Home > Pulmonology > ERS 2020 > Best of Posters > Smartphone-based cough detection helpful in predicting asthma deterioration

Smartphone-based cough detection helpful in predicting asthma deterioration

Presented by
Dr Frank Rassouli, Cantonal Hospital St. Gallen, Switzerland
Conference
ERS 2020
A study evaluating the association between nocturnal coughing and asthma control has demonstrated the predictive value of smartphone-recorded night-time coughing in the detection of periods of uncontrolled asthma [1].

“Until now, we have not had a reliable tool for measuring peoples’ asthma symptoms overnight, so we know very little about night-time coughing and what it means,” said Dr Frank Rassouli (Cantonal Hospital St. Gallen, Switzerland). Smartphones have great potential to monitor different symptoms and detect changes early. Thus, Dr Rassouli worked with research partners from the University of St. Gallen and ETH Zurich to develop an app to measure cough.

The study included 79 adult asthma patients who were being treated at 2 clinics in Switzerland: the Lung Centre at Cantonal Hospital St Gallen and the mediX Group Practice, Zürich. Each patient visited their asthma clinic at the beginning and at the end of the study and was assessed for their use of asthma treatments, symptoms, and the impact of asthma on their daily life. All patients documented their sleep quality and nocturnal cough frequencies daily in the Pittsburgh Sleep Quality Index. In addition, sensor data of smartphones were collected in situ for 29 days. During this period, patients slept while the app audio recorded night-time coughing. The app also prompted patients to report their night-time symptoms.

Asthma was controlled in 192 weeks and uncontrolled in 116 weeks. Clinically significant deterioration occurred in 29 weeks in 25 patients. Mixed regression analyses showed that nocturnal cough and sleep quality were statistically significantly associated with asthma control on both a between- and within-patient level (P<0.05). Decision trees indicated that sleep quality was more useful for the detection of weeks with uncontrolled asthma, while nocturnal cough better detected weeks with asthma control deterioration.

Dr Rassouli said: “Our results suggest that night-time coughing can be measured fairly simply with a smartphone app and that an increase in coughing at night is an indicator that asthma is deteriorating. Monitoring asthma is really important because if we can spot early signs that it is getting worse, we can adjust medication to prevent asthma attacks.” Cut-offs using both markers predicted asthma attacks up to 5 days ahead with balanced accuracy between 70% and 75% (sensitivities 75-88% and specificities 57%-72%).

As the smartphone app was successfully used to monitor coughing in people with asthma, Dr Rassouli and his team plan to try the same technology with people who have chronic obstructive pulmonary disease.

 


    1. Rassouli F, et al. Smartphone-based cough detection predicts asthma control – description of a novel, scalable digital biomarker. Abstract 4569. ERS International Virtual Congress 2020, 7-9 Sept.

 



Posted on