COVID-19 Mortality Prediction From Deep Learning in a Large Multistate Electronic Health Record and Laboratory Information System Data Set: Algorithm Development and Validation.

BACKGROUND: COVID-19 is caused by the SARS-CoV-2 virus and has strikingly heterogeneous clinical manifestations, with most individuals contracting mild disease but a substantial minority experiencing fulminant cardiopulmonary symptoms or death. The clinical covariates and the laboratory tests performed on a patient provide robust statistics to guide clinical treatment. Deep learning approaches on a data set of this nature enable patient stratification and provide methods to guide clinical treatment. OBJECTIVE: Here, we report on the development and prospective validation of a state-of-the-art machine learning model to provide mortality prediction shortly after confirmation of SARS-CoV-2 infection in the Mayo Clinic patient population. METHODS: We retrospectively constructed one of the largest reported and most geographically diverse laboratory information system and electronic health record of COVID-19 data sets in the published literature, which included 11,807 patients residing in 41 states of the United States of America and treated at medical sites across 5 states in 3 time zones. Traditional machine learning models were evaluated independently as well as in a stacked learner approach by using AutoGluon, and various recurrent neural network architectures were considered. The traditional machine learning models were implemented using the AutoGluon-Tabular framework, whereas the recurrent neural networks utilized the TensorFlow Keras framework. We trained these models to operate solely using routine laboratory measurements and clinical covariates available within 72 hours of a patient's first positive COVID-19 nucleic acid test result. RESULTS: The GRU-D recurrent neural network achieved peak cross-validation performance with 0.938 (SE 0.004) as the area under the receiver operating characteristic (AUROC) curve. This model retained strong performance by reducing the follow-up time to 12 hours (0.916 [SE 0.005] AUROC), and the leave-one-out feature importance analysis indicated that the most independently valuable features were age, Charlson comorbidity index, minimum oxygen saturation, fibrinogen level, and serum iron level. In the prospective testing cohort, this model provided an AUROC of 0.901 and a statistically significant difference in survival (P<.001, hazard ratio for those predicted to survive, 95% CI 0.043-0.106). CONCLUSIONS: Our deep learning approach using GRU-D provides an alert system to flag mortality for COVID-19-positive patients by using clinical covariates and laboratory values within a 72-hour window after the first positive nucleic acid test result.

Multiplex testing for the screening of lysosomal storage disease in urine: Sulfatides and glycosaminoglycan profiles in 40 cases of sulfatiduria.

PURPOSE: To describe an efficient and effective multiplex screening strategy for sulfatide degradation disorders and mucolipidosis type II/III (MLII/III) using 3 mL of urine. METHODS: Glycosaminoglycans were analyzed by liquid chromatography-tandem mass spectrometry. Matrix assisted laser desorption/ionization-time of flight tandem mass spectrometry was used to identify free oligosaccharides and identify 22 ceramide trihexosides and 23 sulfatides, which are integrated by 670 calculated ratios. Collaborative Laboratory Integrated Reports (CLIR; https://clir.mayo.edu) was used for post-analytical interpretation of the complex metabolite profile and to aid in the differential diagnosis of abnormal results. RESULTS: Multiplex analysis was performed on 25 sulfatiduria case samples and compiled with retrospective data from an additional 15 cases revealing unique patterns of biomarkers for each disorder of sulfatide degradation (MLD, MSD, and Saposin B deficiency) and for MLII/III, thus allowing the formulation of a novel algorithm for the biochemical diagnosis of these disorders. CONCLUSIONS: Comprehensive and integrated urine screening could be very effective in the initial workup of patients suspected of having a lysosomal disorder as it covers disorders of sulfatide degradation and narrows down the differential diagnosis in patients with elevated glycosaminoglycans.

Diagnosing Lysosomal Storage Disorders: The GM2 Gangliosidoses.

The GM2 gangliosidoses are a group of autosomal recessive lysosomal storage disorders caused by defective ß-hexosaminidase. There are three clinical conditions in this group: Tay-Sachs disease (TSD), Sandhoff disease (SD), and hexosaminidase activator deficiency. The three conditions are clinically indistinguishable. TSD and SD have been identified with infantile, juvenile, and adult onset forms. The activator deficiency is only known to present with infantile onset. Diagnosis of TSD and SD is based on decreased hexosaminidase activity and a change in the percentage of activity between isoforms. There are no biochemical tests currently available for activator deficiency. This unit provides a detailed procedure for identifying TSD and SD in affected individuals and carriers from leukocyte samples, the most robust sample type available.