Cardiac age detected by machine learning applied to the surface ECG of healthy subjects: Creation of a benchmark

Wall, Hein E. C. van der; Hassing, Gert-Jan; Doll, Robert; Westen, Gerard J. P. van; Cohen, Adam F.; Selder, Jasper L.; Kemme, Michiel; Burggraaf, Jacobus; Gal, Pim

doi:10.1016/j.jelectrocard.2022.03.001

Cited by 11 publications

(9 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The current study mechanistically shows that determinants of the emerging concept of cardiovascular ageing are embedded in the ECG along domains beyond the P wave, which has previously been described as an important measure associated with cardiovascular ageing and associated pathologies (15–18). In the original 10-second A-ECG heart age gap, P-wave and spatial QT durations were the two most important A-ECG measures in the model.…”

Section: Discussionmentioning

confidence: 68%

Advanced ECG heart age estimation applicable to both sinus and non-sinus rhythm associates with cardiovascular risk, cardiovascular morbidity, and survival

Al-Falahi,

Schlegel,

Lamela-Palencia

et al. 2024

Preprint

View full text Add to dashboard Cite

BackgroundAn explainable advanced electrocardiography (A-ECG) heart age gap is the difference between A-ECG heart age and chronological age. This gap is an estimate of accelerated cardiovascular ageing expressed in years of healthy human aging, and can intuitively communicate cardiovascular risk to the general population. However, existing A-ECG heart age measures require discernible P waves on the ECG.AimsTo develop and prognostically validate a revised, explainable A-ECG heart age gap without incorporating P-wave measures.MethodsAn A-ECG heart age without P-wave measures (non-P) was derived from the 10-second 12-lead ECG in a derivation cohort using multivariable regression using an existing Bayesian 5-minute 12-lead A-ECG heart age as reference. The non-P heart age was externally validated in a separate cohort of patients referred for cardiovascular magnetic resonance imaging by describing its association with heart failure hospitalization or death using Cox regression, and its association with comorbidities.ResultsIn the derivation cohort (n=2771), A-ECG non-P heart age agreed with the 5-min heart age (R2=0.91, bias 0.0±6.7 years), and increased with increasing co-morbidity. In the validation cohort (n=731, mean age 54±15 years, 43% female, n=139 events over 5.7 [4.8–6.7] years follow-up), increased A-ECG non-P heart age gap (≥10 years) associated with events (hazard ratio [95% confidence interval] 2.04 [1.38–3.00], C-statistic 0.58 [0.54–0.62], and the presence of hypertension, diabetes mellitus, hypercholesterolemia, and heart failure (p≤0.009 for all).ConclusionsAn explainable A-ECG non-P heart age gap applicable to both sinus and non-sinus rhythm associates with cardiovascular risk, cardiovascular morbidity, and survival.

show abstract

Section: Discussionmentioning

confidence: 68%

Advanced ECG heart age estimation applicable to both sinus and non-sinus rhythm associates with cardiovascular risk, cardiovascular morbidity, and survival

Al-Falahi,

Schlegel,

Lamela-Palencia

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Physiological age is a common topic of study in published scientific literature. Multiple studies have developed various tools to estimate physiological age, while others emphasize its influence in myriad decisions ranging from cardiovascular treatment to transplant surgery . Specifically, physiological age has been used to inform individualized cancer screening recommendations for older adults .…”

Section: Discussionmentioning

confidence: 99%

“…Multiple studies have developed various tools to estimate physiological age, while others emphasize its influence in myriad decisions ranging from cardiovascular treatment to transplant surgery. 33 – 36 , 49 , 50 Specifically, physiological age has been used to inform individualized cancer screening recommendations for older adults. 36 Our results suggest that practicing physicians may be unfamiliar with the term or concept of physiological age, or they may perceive it as less relevant in screening cessation decisions.…”

Section: Discussionmentioning

confidence: 99%

Different Types of Patient Health Information Associated With Physician Decision-making Regarding Cancer Screening Cessation for Older Adults

2023

View full text Add to dashboard Cite

ImportanceAlthough guidelines use limited life expectancy to guide physician decision-making regarding cessation of cancer screening, many physicians recommend screening for older adults with limited life expectancies. Different ways of presenting information may influence older adults’ screening decision-making; whether the same is true for physicians is unknown.ObjectiveTo examine how different ways of presenting patient health information are associated with physician decision-making about cancer screening cessation for older adults.Design, Setting, and ParticipantsA national survey was mailed from April 29 to November 8, 2021, to a random sample of 1800 primary care physicians and 600 gynecologists from the American Medical Association Physician Masterfile. Primary care physicians were surveyed about breast, colorectal, or prostate cancer screenings. Gynecologists were surveyed about breast cancer screening.Main Outcomes and MeasuresUsing vignettes of 2 older patients with limited life expectancies, 4 pieces of information about each patient were presented: (1) description of health conditions and functional status, (2) life expectancy, (3) equivalent physiological age, and (4) risk of dying from the specific cancer in the patient’s remaining lifetime. The primary outcome was which information was perceived to be the most influential in screening cessation.ResultsThe final sample included 776 participants (adjusted response rate, 52.8%; mean age, 51.4 years [range, 27-91 years]; 402 of 775 participants were men [51.9%]; 508 of 746 participants were White [68.1%]). The 2 types of information that were most often chosen as the factors most influential in cancer screening cessation were description of the patient’s health or functional status (36.7% of vignettes [569 of 1552]) and risk of death from cancer in the patient’s remaining lifetime (34.9% of vignettes [542 of 1552]). Life expectancy was chosen as the most influential factor in 23.1% of vignettes (358 of 1552). Physiological age was the least often chosen (5.3% of vignettes [83 of 1552]) as the most influential factor. Description of patient’s health or functional status was the most influential factor among primary care physicians (estimated probability, 40.2%; 95% CI, 36.2%-44.2%), whereas risk of death from cancer was the most influential factor among gynecologists (estimated probability, 43.1%; 95% CI, 34.0%-52.1%). Life expectancy was perceived as a more influential factor in the vignette with more limited life expectancy (estimated probability, 27.9%; 95% CI, 24.5%-31.3%) and for colorectal cancer (estimated probability, 33.9%; 95% CI, 27.3%-40.5%) or prostate cancer (28.0%; 95% CI, 21.7%-34.2%) screening than for breast cancer screening (estimated probability, 14.5%; 95% CI, 10.9%-18.0%).Conclusions and RelevanceFindings from this national survey study of physicians suggest that, in addition to the patient’s health and functional status, the cancer risk in the patient’s remaining lifetime and life expectancy were the factors most associated with physician decision-making regarding cancer screening cessation; information on cancer risk in the patient’s remaining lifetime and life expectancy is not readily available during clinical encounters. Decision support tools that present a patient’s cancer risk and/or limited life expectancy may help reduce overscreening among older adults.

show abstract

“…It indicates that ECG and EHR were the predominant data types used, while Grad-CAM and SHAP were the most frequently used XAI methods. More precisely, out of the twenty-seven, six works [46,47,[69][70][71][72] used SHAP as the XAI method across different domains, including stroke, arrhythmia, atrial fibrillation and hospital mortality. The results of the XAI evaluation were either fully or partially inline with the outcome of SHAP.…”

Section: B Proxy-grounded Evaluation In Cardiac Applicationsmentioning

confidence: 99%

A Review of Evaluation Approaches for Explainable AI With Applications in Cardiology

Salih,

Boscolo Galazzo,

Gkontra

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>Explainable artificial intelligence (XAI) elucidates the decision-making process of complex AI models and is important in building trust in model predictions. XAI explanations themselves require evaluation as to accuracy and reasonableness and in the context of use of the underlying AI model. This review details the evaluation of XAI in cardiac AI applications and has found that, of the studies examined, 37% evaluated XAI quality using literature results, 11% used clinicians as domain-experts, 11% used proxies or statistical analysis, with the remaining 43% not assessing the XAI used at all. We aim to inspire additional studies within healthcare, urging researchers not only to apply XAI methods but to systematically assess the resulting explanations, as a step towards developing trustworthy and safe models.</p>

show abstract

Cardiac age detected by machine learning applied to the surface ECG of healthy subjects: Creation of a benchmark

Cited by 11 publications

References 28 publications

Advanced ECG heart age estimation applicable to both sinus and non-sinus rhythm associates with cardiovascular risk, cardiovascular morbidity, and survival

Advanced ECG heart age estimation applicable to both sinus and non-sinus rhythm associates with cardiovascular risk, cardiovascular morbidity, and survival

Different Types of Patient Health Information Associated With Physician Decision-making Regarding Cancer Screening Cessation for Older Adults

A Review of Evaluation Approaches for Explainable AI With Applications in Cardiology

Contact Info

Product

Resources

About