Deep learning and the electrocardiogram: review of the current state-of-the-art.

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 and People Living With Human Immunodeficiency Virus: Outcomes for Hospitalized Patients in New York City.

BACKGROUND: There are limited data regarding the clinical impact of coronavirus disease 2019 (COVID-19) on people living with human immunodeficiency virus (PLWH). In this study, we compared outcomes for PLWH with COVID-19 to a matched comparison group. METHODS: We identified 88 PLWH hospitalized with laboratory-confirmed COVID-19 in our hospital system in New York City between 12 March and 23 April 2020. We collected data on baseline clinical characteristics, laboratory values, HIV status, treatment, and outcomes from this group and matched comparators (1 PLWH to up to 5 patients by age, sex, race/ethnicity, and calendar week of infection). We compared clinical characteristics and outcomes (death, mechanical ventilation, hospital discharge) for these groups, as well as cumulative incidence of death by HIV status. RESULTS: Patients did not differ significantly by HIV status by age, sex, or race/ethnicity due to the matching algorithm. PLWH hospitalized with COVID-19 had high proportions of HIV virologic control on antiretroviral therapy. PLWH had greater proportions of smoking (P < .001) and comorbid illness than uninfected comparators. There was no difference in COVID-19 severity on admission by HIV status (P = .15). Poor outcomes for hospitalized PLWH were frequent but similar to proportions in comparators; 18% required mechanical ventilation and 21% died during follow-up (compared with 23% and 20%, respectively). There was similar cumulative incidence of death over time by HIV status (P = .94). CONCLUSIONS: We found no differences in adverse outcomes associated with HIV infection for hospitalized COVID-19 patients compared with a demographically similar patient group.

Characterization of Patients Who Return to Hospital Following Discharge from Hospitalization for COVID-19.

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.

Machine Learning to Predict Mortality and Critical Events in a Cohort of Patients With COVID-19 in New York City: Model Development and Validation.

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.

Sleep in the Natural Environment: A Pilot Study.

Sleep quality has been directly linked to cognitive function, quality of life, and a variety of serious diseases across many clinical domains. Standard methods for assessing sleep involve overnight studies in hospital settings, which are uncomfortable, expensive, not representative of real sleep, and difficult to conduct on a large scale. Recently, numerous commercial digital devices have been developed that record physiological data, such as movement, heart rate, and respiratory rate, which can act as a proxy for sleep quality in lieu of standard electroencephalogram recording equipment. The sleep-related output metrics from these devices include sleep staging and total sleep duration and are derived via proprietary algorithms that utilize a variety of these physiological recordings. Each device company makes different claims of accuracy and measures different features of sleep quality, and it is still unknown how well these devices correlate with one another and perform in a research setting. In this pilot study of 21 participants, we investigated whether sleep metric outputs from self-reported sleep metrics (SRSMs) and four sensors, specifically Fitbit Surge (a smart watch), Withings Aura (a sensor pad that is placed under a mattress), Hexoskin (a smart shirt), and Oura Ring (a smart ring), were related to known cognitive and psychological metrics, including the n-back test and Pittsburgh Sleep Quality Index (PSQI). We analyzed correlation between multiple device-related sleep metrics. Furthermore, we investigated relationships between these sleep metrics and cognitive scores across different timepoints and SRSM through univariate linear regressions. We found that correlations for sleep metrics between the devices across the sleep cycle were almost uniformly low, but still significant (P < 0.05). For cognitive scores, we found the Withings latency was statistically significant for afternoon and evening timepoints at P = 0.016 and P = 0.013. We did not find any significant associations between SRSMs and PSQI or cognitive scores. Additionally, Oura Ring's total sleep duration and efficiency in relation to the PSQI measure was statistically significant at P = 0.004 and P = 0.033, respectively. These findings can hopefully be used to guide future sensor-based sleep research.

Development of a machine learning model using electrocardiogram signals to improve acute pulmonary embolism screening.

Aims: Clinical scoring systems for pulmonary embolism (PE) screening have low specificity and contribute to computed tomography pulmonary angiogram (CTPA) overuse. We assessed whether deep learning models using an existing and routinely collected data modality, electrocardiogram (ECG) waveforms, can increase specificity for PE detection. Methods and results: We create a retrospective cohort of 21 183 patients at moderate- to high suspicion of PE and associate 23 793 CTPAs (10.0% PE-positive) with 320 746 ECGs and encounter-level clinical data (demographics, comorbidities, vital signs, and labs). We develop three machine learning models to predict PE likelihood: an ECG model using only ECG waveform data, an EHR model using tabular clinical data, and a Fusion model integrating clinical data and an embedded representation of the ECG waveform. We find that a Fusion model [area under the receiver-operating characteristic curve (AUROC) 0.81 ± 0.01] outperforms both the ECG model (AUROC 0.59 ± 0.01) and EHR model (AUROC 0.65 ± 0.01). On a sample of 100 patients from the test set, the Fusion model also achieves greater specificity (0.18) and performance (AUROC 0.84 ± 0.01) than four commonly evaluated clinical scores: Wells' Criteria, Revised Geneva Score, Pulmonary Embolism Rule-Out Criteria, and 4-Level Pulmonary Embolism Clinical Probability Score (AUROC 0.50-0.58, specificity 0.00-0.05). The model is superior to these scores on feature sensitivity analyses (AUROC 0.66-0.84) and achieves comparable performance across sex (AUROC 0.81) and racial/ethnic (AUROC 0.77-0.84) subgroups. Conclusion: Synergistic deep learning of ECG waveforms with traditional clinical variables can increase the specificity of PE detection in patients at least at moderate suspicion for PE.

Relational Learning Improves Prediction of Mortality in COVID-19 in the Intensive Care Unit.

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.

Phe2vec: Automated disease phenotyping based on unsupervised embeddings from electronic health records.

Robust phenotyping of patients from electronic health records (EHRs) at scale is a challenge in clinical informatics. Here, we introduce Phe2vec, an automated framework for disease phenotyping from EHRs based on unsupervised learning and assess its effectiveness against standard rule-based algorithms from Phenotype KnowledgeBase (PheKB). Phe2vec is based on pre-computing embeddings of medical concepts and patients' clinical history. Disease phenotypes are then derived from a seed concept and its neighbors in the embedding space. Patients are linked to a disease if their embedded representation is close to the disease phenotype. Comparing Phe2vec and PheKB cohorts head-to-head using chart review, Phe2vec performed on par or better in nine out of ten diseases. Differently from other approaches, it can scale to any condition and was validated against widely adopted expert-based standards. Phe2vec aims to optimize clinical informatics research by augmenting current frameworks to characterize patients by condition and derive reliable disease cohorts.

Association of SARS-CoV-2 viral load at admission with in-hospital acute kidney injury: A retrospective cohort study.

BACKGROUND: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and the associated Coronavirus Disease 2019 (COVID-19) is a public health emergency. Acute kidney injury (AKI) is a common complication in hospitalized patients with COVID-19 although mechanisms underlying AKI are yet unclear. There may be a direct effect of SARS-CoV-2 virus on the kidney; however, there is currently no data linking SARS-CoV-2 viral load (VL) to AKI. We explored the association of SARS-CoV-2 VL at admission to AKI in a large diverse cohort of hospitalized patients with COVID-19. METHODS AND FINDINGS: We included patients hospitalized between March 13th and May 19th, 2020 with SARS-CoV-2 in a large academic healthcare system in New York City (N = 1,049) with available VL at admission quantified by real-time RT-PCR. We extracted clinical and outcome data from our institutional electronic health records (EHRs). AKI was defined by KDIGO guidelines. We fit a Fine-Gray competing risks model (with death as a competing risk) using demographics, comorbidities, admission severity scores, and log10 transformed VL as covariates and generated adjusted hazard ratios (aHR) and 95% Confidence Intervals (CIs). VL was associated with an increased risk of AKI (aHR = 1.04, 95% CI: 1.01-1.08, p = 0.02) with a 4% increased hazard for each log10 VL change. Patients with a viral load in the top 50th percentile had an increased adjusted hazard of 1.27 (95% CI: 1.02-1.58, p = 0.03) for AKI as compared to those in the bottom 50th percentile. CONCLUSIONS: VL is weakly but significantly associated with in-hospital AKI after adjusting for confounders. This may indicate the role of VL in COVID-19 associated AKI. This data may inform future studies to discover the mechanistic basis of COVID-19 associated AKI.

Contrastive learning improves critical event prediction in COVID-19 patients.

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 dataset 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 dataset and a restricted dataset. CL models consistently outperform CEL models, with differences ranging from 0.04 to 0.15 for area under the precision and recall curve (AUPRC) and 0.05 to 0.1 for area under the receiver-operating characteristic curve (AUROC).

Derivation and Validation of Genome-Wide Polygenic Score for Ischemic Heart Failure.

Background Despite advances in cardiovascular disease and risk factor management, mortality from ischemic heart failure (HF) in patients with coronary artery disease (CAD) remains high. Given the partial role of genetics in HF and lack of reliable risk stratification tools, we developed and validated a polygenic risk score for HF in patients with CAD, which we term HF-PRS. Methods and Results Using summary statistics from a recent genome-wide association study for HF, we developed candidate PRSs in the Mount Sinai BioMe CAD patient cohort (N=6274) by using the pruning and thresholding method and LDPred. We validated the best score in the Penn Medicine BioBank (N=7250) and performed a subgroup analysis in a high-risk cohort who had undergone coronary catheterization. We observed a significant association between HF-PRS score and ischemic HF even after adjusting for evidence of obstructive CAD in patients of European ancestry in both BioMe (odds ratio [OR], 1.14 per SD; 95% CI, 1.05-1.24; P=0.003) and Penn Medicine BioBank (OR, 1.07 per SD; 95% CI, 1.01-1.13; P=0.016). In European patients with CAD in Penn Medicine BioBank who had undergone coronary catheterization, individuals in the top 10th percentile of PRS had a 2-fold increased odds of ischemic HF (OR, 2.0; 95% CI, 1.1-3.7; P=0.02) compared with the bottom 10th percentile. Conclusions A PRS for HF enables risk stratification in patients with CAD. Future prospective studies aimed at demonstrating clinical utility are warranted for adoption in the patient setting.

Federated Learning of Electronic Health Records to Improve Mortality Prediction in Hospitalized Patients With COVID-19: Machine Learning Approach.

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.

Exploring the Potential for Collaborative Use of an App-Based Platform for n-of-1 Trials Among Healthcare Professionals That Treat Patients With Insomnia.

BACKGROUND: N-of-1 trials are single patient, multiple crossover, and comparative effectiveness experiments. Despite their rating as "level 1" evidence, they are not routinely used in clinical medicine to evaluate the effectiveness of treatments. OBJECTIVE: We explored the potential for implementing a mobile app-based n-of-1 trial platform for collaborative use by clinicians and patients to support data-driven decisions around the treatment of insomnia. METHODS: A survey assessing awareness and utilization of n-of-1 trials was administered to healthcare professionals that frequently treat patients with insomnia at the Icahn School of Medicine at Mount Sinai in New York City. RESULTS: A total of 45 healthcare professionals completed the survey and were included in the analysis. We found that 64% (29/45) of healthcare professionals surveyed had not heard of n-of-1 trials. After a brief description of these methods, 75% (30/40) of healthcare professionals reported that they are likely or highly likely to use an app-based n-of-1 trial at least once in the next year if the service were free and easy to offer to their patients. CONCLUSIONS: An app-based n-of-1 trials platform might be a valuable tool for clinicians and patients to identify the best treatments for insomnia. The lack of awareness of n-of-1 trials coupled with receptivity to their use suggests that educational interventions may address a current barrier to wider utilization of n-of-1 trials.

Immune complement and coagulation dysfunction in adverse outcomes of SARS-CoV-2 infection.

Understanding the pathophysiology of SARS-CoV-2 infection is critical for therapeutic and public health strategies. Viral-host interactions can guide discovery of disease regulators, and protein structure function analysis points to several immune pathways, including complement and coagulation, as targets of coronaviruses. To determine whether conditions associated with dysregulated complement or coagulation systems impact disease, we performed a retrospective observational study and found that history of macular degeneration (a proxy for complement-activation disorders) and history of coagulation disorders (thrombocytopenia, thrombosis and hemorrhage) are risk factors for SARS-CoV-2-associated morbidity and mortality-effects that are independent of age, sex or history of smoking. Transcriptional profiling of nasopharyngeal swabs demonstrated that in addition to type-I interferon and interleukin-6-dependent inflammatory responses, infection results in robust engagement of the complement and coagulation pathways. Finally, in a candidate-driven genetic association study of severe SARS-CoV-2 disease, we identified putative complement and coagulation-associated loci including missense, eQTL and sQTL variants of critical complement and coagulation regulators. In addition to providing evidence that complement function modulates SARS-CoV-2 infection outcome, the data point to putative transcriptional genetic markers of susceptibility. The results highlight the value of using a multimodal analytical approach to reveal determinants and predictors of immunity, susceptibility and clinical outcome associated with infection.

Identification of Immune complement function as a determinant of adverse SARS-CoV-2 infection outcome.

Understanding the pathophysiology of SARS-CoV-2 infection is critical for therapeutics and public health intervention strategies. Viral-host interactions can guide discovery of regulators of disease outcomes, and protein structure function analysis points to several immune pathways, including complement and coagulation, as targets of the coronavirus proteome. To determine if conditions associated with dysregulation of the complement or coagulation systems impact adverse clinical outcomes, we performed a retrospective observational study of 11,116 patients who presented with suspected SARS-CoV-2 infection. We found that history of macular degeneration (a proxy for complement activation disorders) and history of coagulation disorders (thrombocytopenia, thrombosis, and hemorrhage) are risk factors for morbidity and mortality in SARS-CoV-2 infected patients - effects that could not be explained by age, sex, or history of smoking. Further, transcriptional profiling of nasopharyngeal (NP) swabs from 650 control and SARS-CoV-2 infected patients demonstrated that in addition to innate Type-I interferon and IL-6 dependent inflammatory immune responses, infection results in robust engagement and activation of the complement and coagulation pathways. Finally, we conducted a candidate driven genetic association study of severe SARS-CoV-2 disease. Among the findings, our scan identified putative complement and coagulation associated loci including missense, eQTL and sQTL variants of critical regulators of the complement and coagulation cascades. In addition to providing evidence that complement function modulates SARS-CoV-2 infection outcome, the data point to putative transcriptional genetic markers of susceptibility. The results highlight the value of using a multi-modal analytical approach, combining molecular information from virus protein structure-function analysis with clinical informatics, transcriptomics, and genomics to reveal determinants and predictors of immunity, susceptibility, and clinical outcome associated with infection.

Hospitalised COVID-19 patients of the Mount Sinai Health System: a retrospective observational study using the electronic medical records.

OBJECTIVE: To assess association of clinical features on COVID-19 patient outcomes. DESIGN: Retrospective observational study using electronic medical record data. SETTING: Five member hospitals from the Mount Sinai Health System in New York City (NYC). PARTICIPANTS: 28 336 patients tested for SARS-CoV-2 from 24 February 2020 to 15 April 2020, including 6158 laboratory-confirmed COVID-19 cases. MAIN OUTCOMES AND MEASURES: Positive test rates and in-hospital mortality were assessed for different racial groups. Among positive cases admitted to the hospital (N=3273), we estimated HR for both discharge and death across various explanatory variables, including patient demographics, hospital site and unit, smoking status, vital signs, lab results and comorbidities. RESULTS: Hispanics (29%) and African Americans (25%) had disproportionately high positive case rates relative to their representation in the overall NYC population (p<0.05); however, no differences in mortality rates were observed in hospitalised patients based on race. Outcomes differed significantly between hospitals (Gray's T=248.9; p<0.05), reflecting differences in average baseline age and underlying comorbidities. Significant risk factors for mortality included age (HR 1.05, 95% CI 1.04 to 1.06; p=1.15e-32), oxygen saturation (HR 0.985, 95% CI 0.982 to 0.988; p=1.57e-17), care in intensive care unit areas (HR 1.58, 95% CI 1.29 to 1.92; p=7.81e-6) and elevated creatinine (HR 1.75, 95% CI 1.47 to 2.10; p=7.48e-10), white cell count (HR 1.02, 95% CI 1.01 to 1.04; p=8.4e-3) and body mass index (BMI) (HR 1.02, 95% CI 1.00 to 1.03; p=1.09e-2). Deceased patients were more likely to have elevated markers of inflammation. CONCLUSIONS: While race was associated with higher risk of infection, we did not find racial disparities in inpatient mortality suggesting that outcomes in a single tertiary care health system are comparable across races. In addition, we identified key clinical features associated with reduced mortality and discharge. These findings could help to identify which COVID-19 patients are at greatest risk of a severe infection response and predict survival.

Federated Learning of Electronic Health Records Improves Mortality Prediction in Patients Hospitalized with COVID-19.

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.

Machine Learning in Cardiology-Ensuring Clinical Impact Lives Up to the Hype.

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.

Prevalence and Impact of Myocardial Injury in Patients Hospitalized With COVID-19 Infection.

BACKGROUND: 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. OBJECTIVES: 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. METHODS: 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. RESULTS: 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 I >0.03 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 I >0.09 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). CONCLUSIONS: 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.

Prevalence and Impact of Myocardial Injury in Patients Hospitalized with COVID-19 Infection.

BACKGROUND: The degree of myocardial injury, reflected by troponin elevation, and associated outcomes among hospitalized patients with Coronavirus Disease (COVID-19) in the US are unknown. OBJECTIVES: To describe the degree of myocardial injury and associated outcomes in a large hospitalized cohort with laboratory-confirmed COVID-19. METHODS: Patients with COVID-19 admitted to one of five Mount Sinai Health System hospitals in New York City between February 27th and April 12th, 2020 with troponin-I (normal value <0.03ng/mL) measured within 24 hours of admission were included (n=2,736). Demographics, medical history, admission labs, and outcomes were captured from the hospital EHR. RESULTS: 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. Even small amounts of myocardial injury (e.g. troponin I 0.03-0.09ng/mL, n=455, 16.6%) were associated with death (adjusted HR: 1.77, 95% CI 1.39-2.26; P<0.001) while greater amounts (e.g. troponin I>0.09 ng/dL, n=530, 19.4%) were associated with more pronounced risk (adjusted HR 3.23, 95% CI 2.59-4.02). CONCLUSIONS: Myocardial injury is prevalent among patients hospitalized with COVID-19, and is associated with higher risk of mortality. Patients with CVD are more likely to have myocardial injury than patients without CVD. Troponin elevation likely reflects non-ischemic or secondary myocardial injury.