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 architecture and feedforward artificial neural network (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 model 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 the model 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.

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.

BACKGROUNDMediastinal masses are relatively uncommon and continue to be an interesting diagnostic and therapeutic challenge to pulmonologists and thoracic surgeons. Mediastinal tumours represent 3% of tumours seen within chest. This study is chosen with an aim to assess the clinical profile of mediastinal masses.

No abstract

Background: Tuberculosis is the most common cause of death from an infectious disease worldwide after HIV/AIDS. Drug resistant tuberculosis continues to be a public health crisis. India stands, one among 27 “high burden” MDR countries and has over 2 million new TB cases every year and TB kill’s nearly 1000 people every day. The WHO 2018 Global Tuberculosis Report estimated that, worldwide, approximately 3.5 percent of all new TB cases and 18 percent of previously treated cases are caused by MDR or rifampicin-mono resistant strains.Methods: Presumptive drug resistance TB cases were subjected for CBNAAT or LPA to detect resistance patterns. About 231 cases of MDR/RR TB cases after pre-treatment evaluation started on CAT- IV regimen and both interim and final outcomes were analyzed.Results: Out of 231cases 172(74.4%) were males and 59(25.6%) were females with age between 13-75yrs. Total of 194 cases culture conversion occurred out of which 28 cases the cultures were reverted back to positives. Final Outcomes were, cured in 84 (36.3%) cases, treatment completed in 42 (18.18%) cases, defaulters in 31 (13.4%) cases, turned to be XDR in 10 (4.32%) cases, treatment failure in 10 (4.32%) cases, 50 (21.6%) cases died, 3(1.29%) cases were transferred out.Conclusions: Approximately 2/3rd of MDR/RR TB cases are retreatment sputum positive cases. Successful outcome observed in 54.54% of cases only. High rates of deaths and defaulters alarm the necessity of more effective implementation and surveillance of the programme.