tuberculosis screening. Methods: We included data from 2143 adults with ≥2 weeks of cough from outpatient clinics in India, Madagascar, the Philippines, South Africa, Tanzania, Uganda, and Vietnam. A standard tuberculosis evaluation was completed, and ≥3 solicited coughs were recorded using a smartphone. We invited teams to develop models using training data to classify microbiologically confirmed tuberculosis disease using (1) cough sound features only and/or (2) cough sound features with routinely available clinical data. After 4 months, they submitted the algorithms for independent test set validation. Models were ranked by area under the receiver operating characteristic curve (AUROC) and partial AUROC (pAUROC) to achieve at least 80% sensitivity and 60% specificity. Results: Eleven cough models and 6 cough-plus-clinical models were submitted. AUROCs for cough models ranged from 0.69 to 0.74, and the highest performing model achieved 55.5% specificity (95% confidence interval, 47.7%-64.2%) at 80% sensitivity. The addition of clinical data improved AUROCs (range, 0.78-0.83); 5 of the 6 models reached the target pAUROC, and the highest performing model had 73.8% specificity (95% confidence interval, 60.8%-80.0%) at 80% sensitivity. The AUROC varied by country and was higher among male and human immunodeficiency virus-negative individuals. Conclusions: In a short period, an open-access data challenge facilitated the development of new cough-based tuberculosis algorithms and demonstrated potential as a tuberculosis screening tool.
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 | 0.013 | 0.028 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.001 | 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".