Cardiovascular Imaging and Intervention Through the Lens of Artificial Intelligence.

Artificial Intelligence (AI) is the simulation of human intelligence in machines so they can perform various actions and execute decision-making. Machine learning (ML), a branch of AI, can analyse information from data and discover novel patterns. AI and ML are rapidly gaining prominence in healthcare as data become increasingly complex. These algorithms can enhance the role of cardiovascular imaging by automating many tasks or calculations, find new patterns or phenotypes in data and provide alternative diagnoses. In interventional cardiology, AI can assist in intraprocedural guidance, intravascular imaging and provide additional information to the operator. AI is slowly expanding its boundaries into interventional cardiology and can fundamentally alter the field. In this review, the authors discuss how AI can enhance the role of cardiovascular imaging and imaging in interventional cardiology.

A Machine-Learning Framework to Identify Distinct Phenotypes of Aortic Stenosis Severity.

OBJECTIVES: The authors explored the development and validation of machine-learning models for augmenting the echocardiographic grading of aortic stenosis (AS) severity. BACKGROUND: In AS, symptoms and adverse events develop secondarily to valvular obstruction and left ventricular decompensation. The current echocardiographic grading of AS severity focuses on the valve and is limited by diagnostic uncertainty. METHODS: Using echocardiography (ECHO) measurements (ECHO cohort, n = 1,052), we performed patient similarity analysis to derive high-severity and low-severity phenogroups of AS. We subsequently developed a supervised machine-learning classifier and validated its performance with independent markers of disease severity obtained using computed tomography (CT) (CT cohort, n = 752) and cardiovascular magnetic resonance (CMR) imaging (CMR cohort, n = 160). The classifier's prognostic value was further validated using clinical outcomes (aortic valve replacement [AVR] and death) observed in the ECHO and CMR cohorts. RESULTS: In 1,964 patients from the 3 multi-institutional cohorts, 1,346 (68%) subjects had either nonsevere or discordant AS severity. Machine learning identified 1,117 (57%) patients as having high-severity and 847 (43%) as having low-severity AS. High-severity patients in CT and CMR cohorts had higher valve calcium scores and left ventricular mass and fibrosis, respectively than the low-severity group. In the ECHO cohort, progression to AVR and progression to death in patients who did not receive AVR was faster in the high-severity group. Compared with the conventional classification of disease severity, machine-learning-based severity classification improved discrimination (integrated discrimination improvement: 0.07; 95% confidence interval: 0.02 to 0.12) and reclassification (net reclassification improvement: 0.17; 95% confidence interval: 0.11 to 0.23) for the outcome of AVR at 5 years. For both ECHO and CMR cohorts, we observed prognostic value of the machine-learning classifications for subgroups with asymptomatic, nonsevere or discordant AS. CONCLUSIONS: Machine learning can integrate ECHO measurements to augment the classification of disease severity in most patients with AS, with major potential to optimize the timing of AVR.

CT assessment of the left atrial appendage post-transcatheter occlusion - A systematic review and meta analysis.

BACKGROUND: Transesophageal echocardiography (TEE) is the standard imaging modality used to assess the left atrial appendage (LAA) after transcatheter device occlusion. Cardiac computed tomography angiography (CCTA) offers an alternative non-invasive modality in these patients. We aimed to conduct a comparison of the two modalities. METHODS: We performed a comprehensive systematic review of the current literature pertaining to CCTA to establish its usefulness during follow-up for patients undergoing LAA device closure. Studies that reported the prevalence of inadequate LAA closure on both CCTA and TEE were further evaluated in a meta-analysis. 19 studies were used in the systematic review, and six studies were used in the meta-analysis. RESULTS: The use of CCTA was associated with a higher likelihood of detecting LAA patency than the use of TEE (OR, 2.79, 95% CI 1.34-5.80, p â€‹= â€‹0.006, I2 â€‹= â€‹70.4%). There was no significant difference in the prevalence of peridevice gap ≥5 â€‹mm (OR, 3.04, 95% CI 0.70-13.17, p â€‹= â€‹0.13, I2 â€‹= â€‹0%) between the two modalities. Studies that reported LAA assessment in early and delayed phase techniques detected a 25%-50% higher prevalence of LAA patency on the delayed imaging. CONCLUSION: CCTA can be used as an alternative to TEE for LAA assessment post occlusion. Standardized CCTA acquisition and interpretation protocols should be developed for clinical practice.

Proposed Requirements for Cardiovascular Imaging-Related Machine Learning Evaluation (PRIME): A Checklist: Reviewed by the American College of Cardiology Healthcare Innovation Council.

Machine learning (ML) has been increasingly used within cardiology, particularly in the domain of cardiovascular imaging. Due to the inherent complexity and flexibility of ML algorithms, inconsistencies in the model performance and interpretation may occur. Several review articles have been recently published that introduce the fundamental principles and clinical application of ML for cardiologists. This paper builds on these introductory principles and outlines a more comprehensive list of crucial responsibilities that need to be completed when developing ML models. This paper aims to serve as a scientific foundation to aid investigators, data scientists, authors, editors, and reviewers involved in machine learning research with the intent of uniform reporting of ML investigations. An independent multidisciplinary panel of ML experts, clinicians, and statisticians worked together to review the theoretical rationale underlying 7 sets of requirements that may reduce algorithmic errors and biases. Finally, the paper summarizes a list of reporting items as an itemized checklist that highlights steps for ensuring correct application of ML models and the consistent reporting of model specifications and results. It is expected that the rapid pace of research and development and the increased availability of real-world evidence may require periodic updates to the checklist.

Usefulness of Semisupervised Machine-Learning-Based Phenogrouping to Improve Risk Assessment for Patients Undergoing Transcatheter Aortic Valve Implantation.

Semisupervised machine-learning methods are able to learn from fewer labeled patient data. We illustrate the potential use of a semisupervised automated machine-learning (AutoML) pipeline for phenotyping patients who underwent transcatheter aortic valve implantation and identifying patient groups with similar clinical outcome. Using the Transcatheter Valve Therapy registry data, we divided 344 patients into 2 sequential cohorts (cohort 1, n = 211, cohort 2, n = 143). We investigated patient similarity analysis to identify unique phenogroups of patients in the first cohort. We subsequently applied the semisupervised AutoML to the second cohort for developing automatic phenogroup labels. The patient similarity network identified 5 patient phenogroups with substantial variations in clinical comorbidities and in-hospital and 30-day outcomes. Cumulative assessment of patients from both cohorts revealed lowest rates of procedural complications in Group 1. In comparison, Group 5 was associated with higher rates of in-hospital cardiovascular mortality (odds ratio [OR] 35, 95% confidence interval [CI] 4 to 309, p = 0.001), in-hospital all-cause mortality (OR 9, 95% CI 2 to 33, p = 0.002), 30-day cardiovascular mortality (OR 18, 95% CI 3 to 94, p <0.001), and 30-day all-cause mortality (OR 3, 95% CI 1.2 to 9, p = 0.02) . For 30-day cardiovascular mortality, using phenogroup data in conjunction with the Society of Thoracic Surgeon score improved the overall prediction of mortality versus using the Society of Thoracic Surgeon scores alone (AUC 0.96 vs AUC 0.8, p = 0.02). In conclusion, we illustrate that semisupervised AutoML platforms identifies unique patient phenogroups who have similar clinical characteristics and overall risk of adverse events post-transcatheter aortic valve implantation.

Machine Learning Assessment of Left Ventricular Diastolic Function Based on Electrocardiographic Features.

BACKGROUND: Left ventricular (LV) diastolic dysfunction is recognized as playing a major role in the pathophysiology of heart failure; however, clinical tools for identifying diastolic dysfunction before echocardiography remain imprecise. OBJECTIVES: This study sought to develop machine-learning models that quantitatively estimate myocardial relaxation using clinical and electrocardiography (ECG) variables as a first step in the detection of LV diastolic dysfunction. METHODS: A multicenter prospective study was conducted at 4 institutions in North America enrolling a total of 1,202 subjects. Patients from 3 institutions (n = 814) formed an internal cohort and were randomly divided into training and internal test sets (80:20). Machine-learning models were developed using signal-processed ECG, traditional ECG, and clinical features and were tested using the test set. Data from the fourth institution was reserved as an external test set (n = 388) to evaluate the model generalizability. RESULTS: Despite diversity in subjects, the machine-learning model predicted the quantitative values of the LV relaxation velocities (e') measured by echocardiography in both internal and external test sets (mean absolute error: 1.46 and 1.93 cm/s; adjusted R2 = 0.57 and 0.46, respectively). Analysis of the area under the receiver operating characteristic curve (AUC) revealed that the estimated e' discriminated the guideline-recommended thresholds for abnormal myocardial relaxation and diastolic and systolic dysfunction (LV ejection fraction) the internal (area under the curve [AUC]: 0.83, 0.76, and 0.75) and external test sets (0.84, 0.80, and 0.81), respectively. Moreover, the estimated e' allowed prediction of LV diastolic dysfunction based on multiple age- and sex-adjusted reference limits (AUC: 0.88 and 0.94 in the internal and external sets, respectively). CONCLUSIONS: A quantitative prediction of myocardial relaxation can be performed using easily obtained clinical and ECG features. This cost-effective strategy may be a valuable first clinical step for assessing the presence of LV dysfunction and may potentially aid in the early diagnosis and management of heart failure patients.

A Network-Based "Phenomics" Approach for Discovering Patient Subtypes From High-Throughput Cardiac Imaging Data.

OBJECTIVES: The authors present a method that focuses on cohort matching algorithms for performing patient-to-patient comparisons along multiple echocardiographic parameters for predicting meaningful patient subgroups. BACKGROUND: Recent efforts in collecting multiomics data open numerous opportunities for comprehensive integration of highly heterogenous data to classify a patient's cardiovascular state, eventually leading to tailored therapies. METHODS: A total of 42 echocardiography features, including 2-dimensional and Doppler measurements, left ventricular (LV) and atrial speckle-tracking, and vector flow mapping data, were obtained in 297 patients. A similarity network was developed to delineate distinct patient phenotypes, and then neural network models were trained for discriminating the phenotypic presentations. RESULTS: The patient similarity model identified 4 clusters (I to IV), with patients in each cluster showed distinctive clinical presentations based on American College of Cardiology/American Heart Association heart failure stage and the occurrence of short-term major adverse cardiac and cerebrovascular events. Compared with other clusters, cluster IV had a higher prevalence of stage C or D heart failure (78%; p < 0.001), New York Heart Association functional classes III or IV (61%; p < 0.001), and a higher incidence of major adverse cardiac and cerebrovascular events (p < 0.001). The neural network model showed robust prediction of patient clusters, with area under the receiver-operating characteristic curve ranging from 0.82 to 0.99 for the independent hold-out validation set. CONCLUSIONS: Automated computational methods for phenotyping can be an effective strategy to fuse multidimensional parameters of LV structure and function. It can identify distinct cardiac phenogroups in terms of clinical characteristics, cardiac structure and function, hemodynamics, and outcomes.

Non-invasive prediction of tissue Doppler-derived E/e' ratio using lung Doppler signals.

AIMS: Lung Doppler signals (LDS) represent the radial movement of small pulmonary blood vessel walls, caused by pulse waves of cardiac origin. We sought to investigate the accuracy and prognostic value of LDS as a predictor of mitral valve early diastolic flow to annular velocity ratio (E/e'), in patients with acute decompensated heart failure (ADHF). METHODS AND RESULTS: We prospectively enrolled patients with ADHF (n = 99, mean age 65 ± 15 years, 61% males) who underwent echocardiographic and simultaneous LDS evaluation at hospital admission. Patients with hospital stay over 72 h underwent a repeat echocardiogram and LDS assessment before discharge. Patients were followed for the occurrence of short-term all-cause mortality and heart failure (HF) hospitalization. Predicted E/e' from LDS correlated with echocardiographic E/e' at admission and discharge (r = 0.67 and 0.83; P < 0.001 for both), respectively. Patients were dichotomized into two groups by the median predicted-E/e'. A high predicted-E/e' was associated with age, hypertension, anaemia, history of HF with preserved ejection fraction (EF), and chronic kidney disease. Over a median follow-up period of 7 months, 22 (22.2%) patients died and 23 (23.2%) patients were rehospitalized for HF. Kaplan-Meier analysis revealed a significantly lower event-free survival in high predicted-E/e' group HF patients with reduced EF (P = 0.0247). No significant differences were observed in HF rehospitalization rates between the two groups. CONCLUSION: In this single-centre prospective study of patients with ADHF, LDS predicted echocardiographic E/e' measurements and showed prognostic value in predicting all-cause mortality in HF patients with a reduced EF.

A low-cost texture-based pipeline for predicting myocardial tissue remodeling and fibrosis using cardiac ultrasound.

BACKGROUND: Maturation of ultrasound myocardial tissue characterization may have far-reaching implications as a widely available alternative to cardiac magnetic resonance (CMR) for risk stratification in left ventricular (LV) remodeling. METHODS: We extracted 328 texture-based features of myocardium from still ultrasound images. After we explored the phenotypes of myocardial textures using unsupervised similarity networks, global LV remodeling parameters were predicted using supervised machine learning models. Separately, we also developed supervised models for predicting the presence of myocardial fibrosis using another cohort who underwent cardiac magnetic resonance (CMR). For the prediction, patients were divided into a training and test set (80:20). FINDINGS: Texture-based tissue feature extraction was feasible in 97% of total 534 patients. Interpatient similarity analysis delineated two patient groups based on the texture features: one group had more advanced LV remodeling parameters compared to the other group. Furthermore, this group was associated with a higher incidence of cardiac deaths (p = 0.001) and major adverse cardiac events (p < 0.001). The supervised models predicted reduced LV ejection fraction (<50%) and global longitudinal strain (<16%) with area under the receiver-operator-characteristics curves (ROC AUC) of 0.83 and 0.87 in the hold-out test set, respectively. Furthermore, the presence of myocardial fibrosis was predicted from only ultrasound myocardial texture with an ROC AUC of 0.84 (sensitivity 86.4% and specificity 83.3%) in the test set. INTERPRETATION: Ultrasound texture-based myocardial tissue characterization identified phenotypic features of LV remodeling from still ultrasound images. Further clinical validation may address critical barriers in the adoption of ultrasound techniques for myocardial tissue characterization. FUNDING: None.

Interpatient Similarities in Cardiac Function: A Platform for Personalized Cardiovascular Medicine.

OBJECTIVES: The authors applied unsupervised machine-learning techniques for integrating echocardiographic features of left ventricular (LV) structure and function into a patient similarity network that predicted major adverse cardiac event(s) (MACE) in an individual patient. BACKGROUND: Patient similarity analysis is an evolving paradigm for precision medicine in which patients are clustered or classified based on their similarities in several clinical features. METHODS: A retrospective cohort of 866 patients was used to develop a network architecture using 9 echocardiographic features of LV structure and function. The data for 468 patients from 2 prospective cohort registries were then added to test the model's generalizability. RESULTS: The map of cross-sectional data in the retrospective cohort resulted in a looped patient network that persisted even after the addition of data from the prospective cohort registries. After subdividing the loop into 4 regions, patients in each region showed unique differences in LV function, with Kaplan-Meier curves demonstrating significant differences in MACE-related rehospitalization and death (both p < 0.001). Addition of network information to clinical risk predictors resulted in significant improvements in net reclassification, integrated discrimination, and median risk scores for predicting MACE (p < 0.05 for all). Furthermore, the network predicted the cardiac disease cycle in each of the 96 patients who had second echocardiographic evaluations. An improvement or remaining in low-risk regions was associated with lower MACE-related rehospitalization rates than worsening or remaining in high-risk regions (3% vs. 37%; p < 0.001). CONCLUSIONS: Patient similarity analysis integrates multiple features of cardiac function to develop a phenotypic network in which patients can be mapped to specific locations associated with specific disease stage and clinical outcomes. The use of patient similarity analysis may have relevance for automated staging of cardiac disease severity, personalized prediction of prognosis, and monitoring progression or response to therapies.

Echocardiographic assessment of mitral regurgitation.

Mitral regurgitation (MR) is one of the most frequent indications for valve surgery in developed countries, and echocardiographic assessment is an essential tool to evaluate its etiologies, severity, and therapeutic indications. The mitral valve apparatus is a complex structure composed of several parts: apart from the mitral valve leaflets and annulus, it also includes the chordae tendineae, papillary muscles, and left ventricular (LV) wall. MR can be caused not only by organic changes of the mitral valve leaflets or chordae (primary MR) but also by extreme mitral annular enlargement or mitral leaflet tethering due to displacement and malfunction of papillary muscles and LV wall (secondary MR). In secondary MR with LV dysfunction, a milder degree of MR can be associated with adverse outcomes compared with primary MR. Grading the severity is the first step in evaluation of indication for surgical/transcatheter interventions. As such, there are several techniques to assess the severity of MR using echocardiography. However, none of the techniques is reliable enough by itself, and it is always recommended to integrate multiple methods. In cases where echocardiographic assessment of MR severity is inconclusive, magnetic resonance may be helpful. In addition to the severity, anatomical information, such as localization in primary MR due to mitral valve prolapse and LV size in secondary MR due to LV dilatation/dysfunction, is an important concern in presurgical echocardiography. Transesophageal echocardiography and three-dimensional echocardiography are key techniques for anatomical evaluation including mitral valve and LV volumes. In transcatheter intervention for MR, echocardiography plays a pivotal role as a guide for procedures and endpoints. In this review article, the authors provide a comprehensive summary of current standards of echocardiographic assessment of MR.

Artificial Intelligence in Cardiovascular Medicine.

PURPOSE OF REVIEW: The ripples of artificial intelligence are being felt in various sectors of human life. Machine learning, a subset of artificial intelligence, extracts information from large databases of information and is gaining traction in various fields of cardiology. In this review, we highlight noteworthy examples of machine learning utilization in echocardiography, nuclear cardiology, computed tomography, and magnetic resonance imaging over the past year. RECENT FINDINGS: In the past year, machine learning (ML) has expanded its boundaries in cardiology with several positive results. Some studies have integrated clinical and imaging information to further augment the accuracy of these ML algorithms. All the studies mentioned in this review have clearly demonstrated superior results of ML in relation to conventional approaches for identifying obstructions or predicting major adverse events in reference to conventional approaches. As the influx of data arriving from gradually evolving technologies in health care and wearable devices continues to be more complex, ML may serve as the bridge to transcend the gap between health care and patients in the future. In order to facilitate a seamless transition between both, a few issues must be resolved for a successful implementation of ML in health care.

Artificial Intelligence in Cardiovascular Imaging: JACC State-of-the-Art Review.

Data science is likely to lead to major changes in cardiovascular imaging. Problems with timing, efficiency, and missed diagnoses occur at all stages of the imaging chain. The application of artificial intelligence (AI) is dependent on robust data; the application of appropriate computational approaches and tools; and validation of its clinical application to image segmentation, automated measurements, and eventually, automated diagnosis. AI may reduce cost and improve value at the stages of image acquisition, interpretation, and decision-making. Moreover, the precision now possible with cardiovascular imaging, combined with "big data" from the electronic health record and pathology, is likely to better characterize disease and personalize therapy. This review summarizes recent promising applications of AI in cardiology and cardiac imaging, which potentially add value to patient care.

Network Tomography for Understanding Phenotypic Presentations in Aortic Stenosis.

OBJECTIVES: This study sought to build a patient-patient similarity network using multiple features of left ventricular (LV) structure and function in patients with aortic stenosis (AS). The study further validated the observations in an experimental murine model of AS. BACKGROUND: The LV response in AS is variable and results in heterogeneous phenotypic presentations. METHODS: The patient similarity network was developed using topological data analysis (TDA) from cross-sectional echocardiographic data collected from 246 patients with AS. Multivariate features of AS were represented on the map, and the network topology was compared with that of a murine AS model by imaging 155 animals at 3, 6, 9, or 12 months of age. RESULTS: The topological map formed a loop in which patients with mild and severe AS were aggregated on the right and left sides, respectively (p < 0.001). These 2 regions were linked through moderate AS; with upper arm of the loop showing patients with predominantly reduced ejection fractions (EFs), and the lower arm showing patients with preserved EFs (p < 0.001). The region of severe AS showed >3 times the increased risk of balloon valvuloplasty, and transcatheter or surgical aortic valve replacement (hazard ratio: 3.88; p < 0.001) compared with the remaining patients in the map. Following aortic valve replacement, patients recovered and moved toward the zone of mild and moderate AS. Topological data analysis in mice showed a similar distribution, with 1 side of the loop corresponding to higher peak aortic velocities than the opposite side (p < 0.0001). The validity of the cross-sectional data that revealed a path of AS progression was confirmed by comparing the locations occupied by 2 groups of mice that were serially imaged. LV systolic and diastolic dysfunction were frequently identified even during moderate AS in both humans and mice. CONCLUSIONS: Multifeature assessments of patient similarity by machine-learning processes may allow precise phenotypic recognition of the pattern of LV responses during the progression of AS.