Background COVID-19 has infected millions of people worldwide and is responsible for several hundred thousand fatalities. The COVID-19 pandemic has necessitated thoughtful resource allocation and early identification of high-risk patients. However, effective methods to meet these needs are lacking. Objective The aims of this study were to analyze the electronic health records (EHRs) of patients who tested positive for COVID-19 and were admitted to hospitals in the Mount Sinai Health System in New York City; to develop machine learning models for making predictions about the hospital course of the patients over clinically meaningful time horizons based on patient characteristics at admission; and to assess the performance of these models at multiple hospitals and time points. Methods We used Extreme Gradient Boosting (XGBoost) and baseline comparator models to predict in-hospital mortality and critical events at time windows of 3, 5, 7, and 10 days from admission. Our study population included harmonized EHR data from five hospitals in New York City for 4098 COVID-19–positive patients admitted from March 15 to May 22, 2020. The models were first trained on patients from a single hospital (n=1514) before or on May 1, externally validated on patients from four other hospitals (n=2201) before or on May 1, and prospectively validated on all patients after May 1 (n=383). Finally, we established model interpretability to identify and rank variables that drive model predictions. Results Upon cross-validation, the XGBoost classifier outperformed baseline models, with an area under the receiver operating characteristic curve (AUC-ROC) for mortality of 0.89 at 3 days, 0.85 at 5 and 7 days, and 0.84 at 10 days. XGBoost also performed well for critical event prediction, with an AUC-ROC of 0.80 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. In external validation, XGBoost achieved an AUC-ROC of 0.88 at 3 days, 0.86 at 5 days, 0.86 at 7 days, and 0.84 at 10 days for mortality prediction. Similarly, the unimputed XGBoost model achieved an AUC-ROC of 0.78 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. Trends in performance on prospective validation sets were similar. At 7 days, acute kidney injury on admission, elevated LDH, tachypnea, and hyperglycemia were the strongest drivers of critical event prediction, while higher age, anion gap, and C-reactive protein were the strongest drivers of mortality prediction. Conclusions We externally and prospectively trained and validated machine learning models for mortality and critical events for patients with COVID-19 at different time horizons. These models identified at-risk patients and uncovered underlying relationships that predicted outcomes.

Preliminary reports suggest that the Coronavirus Disease 2019 (COVID− 19) pandemic has led to disproportionate morbidity and mortality among historically disadvantaged populations. We investigate the racial and socioeconomic associations of COVID− 19 hospitalization among 418,794 participants of the UK Biobank, of whom 549 (0.13%) had been hospitalized. Both Black participants (odds ratio 3.7; 95%CI 2.5–5.3) and Asian participants (odds ratio 2.2; 95%CI 1.5–3.2) were at substantially increased risk as compared to White participants. We further observed a striking gradient in COVID− 19 hospitalization rates according to the Townsend Deprivation Index − a composite measure of socioeconomic deprivation − and household income. Adjusting for socioeconomic factors and cardiorespiratory comorbidities led to only modest attenuation of the increased risk in Black participants, adjusted odds ratio 2.4 (95%CI 1.5–3.7). These observations confirm and extend earlier preliminary and lay press reports of higher morbidity in non-White individuals in the context of a large population of participants in a national biobank. The extent to which this increased risk relates to variation in pre-existing comorbidities, differences in testing or hospitalization patterns, or additional disparities in social determinants of health warrants further study.

The strongest genetic risk factor for Alzheimer's disease (AD) is the Apolipoprotein E type 4 allele (ApoE ε4). The interaction between sex and ApoE ε4 carrier status on AD risk remains an area of intense investigation. We hypothesized that sex modulates the relationship between ApoE ε4 carrier status and brain tau deposition (a quantitative endophenotype in AD) in individuals with mild cognitive impairment (MCI). Methods : Preprocessed 18 F-AV-1451 tau and 18 F-AV-45 amyloid PET images, T1-weighted structural magnetic resonance imaging (MRI) scans, demographic information, and cerebrospinal fluid (CSF) total tau (t-tau) and phosphorylated tau (p-tau) measurements from 108 MCI subjects in the Alzheimer's Disease Neuroimaging Initiative (ADNI) database were included. After downloading pre-processed images from ADNI, an iterative reblurred Van Cittertiteration partial volume correction (PVC) method was applied to all PET images. MRIs were used for PET spatial normalization. Regions of interest (ROIs) were defined in standard space, and standardized uptake value ratio (SUVR) images relative to cerebellum were computed. ApoE ε4 by sex interaction analyses on 18 F-AV-1451 and CSF tau (t-tau, p-tau) were assessed using generalized linear models. The association between 18 F-AV-1451 SUVR and CSF tau (t-tau, p-tau) was assessed. Results : After applying PVC and controlling for age, education level and global cortical 18 F-AV-45 SUVR, we found that the entorhinal cortex, amygdala, parahippocampal gyrus, posterior cingulate, and occipital ROIs exhibited a significant ApoE ε4 by sex interaction effect (false discovery rate P < 0.1) among MCI individuals. We also found a significant ApoE ε4 by sex interaction effect on CSF t-tau and p-tau. 18 F-AV-1451 SUVR in the 5 ROIs with ApoE ε4 by sex interaction was significantly correlated with CSF p-tau and t-tau. Conclusions : Our findings suggest that women are more susceptible to ApoE ε4-associated accumulation of neurofibrillary tangles in MCI compared to males. Both CSF tau (p-tau, t-tau) and brain tau PET are robust quantitative biomarkers for studying ApoE ε4 by sex effects on brain tau deposition in MCI participants.

85Coronavirus 2019 , caused by the SARS-CoV-2 virus, has become the 86 deadliest pandemic in modern history, reaching nearly every country worldwide and 87 overwhelming healthcare institutions. As of April 20, there have been more than 2.4 88 million confirmed cases with over 160,000 deaths. Extreme case surges coupled with 89 challenges in forecasting the clinical course of affected patients have necessitated 90 thoughtful resource allocation and early identification of high-risk patients. However, 91 136 (11.1) 158 (8.6) Diabetes (%) 313 (25.5) 466 (25.5) Asthma (%) 115 (9.4) 132 (7.2) Chronic Obstructive Pulmonary Disease (%) 65 (5.3) 103 (5.6) Cancer (%) 112 (9.1) 94 (5.1) Vital Signs at Hospital Admission, Median (IQR) Heart Rate (bpm) 89 (78 -100) 89 (78 -100) Pulse Oximetry (%) 96 (94 -98) 96 (94 -98) Respiration Rate (breaths / minute) 20 (18 -20) 18 (18 -20) Temperature (F) 98.7 (98.1 -99.9) 97.9 (98.6 -99.5) Systolic Blood Pressure (mmHg) 124 (112 -138) 127 (112 -142) Diastolic Blood Pressure (mmHg) 69 (61 -78) 72 (65 -81) Weight (kg) 80.9 (68.9 -95.3) 78.9 (68.04 -91.7) Admission Laboratory Parameters, Median (IQR) Metabolic markers Sodium (mEq/L) 137 (135 -140) 138 (135 -141) Potassium (mEq/L) 4 (3.6 -4.5) 4.2 (3.9 -4.7) Creatinine (mg/dL) 0.9 (0.7 -1.4) 1.0 (0.8 -1.6) Lactate (mg/dL) 1.7 (1.3 -2.

Background and objectivesSepsis-associated AKI is a heterogeneous clinical entity. We aimed to agnostically identify sepsis-associated AKI subphenotypes using deep learning on routinely collected data in electronic health records.Design, setting, participants, & measurementsWe used the Medical Information Mart for Intensive Care III database, which consists of electronic health record data from intensive care units in a tertiary care hospital in the United States. We included patients ≥18 years with sepsis who developed AKI within 48 hours of intensive care unit admission. We then used deep learning to utilize all available vital signs, laboratory measurements, and comorbidities to identify subphenotypes. Outcomes were mortality 28 days after AKI and dialysis requirement.ResultsWe identified 4001 patients with sepsis-associated AKI. We utilized 2546 combined features for K-means clustering, identifying three subphenotypes. Subphenotype 1 had 1443 patients, and subphenotype 2 had 1898 patients, whereas subphenotype 3 had 660 patients. Subphenotype 1 had the lowest proportion of liver disease and lowest Simplified Acute Physiology Score II scores compared with subphenotypes 2 and 3. The proportions of patients with CKD were similar between subphenotypes 1 and 3 (15%) but highest in subphenotype 2 (21%). Subphenotype 1 had lower median bilirubin levels, aspartate aminotransferase, and alanine aminotransferase compared with subphenotypes 2 and 3. Patients in subphenotype 1 also had lower median lactate, lactate dehydrogenase, and white blood cell count than patients in subphenotypes 2 and 3. Subphenotype 1 also had lower creatinine and BUN than subphenotypes 2 and 3. Dialysis requirement was lowest in subphenotype 1 (4% versus 7% [subphenotype 2] versus 26% [subphenotype 3]). The mortality 28 days after AKI was lowest in subphenotype 1 (23% versus 35% [subphenotype 2] versus 49% [subphenotype 3]). After adjustment, the adjusted odds ratio for mortality for subphenotype 3, with subphenotype 1 as a reference, was 1.9 (95% confidence interval, 1.5 to 2.4).ConclusionsUtilizing routinely collected laboratory variables, vital signs, and comorbidities, we were able to identify three distinct subphenotypes of sepsis-associated AKI with differing outcomes.

While the ApoE ε4 allele is a known risk factor for mild cognitive impairment (MCI) and Alzheimer's disease, brain region specific effects remain elusive. In this study, we investigate whether the ApoE ε4 allele exhibits brain region specific effects in longitudinal glucose uptake among patients with MCI from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Preprocessed FDG PET images, MRIs, and demographic information were downloaded from the ADNI database. An iterative reblurred Van Cittertiteration method was used for partial volume correction (PVC) on all PET images. Structural MRIs were used for PET spatial normalization and region of interest (ROI) definition in standard space. Longitudinal changes in ROI FDG standardized uptake value ratio (SUVR) relative to cerebellum in 24 ApoE ε4 carriers and 24 age-matched ApoE ε4 non-carriers were measured for up to 84-months (median 72 months, SD = 11.2 months) and compared using a generalized linear mixed effects model controlling for gender, education, baseline age, and follow-up period. Additionally, voxelwise analysis was performed by implementing a paired t -test comparing matched baseline and 72 month FDG SUVR images in ApoE carriers and non-carriers separately. Results with PVC were compared with ones from non-PVC based analysis. After applying PVC, the superior fontal, parietal, lateral temporal, medial temporal, caudate, thalamus, and post-cingulate, and amygdala regions had greater longitudinal decreases in FDG uptake in ApoE ε4 carriers with MCI compared to non-carriers with MCI. Similar forebrain and limbic clusters were found through voxelwise analysis. Compared to the PVC based analysis, fewer significant ApoE-associated regions and clusters were found in the non-PVC based PET analysis. Our findings suggest that the ApoE ε4 genotype is associated with a longitudinal decline in glucose uptake in 8 forebrain and limbic brain regions in the context of MCI. In conclusion, this 84-months longitudinal FDG PET study demonstrates a novel ApoE ε4-associated brain-region specific glucose metabolism pattern in patients with MCI. Partial volume correction improved FDG PET quantification.

Systemic lupus erythematous (SLE) is a heterogeneous autoimmune disease in which outcomes vary among different racial groups. Here, we aim to identify SLE subgroups within a multiethnic cohort using an unsupervised clustering approach based on the American College of Rheumatology (ACR) classification criteria. We identify three patient clusters that vary according to disease severity. Methylation association analysis identifies a set of 256 differentially methylated CpGs across clusters, including 101 CpGs in genes in the Type I Interferon pathway, and we validate these associations in an external cohort. A cis-methylation quantitative trait loci analysis identifies 744 significant CpG-SNP pairs. The methylation signature is enriched for ethnic-associated CpGs suggesting that genetic and non-genetic factors may drive outcomes and ethnic-associated methylation differences. Our computational approach highlights molecular differences associated with clusters rather than single outcome measures. This work demonstrates the utility of applying integrative methods to address clinical heterogeneity in multifactorial multi-ethnic disease settings.

No abstract