Scientists recently investigated a smartphone-based app that records cough rates and found it helpful in identifying tuberculosis (TB) and monitoring treatment success.
Suffering from a cough is a primary symptom of a range of respiratory conditions, including tuberculosis (TB). Although treatable, healthcare providers often find monitoring the success of TB treatment challenging.
For example, research points out that current TB treatment monitoring relies on testing sputum and culture conversion, which have low sensitivity and long turnaround times, present a biohazard risk, and are prone to contamination.
Tracking cough frequency can help doctors monitor how well treatments are working, but this requires the person with TB to accurately self-report how many times a day they cough. The results can be challenging and inconclusive.
However, advancements in smartphone app technology have opened new doors for diagnosing and monitoring specific health conditions. For instance, recent reports suggest that apps can detect a stroke as it’s happening, and some apps may help diagnose autism.
The latest app advancement under investigation in clinical trials is a cough monitoring system called Hyfe AI. This smartphone-based app runs specialized software that calculates a person’s cough rate hourly. With this information, healthcare providers could have the data they need to diagnose TB and determine if TB treatment is effective.
To investigate the usefulness of Hyfe AI, researchers recently conducted a study using the new app technology to monitor coughing in people presumed to have TB in Uganda, South Africa, the Philippines, Vietnam, and India. The scientists then compared the cough patterns between people with microbiologically confirmed TB, clinical TB, and other respiratory diseases (ORD).
Their research appears in The International Journal of Tuberculosis and Lung Disease (IJTLD).
At the start of the study, participants 18 or older with a new or worsening cough for at least two weeks were given smartphones with the Hyfe app installed. The app monitored the participant’s cough 24 hours a day for 14 days.
Of the 565 participants who completed cough monitoring, 144 had microbiologically confirmed TB, 48 were treated for clinical TB, and 373 were identified as having ORD.
Among the 144 participants with microbiologically confirmed TB, almost 94% (135) began TB treatment about one day after they enrolled in the study.
On the first day of monitoring, the overall average cough count was five coughs per hour. However, participants with microbiologically confirmed TB had a significantly higher cough rate per hour than those with ORD.
Still, the scientists found no significant difference in cough rate per hour between participants with clinical TB.
Moreover, by day 14 of cough monitoring, the overall cough rate per hour had dropped to 3.5 in all groups — a significant decrease from day one of the study.
Participants with TB showed unique cough frequency trajectories early in treatment that were different from the cough patterns of participants with ORD. Additionally, cough frequency improved more rapidly among participants with microbiologically confirmed TB.
Although more research is needed, scientists suggest that cough-based TB screening may help reduce the overtreatment of people without TB and improve the detection of the condition.
"Continuous cough monitoring should be further explored as a non-invasive biomarker for TB diagnosis and treatment monitoring," the authors wrote.
A clinical trial investigating the performance of the Hyfe Cough Monitoring System is currently underway, with an expected completion date of April 3, 2023.
- Clinical Microbiology Reviews. Tuberculosis Treatment Monitoring and Outcome Measures: New Interest and New Strategies.
- Hyfe AI. Detect & Quantify Cough.
- The International Journal of Tuberculosis and Lung Disease. Continuous cough monitoring: a novel digital biomarker for TB diagnosis and treatment response monitoring.
- Clinical Trials.gov. Clinical Validation of the Hyfe Cough Monitoring System.