Search

Recent artificial intelligence (AI) advancements in cardiovascular care offer potential enhancements in effective diagnosis, treatment, and outcomes. More than 600 U.S. Food and Drug Administration–approved clinical AI algorithms now exist, with 10% focusing on cardiovascular applications, highlighting the growing opportunities for AI to augment care. This review discusses the latest advancements in the field of AI, with a particular focus on the utilization of multimodal inputs and the field of generative AI. Further discussions in this review involve an approach to understanding the larger context in which AI-augmented care may exist, and include a discussion of the need for rigorous evaluation, appropriate infrastructure for deployment, ethics and equity assessments, regulatory oversight, and viable business cases for deployment. Embracing this rapidly evolving technology while setting an appropriately high evaluation benchmark with careful and patient-centered implementation will be crucial for cardiology to leverage AI to enhance patient care and the provider experience. [Display omitted] • Applications of AI to cardiovascular care have accelerated as a result of advances in multimodal inputs and generative technology. • Realizing the potential of AI requires enhanced infrastructure, rigorous evaluation, regulatory oversight, and viable business models. • Clinicians should have a basic understanding of AI, its applications, and limitations to assure appropriate use. [ABSTRACT FROM AUTHOR]

Recent artificial intelligence (AI) advancements in cardiovascular care offer potential enhancements in diagnosis, treatment, and outcomes. Innovations to date focus on automating measurements, enhancing image quality, and detecting diseases using novel methods. Applications span wearables, electrocardiograms, echocardiography, angiography, genetics, and more. AI models detect diseases from electrocardiograms at accuracy not previously achieved by technology or human experts, including reduced ejection fraction, valvular heart disease, and other cardiomyopathies. However, AI's unique characteristics necessitate rigorous validation by addressing training methods, real-world efficacy, equity concerns, and long-term reliability. Despite an exponentially growing number of studies in cardiovascular AI, trials showing improvement in outcomes remain lacking. A number are currently underway. Embracing this rapidly evolving technology while setting a high evaluation benchmark will be crucial for cardiology to leverage AI to enhance patient care and the provider experience. [Display omitted] • AI models can detect cardiovascular disorders including reduced ejection fraction, valvular heart disease, and cardiomyopathies from electrocardiograms with accuracy not previously achieved by human experts or technology. • Despite an exploding number of studies of cardiovascular AI technologies and ongoing patient-oriented trials, evidence of improvement in outcomes is not currently available. • All cardiac imaging modalities now have applications using AI, improving acquisition, measurement, and diagnostic capacity. [ABSTRACT FROM AUTHOR]

The text discusses the financial implications of using artificial intelligence (AI) in healthcare. It highlights the potential for AI tools to identify patients at risk for certain diseases or health outcomes, but notes that insurance coverage for follow-up diagnostic testing may not be readily granted for patients without traditional risk factors or symptoms. The text emphasizes the need for healthcare organizations to address the potential financial harm to patients and advocates for aligning insurance coverage processes with the rapid progress in AI use. It also raises concerns about healthcare disparities and the equitable distribution of AI benefits. [Extracted from the article]

[Display omitted] [ABSTRACT FROM AUTHOR]

Aims: Obstructive hypertrophic cardiomyopathy (oHCM) is a disease of the cardiomyocyte in which dynamic left ventricular outflow track obstruction may lead to heart failure, valvular disease, and sudden death. Little is known about healthcare resource utilization (HRU) and costs associated with oHCM. This study investigated the clinical and economic burden of oHCM in patients with or without symptoms associated with oHCM. Methods: We used the US IBM MarketScan Commercial and Medicare Supplemental database to identify patients with oHCM (January 2009-March 2019). Control patients without cardiomyopathy were matched to each patient with oHCM based on age, sex, region, and index year (3:1 ratio). One-year HRU and cost data were compared between all oHCM, symptomatic oHCM, and asymptomatic oHCM subgroups, and their respective controls. Results: Among 11,401 eligible patients with oHCM (mean age 57 years, 42% female), 5,667 (50%) were symptomatic (23% chest pain, 57% dyspnea, 29% fatigue, 17% syncope). oHCM was associated with significant increases in all-cause hospitalizations, hospital days, outpatient visits, and total healthcare costs (mean ± standard deviation: $26,929 ± 77,720 vs. $6,808 ± 25,712, p<.001) compared with matched controls. These differences were driven mainly by the clinical and economic burden of symptomatic oHCM, which was associated with significant increases in 1-year hospitalization rates (38.0 vs. 6.9%), hospital days (3.7 ± 9.9 vs. 0.4 ± 3.0), and total healthcare costs ($43,586 ± 103,756 vs. $6,768 ± 27,618; all p<.001). Adjustment for comorbidities had minimal impact on these differences. Limitations: The use of claims data relies on International Classification of Diseases (ICD-9 and ICD-10) diagnosis codes, which might be inaccurate. Only commercially insured patients were included. Conclusion: In a real-world population, oHCM was associated with substantial increases in HRU and incremental costs of ≥$20,000/year when compared with matched controls--a difference that increased to ≥$35,000/year among symptomatic patients. Further studies are warranted to understand the potential impact of specific therapies on HRU and the economic burden of oHCM. PLAIN LANGUAGE SUMMARY Obstructive hypertrophic cardiomyopathy (oHCM) is a medical condition in which the heart muscle becomes abnormally thick and can cause partial blockage of blood flow out of the heart. Some patients experience symptoms (such as shortness of breath, chest pain, and fatigue) from this condition while others do not. Little is known about the healthcare resource utilization (HRU) and costs associated with oHCM, and if there are any differences between patients with oHCM who experience symptoms versus those who are asymptomatic. Therefore, we performed a study to investigate the clinical and economic burden of oHCM in patients with or without symptoms associated with oHCM. Based on insurance claims data, ≥50% of all patients with diagnosed oHCM are symptomatic. Symptomatic patients experience nearly 8 times as many hospitalizations and cost the healthcare system >$35,000 per year more than matched controls. In contrast, asymptomatic patients with oHCM have a much smaller difference in HRU and costs (≥$3,600/year) compared with matched controls. The results of this study suggest that effective therapies for oHCM may provide economic value, even if the impact of therapy is limited solely to the relief of symptoms. [ABSTRACT FROM AUTHOR]

Coronary artery calcium (CAC) is a strong predictor of cardiovascular events across all racial and ethnic groups. CAC can be quantified on nonelectrocardiography (ECG)-gated computed tomography (CT) performed for other reasons, allowing for opportunistic screening for subclinical atherosclerosis. The authors investigated whether incidental CAC quantified on routine non–ECG-gated CTs using a deep-learning (DL) algorithm provided cardiovascular risk stratification beyond traditional risk prediction methods. Incidental CAC was quantified using a DL algorithm (DL-CAC) on non–ECG-gated chest CTs performed for routine care in all settings at a large academic medical center from 2014 to 2019. We measured the association between DL-CAC (0, 1-99, or ≥100) with all-cause death (primary outcome), and the secondary composite outcomes of death/myocardial infarction (MI)/stroke and death/MI/stroke/revascularization using Cox regression. We adjusted for age, sex, race, ethnicity, comorbidities, systolic blood pressure, lipid levels, smoking status, and antihypertensive use. Ten-year atherosclerotic cardiovascular disease risk was calculated using the pooled cohort equations. Of 5,678 adults without ASCVD (51% women, 18% Asian, 13% Hispanic/Latinx), 52% had DL-CAC >0. Those with DL-CAC ≥100 had an average 10-year ASCVD risk of 24%; yet, only 26% were on statins. After adjustment, patients with DL-CAC ≥100 had increased risk of death (HR: 1.51; 95% CI: 1.28-1.79), death/MI/stroke (HR: 1.57; 95% CI: 1.33-1.84), and death/MI/stroke/revascularization (HR: 1.69; 95% CI: 1.45-1.98) compared with DL-CAC = 0. Incidental CAC ≥100 was associated with an increased risk of all-cause death and adverse cardiovascular outcomes, beyond traditional risk factors. DL-CAC from routine non–ECG-gated CTs identifies patients at increased cardiovascular risk and holds promise as a tool for opportunistic screening to facilitate earlier intervention. [Display omitted] [ABSTRACT FROM AUTHOR]

Competing Interests: Funding Support and Author Disclosures Dr Jain has received consulting fees from Bristol Myers Squibb, ARTIS Ventures, and Broadview Ventures outside of the submitted work. Dr Sarraju holds stock in Medeloop. Dr Ashley is a founder of Personalis, DeepCell, and Svexa; is a founding advisor of Nuevocor; is a nonexecutive director at AstraZeneca; and has served as an advisor for SequenceBio, Novartis, Medical Excellence Capital, Foresite Capital, and Third Rock Ventures. Dr Harrington has served on the Board of Directors for the American Heart Association and Cytokinetics; has served as a consultant or advisor for the National Heart, Lung, and Blood Institute, Atropos Health, Bitterroot Bio, Bristol Myers Squibb, Bridge Bio, Chiesi, CPC Clinical Research/Colorado Prevention Center, CSL Behring, Edwards Lifesciences, Element Science, Foresight, Merck, and WebMD; has received research grants/contracts for the randomized controlled trials from the National Heart, Lung, and Blood Institute (ISCHEMIA), Duke/Patient-Centered Outcomes Research Institute (ADAPTABLE), Janssen (Factor XIa inhibitor), and CSL (HDL); and has served on the data safety and monitoring board for the Baim Institute and the University of Colorado. Dr Mahaffey has received research support from the American Heart Association, Apple Inc, Bayer Pharmaceuticals, the California Institute for Regenerative Medicine, Commonwealth Serum Laboratories (CSL) Behring, Eidos, Ferring, Gilead, Verily (Google), Idorsia, Johnson & Johnson (J&J), Luitpold, Novartis, the PAC-12, Precordior, and Sanifit; has received consulting fees from Applied Therapeutics, Bayer, Bristol Myers Squibb, BridgeBio, CSL Behring, Elsevier, Fosun Pharma, Human, Johnson & Johnson, Moderna, Myokardia, Novartis, Novo Nordisk, Otsuka, Phasebio, Portola, Quidel, and Theravance; and has equity holdings in Human, Medeloop, Precordior, and Regencor. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose.

Competing Interests: Disclosures The authors have no conflicts to disclose.

Competing Interests: Disclosures The authors have no conflicts of interest to disclose.