ICMA: an integrated cardiac modeling and analysis platform

Hussan, Jagir R.; Hunter, Peter; Gladding, Patrick; Greenberg, Neil L.; Christie, G. Richard; Wu, Alan; Sorby, Hugh; Thomas, James D.

doi:10.1093/bioinformatics/btu809

Cited by 3 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of clinical multiomics will be impeded by cost, time and complexity; however, machine learning is the logical tool to assimilate, predict and visualize results in a way which should disburden clinicians who are otherwise awash in data. To a simplistic degree we are working toward the implementation of some of the technologies outlined in this paper in a rapid cardiac screening clinic, using conventional blood tests, ECG and echocardiography 'omics delivered via a single platform' [19,20,34,35].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Multiomics, Virtual Reality and Artificial Intelligence in Heart Failure

et al. 2021

View full text Add to dashboard Cite

Aim: Multiomics delivers more biological insight than targeted investigations. We applied multiomics to patients with heart failure (HF) and reduced ejection fraction (HFrEF), with machine learning applied to advanced ECG (AECG) and echocardiography artificial intelligence (Echo AI). Patients & methods: In total, 46 patients with HFrEF and 20 controls underwent metabolomic profiling, including liquid/gas chromatography–mass spectrometry and solid-phase microextraction volatilomics in plasma and urine. HFrEF was defined using left ventricular (LV) global longitudinal strain, EF and N-terminal pro hormone BNP. AECG and Echo AI were performed over 5 min, with a subset of patients undergoing a virtual reality mental stress test. Results: A-ECG had similar diagnostic accuracy as N-terminal pro hormone BNP for HFrEF (area under the curve = 0.95, 95% CI: 0.85–0.99), and correlated with global longitudinal strain (r = -0.77, p < 0.0001), while Echo AI-generated measurements correlated well with manually measured LV end diastolic volume r = 0.77, LV end systolic volume r = 0.8, LVEF r = 0.71, indexed left atrium volume r = 0.71 and indexed LV mass r = 0.6, p < 0.005. AI-LVEF and other HFrEF biomarkers had a similar discrimination for HFrEF (area under the curve AI-LVEF = 0.88; 95% CI: -0.03 to 0.15; p = 0.19). Virtual reality mental stress test elicited arrhythmic biomarkers on AECG and indicated blunted autonomic responsiveness (alpha 2 of RR interval variability, p = 1 × 10-4) in HFrEF. Conclusion: Multiomics-related machine learning shows promise for the assessment of HF.

show abstract

Section: Discussionmentioning

confidence: 99%

“…AI-generated indexed LA volume and indexed LV mass were also compared with manual measurements (M). This pipeline is part of the integrated cardiac and modeling and analysis platform developed at the Auckland Bioengineering Institute (Integrated Cardiovascular Project, NSBRI Foundation, NASA Grant NCC 9-58) [20].…”

Section: Advanced Ecgmentioning

confidence: 99%

Multiomics, Virtual Reality and Artificial Intelligence in Heart Failure

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Its modular nature provides multiple points for quality assessment and enables parallel improvement on multiple fronts. Although this represents the first example of a fully automated pipeline, it is important to acknowledge that many groups have made advances at several of these steps separately and insights from these efforts were invaluable for our work [21][4] [12][18] [9]. The primary novelties of this work are the application of CNNs to segment echo images, the development of an empirically validated automated quality score for studies, the automation of common 2D measurements, the validation of automated values against measurements from thousands of studies, and the creation of a complete pipeline that can be deployed on the web.…”

Section: Discussionmentioning

confidence: 99%

A Computer Vision Pipeline for Automated Determination of Cardiac Structure and Function and Detection of Disease by Two-Dimensional Echocardiography

Zhang,

Gajjala,

Agrawal

et al. 2017

Preprint

View full text Add to dashboard Cite

Automated cardiac image interpretation has the potential to transform clinical practice in multiple ways including enabling low-cost serial assessment of cardiac function by non-experts in the primary care and rural setting. We hypothesized that advances in computer vision could enable building a fully automated, scalable analysis pipeline for echocardiogram (echo) interpretation. Our approach entailed: 1) preprocessing of complete echo studies; 2) convolutional neural networks (CNN) for view identification, image segmentation, and phasing of the cardiac cycle; 3) quantification of chamber volumes and left ventricular mass; 4) particle tracking to compute longitudinal strain; and 5) targeted disease detection. CNNs accurately identified views (e.g. 99% for apical 4-chamber) and segmented individual cardiac chambers. The resulting cardiac structure measurements agreed with study report values [e.g. median absolute deviations (MAD) of 11.8 g/kg/m 2 for left ventricular mass index and 7.7 mL/kg/m 2 for left ventricular diastolic volume index, derived from 1319 and 2918 studies, respectively]. In terms of cardiac function, we computed automated ejection fraction and longitudinal strain measurements (within 2 cohorts), which agreed with commercial software-derived values [for ejection fraction, MAD=5.3%, N=3101 studies; for strain, MAD=1.5% (n=197) and 1.6% (n=110)], and demonstrated applicability to serial monitoring of breast cancer patients for trastuzumab cardiotoxicity. Overall, we found that, compared to manual measurements, automated measurements had superior performance across seven internal consistency metrics (e.g. the correlation of left ventricular diastolic volumes with left atrial volumes) with an average increase in the absolute Spearman correlation coefficient of 0.05 (p=0.02). Finally, we used CNNs to develop disease detection algorithms for hypertrophic cardiomyopathy and cardiac amyloidosis, with C-statistics of 0.93 and 0.84, respectively. Our pipeline lays the groundwork for using automated interpretation to support point-of-care handheld cardiac ultrasound and large-scale analysis of the millions of echos archived within healthcare systems.

show abstract