Symptom-based tuberculosis (TB) screening often relies on cough reporting, which may be unreliable. Passive cough monitoring via smartphone apps offers a less subjective alternative. This study evaluated the diagnostic accuracy and implementation feasibility of smartphone-based cough frequency monitoring for identifying individuals likely to have TB in Uganda. We enrolled adults (≥15 years) screened for TB in community settings or tested at health facilities in Kampala. Participants underwent microbiological testing and 48-hour cough monitoring using the Hyfe Research app. TB status was determined using Xpert MTB/RIF Ultra and culture, and inverse probability weighting was applied to adjust for differential enrollment. We compared cough frequency between individuals with and without TB and assessed diagnostic accuracy using weighted ROC curves. We also conducted staff interviews, analyzed thematically, to explore implementation challenges. Of 884 enrolled participants, 197 had valid cough recordings and TB status (101 from community screening, 96 from health facilities). Individuals with TB had higher median cough frequency than those without: 2.2 (interquartile range 0.8-6.1) vs 0.9 (0.4-2.0) coughs per hour in the community and 6.7 (2.6-27.5) vs 2.4 (0.9-4.8) in facilities; Wilcoxon P < 0.0001 for both. AUCs for smartphone-based cough recording were 0.69 (95% CI: 0.58–0.79) in the community and 0.76 (95% CI: 0.6–0.88) in health facilities. At 90% sensitivity, specificities were 20% (95% CI: 0–22%) and 46% (95% CI: 1–32%), respectively. Smartphone-recorded cough frequency was moderately correlated with self-reported cough severity, respiratory-related quality of life scores (Saint George’s Respiratory Questionnaire), and staff-observed coughs. Staff cited device visibility, stigma, and security concerns as barriers to implementation. While smartphone-recorded cough frequency was associated with TB status, it did not meet diagnostic accuracy thresholds for stand-alone screening or triage. Implementation challenges also limited data collection. Addressing operational barriers will be critical to future development and deployment of cough monitoring tools for TB screening.

The authors have declared no competing interest.

This work was supported by grants from the National Institutes of Health (R01HL153611 [to E.A.K.], R01HL138728 [to D.W.D.], and K23AI185268 [to J.S.]) and the Gates Foundation (grant number INV-042921 to E.A.K.). The content is solely the responsibility of the authors and does not necessarily represent the official views of the funders.

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

Informed consent (or adolescent assent and parental informed consent) was obtained from all study participants. The study was approved by the Institutional Review Boards at the Johns Hopkins University School of Medicine and Makerere University School of Public Health.

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes

The deidentified dataset used for this study and a data dictionary are being uploaded to a controlled access data archive, per requirements of the institutional review board that reviewed and approved this study. The upload process is under review and this preprint will be updated with a link to the data as soon as available. At this time, all data produced in the present study are available upon reasonable request to the authors.