All Publications

  • CheXaid: deep learning assistance for physician diagnosis of tuberculosis using chest x-rays in patients with HIV. NPJ digital medicine Rajpurkar, P., O'Connell, C., Schechter, A., Asnani, N., Li, J., Kiani, A., Ball, R. L., Mendelson, M., Maartens, G., van Hoving, D. J., Griesel, R., Ng, A. Y., Boyles, T. H., Lungren, M. P. 2020; 3: 115


    Tuberculosis (TB) is the leading cause of preventable death in HIV-positive patients, and yet often remains undiagnosed and untreated. Chest x-ray is often used to assist in diagnosis, yet this presents additional challenges due to atypical radiographic presentation and radiologist shortages in regions where co-infection is most common. We developed a deep learning algorithm to diagnose TB using clinical information and chest x-ray images from 677 HIV-positive patients with suspected TB from two hospitals in South Africa. We then sought to determine whether the algorithm could assist clinicians in the diagnosis of TB in HIV-positive patients as a web-based diagnostic assistant. Use of the algorithm resulted in a modest but statistically significant improvement in clinician accuracy (p=0.002), increasing the mean clinician accuracy from 0.60 (95% CI 0.57, 0.63) without assistance to 0.65 (95% CI 0.60, 0.70) with assistance. However, the accuracy of assisted clinicians was significantly lower (p<0.001) than that of the stand-alone algorithm, which had an accuracy of 0.79 (95% CI 0.77, 0.82) on the same unseen test cases. These results suggest that deep learning assistance may improve clinician accuracy in TB diagnosis using chest x-rays, which would be valuable in settings with a high burden of HIV/TB co-infection. Moreover, the high accuracy of the stand-alone algorithm suggests a potential value particularly in settings with a scarcity of radiological expertise.

    View details for DOI 10.1038/s41746-020-00322-2

    View details for PubMedID 32964138

  • An RNA-centric dissection of host complexes controlling flavivirus infection. Nature microbiology Ooi, Y. S., Majzoub, K., Flynn, R. A., Mata, M. A., Diep, J., Li, J. K., van Buuren, N., Rumachik, N., Johnson, A. G., Puschnik, A. S., Marceau, C. D., Mlera, L., Grabowski, J. M., Kirkegaard, K., Bloom, M. E., Sarnow, P., Bertozzi, C. R., Carette, J. E. 2019


    Flaviviruses, including dengue virus (DENV) and Zika virus (ZIKV), cause severe human disease. Co-opting cellular factors for viral translation and viral genome replication at the endoplasmic reticulum is a shared replication strategy, despite different clinical outcomes. Although the protein products of these viruses have been studied in depth, how the RNA genomes operate inside human cells is poorly understood. Using comprehensive identification of RNA-binding proteins by mass spectrometry (ChIRP-MS), we took an RNA-centric viewpoint of flaviviral infection and identified several hundred proteins associated with both DENV and ZIKV genomic RNA in human cells. Genome-scale knockout screens assigned putative functional relevance to the RNA-protein interactions observed by ChIRP-MS. The endoplasmic-reticulum-localized RNA-binding proteins vigilin and ribosome-binding protein 1 directly bound viral RNA and each acted at distinct stages in the life cycle of flaviviruses. Thus, this versatile strategy can elucidate features of human biology that control the pathogenesis of clinically relevant viruses.

    View details for DOI 10.1038/s41564-019-0518-2

    View details for PubMedID 31384002