Remote pulmonary pathology diagnosis using a handheld device for acquiring lung sounds at the mouth: a proof of concept study

Obtaining relevant information about respiratory conditions is a unique challenge in the rapidly growing field of telehealth. While auscultation using a stethoscope remains the first-line method in primary care, it is not a practical solution in a home setting, as it requires the presence of both a skilled caregiver and experienced interpreter online. We conducted a proofofconcept study of a simple selfcheck thermometer-like device (OmnySense^®), which acquires auscultatory data through a microphone in the head of the device.

To have a concept of proof that home handled simplified device can asure a remote opion in telemedicine enhancing prompt and ease way to diagnose lung pathologies.

We assessed the agreement between subjective evaluations of lung sounds using the device and those using a digital stethoscope for the presence of crackles and/or wheezes. A total of 385 recordings from 13 patients admitted to the internal department were blindly, individually, and randomly assessed by three experienced physicians. The intra-modality agreement for crackles between evaluators was moderate for both the device and the stethoscope, with kappa statistics of 0.44 and 0.6 for the device and stethoscope, respectively, for the detection of wheezing and 0.46 and 0.4, respectively, for the crackles. The intermodality agreement was moderate for wheezes, with a kappa of 0.53, and was substantial for crackles, with a kappa of 0.71. Comparing the ability of crackles to diagnose pulmonary findings by imaging showed comparable sensitivity and specificity for both modalities.

Our findings suggest that the diagnostic performance of OmnySense’s selfoperating device is similar to that of physician interpretation of digital stethoscope recordings; thus, OmnySense has the potential to become a useful tool in the remote assessment of respiratory conditions and pathologies.