Artificial Intelligence in Cardiovascular Medicine: From Clinical Care, Education, and Research Applications to Foundational Models - A Perspective.

Chinni and Manlhiot's work on machine learning in pediatric and congenital heart disease addresses the unique challenges of applying AI to rare and complex conditions with limited data[12]. Their exploration of time-dependent analysis and dimensionality reduction techniques points towards more personalized treatment strategies for children with heart disease.

Use of Artificial Intelligence Including Multimodal Systems to Improve the Management of Cardiovascular Disease.

The rising prevalence of cardiovascular disease presents an escalating challenge for current health services, which are grappling with increasing demands. Innovative changes are imperative to sustain the delivery of high-quality patient care. Recent technologic advances have resulted in the emergence of artificial intelligence as a viable solution. Advanced algorithms are now capable of performing complex analysis of large volumes of data rapidly and with exceptional accuracy. Multimodality artificial intelligence systems handle a diverse range of data including images, text, video, and audio. Compared with single-modality systems, multimodal artificial intelligence systems appear to hold promise for enhancing overall performance and enabling smoother integration into existing workflows. Such systems can empower physicians with clinical decision support and enhanced efficiency. Owing to the complexity of the field, however, truly multimodal artificial intelligence is still scarce in the management of cardiovascular disease. This article aims to cover current research, emerging trends, and the future utilisation of artificial intelligence in the management of cardiovascular disease, with a focus on multimodality systems.

Ethical Challenges and Opportunities in Applying Artificial Intelligence to Cardiovascular Medicine.

Much anticipation surrounds artificial intelligence's (AI) emergence as a promising tool in health care. It offers potential to revolutionise clinical practice through assistive and autonomous operation. The high prevalence of cardiac disease globally provides an opportunity for AI technology to increase health care efficiency and improve patient outcomes. This article explores the ethical considerations necessary for safe and acceptable implantation of AI within the health care space. We aim to highlight several challenges such as data privacy, consent, sustainability, and cybersecurity. In addition, we outline the future opportunities for AI use in cardiovascular medicine. Overall, we argue that AI deployment demands robust regulation, transparent algorithms, and safeguarding of patient privacy.

Health consumers' ethical concerns towards artificial intelligence in Australian emergency departments.

OBJECTIVES: To investigate health consumers' ethical concerns towards the use of artificial intelligence (AI) in EDs. METHODS: Qualitative semi-structured interviews with health consumers, recruited via health consumer networks and community groups, interviews conducted between January and August 2022. RESULTS: We interviewed 28 health consumers about their perceptions towards the ethical use of AI in EDs. The results discussed in this paper highlight the challenges and barriers for the effective and ethical implementation of AI from the perspective of Australian health consumers. Most health consumers are more likely to support AI health tools in EDs if they continue to be involved in the decision-making process. There is considerably more approval of AI tools that support clinical decision-making, as opposed to replacing it. There is mixed sentiment about the acceptability of AI tools influencing clinical decision-making and judgement. Health consumers are mostly supportive of the use of their data to train and develop AI tools but are concerned with who has access. Addressing bias and discrimination in AI is an important consideration for some health consumers. Robust regulation and governance are critical for health consumers to trust and accept the use of AI. CONCLUSION: Health consumers view AI as an emerging technology that they want to see comprehensively regulated to ensure it functions safely and securely with EDs. Without considerations made for the ethical design, implementation and use of AI technologies, health consumer trust and acceptance in the use of these tools will be limited.

Prevalence of asymptomatic valvular heart disease in the elderly population: a community-based echocardiographic study.

AIMS: With an ageing population, the presence of asymptomatic valvular heart disease (VHD) in the community remains unknown. The aim of this study is to determine the prevalence and associated factors of asymptomatic VHD in individuals ≥60 years old and to evaluate the feasibility of echocardiographic screening for VHD in this population. METHODS AND RESULTS: This was a prospective cohort study conducted between 2007 and 2016 in the UK. Asymptomatic patients with no prior indication for echocardiography were invited to participate and evaluated with a health questionnaire, clinical examination, and transthoracic echocardiography. A total of 10,000 individuals were invited through their general practices. A total of 5429 volunteered to participate, of whom 4237 were eligible for inclusion. VHD was diagnosed in more than a quarter of patients (28.2%). The most common types of VHD were regurgitation of the tricuspid (13.8%), mitral (12.8%), and aortic (8.3%) valves (trivial regurgitation was not included). The rate of prevalence of clinically significant VHD was 2.4% (2.2% moderate and 0.2% severe), with mitral and aortic regurgitation being the most common. The only parameter associated with significant VHD was age (odds ratio 1.07 per 1 year increment, 95% confidence interval 1.05-1.09, P < 0.001). The number needed to scan to diagnose one clinically significant case of VHD is 42 for individuals ≥60 and 15 for those ≥75 years old. CONCLUSION: Asymptomatic VHD is present in a significant proportion of otherwise healthy individuals without known VHD over 60 years old. Age is strongly associated with an increased incidence of significant VHD.

Predicting multifaceted risks using machine learning in atrial fibrillation: insights from GLORIA-AF study.

Aims: Patients with atrial fibrillation (AF) have a higher risk of ischaemic stroke and death. While anticoagulants are effective at reducing these risks, they increase the risk of bleeding. Current clinical risk scores only perform modestly in predicting adverse outcomes, especially for the outcome of death. We aimed to test the multi-label gradient boosting decision tree (ML-GBDT) model in predicting risks for adverse outcomes in a prospective global AF registry. Methods and results: We studied patients from phase II/III of the Global Registry on Long-Term Oral Anti-Thrombotic Treatment in Patients with Atrial Fibrillation registry between 2011 and 2020. The outcomes were all-cause death, ischaemic stroke, and major bleeding within 1 year following the AF. We trained the ML-GBDT model and compared its discrimination with the clinical scores in predicting patient outcomes. A total of 25 656 patients were included [mean age 70.3 years (SD 10.3); 44.8% female]. Within 1 year after AF, ischaemic stroke occurred in 215 (0.8%), major bleeding in 405 (1.6%), and death in 897 (3.5%) patients. Our model achieved an optimized area under the curve in predicting death (0.785, 95% CI: 0.757-0.813) compared with the Charlson Comorbidity Index (0.747, P = 0.007), ischaemic stroke (0.691, 0.626-0.756) compared with CHA2DS2-VASc (0.613, P = 0.028), and major bleeding (0.698, 0.651-0.745) as opposed to HAS-BLED (0.607, P = 0.002), with improvement in net reclassification index (10.0, 12.5, and 23.6%, respectively). Conclusion: The ML-GBDT model outperformed clinical risk scores in predicting the risks in patients with AF. This approach could be used as a single multifaceted holistic tool to optimize patient risk assessment and mitigate adverse outcomes when managing AF.

Associations of Testosterone and Related Hormones With All-Cause and Cardiovascular Mortality and Incident Cardiovascular Disease in Men : Individual Participant Data Meta-analyses.

BACKGROUND: Whether circulating sex hormones modulate mortality and cardiovascular disease (CVD) risk in aging men is controversial. PURPOSE: To clarify associations of sex hormones with these outcomes. DATA SOURCES: Systematic literature review to July 2019, with bridge searches to March 2024. STUDY SELECTION: Prospective cohort studies of community-dwelling men with sex steroids measured using mass spectrometry and at least 5 years of follow-up. DATA EXTRACTION: Independent variables were testosterone, sex hormone-binding globulin (SHBG), luteinizing hormone (LH), dihydrotestosterone (DHT), and estradiol concentrations. Primary outcomes were all-cause mortality, CVD death, and incident CVD events. Covariates included age, body mass index, marital status, alcohol consumption, smoking, physical activity, hypertension, diabetes, creatinine concentration, ratio of total to high-density lipoprotein cholesterol, and lipid medication use. DATA SYNTHESIS: Nine studies provided individual participant data (IPD) (255 830 participant-years). Eleven studies provided summary estimates (n = 24 109). Two-stage random-effects IPD meta-analyses found that men with baseline testosterone concentrations below 7.4 nmol/L (<213 ng/dL), LH concentrations above 10 IU/L, or estradiol concentrations below 5.1 pmol/L had higher all-cause mortality, and those with testosterone concentrations below 5.3 nmol/L (<153 ng/dL) had higher CVD mortality risk. Lower SHBG concentration was associated with lower all-cause mortality (median for quintile 1 [Q1] vs. Q5, 20.6 vs. 68.3 nmol/L; adjusted hazard ratio [HR], 0.85 [95% CI, 0.77 to 0.95]) and lower CVD mortality (adjusted HR, 0.81 [CI, 0.65 to 1.00]). Men with lower baseline DHT concentrations had higher risk for all-cause mortality (median for Q1 vs. Q5, 0.69 vs. 2.45 nmol/L; adjusted HR, 1.19 [CI, 1.08 to 1.30]) and CVD mortality (adjusted HR, 1.29 [CI, 1.03 to 1.61]), and risk also increased with DHT concentrations above 2.45 nmol/L. Men with DHT concentrations below 0.59 nmol/L had increased risk for incident CVD events. LIMITATIONS: Observational study design, heterogeneity among studies, and imputation of missing data. CONCLUSION: Men with low testosterone, high LH, or very low estradiol concentrations had increased all-cause mortality. SHBG concentration was positively associated and DHT concentration was nonlinearly associated with all-cause and CVD mortality. PRIMARY FUNDING SOURCE: Medical Research Future Fund, Government of Western Australia, and Lawley Pharmaceuticals. (PROSPERO: CRD42019139668).

Cardiac computed tomography post-transcatheter aortic valve replacement.

Transcatheter aortic valve replacement (TAVR) is performed to treat aortic stenosis and is increasingly being utilised in the low-to-intermediate-risk population. Currently, attention has shifted towards long-term outcomes, complications and lifelong maintenance of the bioprosthesis. Some patients with TAVR in-situ may develop significant coronary artery disease over time requiring invasive coronary angiography, which may be problematic with the TAVR bioprosthesis in close proximity to the coronary ostia. In addition, younger patients may require a second transcatheter heart valve (THV) to 'replace' their in-situ THV because of gradual structural valve degeneration. Implantation of a second THV carries a risk of coronary obstruction, thereby requiring comprehensive pre-procedural planning. Unlike in the pre-TAVR period, cardiac CT angiography in the post-TAVR period is not well established. However, post-TAVR cardiac CT is being increasingly utilised to evaluate mechanisms for structural valve degeneration and complications, including leaflet thrombosis. Post-TAVR CT is also expected to have a significant role in risk-stratifying and planning future invasive procedures including coronary angiography and valve-in-valve interventions. Overall, there is emerging evidence for post-TAVR CT to be eventually incorporated into long-term TAVR monitoring and lifelong planning.

Low-level elevations in high-sensitivity cardiac troponin predict obstructive coronary artery disease and revascularisation in rural patients with non-ST-elevation myocardial infarction referred for coronary angiography.

Rural patients with non-ST-elevation myocardial infarction (NSTEMI) are transferred to metropolitan hospitals for invasive coronary angiography (ICA). Yet, many do not have obstructive coronary artery disease (CAD). In this analysis of rural Western Australian patients transferred for ICA for NSTEMI, low-level elevations in high-sensitivity cardiac troponin (≤5× upper reference limit) were associated with less obstructive CAD and revascularisation. Along with other factors, this may help identify rural patients not requiring transfer for ICA.

Interpreting Wide-Complex Tachycardia With the Use of Artificial Intelligence.

BACKGROUND: Adopting artificial intelligence (AI) in medicine may improve speed and accuracy in patient diagnosis. We sought to develop an AI algorithm to interpret wide-complex tachycardia (WCT) electrocardiograms (ECGs) and compare its diagnostic accuracy with that of cardiologists. METHODS: Using 3330 WCT ECGs (2906 supraventricular tachycardia [SVT] and 424 ventricular tachycardia [VT]), we created a training/validation (3131) and a test set (199 ECGs). A convolutional neural network structure using a modification of differentiable architecture search was developed to differentiate between SVT and VT. RESULTS: The mean accuracy of electrophysiology (EP) cardiologists was 92.5% with sensitivity 91.7%, specificity 93.4%, positive predictive value 93.7%, and negative predictive value 91.7%. Non-EP cardiologists had an accuracy of 73.2 ± 14.4% with sensitivity, specificity, and positive and negative predictive values of 59.8 ± 18.2%, 93.8 ± 3.7%, 93.6 ± 2.3%, and 73.2 ± 14.4%, respectively. AI had superior sensitivity and accuracy (91.9% and 93.0%, respectively) than non-EP cardiologists and similar performance compared with EP cardiologists. Mean time to interpret each ECG varied from 10.1 to 13.8 seconds for EP cardiologists and from 3.1 to 16.6 seconds for non-EP cardiologists. AI required a mean of 0.0092 ± 0.0035 seconds for each ECG interpretation. CONCLUSIONS: AI appears to diagnose WCT with accuracy superior to non-EP cardiologists and similar to EP cardiologists. Using AI to assist with ECG interpretations may improve patient care.

Early SGLT2 inhibitor use is associated with improved left atrial strain following acute coronary syndrome.

AIM: Left atrial (LA) strain, a novel marker of LA function, reliably predicts diastolic dysfunction. SGLT2 inhibitors improve heart failure outcomes, but limited data exists regarding their use in the immediate aftermath of acute coronary syndrome (ACS). We studied the effect of empagliflozin on LA strain in patients with type 2 diabetes (T2D) and ACS. METHODS: Patients with ACS and T2D were identified and empagliflozin was initiated in eligible patients prior to discharge. Patients not initiated on empagliflozin were analysed as a comparator group. A blinded investigator assessed LA strain using baseline and 3-6 month follow-up echocardiograms. RESULTS: Forty-four participants (n = 22 each group) were included. Baseline characteristics and LA strain were similar in the two groups. LA reservoir, conduit and contractile strain increased in empagliflozin group (28.0 ± 8.4% to 34.6 ± 12.2% p < 0.001, 14.5 ± 5.4% to 16.7 ± 7.0% p = 0.034, 13.5 ± 5.2% to 17.9 ± 7.2% p = 0.005, respectively) but remained unchanged in comparison group (29.2 ± 6.7% to 28.8 ± 7.0%, 12.8 ± 4.2% to 13.3 ± 4.7%, 16.7 ± 5.3% to 15.5 ± 4.5%, respectively, p = NS). The difference in change between groups was significant for LA reservoir (p = 0.003) and contractile strain (p = 0.005). CONCLUSION: In patients with ACS and T2D, addition of empagliflozin to standard ACS therapy prior to discharge is associated with improved LA function.

Telehealth during COVID-19 restrictions in patients with cardiovascular disease: impact on medication prescriptions and patient satisfaction.

BACKGROUND AND AIMS: Telehealth plays an integral part in healthcare delivery. The impact of telehealth and the COVID-19 pandemic on medication prescribing and patient satisfaction with telehealth in cardiology clinics remains unknown. METHODS: A retrospective study of cardiology clinic patients at an Australian tertiary hospital was conducted; 630 patients seen before the COVID-19 pandemic (0.6% telehealth) and 678 during the pandemic (91.2% telehealth) were included. Medication changes, new prescriptions and time to obtaining prescriptions after clinic were compared. To evaluate patients' experiences, cardiology clinic patients reviewed during the pandemic were prospectively invited to participate in an electronic survey sent to their mobile phones. RESULTS: The overall rates of medication changes made in the clinic between the prepandemic and the pandemic periods did not differ significantly (26.9% vs 25.8%). Compared with prepandemic, new cardiac medication prescriptions during clinic were significantly less (9.3% vs 2.5%; P < 0.0001) and recommendations to general practitioners (GP) to initiate cardiac medications were significantly more (2.6% vs 9.1%; P < 0.0001). Time to obtaining new prescriptions was significantly longer in the pandemic cohort (median 0 days (range: 0-32) vs 10.5 days (range: 0-231); P < 0.0001). Two hundred forty-three (32.7%) patients participated in the survey; 50% reported that telehealth was at least as good as face-to-face consultations. Most patients (61.5%) were satisfied with telehealth and most (62.9%) wished to see telehealth continued postpandemic. CONCLUSION: Telehealth during the COVID-19 pandemic was associated with greater reliance on GP to prescribe cardiac medications and delays in obtaining prescriptions among cardiology clinic patients. Although most patients were satisfied with telehealth services, nearly half of the cardiac patients expressed preference towards traditional face-to-face consultations.

Analysis and evaluation of explainable artificial intelligence on suicide risk assessment.

This study explores the effectiveness of Explainable Artificial Intelligence (XAI) for predicting suicide risk from medical tabular data. Given the common challenge of limited datasets in health-related Machine Learning (ML) applications, we use data augmentation in tandem with ML to enhance the identification of individuals at high risk of suicide. We use SHapley Additive exPlanations (SHAP) for XAI and traditional correlation analysis to rank feature importance, pinpointing primary factors influencing suicide risk and preventive measures. Experimental results show the Random Forest (RF) model is excelling in accuracy, F1 score, and AUC (>97% across metrics). According to SHAP, anger issues, depression, and social isolation emerge as top predictors of suicide risk, while individuals with high incomes, esteemed professions, and higher education present the lowest risk. Our findings underscore the effectiveness of ML and XAI in suicide risk assessment, offering valuable insights for psychiatrists and facilitating informed clinical decisions.

Atherosclerosis as the Damocles' sword of human evolution: insights from nonhuman ape-like primates, ancient human remains, and isolated modern human populations.

Atherosclerosis is the leading cause of death worldwide, and the predominant risk factors are advanced age and high-circulating low-density lipoprotein cholesterol (LDL-C). However, the findings of atherosclerosis in relatively young mummified remains and a lack of atherosclerosis in chimpanzees despite high LDL-C call into question the role of traditional cardiovascular risk factors. The inflammatory theory of atherosclerosis may explain the discrepancies between traditional risk factors and observed phenomena in current literature. Following the divergence from chimpanzees several millennia ago, loss of function mutations in immune regulatory genes and changes in gene expression have resulted in an overactive human immune system. The ubiquity of atherosclerosis in the modern era may reflect a selective pressure that enhanced the innate immune response at the cost of atherogenesis and other chronic disease states. Evidence provided from the fields of genetics, evolutionary biology, and paleoanthropology demonstrates a sort of circular dependency between inflammation, immune system functioning, and evolution at both a species and cellular level. More recently, the role of proinflammatory stimuli, somatic mutations, and the gene-environment effect appear to be underappreciated elements in the development and progression of atherosclerosis. Neurobiological stress, metabolic syndrome, and traditional cardiovascular risk factors may instead function as intermediary links between inflammation and atherosclerosis. Therefore, considering evolution as a mechanistic process and atherosclerosis as part of the inertia of evolution, greater insight into future preventative and therapeutic interventions for atherosclerosis can be gained by examining the past.

Obesity in patients without diabetes undergoing coronary artery bypass graft surgery: Time to select patients for semaglutide.

Patients undergoing coronary artery bypass graft (CABG) surgery require intensive secondary prevention. Semaglutide reduced cardiovascular events in patients with cardiovascular disease and overweight or obesity but without diabetes in the SELECT trial. In this real-world study of 1386 patients without diabetes undergoing CABG surgery in an Australian hospital, approximately 1 in 2 patients (53.3 %) were potentially eligible for semaglutide based on the SELECT trial criteria. These findings highlight that a significant percentage of this very high-risk cohort merit receiving semaglutide for weight management and cardiovascular risk reduction. The implications for optimal care, healthcare costs and clinical guidelines require further evaluation.