free-downloads CSEVideos

AI-Enhanced ECGs May Soon Assess Overall Health

Discussion in 'Cardiology' started by Mahmoud Abudeif, Aug 31, 2019.

  1. Mahmoud Abudeif

    Mahmoud Abudeif Golden Member

    Mar 5, 2019
    Likes Received:
    Trophy Points:
    Practicing medicine in:

    Scientists have trained an artificial intelligence tool to predict sex and estimate age from electrocardiogram readouts. They suggest that, with further development, the tool could soon be helping doctors to assess the overall health of their patients.

    One day, an AI-enhanced ECG could estimate a person's overall health.
    An electrocardiogram, also known as an ECG or EKG, is a painless, simple test that records the electrical activity of a person's heart.

    A recent paper in the journal Circulation: Arrhythmia and Electrophysiology, describes how the team developed an artificial intelligence (AI) tool to predict sex and estimate age from ECG data.

    The researchers, from the Mayo Clinic College of Medicine and Science, in Rochester, MN, trained the AI tool, which is of a type known as a convolutional neural network (CNN), using ECG readouts from nearly 500,000 individuals.

    When they tested the CNN's accuracy on a further 275,000 people, they found that it was very good at predicting sex but less good at predicting age. The AI tool got the sex right 90% of the time but only got the age right 72% of the time.

    The team then focused on 100 people in the test batch for whom they had at least 20 years of ECG readouts.

    This closer investigation revealed that the accuracy of the AI tool's age estimates depended on whether the individuals had experienced heart conditions.

    AI has potential to glean 'physiologic age'

    For individuals who had experienced heart conditions, the AI tool's age estimates tended to be greater than their chronological ages.

    For those who had experienced few or no heart conditions, the AI tool's age estimates were much closer to the participants' chronological ages.

    The results showed that for people who had experienced low ejection fraction, high blood pressure, and heart disease, the AI tool estimated their ages to be at least 7 years greater than their chronological ages.

    Ejection fraction is a measure of how well the heart is pumping.

    The researchers say that these results suggest that the tool appears to be estimating biological, or physiologic, age, which, in contrast to chronological age, reflects a person's overall health status and body function.

    "This evidence," says senior study author Dr. Suraj Kapa, assistant professor of medicine at the Mayo Clinic, "that we might be gleaning some sort of 'physiologic age' was certainly both surprising and exciting for [AI's] potential role in future outcomes research and may foster a new area of science where we seek to better understand the biologic underpinnings of such a finding."

    Physiologic age marker to aid overall health assessment

    Even people with no medical training can see that different people appear to age differently.

    Scientists investigating aging research are increasingly turning to physiologic age as a way to measure progress of biological aging processes, as opposed to the simple passage of time.

    To this end, they have proposed a number of biomarkers, including those that measure substances in the blood, epigenetic alterations to DNA, and the level of frailty.

    Dr. Kapa and colleagues suggest that the ability to detect discrepancies between chronological age and the age suggested by the heart's electrical signals could serve as a useful biomarker for hidden heart disease and other conditions.

    "Being able to more accurately assess overall health status may help doctors determine which patients they should examine further to determine if there are asymptomatic or currently silent diseases that could benefit from early diagnosis and intervention," Dr. Kapa explains.

    The researchers call for more research to validate the use of the AI-enhanced ECG as a way to estimate physiologic age in healthy people.

    The data that they used came from people who had undergone ECGs for clinical reasons.

    "While physicians already consider whether a patient 'appears [their] stated age' as part of their baseline physical examination, the ability to more objectively and consistently assess this may impact healthcare on multiple levels."

    -Dr. Suraj Kapa


    Add Reply

  2. Valery1957

    Valery1957 Well-Known Member

    Jan 10, 2019
    Likes Received:
    Trophy Points:
    Practicing medicine in:
    из 9

    http://www.jgc301.com; jgc@jgc301.com | Journal of Geriatric CardiologyJournal of Geriatric Cardiology (2019) 16: 630638 ©2019 JGC All rights reserved; www.jgc301.com Research Article
     Open Access Electrocardiographic predictors of cardiovascular events in patients at high cardiovascular risk: a multicenter study

    Rungroj Krittayaphong1,#, Muenpetch Muenkaew2, Polakit Chiewvit1, Nithima Ratanasit1, Yodying Kaolawanich1, Arintaya Phrommintikul3, for the CORE Investigators 1Division of Cardiology, Department of Medicine, Faculty Of Medicine Siriraj Hospital, Mahidol University, Bangkok, Thailand 2Division of Cardiology, Department of Medicine, Faculty Of Medicine, Thammasat University, Pathum Thani, Thailand 3Department of Internal Medicine, Faculty Of Medicine, Chiang Mai University, Chiang Mai, Thailand

    Abstract Background There are limited data on the prevalence of electrocardiographic (ECG) abnormalities, and their value for predicting a major adverse cardiovascular event (MACE) in patients at high cardiovascular risk. This study aimed to determine the prevalence of ECG abnormalities in patients at high risk for cardiovascular events, and to identify ECG abnormalities that significantly predict MACE. Methods Patients aged ≥ 45 years with established atherosclerotic disease (EAD) were consecutively enrolled from the outpatient clinics of the six participating hospitals during April 2011 to March 2014. The following data were collected: demographic data, cardiovascular risk factors, history of cardiovascular event, physical examination, ECG and medications. ECG was analyzed using Minnesota Code criteria. MACE included cardiovascular death, non-fatal myocardial infarction, and hospitalization due to unstable angina or heart failure. Results A total of 2009 patients were included, 1048 patients (52.2%) had established EAD, and 961 patients (47.8%) had multiple risk factors (MRF). ECG abnormalities included atrial fibrillation (6.7%), premature ventricular contraction (5.4%), pathological Q-wave (Q/QS) (21.3%), T-wave inversion (20.0%), intraventricular ventricular conduction delay (IVCD) (7.3%), left ventricular hypertrophy (LVH) (12.2%), and AV block (12.5%). MACE occurred in 88 patients (4.4%). Independent predictors of MACE were chronic kidney disease, EAD, and the presence of atrial fibrillation, Q/QS, IVCD or LVH by ECG. Conclusions A high prevalence of ECG abnormalities was found. The prevalence of ECG abnormalities was high even among those with risk factors without documented cardiovascular disease. J Geriatr Cardiol 2019; 16: 630638. doi:10.11909/j.issn.1671-5411.2019.08.004 Keywords: Cardiovascular events; Electrocardiographic; High cardiovascular risk; Predictors 1 IntroductionAtherosclerosis is a highly prevalent condition that is the leading cause of death worldwide.[1] Although the trend of disease control seems to be better in developed countries, the burden of disease is increasing in developing countries[2]like Thailand.[3] The REduction of Atherothrombosis for Continued Health (REACH) registry revealed coronary ar-tery disease (CAD), cerebrovascular disease (CVD), and peripheral arterial disease (PAD) to be common manifesta-tions of atherosclerosis.[4] The prevalence of hypertension, diabetes, and dyslipidemia in the REACH registry was 82%, 44%, and 72%, respectively.[4]#Correspondence to: Rungroj Krittayaphong, Division of Cardiology, Department of Medicine, Faculty of Medicine Siriraj Hospital, Mahidol University, Bangkok, Thailand. E-mail: rungroj.kri@mahidol.ac.th Received: May 20, 2019 Revised: June 24, 2019 Accepted: July 23, 2019 Published online: August 28, 2019 Although a decline in cardiovascular disease-related mortality was reported, the morbidity and mortality rates remain unacceptably high.[5] The prevalence of many car-diovascular risk factors is increasing, especially in develop-ing countries.[6] The effect of the revascularization has only minimally influenced the observed reduction in cardiovas-cular mortality.[7,8] It cannot be proven that revascularization treatment plays a major role in reducing mortality among patients with stable disease.[9,10] Therefore, early detection of disease is essential. Electrocardiography (ECG) is a tool that can be used to study electrical abnormalities in patients with cardiac disease. Certain ECG abnormalities can be used to predict adverse events in patients with documented disease, and among those without overt disease.[11,12]Patients at high risk for cardiovascular events are also at high risk for developing ECG abnormalities that may de-velop prior to the onset of serious complications.[13] More-over, patients with risk factors that are well-controlled may have a lower probability of developing complications than

    Krittayaphong R, et al. ECG for risk prediction in high-risk population 631http://www.jgc301.com; jgc@jgc301.com | Journal of Geriatric Cardiologypatients whose risk factors are poorly controlled.[14] The identification of factors that independently predict a major adverse cardiovascular event (MACE) would facilitate ear-lier diagnosis and treatment. However, whether the early detection of disease and earlier treatment would improve the outcome of patients needed to be proven. Accordingly, the aims of this study were to determine the prevalence of ECG abnormalities in patients at high risk for cardiovascular events, and to identify ECG abnormalities that significantly predict a MACE. 2 Methods The Cohort Of patients with high Risk for cardiovascular Events (CORE) registry is a prospective, multicenter, ob-servational, longitudinal study of Thai patients with high atherosclerotic risk. Investigators in this registry include internists, cardiologists, neurologists, endocrinologists, ne-phrologists, and vascular surgeons. Data was collected from six centers that are located in two of Thailand’s five regions. Participating centers included four large university-based teaching hospitals, and two large provincial hospitals. The protocol for this study was approved for each participating center by the Joint Research Ethics Committee, and by the Ethics Committee of the Ministry of Public Health. Signed informed consent was obtained from all patients. 2.1 Study population Patients aged 45 years or older with established athero-sclerotic disease (EAD), which is defined as CAD, CVD, or PAD, or having at least three atherosclerosis risk factors [multiple risk factors (MRF)], were consecutively enrolled from the outpatient clinics of the six participating hospitals during the April 2011 to March 2014 enrollment period. Only patients with available ECG data during six months prior to study enrollment were included in this study. Pa-tients with cardiac implantable electronic devices (CIED) were excluded from the analysis. Documented CAD was defined as satisfying one or more of the following criteria: stable angina with documented CAD, history of unstable angina with documented CAD, history of percutaneous coronary intervention (PCI), history of coronary artery by-pass graft (CABG) surgery, or previous myocardial infarc-tion (MI). Documented CVD was defined as hospitalization with a diagnosis of transient ischemic attack or ischemic stroke. Documented PAD was defined as meeting one or both of the following criteria: current intermittent claudica-tion with ankle-brachial index (ABI) of less than 0.9 and/or previous history of surgery or intervention, such as angio-plasty, stenting, peripheral arterial bypass graft (PABG), or other vascular intervention, including amputation. Athero-sclerosis risk factors consisted of those that were docu-mented in the medical record and/or those for which pa-tients were receiving treatment at the time of study enroll-ment. Those risk factors are listed, as follows: diabetes mel-litus (DM); hypertension [systolic blood pressure (SBP) ≥140 mmHg and/or diastolic blood pressure (DBP) ≥ 90 mmHg or current treatment with antihypertensive agents]; dyslipidemia, which could be hypercholesterolemia (total cholesterol > 200 mg/dL or LDL-cholesterol > 130 mg/dL) or hypertriglyceridemia (> 150 mg/dL) or low HDL choles-terol (< 40 mg/dL) or current treatment with lipid modifying agents; chronic kidney disease (CKD) defined as the pres-ence of proteinuria or estimated glomerular filtration rate (GFR) less than 60 mL/min; current smoker of at least one cigarette per day; men aged 55 years or older, or women aged 65 years or older; and family history of premature atherosclerosis. Patients with one or more of the following conditions were excluded: acute atherosclerotic event within three months, large aortic aneurysm indicated for surgery, current participation in a blinded clinical trial, limited life expec-tancy due to a non-cardiovascular condition, such as cancer or documented human immunodeficiency virus (HIV) in-fection, and/or those who could not commit (for any reason) to returning for all follow-up visits. 2.2 Data collection Data collected at baseline included height, weight, waist circumference, seated SBP and DBP, ankle brachial index (ABI), and medications. Patients were reevaluated at 6, 12, 24, 36, 48, and 60 months. Clinical data and cardiovascular events were prospectively recorded and analyzed. MACE was defined as a composite of cardiovascular death, MI, stroke, unstable angina requiring hospital admission, and heart failure hospitalization. In this study, only subjects who had complete one-year visit data were analyzed. Data were locally collected using a standardized case re-port form. Patient data was then forwarded to the data man-agement group of the Medical Research Network of the Consortium of Thai Medical Schools (MedResNet). Data was checked for quality and completeness prior to data analysis. Random site monitoring was performed annually. 2.3 ECG data collection and analysis Twelve-lead ECG data that was in the medical record within six months prior to enrollment in the CORE registry was collected and recorded. ECG was analyzed using Min-nesota Classification of the ECG for population studies.[15]Based on Minnesota Code ECG classification, the following

Share This Page