Deep Learning for Echo Analysis, Tracking, and Evaluation of Mitral Regurgitation (DELINEATE-MR).

BACKGROUND: Artificial intelligence, particularly deep learning (DL), has immense potential to improve the interpretation of transthoracic echocardiography (TTE). Mitral regurgitation (MR) is the most common valvular heart disease and presents unique challenges for DL, including the integration of multiple video-level assessments into a final study-level classification. METHODS: A novel DL system was developed to intake complete TTEs, identify color MR Doppler videos, and determine MR severity on a 4-step ordinal scale (none/trace, mild, moderate, and severe) using the reading cardiologist as a reference standard. This DL system was tested in internal and external test sets with performance assessed by agreement with the reading cardiologist, weighted κ, and area under the receiver-operating characteristic curve for binary classification of both moderate or greater and severe MR. In addition to the primary 4-step model, a 6-step MR assessment model was studied with the addition of the intermediate MR classes of mild-moderate and moderate-severe with performance assessed by both exact agreement and ±1 step agreement with the clinical MR interpretation. RESULTS: A total of 61 689 TTEs were split into train (n=43 811), validation (n=8891), and internal test (n=8987) sets with an additional external test set of 8208 TTEs. The model had high performance in MR classification in internal (exact accuracy, 82%; κ=0.84; area under the receiver-operating characteristic curve, 0.98 for moderate or greater MR) and external test sets (exact accuracy, 79%; κ=0.80; area under the receiver-operating characteristic curve, 0.98 for moderate or greater MR). Most (63% internal and 66% external) misclassification disagreements were between none/trace and mild MR. MR classification accuracy was slightly higher using multiple TTE views (accuracy, 82%) than with only apical 4-chamber views (accuracy, 80%). In subset analyses, the model was accurate in the classification of both primary and secondary MR with slightly lower performance in cases of eccentric MR. In the analysis of the 6-step classification system, the exact accuracy was 80% and 76% with a ±1 step agreement of 99% and 98% in the internal and external test set, respectively. CONCLUSIONS: This end-to-end DL system can intake entire echocardiogram studies to accurately classify MR severity and may be useful in helping clinicians refine MR assessments.

Challenges and pitfalls in classification of disproportionate mitral regurgitation.

The concept of disproportionate mitral regurgitation (dispropMR) has been introduced to identify patients with functional mitral regurgitation (MR) who benefit from percutaneous treatment. We aimed to examine echocardiographic characteristics behind this entity. We retrospectively included 172 consecutive patients with reduced left ventricular ejection fraction (LVEF), and more than mild MR referred to clinically indicated echocardiography. According to the proportionality ratio (effective regurgitant orifice area (EROA)/left ventricular end-diastolic volume (LVEDV)) patients were divided into dispropMR and proportionate MR (propMR) group. Potential factors which might affect proportionality definition were analyzed. 55 patients (32%) had dispropMR. Discrepant grading of MR severity was observed when using regurgitant volume (RegVol) by proximal isovelocity surface area (PISA) method or volumetric method, with significant discordance only in dispropMR (p < 0.001). Patients with dispropMR had more frequently left ventricular foreshortened images for LVEDV calculation than patients with propMR (p = 0.003), resulting in smaller LVEDV in dispropMR group. DispropMR group had more substantial dynamic variation of regurgitant flow compared to propMR. Accordingly, EROA was consistently overestimated by standard single-point PISA method compared to serial PISA method. This was more pronounced in dispropMR (bias:10.5 ± 28.3 mm2) compared to propMR group (bias:6.4 ± 12.8 mm2). DispropMR may be found in roughly one third of clinically indicated echocardiographic studies in patients with reduced LVEF and more than mild MR. EROA overestimation due to dynamic variation of regurgitant flow and LVEDV underestimation due to LV foreshortening were more frequently found in dispropMR. Our results indicate that methodological limitations of echocardiographic MR grading could not be neglected in classifying the proportionality of MR.

New Evidence Supporting a Novel Conceptual Framework for Distinguishing Proportionate and Disproportionate Functional Mitral Regurgitation.

Importance: Traditionally, physicians distinguished between mitral regurgitation (MR) as a determinant of outcomes and MR as a biomarker of left-ventricular (LV) dysfunction by designating the lesions as primary or secondary, respectively. In primary MR, leaflet abnormalities cause the MR, resulting in modest increases in LV end-diastolic volume over time, whereas in patients with classic secondary MR, LV dysfunction and dilatation lead to MR without structural leaflet abnormalities. However, certain patients with global LV disease (eg, those with left bundle branch block or regional wall motion abnormalities) have the features of primary MR and might respond favorably to interventions that aim to restore the proper functioning of the mitral valve apparatus. Observations: A novel conceptual framework is proposed, which classifies patients with meaningful LV disease based on whether the severity of MR is proportionate or disproportionate to the LV end-diastolic volume. Treatments that reduce LV volumes (eg, neurohormonal antagonists) are effective in proportionate MR but not disproportionate MR. Conversely, procedures that restore mitral valve function (eg, cardiac resynchronization and mitral valve repair) are effective in patients with disproportionate MR but not in those with proportionate MR. The proposed framework explains the discordant findings in the Multicentre Randomized Study of Percutaneous Mitral Valve Repair MitraClip Device in Patients With Severe Secondary Mitral Regurgitation (MITRA-FR) and the Cardiovascular Outcomes Assessment of the MitraClip Percutaneous Therapy for Heart Failure Patients with Functional Mitral Regurgitation (COAPT) trials; differences in procedural success and medical therapy in the 2 studies cannot explain the different results. In addition, the small group of patients in the COAPT trial who had the features of proportionate MR and were similar to those enrolled in the MITRA-FR trial did not respond favorably to transcatheter mitral valve repair. Conclusions and Relevance: The characterization of patients with functional MR into proportionate and disproportionate subtypes may explain the diverse range of responses to drug and device interventions that have been observed.

Misclassification of Mitral Valve Disease and Rate of Surgical Repair in The Society of Thoracic Surgeons Database.

BACKGROUND: Surgical repair of primary mitral regurgitation (MR) is considered an indicator of quality performance. Therefore, accurate data reporting is critical for quality assessment. During an institutional quality review, MR etiology could not be determined in 40% of operations in The Society of Thoracic Surgeons database entries, and therefore our true repair rate could not be reliably ascertained. Therefore, we reviewed all source documents and echocardiograms to assess our true disease etiology and repair rate. METHODS: Source records and echocardiograms of all operations performed in a single health care system for a 1-year period were reviewed by an experienced mitral valve surgeon, an echocardiographic core laboratory, and a data manager. Disease etiology and operation were compared with data previously entered in the database by post hoc chart abstraction. RESULTS: In all, 314 isolated mitral valve operations were performed. The MR was originally classified as primary, 163 (52%); secondary, 22 (7%); rheumatic, 37 (12%); endocarditis, 24 (8%); other, 33 (10%); and unknown, 35 (11%). Reported repair rate for primary MR was 142 of 163 (87.1%). After review, etiology was determined to be primary, 177 (56%); secondary, 33 (11%); rheumatic, 61 (20%); endocarditis, 25 (8%); and others, 18 (5%)-resulting in a change of classification in 99 of 314 patients (31.5%) and a true repair rate for primary MR of 165 of 177 (93.2%). CONCLUSIONS: Source document and imaging review of mitral valve surgery revealed significant discordance with post hoc chart abstraction methods. A more detailed data entry methodology is necessary to accurately report the true disease etiology and repair rates for primary MR.

Functional mitral regurgitation, updated: ventricular or atrial?

Lone atrial fibrillation (AF) can cause functional mitral regurgitation (MR), commonly referred to as "atrial functional MR (AFMR)." This type of MR has recently received much attention as an important cause of heart failure, and it represents a considerable therapeutic target in heart failure patients with AF. Mitral annular dilatation due to left atrial (LA) dilatation can be recognized as an original cause of AFMR, whereas the exact cascade of AFMR etiologies has not been established. AFMR is typically classified as Carpentier type I, and is likely to have a central jet. In contrast, a proportion of AFMR is classified as a combination of Carpentier type I for a flattened anterior mitral leaflet and Carpentier type IIIb for a tethered posterior mitral leaflet and is likely to have an eccentric jet directed toward the LA posterior wall. The traditional functional MR occurring in patients with left ventricular (LV) dilatation and/or systolic dysfunction, which is classified as Carpentier type IIIb, has since been designated "ventricular functional MR (VFMR)" to distinguish it from AFMR. Traditional VFMR, newly recognized AFMR, and their etiologic relations to LV/LA size and function are discussed in this review article.

[Percutaneous treatment of mitral regurgitation]. / Prise en charge interventionnelle de la fuite mitrale.

Mitral regurgitation (MR) is currently the most frequent valvular heart disease, and the second most operated valve in Europe. Around 50% of patients presenting severe MR are denied surgery, despite the adverse prognosis associated with the absence of treatment, due to comorbidities and/or advanced age. During the previous years, percutaneous treatment of MR, whether by replacement or, more frequently, by repair, has been developed, providing an alternative for those patients who are deemed at prohibitive, but also, high surgical risk. Percutaneous edge-to-edge repair is currently the most frequently used technique, and is the only one recommended by the European Guidelines for Valvular Heart Disease Management. In the current article, we review the different strategies for MR repair, as well as the indications and level of evidence for their use.

Echocardiographic assessment of functional mitral regurgitation: opening Pandora's box?

Two recent trials of transcatheter mitral-valve repair in patients with functional mitral regurgitation (FMR) presented opposing results for the MitraClip® compared to medical therapy alone. The conflicting results gave rise to intensive discussions about assessment of mitral valve regurgitation (MR). A recent editorial viewpoint provided a potential explanation presenting a new pathophysiologic concept. However, the echocardiographic characterization of both trials' patients is inconsistent and the discussed concepts appear to suffer from plausibility weaknesses. It is well conceivable that limitations in the echocardiographic assessment of the trial patients introduced a bias regarding the selection of patients with severe (or less severe) MR that may be a more plausible explanation for the differences in outcome. We here illustrate our viewpoint regarding the two MitraClip trials and also illustrate the difficulties in assessing functional MR properly. It may indeed be "opening Pandora's box", but we will also make an attempt to provide a solution.