The uses of AI in cardiology and cardiovascular surgery have involved numerous aspects of cardiovascular care, including:
(1) Automating advanced measurements of EKG and echocardiograms.
(2) Enhancing image quality of nuclear cardiac imaging.
(3) Robotic cardiovascular procedures, including cardiac catheterization and angiography., and detecting diseases diagnosis, treatment, and clinical outcomes.
(4) Wearables for cardiac diagnosis and follow-up; and
(5) Genetics studies that have improved diagnostics and cardiovascular risk predictions.
As of May 2024. the FDA has approved over 80 cardiovascular clinical AI algorithms.
In February 2924, Armoundas et al published A Scientific Statement From the American Heart Association on the Use of Artificial Intelligence in Improving Outcomes in Heart Disease; they included the figure on AI in heart disease.
The authors also stated:
"Yet, despite enormous academic interest and industry financing, AI-based tools, algorithms, and systems of care have yet to improve patient outcomes at scale. Therefore, another objective of this scientific statement is to identify best practices, gaps, and challenges that may improve the applicability of AI tools in each domain. For each application, we will discuss the need to identify and mitigate bias and ensure education and access to AI/ML technologies by all stakeholders across diverse health care settings.
Also in 2024, Elias and coworkers of AI summarized in the following figure the uses of AI in cardiovascular imaging modalities:
Most of the information below is derived from the above two articles.
AI/ML APPLICATIONS IN ELECTROCARDIOGRAPHY
Artificial Intelligence-Machine Learning) (AI/ML) can assist in educating ECG interpretation and evaluating expert capabilities.
Automating ECG can enable interpretation of an exponentially growing number of ECGs.
AI/ML algorithms that interpret ECGs may better mimic expert interpretation.
They can also identify subtle and interrelated nonlinear patterns in the ECG often not recognizable to experts, enhancing disease phenotyping, and may enable the identification of occult disease and prediction of impending disease.
Application of AI/ML on ECGs appears effective in detecting occult structural heart disease up to 1 to 2 years earlier than traditional testing. For example, AI of the ECG can identify left ventricular dysfunction in diverse populations irrespective of sex, race, or ethnicity, from diverse causes, including peripartum cardiomyopathy.
AI/ML of the ECG can identify other structural heart disease, including hypertrophic cardiomyopathy, amyloid heart disease, aortic stenosis, and pulmonary hypertension.
AI/ML APPLICATIONS IN IMAGING IN CARDIOVASCULAR DISEASE
AI/ML-based tools for imaging cardiovascular diseases include:
Referring and scheduling image acquisition.
Image analysis including the reduction of image acquisition and processing times.
Reduction of radiation exposure and contrast dose use; and
Assisting in diagnosis and reporting, with clinical decision support and with estimation of patient prognosis.
AI/ML APPLICATIONS IN ECHOCARDIOGRAPHY
Automated segmentation and volumetric analysis of the cardiac chambers along with ejection fraction (EF) calculation, automated assessment of valvular structures, flow gradient, longitudinal strain and cardiac wall motion abnormalities.
Automated disease detection including automated diagnosis of myocardial infarction, differentiating hypertrophic cardiomyopathy from physiological hypertrophy, constrictive pericarditis, and in detecting heart failure and pulmonary artery hypertension automatically.
AI/ML APPLICATIONS IN CARDIAC CT (INCLUDING CT ANGIOGRAPHY) INCLUDE:
Automated quantification of coronary artery plaques and blood flow. Automated quantification of coronary plaque (both calcified and noncalcified) and of coronary lumen on cardiac CT compares favorably with manual measurements in multiple studies.
Computing fractional flow reserve and myocardial perfusion.
Cardiovascular risk assessment using coronary artery calcium scoring; and
Automating the computing of coronary artery calcium scoring from low-dose chest CT or even from nuclear imaging studies, such as positron emission tomography CTs.
AI/ML APPLICATIONS IN CARDIAC MAGNETIC RESONANCE IMAGING (CMR):
Use in structural and volumetric analysis of cardiac chambers and in estimation of ventricular and myocardial blood flow and perfusion reserve.
Myocardial tissue characterization and prediction of risk of sudden cardiac death from ventricular late gadolinium CMR and to help plan treatment strategies, such as guiding ablation for ventricular tachycardia (VT) by analyzing patterns of late gadolinium CMR indicative of fibrosis that may indicate critical isthmuses for reentrant VT circuits.
Assess ischemic stroke risk from automated atrial chamber morphology and fibrosis burden measurements.
AI/ML APPLICATIONS IN NUCLEAR IMAGING
Applications of AI/ML are increasing with use in myocardial blood flow and flow reserve quantification and associated prognostication of cardiovascular mortality.
AI/ML APPLICATIONS IN CARDIAC TREATMENT PLANNING
Structural interventions are assisted by:
Using fast automated coronary vessel center-line extractions, or
Measuring stenosis for coronary interventions, or
Assessing dynamic mitral annulus, left ventricular outflow tract, sinus of Valsalva, and sinotubular measurements for transcatheter aortic valve or mitral valve replacement or patent foramen ovale closure.
AI/ML APPLICATIONS IN STROKE DIAGNOSIS, PROGNOSTICATION, AND TREATMENT PLANNING
AI/ML facilitates the diagnosis of acute stroke, by automatically detecting intracranial hemorrhage on non-contrast CT of the head.
AI/ML can be applied to baseline CT angiography images of the head to automatically detect large vessel occlusions, reducing the time to successful neurovascular intervention by ≥30 minutes.
On CT of the head, AI/ML can automatically detect early ischemic changes of the brain, without the need for diffusion-weighted MRI.
AI/ML algorithms have improved quantitation of CT or MR brain perfusion imaging and enhanced their ability to predict recovery of cerebral function during the time taken to transport patients for reperfusion therapies
Other applications of AI/ML include neurointerventional planning for the management of acute ischemic stroke and cerebral aneurysms, and for patient recruitment in clinical trials for acute stroke.
AI/ML APPLICATIONS IN HOSPITAL BEDSIDE MONITORING
AI provides tools can harvest subtle signatures across simultaneously acquired vital sign signals, including:
False Alarm Reduction
Clinical Deterioration
Sepsis and Hypotension
Cardiac Arrest
Atrial Fibrillation
Drug-Related Pro-arrhythmia
Perioperative Risk Assessment
AI/ML APPLICATIONS IN IMPLANTABLE AND WEARABLE CARDIAC TECHNOLOGIES
AI/ML are able to interpret cardiovascular and physiological data on a near continuous basis.
Several forms of FDA-cleared implanted devices are available. The efficacy and utility of each implantable device depends on its form factor, sensor type, anatomical placement, and analytics, including noise reduction and interpretation algorithms.
Consumer wearables may or may not contain FDA-cleared components. They may differ in the types of signal captured, signal processing, data security and governance, level of clinical validation, and data integration into medical records.
Motion detection is important because inactivity is associated with adverse cardiovascular outcomes and mortality and because activity provides a context for physiological signals.
The wristwatch is commonly used, but ankle recordings are superior for step counting.
Global positioning system data can augment analysis for outdoor activities, and microelectromechanical barometers can sense changes in elevation to detect activities such as stairs climbed or a fall.
Other form factors include chest patches, chest straps, wearable garments with embedded sensors, smart phones, and head-mounted devices.
Photoplethysmography (PPG) or ECG-based devices can both detect heart rate or rhythm. ECG-based devices are considered the gold standard for rhythm diagnosis.
Atrial fibrillation can be detected by AI-enabled PPG-based devices including the Apple Heart study (Assessment of Wristwatch-Based Photoplethysmography to Identify Cardiac Arrhythmias), WATCH-AF trial (Smartwatches for Detection of Atrial Fibrillation), and others.
Additional sensors in wearables include acoustic sensors to provide a phonocardiogram and skin-impedance sensors for use in garments.
Sensors in implantable devices can detect impedance to electrical current to quantify pulmonary congestion (which reduces thoracic impedance) and direct pressure sensors (e.g., pulmonary artery) for heart failure management.
Comments