Background The integration of machine learning algorithms in decision support tools for physicians is gaining popularity. These tools can tackle the disparities in healthcare access as the technology can be implemented on smartphones. We present the first, large‐scale study on patients with skin of colour, in which the feasibility of a novel mobile health application (mHealth app) was investigated in actual clinical workflows. Objective To develop a mHealth app to diagnose 40 common skin diseases and test it in clinical settings. Methods A convolutional neural network‐based algorithm was trained with clinical images of 40 skin diseases. A smartphone app was generated and validated on 5014 patients, attending rural and urban outpatient dermatology departments in India. The results of this mHealth app were compared against the dermatologists’ diagnoses. Results The machine–learning model, in an in silico validation study, demonstrated an overall top‐1 accuracy of 76.93 ± 0.88% and mean area‐under‐curve of 0.95 ± 0.02 on a set of clinical images. In the clinical study, on patients with skin of colour, the app achieved an overall top‐1 accuracy of 75.07% (95% CI = 73.75–76.36), top‐3 accuracy of 89.62% (95% CI = 88.67–90.52) and mean area‐under‐curve of 0.90 ± 0.07. Conclusion This study underscores the utility of artificial intelligence‐driven smartphone applications as a point‐of‐care, clinical decision support tool for dermatological diagnosis for a wide spectrum of skin diseases in patients of the skin of colour.

Background COVID-19 pneumonia has been associated with severe acute hypoxia, sepsis-like states, thrombosis and chronic sequelae including persisting hypoxia and fibrosis. The molecular hypoxia response pathway has been associated with such pathologies and our recent observations on anti-hypoxic and anti-inflammatory effects of whole aqueous extract of Adhatoda Vasica (AV) prompted us to explore its effects on relevant preclinical mouse models. Methods In this study, we tested the effect of whole aqueous extract of AV, in murine models of bleomycin induced pulmonary fibrosis, Cecum Ligation and Puncture (CLP) induced sepsis, and siRNA induced hypoxia-thrombosis phenotype. The effect on lung of AV treated naïve mice was also studied at transcriptome level. We also determined if the extract may have any effect on SARS-CoV2 replication. Results Oral administration AV extract attenuates increased airway inflammation, levels of transforming growth factor-β1 (TGF-β1), IL-6, HIF-1α and improves the overall survival rates of mice in the models of pulmonary fibrosis and sepsis and rescues the siRNA induced inflammation and associated blood coagulation phenotypes in mice. We observed downregulation of hypoxia, inflammation, TGF-β1, and angiogenesis genes and upregulation of adaptive immunity-related genes in the lung transcriptome. AV treatment also reduced the viral load in Vero cells infected with SARS-CoV2. Conclusion Our results provide a scientific rationale for this ayurvedic herbal medicine in ameliorating the hypoxia-hyperinflammation features and highlights the repurposing potential of AV in COVID-19-like conditions.

Alu repeats contribute to phylogenetic novelties in conserved regulatory networks in primates. Our study highlights how exonized Alus could nucleate large-scale mRNA-miRNA interactions. Using a functional genomics approach, we characterize a transcript isoform of an orphan gene, CYP20A1 (CYP20A1_Alu-LT) that has exonization of 23 Alus in its 3’UTR. CYP20A1_Alu-LT, confirmed by 3’RACE, is an outlier in length (9 kb 3’UTR) and widely expressed. Using publically available datasets, we demonstrate its expression in higher primates and presence in single nucleus RNA-seq of 15928 human cortical neurons. miRanda predicts ∼4700 miRNA recognition elements (MREs) for ∼1000 miRNAs, primarily originated within these 3’UTR-Alus. CYP20A1_Alu-LT could be a potential multi-miRNA sponge as it harbors ≥10 MREs for 140 miRNAs and has cytosolic localization. We further tested whether expression of CYP20A1_Alu-LT correlates with mRNAs harboring similar MRE targets. RNA-seq with conjoint miRNA-seq analysis was done in primary human neurons where we observed CYP20A1_Alu-LT to be downregulated during heat shock response and upregulated in HIV1-Tat treatment. 380 genes were positively correlated with its expression (significantly downregulated in heat shock and upregulated in Tat) and they harbored MREs for nine expressed miRNAs which were also enriched in CYP20A1_Alu-LT. MREs were significantly enriched in these 380 genes compared to random sets of differentially expressed genes (p = 8.134e-12). Gene ontology suggested involvement of these genes in neuronal development and hemostasis pathways thus proposing a novel component of Alu-miRNA mediated transcriptional modulation that could govern specific physiological outcomes in higher primates.