Prediction of short-term atrial fibrillation risk using primary care electronic health records

Phenotypic characterization of people at risk of atrial fibrillation: protocol for the FIND-AF longitudinal cohort study

AIMS

The Future Innovations in Novel Detection of Atrial Fibrillation (FIND-AF) longitudinal cohort study is a multi-centre prospective cohort study of patients identified at risk of atrial fibrillation (AF). The aim of the FIND-AF longitudinal cohort study is to provide multi-modal phenotypic characterization of these patients.

METHODS AND RESULTS

A total of 1955 participants identified as at risk of AF by the FIND-AF algorithm from primary care electronic health record (EHR) data, aged 30 years and above and eligible for oral anticoagulation, will be recruited between October 2023 and November 2024 to receive home-based intermittent electrocardiogram monitoring. About 500 participants without diagnosed AF will then undergo cross-sectional phenotypic characterization including physical examination, symptoms assessment, serum blood biomarkers and echocardiography, and non-stress cardiac magnetic resonance imaging. Longitudinal information about cardio-renal-metabolic-pulmonary outcomes will be ascertained from linkages to EHR data. The study is funded by the British Heart Foundation (CC/22/250026). The study has ethical approval (North West-Greater Manchester South Research Ethics Committee reference 23/NW/0180). Findings will be announced at relevant conferences and published in peer-reviewed journals in line with the funder's open-access policy.

CONCLUSION

The FIND-AF multi-centre prospective longitudinal cohort study aims to (i) provide evidence for the impact of comorbidities on AF genesis, (ii) uncover actionable targets to prevent AF, and (iii) act as a platform for cohort randomized clinical trials that investigate enhanced detection and prevention of AF.

A novel, machine-learning model for prediction of short-term ASCVD risk over 90 and 365 days

Background

Current atherosclerotic cardiovascular disease (ASCVD) risk assessment tools like the Pooled Cohort Equations (PCEs) and PREVENT™ scores offer long-term predictions but may not effectively drive behavior change. Short-term risk predictions using mobile health (mHealth) data and electronic health records (EHRs) could enhance clinical decision-making and patient engagement. The aim of this study was to develop a short-term ASCVD risk prediction model for hypertensive individuals using mHealth and EHR data and compare its performance to existing risk assessment tools.

Methods

This is a retrospective cohort study including 51,127 hypertensive participants aged ≥18 years old who enrolled in the Hello Heart CV risk self-management program between January 2015 and January 2024. A machine learning (ML) model was derived from EHR data and mHealth measurements of blood pressure (BP) and heart rate (HR) collected via at-home BP monitors. Its performance was compared to that of PCE and PREVENT.

Results

The XgBoost model incorporating 291 features outperformed the PCE and PREVENT scores in discriminating ASCVD risk for both prediction periods. For 90-day prediction, mean C-statistics were 0.81 (XgBoost) vs. 0.74 (PCE) and 0.65 (PREVENT). Similar findings were observed for 365-day prediction. mHealth measurements incrementally enhanced 365-day risk prediction (ROC-AUC 0.82 vs. 0.80 without mHealth).

Conclusion

An EHR and mHealth-based ML model offers superior short-term ASCVD prediction compared to traditional tools. This approach supports personalized preventive strategies, particularly for populations with incomplete features for PCE or PREVENT. Further research should explore this novel risk prediction framework, and particularly additional mHealth data integration for broader applicability and increased predictive power.

Usefulness of the C2HEST score to predict new onset atrial fibrillation. A systematic review and meta-analysis on >11 million subjects

BACKGROUND

The incidence of new-onset atrial fibrillation (NOAF) is increasing in the last decades. NOAF is associated with worse long-term prognosis. The C2HEST score has been recently proposed to stratify the risk of NOAF. Pooled data on the performance of the C2HEST score are lacking.

METHODS

Systematic review and meta-analysis of observational studies reporting data on NOAF according to the C2HEST score. We searched PubMed, Web of Science and Google scholar databases without time restrictions until June 2023 according to PRISMA guidelines. Meta-analysis of the area under the curve (AUC) with 95% confidence interval (95% CI) and a sensitivity analysis according to setting of care and countries were performed.

RESULTS

Of 360 studies, 17 were included in the analysis accounting for 11,067,496 subjects/patients with 307,869 NOAF cases. Mean age ranged from 41.3 to 71.2 years. The prevalence of women ranged from 10.6 to 54.75%. The pooled analysis gave an AUC of .70 (95% CI .66-.74). A subgroup analysis on studies from general population/primary care yielded an AUC of 0.69 (95% CI 0.64-0.75). In the subgroup of patients with cardiovascular disease, the AUC was .71 (.69-.79). The C2HEST score performed similarly in Asian (AUC .72, 95% CI .68-.77), and in Western patients (AUC .68, 95% CI .62-.75). The best performance was observed in studies with a mean age <50 years (n = 3,144,704 with 25,538 NOAF, AUC .78, 95% CI .76-.79).

CONCLUSION

The C2HEST score may be used to predict NOAF in primary and secondary prevention patients, and in patients across different countries. Early detection of NOAF may aid prompt initiation of management and follow-up, potentially leading to a reduction of AF-related complications.

From sleep patterns to heart rhythm: Predicting atrial fibrillation from overnight polysomnograms

BACKGROUND

Atrial fibrillation (AF) is often asymptomatic and thus under-observed. Given the high risks of stroke and heart failure among patients with AF, early prediction and effective management are crucial. Given the prevalence of obstructive sleep apnea among AF patients, electrocardiogram (ECG) analysis from polysomnography (PSG) offers a unique opportunity for early AF prediction. Our aim is to identify individuals at high risk of AF development from single‑lead ECGs during standard PSG.

METHODS

We analyzed 18,782 single‑lead ECG recordings from 13,609 subjects undergoing PSG at the Massachusetts General Hospital sleep laboratory. AF presence was identified using ICD-9/10 codes. The dataset included 15,913 recordings without AF history and 2054 recordings from patients diagnosed with AF between one month to fifteen years post-PSG. Data were partitioned into training, validation, and test cohorts ensuring that individual patients remained exclusive to each cohort. The test set was held out during the training process. We employed two different methods for feature extraction to build a final model for AF prediction: Extraction of hand-crafted ECG features and a deep learning method. For extraction of ECG-hand-crafted features, recordings were split into 30-s windows, and those with a signal quality index (SQI) below 0.95 were discarded. From each remaining window, 150 features were extracted from the time, frequency, time-frequency domains, and phase-space reconstructions of the ECG. A compilation of 12 statistical features summarized these window-specific features per recording, resulting in 1800 features (12 × 150). A pre-trained deep neural network from the PhysioNet Challenge 2021 was updated using transfer learning to discriminate recordings with and without AF. The model processed PSG ECGs in 16-s windows to generate AF probabilities, from which 13 statistical features were extracted. Combining 1800 features from feature extraction with 13 from the deep learning model, we performed a feature selection and subsequently trained a shallow neural network to predict future AF and evaluated its performance on the test cohort.

RESULTS

On the test set, our model exhibited sensitivity, specificity, and precision of 0.67, 0.81, and 0.3, respectively, for AF prediction. Survival analysis revealed a hazard ratio of 8.36 (p-value: 1.93 × 10-52) for AF outcomes using the log-rank test.

CONCLUSIONS

Our proposed ECG analysis method, utilizing overnight PSG data, shows promise in AF prediction despite modest precision, suggesting false positives. This approach could enable low-cost screening and proactive treatment for high-risk patients. Refinements, including additional physiological parameters, may reduce false positives, enhancing clinical utility and accuracy.

Increasing the reach: optimizing screening for atrial fibrillation-the STROKESTOP III study

AIMS

Atrial fibrillation (AF) is the most common type of cardiac arrythmia and is an important risk factor for ischaemic stroke. Many cases of AF remain undiagnosed due to its paroxysmal, intermittent, and often asymptomatic nature. Early detection of AF through screening and initiation of treatment with oral anticoagulants can prevent stroke, increase life expectancy, and decrease the cost of healthcare for the society. However, participation has been low in previous AF screening studies employing population screening. The aim of this study is to determine whether opportunistic screening is a superior method to increase participation in comparison to population screening. We hypothesize that opportunistic screening will significantly increase participation.

METHODS AND RESULTS

In our study, STROKESTOP III, a randomized prospective cohort study, we compare two different methods of AF screening in high-risk individuals: population screening vs. opportunistic screening. Sixteen different primary clinics in Värmland, Sweden, serving 75-76-year-old individuals (n = 2954), will be randomized to either population screening or opportunistic screening. The individuals will be instructed to record electrocardiogram (ECG) for 30 s, 3 times daily for 2 weeks, using a handheld one-lead ECG device. Patients with detected AF will be referred to their primary healthcare physician and offered treatment. The main objective of the study is to determine the rate of participation in opportunistic screening in comparison to population screening.

CONCLUSIONS

The STROKESTOP III study will provide valuable information on which screening method to use for improved participation in atrial fibrillation screening.

Artificial intelligence-enabled atrial fibrillation detection using smartwatches: current status and future perspectives

Atrial fibrillation (AF) significantly increases the risk of stroke and heart failure, but is frequently asymptomatic and intermittent; therefore, its timely diagnosis poses challenges. Early detection in selected patients may aid in stroke prevention and mitigate structural heart complications through prompt intervention. Smartwatches, coupled with powerful artificial intelligence (AI)-enabled algorithms, offer a promising tool for early detection due to their widespread use, easiness of use, and potential cost-effectiveness. Commercially available smartwatches have gained clearance from the FDA to detect AF and are becoming increasingly popular. Despite their promise, the evolving landscape of AI-enabled smartwatch-based AF detection raises questions about the clinical value of this technology. Following the ongoing digital transformation of healthcare, clinicians should familiarize themselves with how AI-enabled smartwatches function in AF detection and navigate their role in clinical settings to deliver optimal patient care. In this review, we provide a concise overview of the characteristics of AI-enabled smartwatch algorithms, their diagnostic performance, clinical value, limitations, and discuss future perspectives in AF diagnosis.

Precise risk-prediction model including arterial stiffness for new-onset atrial fibrillation using machine learning techniques

Atrial fibrillation (AF) is the most common clinically significant cardiac arrhythmia and is an important risk factor for ischemic cerebrovascular events. This study used machine learning techniques to develop and validate a new risk prediction model for new-onset AF that incorporated the use electrocardiogram to diagnose AF, data from participants with a wide age range, and considered hypertension and measures of atrial stiffness. In Japan, Industrial Safety and Health Law requires employers to provide annual health check-ups to their employees. This study included 13 410 individuals who underwent health check-ups on at least four successive years between 2005 and 2015 (new-onset AF, n = 110; non-AF, n = 13 300). Data were entered into a risk prediction model using machine learning methods (eXtreme Gradient Boosting and Shapley Additive Explanation values). Data were randomly split into a training set (80%) used for model construction and development, and a test set (20%) used to test performance of the derived model. The area under the receiver operator characteristic curve for the model in the test set was 0.789. The best predictor of new-onset AF was age, followed by the cardio-ankle vascular index, estimated glomerular filtration rate, sex, body mass index, uric acid, γ-glutamyl transpeptidase level, triglycerides, systolic blood pressure at cardio-ankle vascular index measurement, and alanine aminotransferase level. This new model including arterial stiffness measure, developed with data from a general population using machine learning methods, could be used to identify at-risk individuals and potentially facilitation the prevention of future AF development.

From Sleep Patterns to Heart Rhythms: Predicting Atrial Fibrillation from Overnight Polysomnograms

Background

Atrial fibrillation (AF) is often asymptomatic and thus under-observed. Given the high risks of stroke and heart failure among patients with AF, early prediction and effective management are crucial. Importantly, obstructive sleep apnea is highly prevalent among AF patients (60-90%); therefore, electrocardiogram (ECG) analysis from polysomnography (PSG), a standard diagnostic tool for subjects with suspected sleep apnea, presents a unique opportunity for the early prediction of AF. Our goal is to identify individuals at a high risk of developing AF in the future from a single-lead ECG recorded during standard PSGs.

Methods

We analyzed 18,782 single-lead ECG recordings from 13,609 subjects at Massachusetts General Hospital, identifying AF presence using ICD-9/10 codes in medical records. Our dataset comprises 15,913 recordings without a medical record for AF and 2,056 recordings from patients who were first diagnosed with AF between 1 day to 15 years after the PSG recording. The PSG data were partitioned into training, validation, and test cohorts. In the first phase, a signal quality index (SQI) was calculated in 30-second windows and those with SQI < 0.95 were removed. From each remaining window, 150 hand-crafted features were extracted from time, frequency, time-frequency domains, and phase-space reconstructions of the ECG. A compilation of 12 statistical features summarized these window-specific features per recording, resulting in 1,800 features. We then updated a pre-trained deep neural network and data from the PhysioNet Challenge 2021 using transfer-learning to discriminate between recordings with and without AF using the same Challenge data. The model was applied to the PSG ECGs in 16-second windows to generate the probability of AF for each window. From the resultant probability sequence, 13 statistical features were extracted. Subsequently, we trained a shallow neural network to predict future AF using the extracted ECG and probability features.

Results

On the test set, our model demonstrated a sensitivity of 0.67, specificity of 0.81, and precision of 0.3 for predicting AF. Further, survival analysis for AF outcomes, using the log-rank test, revealed a hazard ratio of 8.36 (p-value of 1.93 × 10 -52 ).

Conclusions

Our proposed ECG analysis method, utilizing overnight PSG data, shows promise in AF prediction despite a modest precision indicating the presence of false positive cases. This approach could potentially enable low-cost screening and proactive treatment for high-risk patients. Ongoing refinement, such as integrating additional physiological parameters could significantly reduce false positives, enhancing its clinical utility and accuracy.

Risk calculator for incident atrial fibrillation across a range of prediction horizons

BACKGROUND

The increasing burden of atrial fibrillation (AF) emphasizes the need to identify high-risk individuals for enrolment in clinical trials of AF screening and primary prevention. We aimed to develop prediction models to identify individuals at high-risk of AF across prediction horizons from 6-months to 10-years.

METHODS

We used secondary-care linked primary care electronic health record data from individuals aged ≥30 years without known AF in the UK Clinical Practice Research Datalink-GOLD dataset between January 2, 1998 and November 30, 2018; randomly divided into derivation (80%) and validation (20%) datasets. Models were derived using logistic regression from known AF risk factors for incident AF in prediction periods of 6 months, 1-year, 2-years, 5-years, and 10-years. Performance was evaluated using in the validation dataset with bootstrap validation with 200 samples, and compared against the CHA2DS2-VASc and C2HEST scores.

RESULTS

Of 2,081,139 individuals in the cohort (1,664,911 in the development dataset, 416,228 in the validation dataset), the mean age was 49.9 (SD 15.4), 50.7% were women, and 86.7% were white. New cases of AF were 7,386 (0.4%) within 6 months, 15,349 (0.7%) in 1 year, 38,487 (1.8%) in 5 years, and 79,997 (3.8%) by 10 years. Valvular heart disease and heart failure were the strongest predictors, and association of hypertension with AF increased at longer prediction horizons. The optimal risk models incorporated age, sex, ethnicity, and 8 comorbidities. The models demonstrated good-to-excellent discrimination and strong calibration across prediction horizons (AUROC, 95%CI, calibration slope: 6-months, 0.803, 0.789-0.821, 0.952; 1-year, 0.807, 0.794-0.819, 0.962; 2-years, 0.815, 0.807-0.823, 0.973; 5-years, 0.807, 0.803-0.812, 1.000; 10-years 0.780, 0.777-0.784, 1.010), and superior to the CHA2DS2-VASc and C2HEST scores. The models are available as a web-based FIND-AF calculator.

CONCLUSIONS

The FIND-AF models demonstrate high discrimination and calibration across short- and long-term prediction horizons in 2 million individuals. Their utility to inform trial enrolment and clinical decisions for AF screening and primary prevention requires further study.

Development and trends in research on hypertension and atrial fibrillation: A bibliometric analysis from 2003 to 2022

BACKGROUND

This study aimed to comprehensively analyze research related to hypertension and atrial fibrillation, 2 common cardiovascular diseases with significant global public health implications, using bibliometric methods from 2003 to 2022.

METHODS

From the Web of Science Core Collection database, literature on the theme of hypertension and atrial fibrillation was retrieved. Subsequently, comprehensive bibliometric analyses were conducted across multiple dimensions utilizing software tools such as VOSviewer, Citespace, Pajek, Scimago Graphica, and ClusterProfiler. These analyses encompassed examinations of the literature according to country/region, institution, authors, journals, citation relationships, and keywords.

RESULTS

It revealed an increasing interest and shifting focus in research over the years. The analysis covered 7936 relevant publications, demonstrating a gradual rise in research activity regarding hypertension combined with atrial fibrillation over the past 2 decades, with a stable growth trend in research outcomes. Geographically, Europe and the Americas, particularly the United States, have shown the most active research in this field, while China has also gained importance in recent years. Regarding institutional contributions, internationally renowned institutions such as the University of Birmingham and the Mayo Clinic have emerged as core forces in this research direction. Additionally, Professor Lip Gregory, with his prolific research output, has stood out among numerous scholars. The American Journal of Cardiology has become a primary platform for publishing research related to hypertension and atrial fibrillation, highlighting its central role in advancing knowledge dissemination in this field. The research focus has shifted from exploring the pathophysiological mechanisms to investigating the treatment of complications and risk factors associated with hypertension and atrial fibrillation. Future research will focus on in-depth exploration of genetic and molecular mechanisms, causal relationship exploration through Mendelian randomization studies, and the application of machine learning techniques in prediction and treatment, aiming to promote the development of precision medicine for cardiovascular diseases.

CONCLUSION

In conclusion, this study provides a comprehensive overview of the developmental trajectory of research on hypertension and atrial fibrillation, presenting novel insights into trends and future research directions, thus offering information support and guidance for research in this crucial field of cardiovascular medicine.

Epidemiology, prognosis, and challenges in the management of hyperthyroidism-related atrial fibrillation

Atrial fibrillation (AF) is a common condition with a global estimated prevalence of 60 million cases, and the most common cardiac complication of hyperthyroidism, occurring in 5-15% of overtly hyperthyroid patients. Additionally, subclinical hyperthyroidism and high-normal free T4 have been associated with an increased risk in the development of AF. Hyperthyroidism-related AF is a reversible cause of AF, and the majority of patients spontaneously revert to sinus rhythm in 4-6 months during or after restoration of euthyroidism. Therefore, restoring thyroid function is an indispensable element in hyperthyroidism-related AF management. Rate control with beta-blockers consists another first-line therapy, reserving rhythm control in cases of persistent hyperthyroidism-related AF. It is still controversial whether hyperthyroidism is an independent risk factor of stroke in nonvalvular AF. As a result, initiating anticoagulation should be guided by the clinical thromboembolic risk score CHA2DS2-VASc score in the same way it is applied in patients with non-hyperthyroidism-related AF. Treatment with the novel direct oral anticoagulants appears to be as beneficial and may be safer than warfarin in patients with hyperthyroidism-related AF. In this review, we address the epidemiology, prognosis, and diagnosis of hyperthyroidism-related AF, and we discuss the management strategies and controversies in patients with hyperthyroidism-related AF.

Predicting incident heart failure from population-based nationwide electronic health records: protocol for a model development and validation study

INTRODUCTION

Heart failure (HF) is increasingly common and associated with excess morbidity, mortality, and healthcare costs. Treatment of HF can alter the disease trajectory and reduce clinical events in HF. However, many cases of HF remain undetected until presentation with more advanced symptoms, often requiring hospitalisation. Predicting incident HF is challenging and statistical models are limited by performance and scalability in routine clinical practice. An HF prediction model implementable in nationwide electronic health records (EHRs) could enable targeted diagnostics to enable earlier identification of HF.

METHODS AND ANALYSIS

We will investigate a range of development techniques (including logistic regression and supervised machine learning methods) on routinely collected primary care EHRs to predict risk of new-onset HF over 1, 5 and 10 years prediction horizons. The Clinical Practice Research Datalink (CPRD)-GOLD dataset will be used for derivation (training and testing) and the CPRD-AURUM dataset for external validation. Both comprise large cohorts of patients, representative of the population of England in terms of age, sex and ethnicity. Primary care records are linked at patient level to secondary care and mortality data. The performance of the prediction model will be assessed by discrimination, calibration and clinical utility. We will only use variables routinely accessible in primary care.

ETHICS AND DISSEMINATION

Permissions for CPRD-GOLD and CPRD-AURUM datasets were obtained from CPRD (ref no: 21_000324). The CPRD ethical approval committee approved the study. The results will be submitted as a research paper for publication to a peer-reviewed journal and presented at peer-reviewed conferences.

TRIAL REGISTRATION DETAILS

The study was registered on Clinical Trials.gov (NCT05756127). A systematic review for the project was registered on PROSPERO (registration number: CRD42022380892).

BIR: Biomedical Information Retrieval System for Cancer Treatment in Electronic Health Record Using Transformers

The rapid growth of electronic health records (EHRs) has led to unprecedented biomedical data. Clinician access to the latest patient information can improve the quality of healthcare. However, clinicians have difficulty finding information quickly and easily due to the sheer data mining volume. Biomedical information retrieval (BIR) systems can help clinicians find the information required by automatically searching EHRs and returning relevant results. However, traditional BIR systems cannot understand the complex relationships between EHR entities. Transformers are a new type of neural network that is very effective for natural language processing (NLP) tasks. As a result, transformers are well suited for tasks such as machine translation and text summarization. In this paper, we propose a new BIR system for EHRs that uses transformers for predicting cancer treatment from EHR. Our system can understand the complex relationships between the different entities in an EHR, which allows it to return more relevant results to clinicians. We evaluated our system on a dataset of EHRs and found that it outperformed state-of-the-art BIR systems on various tasks, including medical question answering and information extraction. Our results show that Transformers are a promising approach for BIR in EHRs, reaching an accuracy and an F1-score of 86.46%, and 0.8157, respectively. We believe that our system can help clinicians find the information they need more quickly and easily, leading to improved patient care.

Inequalities in care delivery and outcomes for myocardial infarction, heart failure, atrial fibrillation, and aortic stenosis in the United Kingdom

Cardiovascular diseases are a leading cause of death and disability globally, with inequalities in burden and care delivery evident in Europe. To address this challenge, The Lancet Regional Health-Europe convened experts from a range of countries to summarise the current state of knowledge on cardiovascular disease inequalities across Europe. This Series paper presents evidence from nationwide secondary care registries and primary care healthcare records regarding inequalities in care delivery and outcomes for myocardial infarction, heart failure, atrial fibrillation, and aortic stenosis in the National Health Service (NHS) across the United Kingdom (UK) by age, sex, ethnicity and geographical location. Data suggest that women and older people less frequently receive guideline-recommended treatment than men and younger people. There are limited publications about ethnicity in the UK for the studied disease areas. Finally, there is inter-healthcare provider variation in cardiovascular care provision, especially for transcatheter aortic valve implantation, which is associated with differing outcomes for patients with the same disease. Providing equitable care is a founding principle of the UK NHS, which is well positioned to deliver innovative policy responses to reverse observed inequalities. Understanding differences in care may enable the implementation of appropriate strategies to mitigate differences in outcomes.

Future Innovations in Novel Detection for Atrial Fibrillation (FIND-AF): pilot study of an electronic health record machine learning algorithm-guided intervention to identify undiagnosed atrial fibrillation

INTRODUCTION

Atrial fibrillation (AF) is associated with a fivefold increased risk of stroke. Oral anticoagulation reduces the risk of stroke, but AF is elusive. A machine learning algorithm (Future Innovations in Novel Detection of Atrial Fibrillation (FIND-AF)) developed to predict incident AF within 6 months using data in primary care electronic health records (EHRs) could be used to guide AF screening. The objectives of the FIND-AF pilot study are to determine yields of AF during ECG monitoring across AF risk estimates and establish rates of recruitment and protocol adherence in a remote AF screening pathway.

METHODS AND ANALYSIS

The FIND-AF Pilot is an interventional, non-randomised, single-arm, open-label study that will recruit 1955 participants aged 30 years or older, without a history of AF and eligible for oral anticoagulation, identified as higher risk and lower risk by the FIND-AF risk score from their primary care EHRs, to a period of remote ECG monitoring with a Zenicor-ECG device. The primary outcome is AF diagnosis during ECG monitoring, and secondary outcomes include recruitment rates, withdrawal rates, adherence to ECG monitoring and prescription of oral anticoagulation to participants diagnosed with AF during ECG monitoring.

ETHICS AND DISSEMINATION

The study has ethical approval (the North West-Greater Manchester South Research Ethics Committee reference 23/NW/0180). Findings will be announced at relevant conferences and published in peer-reviewed journals in line with the Funder's open access policy.

TRIAL REGISTRATION NUMBER

NCT05898165.