An observational study in COPD (Chronic Obstructive Pulmonary Disease), Artificial Intelligence and Cough, sponsored by Ruijin Hospital. Completed at 1 site in China. Open to participants aged 30 Years and older. Per ClinicalTrials.gov, last updated 2026-10-22.
Sponsored by Ruijin Hospital · Observational
Chronic Obstructive Pulmonary Disease (COPD) is widely underdiagnosed in low- and middle-income countries and regions, due to the lack of accessible tools. Conventional spiromery tests for COPD diagnosis are expensive, require trained personnel to operate properly. Portable spirometry highly relies on the quality assurance of the tests. Since artificial intelligence (AI)-based cough analysis has demonstrated promising results in COPD diagnosis, this study aimed to evaluate the accuracy of an AI-based cough analysis software (Cough Search) compared to a portable spirometer for the auxiliary diagnosis of COPD.
4,252 studies on the registry are indexed under Pulmonary Disease, Chronic Obstructive; 707 are open to participants now.
This study's enrollment of 466 is above the median of 183 across 1,099 observational studies indexed under Pulmonary Disease, Chronic Obstructive.
Browse Pulmonary Disease, Chronic Obstructive studies →Ruijin Hospital is the lead sponsor of 667 studies on the registry; 376 are open to participants now.
Counted across the registry records on this site, refreshed daily.
Definition of suspected COPD or a population at high risk of COPD: individuals aged over 30 years who have established risk factors for COPD (such as a history of smoking or dust exposure) or symptoms consistent with the clinical manifestations of COPD (such as cough, sputum production, or dyspnea).
Inclusion Criteria:
Definition of suspected COPD or a population at high risk of COPD
Sensitivity, specificity, and area under the receiver operating characteristic curve of LH-002 for COPD diagnosis
The diagnostic performance of the LH-002 COPD auxiliary diagnostic software will be evaluated against the clinical reference diagnosis established by independent respiratory physicians according to the GOLD 2024 criteria. The clinical reference diagnosis will incorporate post-bronchodilator spirometry, with an FEV1/FVC ratio of less than 0.70 indicating persistent airflow obstruction, together with relevant clinical information. Sensitivity and specificity will be reported with exact 95% confidence intervals calculated using the Clopper-Pearson method. The area under the receiver operating characteristic curve will be reported with a 95% confidence interval calculated using the DeLong method.
Time frame: During the single study visit, after completion of the LH-002 assessment and pre- and post-bronchodilator portable spirometry, up to 1 day
Paired differences in sensitivity and specificity between LH-002 and portable spirometry for COPD diagnosis
The sensitivity and specificity of LH-002 and portable spirometry for COPD diagnosis will be compared using paired data, with the clinical reference diagnosis as the reference standard. Superiority in sensitivity will be evaluated using the difference defined as sensitivity of LH-002 minus sensitivity of portable spirometry. Superiority will be concluded if the lower bound of the 95% confidence interval for this difference is greater than 0. Non-inferiority in specificity will be evaluated using the difference defined as specificity of LH-002 minus specificity of portable spirometry, with a non-inferiority margin of -0.05. Non-inferiority will be concluded if the lower bound of the 95% confidence interval is greater than -0.05. Paired comparisons will be performed using the McNemar test or an equivalent method.
Time frame: During the single study visit, after completion of both LH-002 assessment and portable spirometry, up to 1 day
Sensitivity, specificity, and area under the receiver operating characteristic curve of LH-002 for COPD diagnosis in prespecified subgroups
The diagnostic performance of LH-002 will be evaluated in prespecified subgroups defined by age (younger than 40 years, 40 to 64 years, and 65 years or older), sex, smoking history, COPD severity according to GOLD grades 1 to 4, and relevant comorbid respiratory conditions, including asthma, bronchiectasis, acute upper or lower respiratory tract infection, and chronic bronchitis. Sensitivity, specificity, and area under the receiver operating characteristic curve will be reported with 95% confidence intervals for each subgroup.
Time frame: During the single study visit, after completion of the diagnostic assessments, up to 1 day
Time required to complete one LH-002 assessment compared with one portable spirometry test
The completion time, measured in minutes, will be recorded for one LH-002 assessment and one portable spirometry test. For LH-002, completion time will be measured from the time the device is ready and cough recording begins until the diagnostic report is generated. For portable spirometry, completion time will be measured from the start of the test procedure until the pulmonary function report is obtained. The paired mean or median difference between the two methods will be reported with a 95% confidence interval. A paired t test will be used for normally distributed data; otherwise, the Wilcoxon signed-rank test will be used.
Time frame: During the single study visit, with the completion time recorded for each diagnostic method, up to 1 day
System Usability Scale scores for LH-002 and portable spirometry reported by healthcare professionals
Healthcare professionals operating LH-002 and portable spirometry will complete the System Usability Scale. The System Usability Scale provides a total score ranging from 0 to 100, with higher scores indicating better perceived usability. Scores for each method and the paired difference between methods will be summarized as mean and standard deviation or median and interquartile range, as appropriate, together with 95% confidence intervals. Paired comparisons will use a paired t test for normally distributed data or the Wilcoxon signed-rank test otherwise.
Time frame: Immediately after the healthcare professional completes both diagnostic procedures during the single study visit, up to 1 day
Documents are hosted by the registry — open the source record to download them.
Plan to share: No
From the registry record's own update history. This site started tracking changes on Sep 25, 2026; for anything earlier, see the record history on ClinicalTrials.gov ↗
This study is completed, as verified in Sep 2026. You cannot join it, but the record below documents what was studied.
Get an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.
Pulmonary Disease, Chronic Obstructive →