Search

Background Data on patients with coronavirus disease 2019 (COVID-19) who return to hospital after discharge are scarce. Characterization of these patients may inform post-hospitalization care. Objective To describe clinical characteristics of patients with COVID-19 who returned to the emergency department (ED) or required readmission within 14 days of discharge. Design Retrospective cohort study of SARS-COV-2-positive patients with index hospitalization between February 27 and April 12, 2020, with ≥ 14-day follow-up. Significance was defined as P < 0.05 after multiplying P by 125 study-wide comparisons. Participants Hospitalized patients with confirmed SARS-CoV-2 discharged alive from five New York City hospitals. Main Measures Readmission or return to ED following discharge. Results Of 2864 discharged patients, 103 (3.6%) returned for emergency care after a median of 4.5 days, with 56 requiring inpatient readmission. The most common reason for return was respiratory distress (50%). Compared with patients who did not return, there were higher proportions of COPD (6.8% vs 2.9%) and hypertension (36% vs 22.1%) among those who returned. Patients who returned also had a shorter median length of stay (LOS) during index hospitalization (4.5 [2.9,9.1] vs 6.7 [3.5, 11.5] days; Padjusted = 0.006), and were less likely to have required intensive care on index hospitalization (5.8% vs 19%; Padjusted = 0.001). A trend towards association between absence of in-hospital treatment-dose anticoagulation on index admission and return to hospital was also observed (20.9% vs 30.9%, Padjusted = 0.06). On readmission, rates of intensive care and death were 5.8% and 3.6%, respectively. Conclusions Return to hospital after admission for COVID-19 was infrequent within 14 days of discharge. The most common cause for return was respiratory distress. Patients who returned more likely had COPD and hypertension, shorter LOS on index-hospitalization, and lower rates of in-hospital treatment-dose anticoagulation. Future studies should focus on whether these comorbid conditions, longer LOS, and anticoagulation are associated with reduced readmissions. Electronic supplementary material The online version of this article (10.1007/s11606-020-06120-6) contains supplementary material, which is available to authorized users.

Translation of intravenously administered nanomaterials to the clinic is limited due to adverse infusion reactions. While these reactions are infrequent, with up to 10% prone to experiencing infusion reactions, the reactions can be severe and life-threatening. One of the innate immune pathways, the complement activation pathway, plays a significant role in mediating this response. Nanoparticle surface properties are a relevant design feature, as they control the blood proteins the nanoparticles interact with and allow the nanoparticles to evade the immune reaction. PEGylation of nanosurfaces is critical in improving the blood circulation of nanoparticles and reducing opsonization. Our goal was to understand whether modifying the surface architecture by varying the PEG density and architecture can impact the complement response in vitro. We utilized block copolymers of poly(lactic acid)-b-poly(ethylene glycol) prepared with poly(ethylene glycol) macroinitiators of molecular weights 3400 and 5000 Da. Tracking the complement biomarker C5a, we monitored the impact of changing PEGylation of the nanoparticles. We also investigated how the changing PEG length on the nanoparticle surface impacts further strengthening the stealth properties. Lastly, we determined which cytokines change upon blood incubation with nanoparticles in vitro to understand the extent to which inflammation may occur and the crosstalk between the complement and immune responses. Increasing PEGylation reduced the generation of complement-mediated anaphylatoxin C5a in vitro, with 5000 Da PEG more effectively reducing levels of C5a generated compared to 3400 Da PEG. The insights gathered regarding the impact of PEG density and PEG chain length would be critical in developing stealth nanoparticles that do not lead to infusion reactions upon intravenous administration.

Objective: This study aims to assess the correlation of exhaled CO and nicotine dependence with the occurrence of oral mucosal lesions while also taking into consideration socio-demographic, clinical and anthropometrical characteristics of participants. Methods: An observational cross-sectional study was carried out among smokers who visited the tobacco cessation center at Tertiary Care Dental Hospital in Goa, India. An intra-oral soft tissue examination for detecting presence of oral mucosal lesions followed by a questionnaire-based interview for the measurement of exposure, sociodemographic factors, body mass index, cooking habits and nicotine dependence was conducted. The exhaled CO levels were measured with a CO breath analyzer. Statistical analysis was performed using IBM SPSS version 20.0 Descriptive statistics were calculated and multivariable analysis was done to assess the association of different variables with oral mucosal lesions and carbon monoxide levels. p-value ≤ 0.05 was considered as statistically significant. Results: Of the 173 subjects enrolled in the study, 69.36% were without any lesions while 30.63% were diagnosed with some lesion. In the regression analysis, the variables of physical activity (present vs absent OR: 5.808), exhaled CO levels (OR: 1.098) and nicotine dependence (mild vs moderate OR: 6.518) were significant risk factors influencing the presence of oral mucosal lesions. Usage of both cigarettes and bidis by smokers exhibited highest mean exhaled CO values of 19.67±1.506 ppm. Exhaled CO levels were significantly higher in smokers who were overweight (14.96±9.14 ppm), physically inactive (13.98±8.26 ppm), highly nicotine dependent (20.67±8.30) and used coal for cooking (12.55±8.17). Conclusion: A robust correlation between exhaled CO levels, nicotine dependence and incidence of oral mucosal lesions was established. The multifactorial tenacity of exhaled CO which is affected by smoked tobacco as well as variables such as physical activity, BMI, cooking habits and type of smoking habit should be noted.

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.

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.

In the recent decade, deep learning, a subset of artificial intelligence and machine learning, has been used to identify patterns in big healthcare datasets for disease phenotyping, event predictions, and complex decision making. Public datasets for electrocardiograms (ECGs) have existed since the 1980s and have been used for very specific tasks in cardiology, such as arrhythmia, ischemia, and cardiomyopathy detection. Recently, private institutions have begun curating large ECG databases that are orders of magnitude larger than the public databases for ingestion by deep learning models. These efforts have demonstrated not only improved performance and generalizability in these aforementioned tasks but also application to novel clinical scenarios. This review focuses on orienting the clinician towards fundamental tenets of deep learning, state-of-the-art prior to its use for ECG analysis, and current applications of deep learning on ECGs, as well as their limitations and future areas of improvement.

Coronavirus 2019 (COVID-19), caused by the SARS-CoV-2 virus, has become the deadliest pandemic in modern history, reaching nearly every country worldwide and overwhelming healthcare institutions. As of April 20, there have been more than 2.4 million confirmed cases with over 160,000 deaths. Extreme case surges coupled with challenges in forecasting the clinical course of affected patients have necessitated thoughtful resource allocation and early identification of high-risk patients. However, effective methods for achieving this are lacking. In this paper, we use electronic health records from over 3,055 New York City confirmed COVID-19 positive patients across five hospitals in the Mount Sinai Health System and present a decision tree-based machine learning model for predicting in-hospital mortality and critical events. This model is first trained on patients from a single hospital and then externally validated on patients from four other hospitals. We achieve strong performance, notably predicting mortality at 1 week with an AUC-ROC of 0.84. Finally, we establish model interpretability by calculating SHAP scores to identify decisive features, including age, inflammatory markers (procalcitonin and LDH), and coagulation parameters (PT, PTT, D-Dimer). To our knowledge, this is one of the first models with external validation to both predict outcomes in COVID-19 patients with strong validation performance and identify key contributors in outcome prediction that may assist clinicians in making effective patient management decisions.One-Sentence SummaryWe identify clinical features that robustly predict mortality and critical events in a large cohort of COVID-19 positive patients in New York City.

Deep Learning (DL) models typically require large-scale, balanced training data to be robust, generalizable, and effective in the context of healthcare. This has been a major issue for developing DL models for the coronavirus-disease 2019 (COVID-19) pandemic where data are highly class imbalanced. Conventional approaches in DL use cross-entropy loss (CEL) which often suffers from poor margin classification. We show that contrastive loss (CL) improves the performance of CEL especially in imbalanced electronic health records (EHR) data for COVID-19 analyses. We use a diverse EHR data set to predict three outcomes: mortality, intubation, and intensive care unit (ICU) transfer in hospitalized COVID-19 patients over multiple time windows. To compare the performance of CEL and CL, models are tested on the full data set and a restricted data set. CL models consistently outperform CEL models with differences ranging from 0.04 to 0.15 for AUPRC and 0.05 to 0.1 for AUROC., Deep learning models applied on EHR data often utilize cross-entropy loss (CEL) as the primary optimization function. But CEL may not be suitable for real-world scenarios with imbalanced data. We develop a learning framework that incorporates both CEL and contrastive loss (CL) to tackle this issue. Our framework achieves better predictive performance and feature interpretability, particularly for imbalanced data.

Background: Various medications are cleared by the kidneys, therefore patients with impaired renal function, especially dialysis patients are at risk for adverse drug events (ADEs). There are limited studies on ADEs in maintenance dialysis patients. Methods: We utilized a nationally representative database, the Nationwide Emergency Department Sample, from 2008 to 2013, to compare emergency department (ED) visits for dialysis and propensity matched non-dialysis patients. Log binomial regression was used to calculate relative risk of hospital admission and logistic regression to calculate ORs for in-hospital mortality while adjusting for patient and hospital characteristics. Results: While ED visits for ADEs decreased in both groups, they were over 10-fold higher in dialysis patients than non-dialysis patients (65.8–88.5 per 1,000 patients vs. 4.6–5.4 per 1,000 patients respectively, p < 0.001). The top medication category associated with ED visits for ADEs in dialysis patients is agents primarily affecting blood constituents, which has increased. After propensity matching, patient admission was higher in dialysis patients than non-dialysis patients, (88 vs. 76%, p < 0.001). Dialysis was associated with a 3% increase in risk of admission and 3 times the odds of in-hospital mortality (adjusted OR 3, 95% CI 2.7–2.3.3). Conclusions: ED visits for ADEs are substantially higher in dialysis patients than non-dialysis patients. In dialysis patients, ADEs associated with agents primarily affecting blood constituents are on the rise. ED visits for ADEs in dialysis patients have higher inpatient admissions and in-hospital mortality. Further studies are needed to identify and implement measures aimed at reducing ADEs in dialysis patients.