Search

Competing Interests: We declare no competing interests. This study did not receive any funding. RM, VA, and AJRM contributed equally.

The world has been facing the COVID-19 pandemic since December 2019. Timely and efficient diagnosis of COVID-19 suspected patients plays a significant role in medical treatment. The deep transfer learning-based automated COVID-19 diagnosis on chest X-ray is required to counter the COVID-19 outbreak. This work proposes a real-time Internet of Things (IoT) framework for early diagnosis of suspected COVID-19 patients by using ensemble deep transfer learning. The proposed framework offers real-time communication and diagnosis of COVID-19 suspected cases. The proposed IoT framework ensembles four deep learning models such as InceptionResNetV2, ResNet152V2, VGG16, and DenseNet201. The medical sensors are utilized to obtain the chest X-ray modalities and diagnose the infection by using the deep ensemble model stored on the cloud server. The proposed deep ensemble model is compared with six well-known transfer learning models over the chest X-ray dataset. Comparative analysis revealed that the proposed model can help radiologists to efficiently and timely diagnose the COVID-19 suspected patients., Competing Interests: The authors declare that they have no conflicts of interest., (Copyright © 2021 Ahmed I. Iskanderani et al.)

Leprosy is not eradicable with currently available diagnostics or interventions, as evidenced by its stable incidence. Early diagnosis of Mycobacterium leprae infection should therefore be emphasized in leprosy research. It remains challenging to develop tests based on immunological biomarkers that distinguish individuals controlling bacterial replication from those developing disease. To identify biomarkers for field-applicable diagnostics, we determined cytokines/chemokines induced by M. leprae proteins in blood of leprosy patients and endemic controls (EC) from high leprosy-prevalence areas (Bangladesh, Brazil, Ethiopia) and from South Korea, where leprosy is not endemic anymore. M. leprae-sonicate-induced IFN-γ was similar for all groups, excluding M. leprae/IFN-γ as a diagnostic readout. By contrast, ML2478 and ML0840 induced high IFN-γ concentrations in Bangladeshi EC, which were completely absent for South Korean controls. Importantly, ML2478/IFN-γ could indicate distinct degrees of M. leprae exposure, and thereby the risk of infection and transmission, in different parts of Brazilian and Ethiopian cities. Notwithstanding these discriminatory responses, M. leprae proteins did not distinguish patients from EC in one leprosy-endemic area based on IFN-γ. Analyses of additional cytokines/chemokines showed that M. leprae and ML2478 induced significantly higher concentrations of MCP-1, MIP-1β, and IL-1β in patients compared with EC, whereas IFN-inducible protein-10, like IFN-γ, differed between EC from areas with dissimilar leprosy prevalence. This study identifies M. leprae-unique Ags, particularly ML2478, as biomarker tools to measure M. leprae exposure using IFN-γ or IFN-inducible protein-10, and also shows that MCP-1, MIP-1β, and IL-1β can potentially distinguish pathogenic immune responses from those induced during asymptomatic exposure to M. leprae.