Identifying Risk of Adverse Outcomes in COVID-19 Patients via Artificial Intelligence-Powered Analysis of 12-Lead Intake Electrocardiogram

Machine and deep learning methods for clinical outcome prediction based on physiological data of COVID-19 patients: a scoping review

INTRODUCTION

Since the beginning of the COVID-19 pandemic, numerous machine and deep learning (MDL) methods have been proposed in the literature to analyze patient physiological data. The objective of this review is to summarize various aspects of these methods and assess their practical utility for predicting various clinical outcomes.

METHODS

We searched PubMed, Scopus, and Cochrane Library, screened and selected the studies matching the inclusion criteria. The clinical analysis focused on the characteristics of the patient cohorts in the studies included in this review, the specific tasks in the context of the COVID-19 pandemic that machine and deep learning methods were used for, and their practical limitations. The technical analysis focused on the details of specific MDL methods and their performance.

RESULTS

Analysis of the 48 selected studies revealed that the majority (∼54 %) of them examined the application of MDL methods for the prediction of survival/mortality-related patient outcomes, while a smaller fraction (∼13 %) of studies also examined applications to the prediction of patients' physiological outcomes and hospital resource utilization. 21 % of the studies examined the application of MDL methods to multiple clinical tasks. Machine and deep learning methods have been shown to be effective at predicting several outcomes of COVID-19 patients, such as disease severity, complications, intensive care unit (ICU) transfer, and mortality. MDL methods also achieved high accuracy in predicting the required number of ICU beds and ventilators.

CONCLUSION

Machine and deep learning methods have been shown to be valuable tools for predicting disease severity, organ dysfunction and failure, patient outcomes, and hospital resource utilization during the COVID-19 pandemic. The discovered knowledge and our conclusions and recommendations can also be useful to healthcare professionals and artificial intelligence researchers in managing future pandemics.

Explainable Machine Learning to Predict Anchored Reentry Substrate Created by Persistent Atrial Fibrillation Ablation in Computational Models

Background Postablation arrhythmia recurrence occurs in ~40% of patients with persistent atrial fibrillation. Fibrotic remodeling exacerbates arrhythmic activity in persistent atrial fibrillation and can play a key role in reentrant arrhythmia, but emergent interaction between nonconductive ablation-induced scar and native fibrosis (ie, residual fibrosis) is poorly understood. Methods and Results We conducted computational simulations in pre- and postablation left atrial models reconstructed from late gadolinium enhanced magnetic resonance imaging scans to test the hypothesis that ablation in patients with persistent atrial fibrillation creates new substrate conducive to recurrent arrhythmia mediated by anchored reentry. We trained a random forest machine learning classifier to accurately pinpoint specific nonconductive tissue regions (ie, areas of ablation-delivered scar or vein/valve boundaries) with the capacity to serve as substrate for anchored reentry-driven recurrent arrhythmia (area under the curve: 0.91±0.03). Our analysis suggests there is a distinctive nonconductive tissue pattern prone to serving as arrhythmogenic substrate in postablation models, defined by a specific size and proximity to residual fibrosis. Conclusions Overall, this suggests persistent atrial fibrillation ablation transforms substrate that favors functional reentry (ie, rotors meandering in excitable tissue) into an arrhythmogenic milieu more conducive to anchored reentry. Our work also indicates that explainable machine learning and computational simulations can be combined to effectively probe mechanisms of recurrent arrhythmia.

Machine Learning and the Conundrum of Stroke Risk Prediction

Stroke is a leading cause of death worldwide. With escalating healthcare costs, early non-invasive stroke risk stratification is vital. The current paradigm of stroke risk assessment and mitigation is focused on clinical risk factors and comorbidities. Standard algorithms predict risk using regression-based statistical associations, which, while useful and easy to use, have moderate predictive accuracy. This review summarises recent efforts to deploy machine learning (ML) to predict stroke risk and enrich the understanding of the mechanisms underlying stroke. The surveyed body of literature includes studies comparing ML algorithms with conventional statistical models for predicting cardiovascular disease and, in particular, different stroke subtypes. Another avenue of research explored is ML as a means of enriching multiscale computational modelling, which holds great promise for revealing thrombogenesis mechanisms. Overall, ML offers a new approach to stroke risk stratification that accounts for subtle physiologic variants between patients, potentially leading to more reliable and personalised predictions than standard regression-based statistical associations.