A novel fully automated method for mitral regurgitant orifice area quantification

Clinical applications of artificial intelligence and machine learning in neurocardiology: a comprehensive review

Neurocardiology is an evolving field focusing on the interplay between the nervous system and cardiovascular system that can be used to describe and understand many pathologies. Acute ischemic stroke can be understood through this framework of an interconnected, reciprocal relationship such that ischemic stroke occurs secondary to cardiac pathology (the Heart-Brain axis), and cardiac injury secondary to various neurological disease processes (the Brain-Heart axis). The timely assessment, diagnosis, and subsequent management of cerebrovascular and cardiac diseases is an essential part of bettering patient outcomes and the progression of medicine. Artificial intelligence (AI) and machine learning (ML) are robust areas of research that can aid diagnostic accuracy and clinical decision making to better understand and manage the disease of neurocardiology. In this review, we identify some of the widely utilized and upcoming AI/ML algorithms for some of the most common cardiac sources of stroke, strokes of undetermined etiology, and cardiac disease secondary to stroke. We found numerous highly accurate and efficient AI/ML products that, when integrated, provided improved efficacy for disease prediction, identification, prognosis, and management within the sphere of stroke and neurocardiology. In the focus of cryptogenic strokes, there is promising research elucidating likely underlying cardiac causes and thus, improved treatment options and secondary stroke prevention. While many algorithms still require a larger knowledge base or manual algorithmic training, AI/ML in neurocardiology has the potential to provide more comprehensive healthcare treatment, increase access to equitable healthcare, and improve patient outcomes. Our review shows an evident interest and exciting new frontier for neurocardiology with artificial intelligence and machine learning.

The evolving role of cardiac magnetic resonance in primary mitral regurgitation: ready for prime time?

A fifth of patients with primary degenerative mitral regurgitation continue to present with de novo ventricular dysfunction following surgery and higher rates of heart failure, morbidity, and mortality. This raises questions as to why the left ventricle (LV) might fail to recover and has led to support for better LV characterization; cardiac magnetic resonance (CMR) may play a role in this regard, pending further research and outcome data. CMR has widely acknowledged advantages, particularly in repeatability of measurements of volume and ejection fraction, yet recent guidelines relegate its use to cases where there is discordant information or poor-quality imaging from echocardiography because of the lack of data regarding the CMR-based ejection fraction threshold for surgery and CMR-based outcome data. This article reviews the current evidence regarding the role of CMR in an integrated surveillance and surgical timing programme.

Anatomical Regurgitant Orifice Detection and Quantification from 3-D Echocardiographic Images

The vena contracta and effective regurgitant orifice area (EROA) are currently used for the clinical assessment of mitral regurgitation (MR) from 2-D color Doppler imaging. In addition to being highly user dependent and having low repeatability, these methods do not represent accurately the anatomic regurgitant orifice (ARO), which affects the adequate assessment of MR patients. We propose a novel method for semi-automatic detection and quantitative assessment of the 3-D ARO shape from 3-D transesophageal echocardiographic images. The algorithm was tested on a set of 25 patients with MR, and compared with EROA for validation. Results indicate the robustness of the proposed approach, with low variability in relation to different settings of user-defined segmentation parameters. Although EROA and ARO exhibited a good correlation (r = 0.8), relatively large biases were measured, indicating that EROA probably underestimates the real shape and size of the regurgitant orifice. Along with the higher reproducibility of the proposed approach, this highlights the limitations of current clinical approaches and underlines the importance of accurate assessment of the ARO shape for diagnosis and treatment in MR patients.

Three-Dimensional Field Optimization Method: Clinical Validation of a Novel Color Doppler Method for Quantifying Mitral Regurgitation

BACKGROUND

Assessment of mitral regurgitation (MR) severity by echocardiography is important for clinical decision making, but MR severity can be challenging to quantitate accurately and reproducibly. The accuracy of effective regurgitant orifice area (EROA) and regurgitant volume (RVol) calculated using two-dimensional (2D) proximal isovelocity surface area is limited by the geometric assumptions of proximal isovelocity surface area shape, and both variables demonstrate interobserver variability. The aim of this study was to compare a novel automated three-dimensional (3D) echocardiographic method for calculating MR regurgitant flow using standard 2D techniques.

METHODS

A sheep model of ischemic MR and patients with MR were prospectively examined. Patients with a range of severity of MR were examined. EROA and RVol were calculated from 3D color Doppler acquisitions using a novel computer-automated algorithm based on the field optimization method to measure EROA and RVol. For an independent comparison group, the 3D field optimization method was compared with 2D methods for grading MR in an experimental ovine model of MR.

RESULTS

Fifteen 3D data sets from nine sheep (open-chest transthoracic echocardiographic data sets) and 33 transesophageal data sets from patients with MR were prospectively examined. For sheep data sets, mean 2D EROA was 0.16 ± 0.05 cm², and mean 2D RVol was 21.84 ± 8.03 mL. Mean 3D EROA was 0.09 ± 0.04 cm², and mean 3D RVol was 14.40 ± 5.79 cm³. There was good correlation between 2D and 3D EROA (R = 0.70) and RVol (R = 0.80). For patient data sets, mean 2D EROA was 0.35 ± 0.35 cm², and mean 2D RVol was 58.9 ± 52.9 mL. Mean 3D EROA was 0.34 ± 0.29 cm², and mean 3D RVol was 54.6 ± 36.5 mL. There was excellent correlation between 2D and 3D EROA (R = 0.94) and RVol (R = 0.84). Bland-Altman analysis revealed greater interobserver variability for 2D RVol measurements compared with 3D RVol using the 3D field optimization method measurements, but variability was statistically significant only for RVol.

CONCLUSIONS

Direct automated measurement of proximal isovelocity surface area region for EROA calculation using real-time 3D color Doppler echocardiography is feasible, with a high correlation to current 2D EROA methods but less variability. This novel automated method provides an accurate and highly reproducible method for calculating EROA.

Autologous bone marrow-derived stem cell therapy in heart disease: discrepancies and contradictions

BACKGROUND

Autologous bone marrow stem cell therapy is the greatest advance in the treatment of heart disease for a generation according to pioneering reports. In response to an unanswered letter regarding one of the largest and most promising trials, we attempted to summarise the findings from the most innovative and prolific laboratory.

METHOD AND RESULTS

Amongst 48 reports from the group, there appeared to be 5 actual clinical studies ("families" of reports). Duplicate or overlapping reports were common, with contradictory experimental design, recruitment and results. Readers cannot always tell whether a study is randomised versus not, open-controlled or blinded placebo-controlled, or lacking a control group. There were conflicts in recruitment dates, criteria, sample sizes, million-fold differences in cell counts, sex reclassification, fractional numbers of patients and conflation of competitors' studies with authors' own. Contradictory results were also common. These included arithmetical miscalculations, statistical errors, suppression of significant changes, exaggerated description of own findings, possible silent patient deletions, fractional numbers of coronary arteries, identical results with contradictory sample sizes, contradictory results with identical sample sizes, misrepresented survival graphs and a patient with a negative NYHA class. We tabulate over 200 discrepancies amongst the reports. The 5 family-flagship papers (Strauer 2002, STAR, IACT, ABCD, BALANCE) have had 2665 citations. Of these, 291 citations were to the pivotal STAR or IACT-JACC papers, but 97% of their eligible citing papers did not mention any discrepancies. Five meta-analyses or systematic reviews covered these studies, but none described any discrepancies and all resolved uncertainties by undisclosed methods, in mutually contradictory ways. Meta-analysts disagreed whether some studies were randomised or "accepter-versus-rejecter". Our experience of presenting the discrepancies to journals is that readers may remain unaware of such problems.

CONCLUSIONS

Modern reporting of clinical research can still be imperfect. The scientific literature absorbs such reports largely uncritically. Even meta-analyses seem to resolve contradictions haphazardly. Discrepancies communicated to journals are not guaranteed to reach the scientific community. Journals could consider prioritising systematic reporting of queries even if seemingly minor, and establishing a policy of "habeas data".

Evidence-based recommendations for PISA measurements in mitral regurgitation: systematic review, clinical and in-vitro study

Background

Guidelines for quantifying mitral regurgitation (MR) using “proximal isovelocity surface area” (PISA) instruct operators to measure the PISA radius from valve orifice to Doppler flow convergence “hemisphere”. Using clinical data and a physically-constructed MR model we (A) analyse the actually-observed colour Doppler PISA shape and (B) test whether instructions to measure a “hemisphere” are helpful.

Methods and results

In part A, the true shape of PISA shells was investigated using three separate approaches. First, a systematic review of published examples consistently showed non-hemispherical, “urchinoid” shapes. Second, our clinical data confirmed that the Doppler-visualized surface is non-hemispherical. Third, in-vitro experiments showed that round orifices never produce a colour Doppler hemisphere.

In part B, six observers were instructed to measure hemisphere radius r_h and (on a second viewing) urchinoid distance (d_u) in 11 clinical PISA datasets; 6 established experts also measured PISA distance as the gold standard. r_h measurements, generated using the hemisphere instruction significantly underestimated expert values (− 28%, p < 0.0005), meaning r_h² was underestimated by approximately 2-fold. d_u measurements, generated using the non-hemisphere instruction were less biased (+ 7%, p = 0.03).

Finally, frame-to-frame variability in PISA distance was found to have a coefficient of variation (CV) of 25% in patients and 9% in in-vitro data. Beat-to-beat variability had a CV of 15% in patients.

Conclusions

Doppler-visualized PISA shells are not hemispherical: we should avoid advising observers to measure a hemispherical radius because it encourages underestimation of orifice area by approximately two-fold. If precision is needed (e.g. to detect changes reliably) multi-frame averaging is essential.