Continuous digital cough monitoring during 6-month pulmonary tuberculosis treatment
Bibliographic record
Abstract
Background: Recent advances in digital and wearable technologies with artificial intelligence (AI) enable the use of continuous cough monitoring (CCM) to objectively monitor symptoms as surrogate markers of treatment efficacy in pulmonary tuberculosis (PTB). The objectives of this study were to describe the evolution of cough during PTB treatment in adults and to assess the feasibility of community-based CCM. Methods: We prospectively enrolled PTB adult participants upon treatment initiation. Participants' coughs were continuously monitored during 6 months with a smartphone loaded with an app able to detect cough by using an AI algorithm. Results: 22 participants were included. The median (interquartile range (IQR)) age was 28.5 (22-42) years and 62% were male. The median (IQR) coughs per hour (medCPH) was 11.0 (7.0-27.0) at week 1. By the end of the intensive phase of PTB treatment at week 8, the medCPH was 3.5 (1.5-7.0), which was significantly lower than the medCPH at week 1 (p=0.002). At week 26 (end of treatment), the medCPH was 1.0 (1.0-2.5). The adherence to CCM was high during the first 13 weeks of PTB treatment and then waned over time. The adherence was similar during daytime and night-time. Conclusion: Cough counts rapidly drop during the intensive phase of PTB treatment and then slowly decrease to a low baseline level by the end of the treatment. Community-based CCM using digital technology is feasible in low-resource settings but requires evaluation of alternative approaches to overcome adherence issues and technical limitations (mobile internet and electricity availability).
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".