The combination of wearable coughing devices and machine learning may one day allow for more accurate monitoring of patient symptoms.
However, the authors of the report warned that it is still not clear how closely cough data correlates with disease progression and activity. That's what the report was
Chronic cough is an important feature of interstitial pulmonary disease, noted by Giovanni Ferrara, MD, author of the University of Alberta, and colleagues.1 Cough can have a significant impact on the quality of life of patients with lung disease;
However, it is difficult to use cough as an objective indicator of cough severity, as existing surveys rely on patient recollections and may capture patient experiences only on certain days.1 According to Ferrara and colleagues, other tools for monitoring disease progression appear to represent only a single time point, such as spirometry and radiology.
“There is a clear need for techniques that can assess coughs in these patients more frequently, and I write for a long period of time,” they write.
One possible solution is to use a wearable device to monitor your cough. Early studies suggest that such devices may be able to capture meaningful cough data, and can then be analyzed via machine learning to identify patterns related to patient surveys. Especially in research
Ferrara and her colleagues wanted to see how well the device works in a population of patients with pulmonary fibrosis.1 Their study had two important endpoints. The primary endpoint was to check whether patients would wear devices for at least 70% of the 6-month study protocol. The secondary endpoint was to check whether the data generated by the device were meaningfully associated with two important lung disease questionnaires: the Leicester Cough Survey (LCQ) and the King's Short Interstitial Lung Disease Questionnaire (K-Bild).
The investigators recruited eight patients in the study. Patients ranged from 54 to 78 years of age, with a variety of diagnoses of pulmonary fibrosis, including IPF and PPF. Each enrollee completed a baseline questionnaire, and all but one patient received disease-modifying therapy during the study period.
Patients' devices were lower than expected. Only one patient met the primary outcome threshold of wearing the device for at least 70% of the study days. The patient wore a device for 85.6% of the days. Another patient wore the device for 68.8%. However, on average, participants only wore the device about half the day of the study protocol. One patient quickly left the study and did not wear the device.
“There were various reasons for noncompliance, but it included mild discomfort, inconvenience and indifference to adopting consistent use. It also highlights the fact that one patient left the study due to a moderate, reversible skin reaction and another patient dropped out shortly after being enrolled,” wrote Ferrara and colleagues.
The authors said low device utilization highlights the importance of wearable devices design and ergonomics.
Still, despite low compliance, investigators said the device was still capturing sufficient longitudinal data to correlate cough intensity with K-Bild and LCQ surveys. Therefore, they said, even partial use of such devices could provide clinically meaningful insights.
However, the authors warned that given the size of the study, the time frame, and the lack of spirometry and radiation endpoints, it is still impossible to say whether the device can properly track disease progression or activity. They added that cough intensity is not currently considered in clinical practice, cough is dynamic and cough patterns are very diverse.
Therefore, the authors stated that their research serves as a useful proof of concepts for cough monitoring and machine learning in pulmonary fibrosis, but that further research will be required to determine the role that such techniques should play in patient care.
reference
1. FeistMD, Huang Y, Kalluri M, et al. Decoding function of objective cough in progressive pulmonary fibrosis: a 6-month feasibility study. Am J Med. Released online on August 5th, 2025. doi: 10.1016/j.amjmed.2025.07.027
2. LeeJ, White E, Freiheit E, et al. Cough-specific quality of life predicts disease progression in patients with interstitial pulmonary disease: data from basal pulmonary fibrosis patient registration. chest. 2022; 162(3): 603-613. doi: 10.1016/j.chest.2022.03.025
3. RheeH, Belyea MJ, Sterling M, Bocko MF. Assessment of the validity of automated devices for adolescent asthma monitoring: a correlation design. J Med Internet Res. 2015; 17 (10): E234. doi: 10.2196/jmir.4975
