Journal of Technology and Informatics
RespiScan: Tuberculosis Triage Support from Cough Acoustics Using Continuous Wavelet Transform Scalograms and MobileNetV2
DOI:
https://doi.org/10.37802/Keywords:
Clinical Pre-Screening, Continuous Wavelet Transform, Cough Acoustics, MobileNetV2, TuberculosisAbstract
Tuberculosis (TB) requires accessible pre-screening approaches for referral prioritization in resource-limited settings. Cough-acoustic studies have not always reported subject-level partitioning, patient-level evaluation, operating-point selection, and performance uncertainty consistently. This study presents RespiScan, a patient-level triage-support framework using complex Morlet Continuous Wavelet Transform scalograms and ImageNet-pretrained MobileNetV2 with corrected weighted focal loss. We curated a secondary cohort of 198 subjects (87 TB and 111 Non-TB) from TBscreen and Coswara. Audio was standardized to 16-kHz mono, one-second segments, capped at 10 clean recordings per subject, and partitioned strictly by subject into 137 training, 30 validation, and 31 internal-holdout subjects. Training-only augmentation used 10-dB environmental noise for both classes and speed perturbation for Non-TB. We selected the Non-TB: TB weight of 1.5:1.0 from three validation-only settings, then averaged patient scores before applying a validation-derived Youden threshold of 0.424084. On the internal holdout, RespiScan achieved an AUROC of 0.8866 (95% CI: 0.7479-0.9832), 77.42% accuracy, 71.43% sensitivity, and 82.35% specificity. Wide uncertainty, source-label confounding, and exploratory calibration preclude clinical-readiness claims; larger source-balanced prospective validation is required.
Downloads
References
[1] World Health Organization, Global Tuberculosis Report 2024. Geneva, Switzerland: World Health Organization, 2024. [Online]. Available: https://www.who.int/teams/global-programme-on-tuberculosis-and-lung-health/tb-reports/global-tuberculosis-report-2024
[2] World Health Organization, Target Product Profile for Tuberculosis Diagnosis and Detection of Drug Resistance. Geneva, Switzerland: World Health Organization, 2024. [Online]. Available: https://www.who.int/publications/i/item/9789240097698
[3] World Health Organization, High-Priority Target Product Profiles for New Tuberculosis Diagnostics: Report of a Consensus Meeting. Geneva, Switzerland: World Health Organization, 2014. [Online]. Available: https://www.who.int/publications/i/item/WHO-HTM-TB-2014.18
[4] M. Pahar, M. Klopper, B. Reeve, R. Warren, G. Theron, and T. Niesler, "Automatic cough classification for tuberculosis screening in a real-world environment," Physiological Measurement, vol. 42, no. 10, p. 105014, 2021, doi: 10.1088/1361-6579/ac2fb8.
[5] M. Sharma et al., "TBscreen: A passive cough classifier for tuberculosis screening with a controlled dataset," Science Advances, vol. 10, no. 1, p. eadi0282, 2024, doi: 10.1126/sciadv.adi0282.
[6] S. Huddart et al., "A dataset of solicited cough sound for tuberculosis triage testing," Scientific Data, vol. 11, no. 1, p. 1149, 2024, doi: 10.1038/s41597-024-03972-z.
[7] D. Jaganath et al., "Accelerating cough-based algorithms for pulmonary tuberculosis screening: Results from the CODA TB DREAM Challenge," Open Forum Infectious Diseases, vol. 12, no. 10, p. ofaf572, 2025, doi: 10.1093/ofid/ofaf572.
[8] D. Bhattacharya et al., "Coswara: A respiratory sounds and symptoms dataset for remote screening of SARS-CoV-2 infection," Scientific Data, vol. 10, no. 1, p. 397, 2023, doi: 10.1038/s41597-023-02266-0.
[9] S. Mallat, A Wavelet Tour of Signal Processing: The Sparse Way, 3rd ed. Burlington, MA, USA: Academic Press, 2009.
[10] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, "MobileNetV2: Inverted residuals and linear bottlenecks," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 4510-4520, doi: 10.1109/CVPR.2018.00474.
[11] J. Thiemann, N. Ito, and E. Vincent, "The diverse environments multi-channel acoustic noise database (DEMAND): A database of multichannel environmental noise recordings," Proceedings of Meetings on Acoustics, vol. 19, no. 1, p. 035081, 2013, doi: 10.1121/1.4799597.
[12] T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollar, "Focal loss for dense object detection," in Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2980-2988, doi: 10.1109/ICCV.2017.324.
[13] G. S. Collins et al., "TRIPOD+AI statement: Updated guidance for reporting clinical prediction models that use regression or machine learning methods," BMJ, vol. 385, p. e078378, 2024, doi: 10.1136/bmj-2023-078378.
[14] B. Van Calster et al., "Calibration: The Achilles heel of predictive analytics," BMC Medicine, vol. 17, p. 230, 2019, doi: 10.1186/s12916-019-1466-7.
[15] R. D. Riley et al., "Minimum sample size for external validation of a clinical prediction model with a binary outcome," Statistics in Medicine, vol. 40, no. 19, pp. 4230-4251, 2021, doi: 10.1002/sim.9025.
[16] C. J. Kelly, A. Karthikesalingam, M. Suleyman, G. Corrado, and D. King, "Key challenges for delivering clinical impact with artificial intelligence," BMC Medicine, vol. 17, p. 195, 2019, doi: 10.1186/s12916-019-1426-2.
[17] A. A. H. de Hond et al., "Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: A scoping review," npj Digital Medicine, vol. 5, p. 2, 2022, doi: 10.1038/s41746-021-00549-7.
[18] C. Infante, D. B. Chamberlain, R. Kodgule, and R. R. Fletcher, "Classification of voluntary coughs applied to the screening of respiratory disease," in 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2017, pp. 1413-1416, doi: 10.1109/EMBC.2017.8037098.
[19] K. S. Alqudaihi et al., "Cough sound detection and diagnosis using artificial intelligence techniques: Challenges and opportunities," IEEE Access, vol. 9, pp. 102327-102344, 2021, doi: 10.1109/ACCESS.2021.3097559.
[20] A. E. Edet, S. J. Inyang, I. J. Umoren, and U. E. Etuk, "Machine learning approach for classification of cyber threats actors in web region," Journal of Technology and Informatics (JoTI), vol. 6, no. 1, pp. 70-77, 2024, doi: 10.37802/joti.v6i1.679.
[21] N. C. I. Natun, M. A. Santhia, and Y. R. Kaesmetan, "Identifikasi pengenalan wajah berdasarkan jenis kelamin menggunakan metode Convolutional Neural Network (CNN)," Journal of Technology and Informatics (JoTI), vol. 6, no. 1, pp. 50-57, 2024, doi: 10.37802/joti.v6i1.694.
[22] R. Z. Megantara, P. I. Faot, R. H. Ito, K. F. Annabel, and O. Karnalim, "Pemanfaatan machine learning dalam prediksi rating: Studi kasus pada data abstrak publikasi ilmiah," Journal of Technology and Informatics (JoTI), vol. 7, no. 1, pp. 62-75, 2025, doi: 10.37802/joti.v7i1.999.
[23] L. A. Sanjani, R. B. M. Putra, and U. L. Yuhana, "Exploring the application of machine learning for automatic inbound email classification in CRM system at XYZ Company," Journal of Technology and Informatics (JoTI), vol. 6, no. 1, pp. 1-7, 2024, doi: 10.37802/joti.v6i1.715.
[24] A. Aryanti, F. D. Wulandari, M. Rafiif, F. Alghaniyyu, N. Kirana, and M. N. Alfazri, "Segmentasi dan klasifikasi risiko perdarahan dengan algoritma K-Means dan Naive Bayes berdasarkan data klinis dan transfusi," Journal of Technology and Informatics (JoTI), vol. 7, no. 2, pp. 211-219, 2025, doi: 10.37802/joti.v7i2.1124.
[25] G. H. R. Botha, G. Theron, R. M. Warren, M. Klopper, K. Dheda, P. D. van Helden, and T. R. Niesler, "Detection of tuberculosis by automatic cough sound analysis," Physiological Measurement, vol. 39, no. 4, p. 045005, 2018, doi: 10.1088/1361-6579/aab6d0.
