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.

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.

A genetic etiology is identified for one-third of patients with congenital heart disease (CHD), with 8% of cases attributable to coding de novo variants (DNVs). To assess the contribution of noncoding DNVs to CHD, we compared genome sequences from 749 CHD probands and their parents with those from 1,611 unaffected trios. Neural network prediction of noncoding DNV transcriptional impact identified a burden of DNVs in individuals with CHD (n = 2,238 DNVs) compared to controls (n = 4,177; P = 8.7 × 10⁻⁴). Independent analyses of enhancers showed an excess of DNVs in associated genes (27 genes versus 3.7 expected, P = 1 × 10⁻⁵). We observed significant overlap between these transcription-based approaches (odds ratio (OR) = 2.5, 95% confidence interval (CI) 1.1–5.0, P = 5.4 × 10⁻³). CHD DNVs altered transcription levels in 5 of 31 enhancers assayed. Finally, we observed a DNV burden in RNA-binding-protein regulatory sites (OR = 1.13, 95% CI 1.1–1.2, P = 8.8 × 10⁻⁵). Our findings demonstrate an enrichment of potentially disruptive regulatory noncoding DNVs in a fraction of CHD at least as high as that observed for damaging coding DNVs.

All‐solid‐state batteries with conversion‐type cathodes promise to exceed the performance of lithium‐ion batteries due to their high theoretical specific energy and potential safety. However, the reported performance of solid‐state batteries is still unsatisfactory due to poor electronic and ionic conduction in the composite cathodes. Here, in situ formation of active material as well as highly effective ion‐ and electron‐conducting paths via electrochemical decomposition of Li₆PS₅Cl_0.5Br_0.5 (LPSCB)/multiwalled carbon nanotube mixtures during cycling is reported. Effectively, the LPSCB electrolyte forms a multiphase conversion‐type cathode by partial decomposition during the first discharge. Comprehensive characterization, especially operando pressure monitoring, reveals a co‐redox process of two redox‐active elements during cycling. The monolithic LPSCB‐based cell shows stable cycling over 1000 cycles with a very high capacity retention of 94% at high current density (0.885 mA cm⁻², ≈0.7 C) at room temperature and a high areal capacity of 12.56 mAh cm⁻² is achieved.

Perfusing fixatives through the cerebrovascular system is the gold standard approach in animals to prepare brain tissue for spatial biomolecular profiling, circuit tracing, and ultrastructural studies such as connectomics. Translating these discoveries to humans requires examination of postmortem autopsy brain tissue. Yet banked brain tissue is routinely prepared using immersion fixation, which is a significant barrier to optimal preservation of tissue architecture. The challenges involved in adopting perfusion fixation in brain banks and the extent to which it improves histology quality are not well defined. We searched four databases to identify studies that have performed perfusion fixation in human brain tissue and screened the references of the eligible studies to identify further studies. From the included studies, we extracted data about the methods that they used, as well as any data comparing perfusion fixation to immersion fixation. The protocol was preregistered at the Open Science Framework: https://osf.io/cv3ys/ . We screened 4489 abstracts, 214 full-text publications, and identified 35 studies that met our inclusion criteria, which collectively reported on the perfusion fixation of 558 human brains. We identified a wide variety of approaches to perfusion fixation, including perfusion fixation of the brain in situ and ex situ, perfusion fixation through different sets of blood vessels, and perfusion fixation with different washout solutions, fixatives, perfusion pressures, and postfixation tissue processing methods. Through a qualitative synthesis of data comparing the outcomes of perfusion and immersion fixation, we found moderate confidence evidence showing that perfusion fixation results in equal or greater subjective histology quality compared to immersion fixation of relatively large volumes of brain tissue, in an equal or shorter amount of time. This manuscript serves as a resource for investigators interested in building upon the methods and results of previous research in designing their own perfusion fixation studies in human brains or other large animal brains. We also suggest several future research directions, such as comparing the in situ and ex situ approaches to perfusion fixation, studying the efficacy of different washout solutions, and elucidating the types of brain donors in which perfusion fixation is likely to result in higher fixation quality than immersion fixation.