An ECG-based machine learning model for predicting new-onset atrial fibrillation is superior to age and clinical features in identifying patients at high stroke risk

BACKGROUND

Several large trials have employed age or clinical features to select patients for atrial fibrillation (AF) screening to reduce strokes. We hypothesized that a machine learning (ML) model trained to predict AF risk from 12‑lead electrocardiogram (ECG) would be more efficient than criteria based on clinical variables in indicating a population for AF screening to potentially prevent AF-related stroke.

METHODS

We retrospectively included all patients with clinical encounters in Geisinger without a prior history of AF. Incidence of AF within 1 year and AF-related strokes within 3 years of the encounter were identified. AF-related stroke was defined as a stroke where AF was diagnosed at the time of stroke or within a year after the stroke. The efficiency of five methods was evaluated for selecting a cohort for AF screening. The methods were selected from four clinical trials (mSToPS, GUARD-AF, SCREEN-AF and STROKESTOP) and the ECG-based ML model. We simulated patient selection for the five methods between the years 2011 and 2014 and evaluated outcomes for 1 year intervals between 2012 and 2015, resulting in a total of twenty 1-year periods. Patients were considered eligible if they met the criteria before the start of the given 1-year period or within that period. The primary outcomes were numbers needed to screen (NNS) for AF and AF-associated stroke.

RESULTS

The clinical trial models indicated large proportions of the population with a prior ECG for AF screening (up to 31%), coinciding with NNS ranging from 14 to 18 for AF and 249-359 for AF-associated stroke. At comparable sensitivity, the ECG ML model indicated a modest number of patients for screening (14%) and had the highest efficiency in NNS for AF (7.3; up to 60% reduction) and AF-associated stroke (223; up to 38% reduction).

CONCLUSIONS

An ECG-based ML risk prediction model is more efficient than contemporary AF-screening criteria based on age alone or age and clinical features at indicating a population for AF screening to potentially prevent AF-related strokes.

Generalizability and quality control of deep learning-based 2D echocardiography segmentation models in a large clinical dataset

Use of machine learning (ML) for automated annotation of heart structures from echocardiographic videos is an active research area, but understanding of comparative, generalizable performance among models is lacking. This study aimed to (1) assess the generalizability of five state-of-the-art ML-based echocardiography segmentation models within a large Geisinger clinical dataset, and (2) test the hypothesis that a quality control (QC) method based on segmentation uncertainty can further improve segmentation results. Five models were applied to 47,431 echocardiography studies that were independent from any training samples. Chamber volume and mass from model segmentations were compared to clinically-reported values. The median absolute errors (MAE) in left ventricular (LV) volumes and ejection fraction exhibited by all five models were comparable to reported inter-observer errors (IOE). MAE for left atrial volume and LV mass were similarly favorable to respective IOE for models trained for those tasks. A single model consistently exhibited the lowest MAE in all five clinically-reported measures. We leveraged the tenfold cross-validation training scheme of this best-performing model to quantify segmentation uncertainty. We observed that removing segmentations with high uncertainty from 14 to 71% studies reduced volume/mass MAE by 6-10%. The addition of convexity filters improved specificity, efficiently removing < 10% studies with large MAE (16-40%). In conclusion, five previously published echocardiography segmentation models generalized to a large, independent clinical dataset-segmenting one or multiple cardiac structures with overall accuracy comparable to manual analyses-with variable performance. Convexity-reinforced uncertainty QC efficiently improved segmentation performance and may further facilitate the translation of such models.

Analysis of rare genetic variation underlying cardiometabolic diseases and traits among 200,000 individuals in the UK Biobank

Cardiometabolic diseases are the leading cause of death worldwide. Despite a known genetic component, our understanding of these diseases remains incomplete. Here, we analyzed the contribution of rare variants to 57 diseases and 26 cardiometabolic traits, using data from 200,337 UK Biobank participants with whole-exome sequencing. We identified 57 gene-based associations, with broad replication of novel signals in Geisinger MyCode. There was a striking risk associated with mutations in known Mendelian disease genes, including MYBPC3, LDLR, GCK, PKD1 and TTN. Many genes showed independent convergence of rare and common variant evidence, including an association between GIGYF1 and type 2 diabetes. We identified several large effect associations for height and 18 unique genes associated with blood lipid or glucose levels. Finally, we found that between 1.0% and 2.4% of participants carried rare potentially pathogenic variants for cardiometabolic disorders. These findings may facilitate studies aimed at therapeutics and screening of these common disorders.

Deep-learning-assisted analysis of echocardiographic videos improves predictions of all-cause mortality

Machine learning promises to assist physicians with predictions of mortality and of other future clinical events by learning complex patterns from historical data, such as longitudinal electronic health records. Here we show that a convolutional neural network trained on raw pixel data in 812,278 echocardiographic videos from 34,362 individuals provides superior predictions of one-year all-cause mortality. The model's predictions outperformed the widely used pooled cohort equations, the Seattle Heart Failure score (measured in an independent dataset of 2,404 patients with heart failure who underwent 3,384 echocardiograms), and a machine learning model involving 58 human-derived variables from echocardiograms and 100 clinical variables derived from electronic health records. We also show that cardiologists assisted by the model substantially improved the sensitivity of their predictions of one-year all-cause mortality by 13% while maintaining prediction specificity. Large unstructured datasets may enable deep learning to improve a wide range of clinical prediction models.

Deep Neural Networks Can Predict New-Onset Atrial Fibrillation From the 12-Lead ECG and Help Identify Those at Risk of Atrial Fibrillation-Related Stroke

Supplemental Digital Content is available in the text.

Atrial fibrillation (AF) is associated with substantial morbidity, especially when it goes undetected. If new-onset AF could be predicted, targeted screening could be used to find it early. We hypothesized that a deep neural network could predict new-onset AF from the resting 12-lead ECG and that this prediction may help identify those at risk of AF-related stroke.

Dopaminergic contributions to hippocampal pathophysiology in schizophrenia: a computational study

Since the original formulation of the dopamine hypothesis, a number of other cellular-level abnormalities--eg, NMDA receptor hypofunction, GABA system dysfunction, neural connectivity disturbances--have been identified in schizophrenia, but the manner in which these potentially interact with hyperdopaminergia to lead to schizophrenic symptomatology remains uncertain. Previously, we created a neuroanatomically detailed, biophysically realistic computational model of hippocampus in the control (unaffected) and schizophrenic conditions, implemented on a 72-processor supercomputer platform. In the current study, we apply the effects of dopamine (DA), dose-dependently, to both models on the basis of an exhaustive review of the neurophysiologic literature on DA's ion channel and synaptic level effects. To index schizophrenic behavior, we use the specific inability of the model to attune to the 40 Hz (gamma band) frequency, a finding that has been well replicated in the clinical electroencephalography (EEG) and magnetoencephalography literature. In trials using 20 'simulated patients', we find that DA applied to the control model produces modest increases in 40 Hz activity, similar to experimental studies. However, in the schizophrenic model, increasing DA induces a decrement in 40 Hz resonance. This modeling work is significant in that it suggests that DA's effects may vary based on the neural substrate on which it acts, and--via simulated EEG recordings-points to the neurophysiologic mechanisms by which this may occur. We also feel that it makes a methodological contribution, as it exhibits a process by which a large amount of neurobiological data can be integrated to run pharmacologically relevant in silico experiments, using a systems biology approach.

Development of antipsychotic medications with novel mechanisms of action based on computational modeling of hippocampal neuropathology

A large number of cellular level abnormalities have been identified in the hippocampus of schizophrenic subjects. Nonetheless, it remains uncertain how these pathologies interact at a system level to create clinical symptoms, and this has hindered the development of more effective antipsychotic medications. Using a 72-processor supercomputer, we created a tissue level hippocampal simulation, featuring multicompartmental neuron models with multiple ion channel subtypes and synaptic channels with realistic temporal dynamics. As an index of the schizophrenic phenotype, we used the specific inability of the model to attune to 40 Hz (gamma band) stimulation, a well-characterized abnormality in schizophrenia. We examined several possible combinations of putatively schizophrenogenic cellular lesions by systematically varying model parameters representing NMDA channel function, dendritic spine density, and GABA system integrity, conducting 910 trials in total. Two discrete “clusters” of neuropathological changes were identified. The most robust was characterized by co-occurring modest reductions in NMDA system function (-30%) and dendritic spine density (-30%). Another set of lesions had greater NMDA hypofunction along with low level GABA system dysregulation. To the schizophrenic model, we applied the effects of 1,500 virtual medications, which were implemented by varying five model parameters, independently, in a graded manner; the effects of known drugs were also applied. The simulation accurately distinguished agents that are known to lack clinical efficacy, and identified novel mechanisms (e.g., decrease in AMPA conductance decay time constant, increase in projection strength of calretinin-positive interneurons) and combinations of mechanisms that could re-equilibrate model behavior. These findings shed light on the mechanistic links between schizophrenic neuropathology and the gamma band oscillatory abnormalities observed in the illness. As such, they generate specific falsifiable hypotheses, which can guide postmortem and other laboratory research. Significantly, this work also suggests specific non-obvious targets for potential pharmacologic agents.