Search

BackgroundRight ventricular ejection fraction (RVEF) and end-diastolic volume (RVEDV) are not readily assessed through traditional modalities. Deep-learning enabled 12-lead electrocardiogram analysis (DL-ECG) for estimation of RV size or function is unexplored.MethodsWe trained a DL-ECG model to predict RV dilation (RVEDV>120 mL/m2), RV dysfunction (RVEF<40%), and numerical RVEDV/RVEF from 12-lead ECG paired with reference-standard cardiac MRI (cMRI) volumetric measurements in UK biobank (UKBB; n=42,938). We fine-tuned in a multi-center health system (MSHoriginal; n=3,019) with prospective validation over 4 months (MSHvalidation; n=115). We evaluated performance using area under the receiver operating curve (AUROC) for categorical and mean absolute error (MAE) for continuous measures overall and in key subgroups. We assessed association of RVEF prediction with transplant-free survival with Cox proportional hazards models.ResultsPrevalence of RV dysfunction for UKBB/MSHoriginal/MSHvalidationcohorts was 1.0%/18.0%/15.7%, respectively. RV dysfunction model AUROC for UKBB/MSHoriginal/MSHvalidationcohorts was 0.86/0.81/0.77, respectively. Prevalence of RV dilation for UKBB/MSHoriginal/MSHvalidationcohorts was 1.6%/10.6%/4.3%. RV dilation model AUROC for UKBB/MSHoriginal/MSHvalidationcohorts 0.91/0.81/0.92, respectively. MSHoriginalMAE was RVEF=7.8% and RVEDV=17.6 ml/m2. Performance was similar in key subgroups including with and without left ventricular dysfunction. Over median follow-up of 2.3 years, predicted RVEF was independently associated with composite outcome (HR 1.37 for each 10% decrease, p=0.046).ConclusionsDL-ECG analysis can accurately identify significant RV dysfunction and dilation both overall and in key subgroups. Predicted RVEF is independently associated with clinical outcome.

Of the several thousand diseases that affect humans, only about 500 have treatments approved by the U.S. Food and Drug Administration. Even for those with approved treatments, discovering new drugs can offer alternative options that cause fewer side effects and replace drugs that are ineffective for certain patient groups. However, identifying new therapeutic opportunities for diseases with limited treatment options remains a challenge, as existing algorithms often perform poorly. Here, we leverage recent advances in geometric deep learning and human-centered AI to introduce TXGNN, a model for identifying therapeutic opportunities for diseases with limited treatment options and minimal molecular understanding. TXGNN is a graph neural network pre-trained on a comprehensive knowledge graph of 17,080 clinically-recognized diseases and 7,957 therapeutic candidates. The model can process various therapeutic tasks, such as indication and contraindication prediction, in a unified formulation. Once trained, we show that TXGNN can perform zero-shot inference on new diseases without additional parameters or fine-tuning on ground truth labels. Evaluation of TXGNN shows significant improvements over existing methods, with up to 49.2% higher accuracy in indication tasks and 35.1% higher accuracy in contraindication tasks. TXGNN can also predict therapeutic use for new drugs developed since June 2021. To facilitate interpretation and analysis of the model’s predictions by clinicians, we develop a human-AI explorer for TXGNN and evaluate its usability with medical experts. Finally, we demonstrate that TXGNN’s novel predictions are consistent with off-label prescription decisions made by clinicians in a large healthcare system. These label-efficient and clinician-centered learning systems pave the way for improvements for many therapeutic tasks.

BackgroundSubstantial effort has been directed towards demonstrating use cases of Artificial Intelligence in healthcare, yet limited evidence exists about the long-term viability and consequences of machine learning model deployment.MethodsWe use data from 130,000 patients spread across two large hospital systems to create a simulation framework for emulating real-world deployment of machine learning models. We consider interactions resulting from models being re-trained to improve performance or correct degradation, model deployment with respect to future model development, and simultaneous deployment of multiple models. We simulate possible combinations of deployment conditions, degree of physician adherence to model predictions, and the effectiveness of these predictions.ResultsModel performance shows a severe decline following re-training even when overall model use and effectiveness is relatively low. Further, the deployment of any model erodes the validity of labels for outcomes linked on a pathophysiological basis, thereby resulting in loss of performance for future models. In either case, mitigations applied to offset loss of performance are not fully corrective. Finally, the randomness inherent to a system with multiple deployed models increases exponentially with adherence to model predictions.ConclusionsOur results indicate that model use precipitates interactions that damage the validity of deployed models, and of models developed in the future. Without mechanisms which track the implementation of model predictions, the true effect of model deployment on clinical care may be unmeasurable, and lead to patient data tainted by model use being permanently archived within the Electronic Healthcare Record.

Background and objectives AKI treated with dialysis initiation is a common complication of coronavirus disease 2019 (COVID-19) among hospitalized patients. However, dialysis supplies and personnel are often limited. Design, setting, participants, & measurements Using data from adult patients hospitalized with COVID-19 from five hospitals from the Mount Sinai Health System who were admitted between March 10 and December 26, 2020, we developed and validated several models (logistic regression, Least Absolute Shrinkage and Selection Operator (LASSO), random forest, and eXtreme GradientBoosting [XGBoost; with and without imputation]) for predicting treatment with dialysis or death at various time horizons (1, 3, 5, and 7 days) after hospital admission. Patients admitted to the Mount Sinai Hospital were used for internal validation, whereas the other hospitals formed part of the external validation cohort. Features included demographics, comorbidities, and laboratory and vital signs within 12 hours of hospital admission. Results A total of 6093 patients (2442 in training and 3651 in external validation) were included in the final cohort. Of the different modeling approaches used, XGBoost without imputation had the highest area under the receiver operating characteristic (AUROC) curve on internal validation (range of 0.93–0.98) and area under the precision-recall curve (AUPRC; range of 0.78–0.82) for all time points. XGBoost without imputation also had the highest test parameters on external validation (AUROC range of 0.85–0.87, and AUPRC range of 0.27–0.54) across all time windows. XGBoost without imputation outperformed all models with higher precision and recall (mean difference in AUROC of 0.04; mean difference in AUPRC of 0.15). Features of creatinine, BUN, and red cell distribution width were major drivers of the model’s prediction. Conclusions An XGBoost model without imputation for prediction of a composite outcome of either death or dialysis in patients positive for COVID-19 had the best performance, as compared with standard and other machine learning models. Podcast This article contains a podcast at https://www.asn-online.org/media/podcast/CJASN/2021_07_09_CJN17311120.mp3

BACKGROUND AND OBJECTIVES: Left ventricular ejection fraction is disrupted in patients on maintenance hemodialysis and can be estimated using deep learning models on electrocardiograms. Smaller sample sizes within this population may be mitigated using transfer learning. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS: We identified patients on hemodialysis with transthoracic echocardiograms within 7 days of electrocardiogram using diagnostic/procedure codes. We developed four models: (1) trained from scratch in patients on hemodialysis, (2) pretrained on a publicly available set of natural images (ImageNet), (3) pretrained on all patients not on hemodialysis, and (4) pretrained on patients not on hemodialysis and fine-tuned on patients on hemodialysis. We assessed the ability of the models to classify left ventricular ejection fraction into clinically relevant categories of ≤40%, 41% to ≤50%, and >50%. We compared performance by area under the receiver operating characteristic curve. RESULTS: We extracted 705,075 electrocardiogram:echocardiogram pairs for 158,840 patients not on hemodialysis used for development of models 3 and 4 and n=18,626 electrocardiogram:echocardiogram pairs for 2168 patients on hemodialysis for models 1, 2, and 4. The transfer learning model achieved area under the receiver operating characteristic curves of 0.86, 0.63, and 0.83 in predicting left ventricular ejection fraction categories of ≤40% (n=461), 41%–50% (n=398), and >50% (n=1309), respectively. For the same tasks, model 1 achieved area under the receiver operating characteristic curves of 0.74, 0.55, and 0.71, respectively; model 2 achieved area under the receiver operating characteristic curves of 0.71, 0.55, and 0.69, respectively, and model 3 achieved area under the receiver operating characteristic curves of 0.80, 0.51, and 0.77, respectively. We found that predictions of left ventricular ejection fraction by the transfer learning model were associated with mortality in a Cox regression with an adjusted hazard ratio of 1.29 (95% confidence interval, 1.04 to 1.59). CONCLUSION: A deep learning model can determine left ventricular ejection fraction for patients on hemodialysis following pretraining on electrocardiograms of patients not on hemodialysis. Predictions of low ejection fraction from this model were associated with mortality over a 5-year follow-up period. PODCAST: This article contains a podcast at https://www.asn-online.org/media/podcast/CJASN/2022_06_06_CJN16481221.mp3

Background/Aims: Acute kidney injury (AKI) in critically ill patients is common, and continuous renal replacement therapy (CRRT) is a preferred mode of renal replacement therapy (RRT) in hemodynamically unstable patients. Prediction of clinical outcomes in patients on CRRT is challenging. We utilized several approaches to predict RRT-free survival (RRTFS) in critically ill patients with AKI requiring CRRT. Methods: We used the Medical Information Mart for Intensive Care (MIMIC-III) database to identify patients ≥18 years old with AKI on CRRT, after excluding patients who had ESRD on chronic dialysis, and kidney transplantation. We defined RRTFS as patients who were discharged alive and did not require RRT ≥7 days prior to hospital discharge. We utilized all available biomedical data up to CRRT initiation. We evaluated 7 approaches, including logistic regression (LR), random forest (RF), support vector machine (SVM), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), multilayer perceptron (MLP), and MLP with long short-term memory (MLP + LSTM). We evaluated model performance by using area under the receiver operating characteristic (AUROC) curves. Results: Out of 684 patients with AKI on CRRT, 205 (30%) patients had RRTFS. The median age of patients was 63 years and their median Simplified Acute Physiology Score (SAPS) II was 67 (interquartile range 52–84). The MLP + LSTM showed the highest AUROC (95% CI) of 0.70 (0.67–0.73), followed by MLP 0.59 (0.54–0.64), LR 0.57 (0.52–0.62), SVM 0.51 (0.46–0.56), AdaBoost 0.51 (0.46–0.55), RF 0.44 (0.39–0.48), and XGBoost 0.43 (CI 0.38–0.47). Conclusions: A MLP + LSTM model outperformed other approaches for predicting RRTFS. Performance could be further improved by incorporating other data types.

Background and objectives Sepsis-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, & measurements We 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. Results We 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). Conclusions Utilizing routinely collected laboratory variables, vital signs, and comorbidities, we were able to identify three distinct subphenotypes of sepsis-associated AKI with differing outcomes.

Background Early reports indicate that AKI is common among patients with coronavirus disease 2019 (COVID-19) and associated with worse outcomes. However, AKI among hospitalized patients with COVID-19 in the United States is not well described. Methods 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. We describe the frequency of AKI and dialysis requirement, AKI recovery, and adjusted odds ratios (aORs) with mortality. Results Of 3993 hospitalized patients with COVID-19, AKI occurred in 1835 (46%) patients; 347 (19%) of the patients with AKI required dialysis. The proportions with stages 1, 2, or 3 AKI were 39%, 19%, and 42%, respectively. A total of 976 (24%) patients were admitted to intensive care, and 745 (76%) experienced AKI. Of the 435 patients with AKI and urine studies, 84% had proteinuria, 81% had hematuria, and 60% had leukocyturia. Independent predictors of severe AKI were CKD, men, and higher serum potassium at admission. In-hospital mortality was 50% among patients with AKI versus 8% among those without AKI (aOR, 9.2; 95% confidence interval, 7.5 to 11.3). Of survivors with AKI who were discharged, 35% had not recovered to baseline kidney function by the time of discharge. An additional 28 of 77 (36%) patients who had not recovered kidney function at discharge did so on posthospital follow-up. Conclusions AKI is common among patients hospitalized with COVID-19 and is associated with high mortality. Of all patients with AKI, only 30% survived with recovery of kidney function by the time of discharge.

Despite substantial advances in the study, treatment, and prevention of cardiovascular disease, numerous challenges relating to optimally screening, diagnosing, and managing patients remain. Simultaneous improvements in computing power, data storage, and data analytics have led to the development of new techniques to address these challenges. One powerful tool to this end is machine learning (ML), which aims to algorithmically identify and represent structure within data. Machine learning’s ability to efficiently analyze large and highly complex data sets make it a desirable investigative approach in modern biomedical research. Despite this potential and enormous public and private sector investment, few prospective studies have demonstrated improved clinical outcomes from this technology. This is particularly true in cardiology, despite its emphasis on objective, data-driven results. This threatens to stifle ML’s growth and use in mainstream medicine. We outline the current state of ML in cardiology and outline methods through which impactful and sustainable ML research can occur. Following these steps can ensure ML reaches its potential as a transformative technology in medicine.

PURPOSE OF REVIEW: The universal adoption of electronic health records, improvement in technology, and the availability of continuous monitoring has generated large quantities of healthcare data. Machine learning is increasingly adopted by nephrology researchers to analyze this data in order to improve the care of their patients. RECENT FINDINGS: In this review, we provide a broad overview of the different types of machine learning algorithms currently available and how researchers have applied these methods in nephrology research. Current applications have included prediction of acute kidney disease and chronic kidney disease along with progression of kidney disease. Researchers have demonstrated the ability of machine learning to read kidney biopsy samples, identify patient outcomes from unstructured data, identify subtypes in complex diseases, and discuss the potential benefits on drug discovery. We end with a discussion on the ethics and potential pitfalls of machine learning. SUMMARY: Machine learning provides researchers with the ability to analyze data which was previously inaccessible. While still burgeoning several studies show promising results which will enable researchers to perform larger scale studies and clinicians the ability to provide more personalized care. However, we must ensure that implementation aids providers and does not lead to harm to patients.

Background Acute kidney injury (AKI) is a known complication of COVID-19 and is associated with an increased risk of in-hospital mortality. Unbiased proteomics using biological specimens can lead to improved risk stratification and discover pathophysiological mechanisms. Methods Using measurements of ~4000 plasma proteins in two cohorts of patients hospitalized with COVID-19, we discovered and validated markers of COVID-associated AKI (stage 2 or 3) and long-term kidney dysfunction. In the discovery cohort (N= 437), we identified 413 higher plasma abundances of protein targets and 40 lower plasma abundances of protein targets associated with COVID-AKI (adjusted p Results We demonstrate that COVID-AKI is associated with increased markers of tubular injury (NGAL) and myocardial injury. Using estimated glomerular filtration (eGFR) measurements taken after discharge, we also find that 25 of the 62 AKI-associated proteins are significantly associated with decreased post-discharge eGFR (adjusted p desmocollin-2, trefoil factor 3, transmembrane emp24 domain-containing protein 10, and cystatin-Cindicating tubular dysfunction and injury. Conclusions Using clinical and proteomic data, our results suggest that while both acute and long-term COVID-associated kidney dysfunction are associated with markers of tubular dysfunction, AKI is driven by a largely multifactorial process involving hemodynamic instability and myocardial damage.

Federated learning is a technique for training predictive models without sharing patient-level data, thus maintaining data security while allowing inter-institutional collaboration. We used federated learning to predict acute kidney injury within three and seven days of admission, using demographics, comorbidities, vital signs, and laboratory values, in 4029 adults hospitalized with COVID-19 at five sociodemographically diverse New York City hospitals, between March-October 2020. Prediction performance of federated models was generally higher than single-hospital models and was comparable to pooled-data models. In the first use-case in kidney disease, federated learning improved prediction of a common complication of COVID-19, while preserving data privacy.

BackgroundRapid evaluation of left and right ventricular function using deep learning (DL) on electrocardiograms (ECG) can assist diagnostic workflow. However, DL tools to estimate right ventricular (RV) function do not exist, while ones to estimate left ventricular (LV) function are restricted to quantification of very low LV function only.ObjectivesThis study sought to develop deep learning models capable of comprehensively quantifying left and right ventricular dysfunction from ECG data in a large, diverse population.MethodsA multi-center study was conducted with data from five New York City hospitals; four for internal testing and one serving as external validation. We created novel DL models to classify Left Ventricular Ejection Fraction (LVEF) into categories derived from the latest universal definition of heart failure, estimate LVEF through regression, and predict a composite outcome of either RV systolic dysfunction or RV dilation.ResultsWe obtained echocardiogram LVEF estimates for 147,636 patients paired to 715,890 ECGs. We used Natural Language Processing (NLP) to extract RV size and systolic function information from 404,502 echocardiogram reports paired to 761,510 ECGs for 148,227 patients.For LVEF classification in internal testing, Area Under Curve (AUC) at detection of LVEF50% was 0.94 (95% CI:0.94-0.94), 0.82 (0.81-0.83), and 0.89 (0.89-0.89) respectively. For external validation, these results were 0.94 (0.94-0.95), 0.73 (0.72-0.74) and 0.87 (0.87-0.88). For regression, the mean absolute error was 5.84% (5.82-5.85) for internal testing, and 6.14% (6.13-6.16) in external validation. For prediction of the composite RV outcome, AUC was 0.84 (0.84-0.84) in both internal testing and external validation.ConclusionsDL on ECG data can be utilized to create inexpensive screening, diagnostic, and predictive tools for both LV/RV dysfunction. Such tools may bridge the applicability of ECGs and echocardiography, and enable prioritization of patients for further interventions for either sided failure progressing to biventricular disease.

This study sought to develop DL models capable of comprehensively quantifying left and right ventricular dysfunction from ECG data in a large, diverse population.Rapid evaluation of left and right ventricular function using deep learning (DL) on electrocardiograms (ECGs) can assist diagnostic workflow. However, DL tools to estimate right ventricular (RV) function do not exist, whereas those to estimate left ventricular (LV) function are restricted to quantification of very low LV function only.A multicenter study was conducted with data from 5 New York City hospitals: 4 for internal testing and 1 serving as external validation. We created novel DL models to classify left ventricular ejection fraction (LVEF) into categories derived from the latest universal definition of heart failure, estimate LVEF through regression, and predict a composite outcome of either RV systolic dysfunction or RV dilation.We obtained echocardiogram LVEF estimates for 147,636 patients paired to 715,890 ECGs. We used natural language processing (NLP) to extract RV size and systolic function information from 404,502 echocardiogram reports paired to 761,510 ECGs for 148,227 patients. For LVEF classification in internal testing, area under curve (AUC) at detection of LVEF ≤40%, 40% LVEF ≤50%, and LVEF50% was 0.94 (95% CI: 0.94-0.94), 0.82 (95% CI: 0.81-0.83), and 0.89 (95% CI: 0.89-0.89), respectively. For external validation, these results were 0.94 (95% CI: 0.94-0.95), 0.73 (95% CI: 0.72-0.74), and 0.87 (95% CI: 0.87-0.88). For regression, the mean absolute error was 5.84% (95% CI: 5.82%-5.85%) for internal testing and 6.14% (95% CI: 6.13%-6.16%) in external validation. For prediction of the composite RV outcome, AUC was 0.84 (95% CI: 0.84-0.84) in both internal testing and external validation.DL on ECG data can be used to create inexpensive screening, diagnostic, and predictive tools for both LV and RV dysfunction. Such tools may bridge the applicability of ECGs and echocardiography and enable prioritization of patients for further interventions for either sided failure progressing to biventricular disease.

Traditional Machine Learning (ML) models have had limited success in predicting Coronoavirus-19 (COVID-19) outcomes using Electronic Health Record (EHR) data partially due to not effectively capturing the inter-connectivity patterns between various data modalities. In this work, we propose a novel framework that utilizes relational learning based on a heterogeneous graph model (HGM) for predicting mortality at different time windows in COVID-19 patients within the intensive care unit (ICU). We utilize the EHRs of one of the largest and most diverse patient populations across five hospitals in major health system in New York City. In our model, we use an LSTM for processing time varying patient data and apply our proposed relational learning strategy in the final output layer along with other static features. Here, we replace the traditional softmax layer with a Skip-Gram relational learning strategy to compare the similarity between a patient and outcome embedding representation. We demonstrate that the construction of a HGM can robustly learn the patterns classifying patient representations of outcomes through leveraging patterns within the embeddings of similar patients. Our experimental results show that our relational learning-based HGM model achieves higher area under the receiver operating characteristic curve (auROC) than both comparator models in all prediction time windows, with dramatic improvements to recall.

Acute Kidney Injury (AKI) is among the most common complications of Coronavirus Disease 2019 (COVID-19). Throughout 2020 pandemic, the clinical approach to COVID-19 has progressively improved, but it is unknown how these changes have affected AKI incidence and severity. In this retrospective analysis, we report the trend over time of COVID-19 associated AKI and need of renal replacement therapy in a large health system in New York City, the first COVID-19 epicenter in United States.

ObjectiveThe COVID-19 pandemic is a global public health crisis, with over 33 million cases and 999 000 deaths worldwide. Data are needed regarding the clinical course of hospitalised patients, particularly in the USA. We aimed to compare clinical characteristic of patients with COVID-19 who had in-hospital mortality with those who were discharged alive.DesignDemographic, clinical and outcomes data for patients admitted to five Mount Sinai Health System hospitals with confirmed COVID-19 between 27 February and 2 April 2020 were identified through institutional electronic health records. We performed a retrospective comparative analysis of patients who had in-hospital mortality or were discharged alive.SettingAll patients were admitted to the Mount Sinai Health System, a large quaternary care urban hospital system.ParticipantsParticipants over the age of 18 years were included.Primary outcomesWe investigated in-hospital mortality during the study period.ResultsA total of 2199 patients with COVID-19 were hospitalised during the study period. As of 2 April, 1121 (51%) patients remained hospitalised, and 1078 (49%) completed their hospital course. Of the latter, the overall mortality was 29%, and 36% required intensive care. The median age was 65 years overall and 75 years in those who died. Pre-existing conditions were present in 65% of those who died and 46% of those discharged. In those who died, the admission median lymphocyte percentage was 11.7%, D-dimer was 2.4 μg/mL, C reactive protein was 162 mg/L and procalcitonin was 0.44 ng/mL. In those discharged, the admission median lymphocyte percentage was 16.6%, D-dimer was 0.93 μg/mL, C reactive protein was 79 mg/L and procalcitonin was 0.09 ng/mL.ConclusionsIn our cohort of hospitalised patients, requirement of intensive care and mortality were high. Patients who died typically had more pre-existing conditions and greater perturbations in inflammatory markers as compared with those who were discharged.

BACKGROUND Machine learning models require large datasets that may be siloed across different health care institutions. Machine learning studies that focus on COVID-19 have been limited to single-hospital data, which limits model generalizability. OBJECTIVE We aimed to use federated learning, a machine learning technique that avoids locally aggregating raw clinical data across multiple institutions, to predict mortality in hospitalized patients with COVID-19 within 7 days. METHODS Patient data were collected from the electronic health records of 5 hospitals within the Mount Sinai Health System. Logistic regression with L1 regularization/least absolute shrinkage and selection operator (LASSO) and multilayer perceptron (MLP) models were trained by using local data at each site. We developed a pooled model with combined data from all 5 sites, and a federated model that only shared parameters with a central aggregator. RESULTS The LASSOfederated model outperformed the LASSOlocal model at 3 hospitals, and the MLPfederated model performed better than the MLPlocal model at all 5 hospitals, as determined by the area under the receiver operating characteristic curve. The LASSOpooled model outperformed the LASSOfederated model at all hospitals, and the MLPfederated model outperformed the MLPpooled model at 2 hospitals. CONCLUSIONS The federated learning of COVID-19 electronic health record data shows promise in developing robust predictive models without compromising patient privacy.

Background Machine learning models require large datasets that may be siloed across different health care institutions. Machine learning studies that focus on COVID-19 have been limited to single-hospital data, which limits model generalizability. Objective We aimed to use federated learning, a machine learning technique that avoids locally aggregating raw clinical data across multiple institutions, to predict mortality in hospitalized patients with COVID-19 within 7 days. Methods Patient data were collected from the electronic health records of 5 hospitals within the Mount Sinai Health System. Logistic regression with L1 regularization/least absolute shrinkage and selection operator (LASSO) and multilayer perceptron (MLP) models were trained by using local data at each site. We developed a pooled model with combined data from all 5 sites, and a federated model that only shared parameters with a central aggregator. Results The LASSOfederated model outperformed the LASSOlocal model at 3 hospitals, and the MLPfederated model performed better than the MLPlocal model at all 5 hospitals, as determined by the area under the receiver operating characteristic curve. The LASSOpooled model outperformed the LASSOfederated model at all hospitals, and the MLPfederated model outperformed the MLPpooled model at 2 hospitals. Conclusions The federated learning of COVID-19 electronic health record data shows promise in developing robust predictive models without compromising patient privacy.

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.

Multisystem inflammatory syndrome in children (MIS-C) presents with fever, inflammation and pathology of multiple organs in individuals under 21 years of age in the weeks following severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. Although an autoimmune pathogenesis has been proposed, the genes, pathways and cell types causal to this new disease remain unknown. Here we perform RNA sequencing of blood from patients with MIS-C and controls to find disease-associated genes clustered in a co-expression module annotated to CD56dimCD57+ natural killer (NK) cells and exhausted CD8+ T cells. A similar transcriptome signature is replicated in an independent cohort of Kawasaki disease (KD), the related condition after which MIS-C was initially named. Probing a probabilistic causal network previously constructed from over 1,000 blood transcriptomes both validates the structure of this module and reveals nine key regulators, including TBX21, a central coordinator of exhausted CD8+ T cell differentiation. Together, this unbiased, transcriptome-wide survey implicates downregulation of NK cells and cytotoxic T cell exhaustion in the pathogenesis of MIS-C., Multisystem inflammatory syndrome in children (MIS-C) onsets in COVID-19 patients with manifestations similar to Kawasaki disease (KD). Here the author probe the peripheral blood transcriptome of MIS-C patients to find signatures related to natural killer (NK) cell activation and CD8+ T cell exhaustion that are shared with KD patients.

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.

Machine learning (ML) models require large datasets which may be siloed across different healthcare institutions. Using federated learning, a ML technique that avoids locally aggregating raw clinical data across multiple institutions, we predict mortality within seven days in hospitalized COVID-19 patients. Patient data was collected from Electronic Health Records (EHRs) from five hospitals within the Mount Sinai Health System (MSHS). Logistic Regression with L1 regularization (LASSO) and Multilayer Perceptron (MLP) models were trained using local data at each site, a pooled model with combined data from all five sites, and a federated model that only shared parameters with a central aggregator. Both the federated LASSO and federated MLP models performed better than their local model counterparts at four hospitals. The federated MLP model also outperformed the federated LASSO model at all hospitals. Federated learning shows promise in COVID-19 EHR data to develop robust predictive models without compromising patient privacy.

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.

Urinary tract stones have high heritability indicating a strong genetic component. However, genome-wide association studies (GWAS) have uncovered only a few genome wide significant single nucleotide polymorphisms (SNPs). Polygenic risk scores (PRS) sum cumulative effect of many SNPs and shed light on underlying genetic architecture. Using GWAS summary statistics from 361,141 participants in the United Kingdom Biobank, we generated a PRS and determined association with stone diagnosis in 28,877 participants in the Mount Sinai BioMe Biobank. In BioMe (1,071 cases and 27,806 controls), for every standard deviation increase, we observed a significant increment in adjusted odds ratio of a factor of 1.2 (95% confidence interval 1.13-1.26). In comparison, a risk score comprised of GWAS significant SNPs was not significantly associated with diagnosis. After stratifying individuals into low and high-risk categories on clinical risk factors, there was a significant increment in adjusted odds ratio of 1.3 (1.12-1.6) in the low- and 1.2 (1.1-1.2) in the high-risk group for every standard deviation increment in PRS. In a 14,348-participant validation cohort (Penn Medicine Biobank), every standard deviation increment was associated with a significant adjusted odds ratio of 1.1 (1.03 – 1.2). Thus, a genome-wide PRS is associated with urinary tract stones overall and in the absence of known clinical risk factors and illustrates their complex polygenic architecture.

The degree of myocardial injury, as reflected by troponin elevation, and associated outcomes among U.S. hospitalized patients with coronavirus disease-2019 (COVID-19) are unknown.The purpose of this study was to describe the degree of myocardial injury and associated outcomes in a large hospitalized cohort with laboratory-confirmed COVID-19.Patients with COVID-19 admitted to 1 of 5 Mount Sinai Health System hospitals in New York City between February 27, 2020, and April 12, 2020, with troponin-I (normal value 0.03 ng/ml) measured within 24 h of admission were included (n = 2,736). Demographics, medical histories, admission laboratory results, and outcomes were captured from the hospitals' electronic health records.The median age was 66.4 years, with 59.6% men. Cardiovascular disease (CVD), including coronary artery disease, atrial fibrillation, and heart failure, was more prevalent in patients with higher troponin concentrations, as were hypertension and diabetes. A total of 506 (18.5%) patients died during hospitalization. In all, 985 (36%) patients had elevated troponin concentrations. After adjusting for disease severity and relevant clinical factors, even small amounts of myocardial injury (e.g., troponin I0.03 to 0.09 ng/ml; n = 455; 16.6%) were significantly associated with death (adjusted hazard ratio: 1.75; 95% CI: 1.37 to 2.24; p 0.001) while greater amounts (e.g., troponin I0.09 ng/dl; n = 530; 19.4%) were significantly associated with higher risk (adjusted HR: 3.03; 95% CI: 2.42 to 3.80; p 0.001).Myocardial injury is prevalent among patients hospitalized with COVID-19; however, troponin concentrations were generally present at low levels. Patients with CVD are more likely to have myocardial injury than patients without CVD. Troponin elevation among patients hospitalized with COVID-19 is associated with higher risk of mortality.

ImportancePreliminary reports indicate that acute kidney injury (AKI) is common in coronavirus disease (COVID)-19 patients and is associated with worse outcomes. AKI in hospitalized COVID-19 patients in the United States is not well-described.ObjectiveTo provide information about frequency, outcomes and recovery associated with AKI and dialysis in hospitalized COVID-19 patients.DesignObservational, retrospective study.SettingAdmitted to hospital between February 27 and April 15, 2020.ParticipantsPatients aged ≥18 years with laboratory confirmed COVID-19ExposuresAKI (peak serum creatinine increase of 0.3 mg/dL or 50% above baseline).Main Outcomes and MeasuresFrequency of AKI and dialysis requirement, AKI recovery, and adjusted odds ratios (aOR) with mortality. We also trained and tested a machine learning model for predicting dialysis requirement with independent validation.ResultsA total of 3,235 hospitalized patients were diagnosed with COVID-19. AKI occurred in 1406 (46%) patients overall and 280 (20%) with AKI required renal replacement therapy. The incidence of AKI (admission plus new cases) in patients admitted to the intensive care unit was 68% (553 of 815). In the entire cohort, the proportion with stages 1, 2, and 3 AKI were 35%, 20%, 45%, respectively. In those needing intensive care, the respective proportions were 20%, 17%, 63%, and 34% received acute renal replacement therapy. Independent predictors of severe AKI were chronic kidney disease, systolic blood pressure, and potassium at baseline. In-hospital mortality in patients with AKI was 41% overall and 52% in intensive care. The aOR for mortality associated with AKI was 9.6 (95% CI 7.4-12.3) overall and 20.9 (95% CI 11.7-37.3) in patients receiving intensive care. 56% of patients with AKI who were discharged alive recovered kidney function back to baseline. The area under the curve (AUC) for the machine learned predictive model using baseline features for dialysis requirement was 0.79 in a validation test.Conclusions and RelevanceAKI is common in patients hospitalized with COVID-19, associated with worse mortality, and the majority of patients that survive do not recover kidney function. A machine-learned model using admission features had good performance for dialysis prediction and could be used for resource allocation.Key PointsQuestionWhat is incidence and outcomes of acute kidney injury (AKI) in patients hospitalized with COVID-19?FindingsIn this observational study of 3,235 hospitalized patients with COVID-19 in New York City, AKI occurred in 46% of patients and 20% of those patients required dialysis. AKI was associated with increased mortality. 44% of patients discharged alive had residual acute kidney disease. A machine learned predictive model using baseline features for dialysis requirement had an AUC Of 0.79.MeaningAKI was common in patients with COVID-19, associated with increased mortality, and nearly half of patients had acute kidney disease on discharge.

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.