Li Li

TL;DR: The findings indicate that deep learning applied to EHRs can derive patient representations that offer improved clinical predictions, and could provide a machine learning framework for augmenting clinical decision systems.

TL;DR: The authors found that classical T2D features such as obesity, high blood sugar, kidney disease, and eye disease, were limited to subtype 1, whereas other comorbidities such as cancer and neurological diseases were specific to subtypes 2 and 3, respectively.

TL;DR: This retrospective, observational study involved a review of data from electronic health records of patients aged ≥18 years with laboratory-confirmed COVID-19 admitted to the Mount Sinai Health System from February 27 to May 30, 2020 to describe the frequency of AKI and dialysis requirement, AKI recovery, and adjusted odds ratios with mortality.

TL;DR: Novel findings reported here include an endothelial phenotype of ACE2 in selected organs, which correlates with clotting abnormalities and thrombotic microangiopathy, addressing the prominent coagulopathy and neuropsychiatric symptoms.

TL;DR: A fully automated system to reannotate all types of microarrays in GEO periodically by relating every probe identifier to Entrez Gene identifiers, and successfully reannotated 66% gene expression platforms, allowing reuse of 77% of samples across 79 species.