Development and Clinical Validation of Swaasa AI Platform for screening and prioritization of Pulmonary TB

Abstract

Acoustic signal analysis has been employed in various medical devices. However, studies involving cough sound analysis to screen the potential Pulmonary Tuberculosis (PTB) suspects are very few. The main objective of this cross-sectional validation study was to develop and validate the Swaasa AI platform to screen and prioritize at risk patients for PTB based on the signature cough sound as well as symptomatic information provided by the subjects. The voluntary cough sound data was collected at Andhra Medical College-India. An Algorithm based on multimodal Convolutional Neural Network (CNN) architecture and tabular features was built and validated on a total of 567 subjects, comprising 278 positive and 289 negative PTB cases. The output from these two models was combined to detect the likely presence (positive cases) of PTB. In the clinical validation phase, the AI-model was found to be 86.82% accurate in detecting the likely presence of PTB with 90.36% sensitivity and 84.67% specificity. The pilot testing of Swaasa was conducted at a peripheral health care centre, RHC Simhachalam-India on 65 presumptive PTB cases. Out of which, 15 subjects truly turned out to be PTB positive with a Positive Predictive Value of 75%. The validation results obtained from Swaasa AI Platform are quite encouraging. This platform has the potential to fulfil the unmet need of a cost-effective PTB screening method. It works remotely, presents instantaneous results, and does not require a highly trained operator. Therefore, it could be implemented in various inaccessible, resource-poor parts of the world.

Cough Sounds in Screening and Diagnostics: A Scoping Review

“…27 Kuluozturk et al used a machine learning model to diagnose COVID-19 as well as heart failure and acute asthma based on cough sounds, 28 whereas Yellapu et al focused on the diagnosis of pulmonary tuberculosis. 29 Novel cough detection algorithms have also continued to be developed, 30,31 and Xu et al proposed a smartphone-based cough sound analysis as a potential home-based pulmonary function test. 32 Importantly, the effort to expand publicly available cough sound datasets has also continued, improving the landscape for better training and testing of future machine learning models.…”

“…For instance, a recent study by Davidson et al sought to classify COVID‐19‐related pneumonia severity based on cough sounds 27 . Kuluozturk et al used a machine learning model to diagnose COVID‐19 as well as heart failure and acute asthma based on cough sounds, 28 whereas Yellapu et al focused on the diagnosis of pulmonary tuberculosis 29 . Novel cough detection algorithms have also continued to be developed, 30,31 and Xu et al proposed a smartphone‐based cough sound analysis as a potential home‐based pulmonary function test 32 .…”

A Cross-sectional Feasibility Study to Evaluate the Usability and Efficacy of “Swaasa”: An AI-Platform for Rapid Respiratory Health Assessment

“…To identify respiratory disease patterns, a pattern classifier was developed using a combined logic approach. This classifier integrated a CNN and a FFANN model to automatically classify different types of respiratory diseases based on the signature patterns present in the cough data [22]. The classifier was trained on a dataset ensuring consistency and generalizability of the results.…”

“…To further optimize the analysis, the final layers of these two models were merged, enabling the integration of their outputs and providing a more thorough and accurate assessment of the cough data. This fusion of models (combined logic) enhances the overall prediction capability of the platform [22]. To evaluate its effectiveness and feasibility a cross- sectional pilot study was conducted on 355 subjects at Simhachalam Rural Healthcare Centre (RHC).…”