Dataset Information

Incident atrial fibrillation and its risk prediction in patients developing COVID-19: A machine learning based algorithm approach.

ABSTRACT:

Background

The elderly multi-morbid patient is at high risk of adverse outcomes with COVID-19 complications, and in the general population, the development of incident AF is associated with worse outcomes in such patients. There is therefore the need to identify those patients with COVID-19 who are at highest risk of developing incident AF. We therefore investigated incident AF risks in a large prospective population of elderly patients with/without incident COVID-19 cases and baseline cardiovascular/non-cardiovascular multi-morbidities. We used two approaches: main effect modeling and secondly, a machine-learning (ML) approach, accounting for the complex dynamic relationships among comorbidity variables.

Methods

We studied a prospective elderly US cohort of 280,592 patients from medical databases in an 8-month investigation of with/without newly incident COVID19 cases. Incident AF outcomes were examined in relationship to diverse multi-morbid conditions, COVID-19 status and demographic variables, with ML accounting for the dynamic nature of changing multimorbidity risk factors.

Results

Multi-morbidity contributed to the onset of confirmed COVID-19 cases with cognitive impairment (OR 1.69; 95%CI 1.52-1.88), anemia (OR 1.41; 95%CI 1.32-1.50), diabetes mellitus (OR 1.35; 95%CI 1.27-1.44) and vascular disease (OR 1.30; 95%CI 1.21-1.39) having the highest associations. A main effect model (C-index value 0.718) showed that COVID-19 had the highest association with incident AF cases (OR 3.12; 95%CI 2.61-3.710, followed by congestive heart failure (1.72; 95%CI 1.50-1.96), then coronary artery disease (OR 1.43; 95%CI 1.27-1.60) and valvular disease (1.42; 95%CI 1.26-1.60). The ML algorithm demonstrated improved discriminatory validity incrementally over the statistical main effect model (training: C-index 0.729, 95%CI 0.718-0.740; validation: C-index 0.704, 95%CI 0.687-0.72). Calibration of the ML based formulation was satisfactory and better than the main-effect model. Decision curve analysis demonstrated that the clinical utility for the ML based formulation was better than the 'treat all' strategy and the main effect model.

Conclusion

COVID-19 status has major implications for incident AF in a cohort with diverse cardiovascular/non-cardiovascular multi-morbidities. Our ML approach accounting for dynamic multimorbidity changes had good prediction for new onset AF amongst incident COVID19 cases.

SUBMITTER: Lip GYH

PROVIDER: S-EPMC8118660 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundSince the beginning of coronavirus disease 2019 (COVID-19), the development of predictive models has sparked relevant interest due to the initial lack of knowledge about diagnosis, treatment, and prognosis. The present study aimed at developing a model, through a machine learning approach, to predict intensive care unit (ICU) mortality in COVID-19 patients based on predefined clinical parameters.ResultsObservational multicenter cohort study. All COVID-19 adult patients admitted to 25 ICUs belonging to the VENETO ICU network (February 28th 2020-april 4th 2021) were enrolled. Patients admitted to the ICUs before 4th March 2021 were used for model training ("training set"), while patients admitted after the 5th of March 2021 were used for external validation ("test set 1"). A further group of patients ("test set 2"), admitted to the ICU of IRCCS Ca' Granda Ospedale Maggiore Policlinico of Milan, was used for external validation. A SuperLearner machine learning algorithm was applied for model development, and both internal and external validation was performed. Clinical variables available for the model were (i) age, gender, sequential organ failure assessment score, Charlson Comorbidity Index score (not adjusted for age), Palliative Performance Score; (ii) need of invasive mechanical ventilation, non-invasive mechanical ventilation, O2 therapy, vasoactive agents, extracorporeal membrane oxygenation, continuous venous-venous hemofiltration, tracheostomy, re-intubation, prone position during ICU stay; and (iii) re-admission in ICU. One thousand two hundred ninety-three (80%) patients were included in the "training set", while 124 (8%) and 199 (12%) patients were included in the "test set 1" and "test set 2," respectively. Three different predictive models were developed. Each model included different sets of clinical variables. The three models showed similar predictive performances, with a training balanced accuracy that ranged between 0.72 and 0.90, while the cross-validation performance ranged from 0.75 to 0.85. Age was the leading predictor for all the considered models.ConclusionsOur study provides a useful and reliable tool, through a machine learning approach, for predicting ICU mortality in COVID-19 patients. In all the estimated models, age was the variable showing the most important impact on mortality.

Project description:Importance:Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia, and its early detection could lead to significant improvements in outcomes through the appropriate prescription of anticoagulation medication. Although a variety of methods exist for screening for AF, a targeted approach, which requires an efficient method for identifying patients at risk, would be preferred. Objective:To examine machine learning approaches applied to electronic health record data that have been harmonized to the Observational Medical Outcomes Partnership Common Data Model for identifying risk of AF. Design, Setting, and Participants:This diagnostic study used data from 2?252?219 individuals cared for in the UCHealth hospital system, which comprises 3 large hospitals in Colorado, from January 1, 2011, to October 1, 2018. Initial analysis was performed in December 2018; follow-up analysis was performed in July 2019. Exposures:All Observational Medical Outcomes Partnership Common Data Model-harmonized electronic health record features, including diagnoses, procedures, medications, age, and sex. Main Outcomes and Measures:Classification of incident AF in designated 6-month intervals, adjudicated retrospectively, based on area under the receiver operating characteristic curve and F1 statistic. Results:Of 2?252?219 individuals (1?225?533 [54.4%] women; mean [SD] age, 42.9 [22.3] years), 28?036 (1.2%) developed incident AF during a designated 6-month interval. The machine learning model that used the 200 most common electronic health record features, including age and sex, and random oversampling with a single-layer, fully connected neural network provided the optimal prediction of 6-month incident AF, with an area under the receiver operating characteristic curve of 0.800 and an F1 score of 0.110. This model performed only slightly better than a more basic logistic regression model composed of known clinical risk factors for AF, which had an area under the receiver operating characteristic curve of 0.794 and an F1 score of 0.079. Conclusions and Relevance:Machine learning approaches to electronic health record data offer a promising method for improving risk prediction for incident AF, but more work is needed to show improvement beyond standard risk factors.

Project description:BackgroundSome attempts have been made to detect atrial fibrillation (AF) with a wearable device equipped with photoelectric volumetric pulse wave technology, and it is expected to be applied under real clinical conditions.ObjectiveThis study is the second part of a 2-phase study aimed at developing a method for immediate detection of paroxysmal AF, using a wearable device with built-in photoplethysmography (PPG). The objective of this study is to develop an algorithm to immediately diagnose AF by an Apple Watch equipped with a PPG sensor that is worn by patients undergoing cardiac surgery and to use machine learning on the pulse data output from the device.MethodsA total of 80 patients who underwent cardiac surgery at a single institution between June 2020 and March 2021 were monitored for postoperative AF, using a telemetry-monitored electrocardiogram (ECG) and an Apple Watch. AF was diagnosed by qualified physicians from telemetry-monitored ECGs and 12-lead ECGs; a diagnostic algorithm was developed using machine learning on the pulse rate data output from the Apple Watch.ResultsOne of the 80 patients was excluded from the analysis due to redness caused by wearing the Apple Watch. Of 79 patients, 27 (34.2%) developed AF, and 199 events of AF including brief AF were observed. Of them, 18 events of AF lasting longer than 1 hour were observed, and cross-correlation analysis showed that pulse rate measured by Apple Watch was strongly correlated (cross-correlation functions [CCF]: 0.6-0.8) with 8 events and very strongly correlated (CCF>0.8) with 3 events. The diagnostic accuracy by machine learning was 0.9416 (sensitivity 0.909 and specificity 0.838 at the point closest to the top left) for the area under the receiver operating characteristic curve.ConclusionsWe were able to safely monitor pulse rate in patients who wore an Apple Watch after cardiac surgery. Although the pulse rate measured by the PPG sensor does not follow the heart rate recorded by telemetry-monitored ECGs in some parts, which may reduce the accuracy of AF diagnosis by machine learning, we have shown the possibility of clinical application of using only the pulse rate collected by the PPG sensor for the early detection of AF.

Project description:BackgroundAtrial fibrillation (AF) increases the risk of stroke 5-fold and there is rising interest to determine if AF severity or burden can further risk stratify these patients, particularly for near-term events. Using continuous remote monitoring data from cardiac implantable electronic devices, we sought to evaluate if machine learned signatures of AF burden could provide prognostic information on near-term risk of stroke when compared to conventional risk scores.Methods and resultsWe retrospectively identified Veterans Health Administration serviced patients with cardiac implantable electronic device remote monitoring data and at least one day of device-registered AF. The first 30 days of remote monitoring in nonstroke controls were compared against the past 30 days of remote monitoring before stroke in cases. We trained 3 types of models on our data: (1) convolutional neural networks, (2) random forest, and (3) L1 regularized logistic regression (LASSO). We calculated the CHA2DS2-VASc score for each patient and compared its performance against machine learned indices based on AF burden in separate test cohorts. Finally, we investigated the effect of combining our AF burden models with CHA2DS2-VASc. We identified 3114 nonstroke controls and 71 stroke cases, with no significant differences in baseline characteristics. Random forest performed the best in the test data set (area under the curve [AUC]=0.662) and convolutional neural network in the validation dataset (AUC=0.702), whereas CHA2DS2-VASc had an AUC of 0.5 or less in both data sets. Combining CHA2DS2-VASc with random forest and convolutional neural network yielded a validation AUC of 0.696 and test AUC of 0.634, yielding the highest average AUC on nontraining data.ConclusionsThis proof-of-concept study found that machine learning and ensemble methods that incorporate daily AF burden signature provided incremental prognostic value for risk stratification beyond CHA2DS2-VASc for near-term risk of stroke.

Project description:BackgroundRacial disparities in health care are well documented in the United States. As machine learning methods become more common in health care settings, it is important to ensure that these methods do not contribute to racial disparities through biased predictions or differential accuracy across racial groups.ObjectiveThe goal of the research was to assess a machine learning algorithm intentionally developed to minimize bias in in-hospital mortality predictions between white and nonwhite patient groups.MethodsBias was minimized through preprocessing of algorithm training data. We performed a retrospective analysis of electronic health record data from patients admitted to the intensive care unit (ICU) at a large academic health center between 2001 and 2012, drawing data from the Medical Information Mart for Intensive Care-III database. Patients were included if they had at least 10 hours of available measurements after ICU admission, had at least one of every measurement used for model prediction, and had recorded race/ethnicity data. Bias was assessed through the equal opportunity difference. Model performance in terms of bias and accuracy was compared with the Modified Early Warning Score (MEWS), the Simplified Acute Physiology Score II (SAPS II), and the Acute Physiologic Assessment and Chronic Health Evaluation (APACHE).ResultsThe machine learning algorithm was found to be more accurate than all comparators, with a higher sensitivity, specificity, and area under the receiver operating characteristic. The machine learning algorithm was found to be unbiased (equal opportunity difference 0.016, P=.20). APACHE was also found to be unbiased (equal opportunity difference 0.019, P=.11), while SAPS II and MEWS were found to have significant bias (equal opportunity difference 0.038, P=.006 and equal opportunity difference 0.074, P<.001, respectively).ConclusionsThis study indicates there may be significant racial bias in commonly used severity scoring systems and that machine learning algorithms may reduce bias while improving on the accuracy of these methods.