scholarly journals Automated left ventricular dimension assessment using artificial intelligence

2021 ◽  
Vol 42 (Supplement_1) ◽  
Author(s):  
C Stowell ◽  
J Howard ◽  
G Cole ◽  
K Ananthan ◽  
C Demetrescu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
External Validation ◽  
Posterior Wall ◽  
Left Ventricular ◽  
Validation Dataset ◽  
Left Ventricular Dimension ◽  
Collaborative Platform ◽  
Consensus Standard ◽  
The Individual ◽  
Ventricular Dimension

Abstract Background and purpose Artificial intelligence (AI) has the potential to greatly improve efficiency and reproducibility of quantification in echocardiography, but to gain widespread use it must both meet expert standards of excellence and have a transparent methodology. We developed an online platform to enable multiple collaborators to annotate medical images for training and validating neural networks. Methods Using our online collaborative platform 9 expert echocardiographers labelled 2056 images that comprised the training dataset. They labelled the four points from where the standard parasternal long axis (PLAX) measurements (interventricular septum, posterior wall, left ventricular dimension) would be made. Using these labelled images we trained a 2d convolutional neural network to replicate these labels. Separately, we curated an external validation dataset of the systolic and diastolic frames of 100 PLAX acquisitions. Each of these images were labelled twice by 13 different experts, and the average of the 26 measurements was taken as the consensus standard. We then compared the individual experts and the AI measurements on the external validation dataset to the consensus standard, and calculated the precision standard deviation (SD) of the signed differences from the consensus standard. Results For diastolic septum thickness, the AI had a precision SD of 1.8 mm (ICC 0.81; 95% CI 0.73 to 0.97), compared with 2.0 mm for the individual experts (ICC 0.64; 95% CI 0.57 to 0.72). For diastolic posterior wall thickness, the AI had a precision SD 1.4 mm (ICC 0.54; 95% CI 0.38 to 0.66), and the individual experts 2.2 mm (ICC 0.37; 95% CI 0.29 to 0.46). The AI's precision SD for left ventricular internal dimension was 3.5 mm (ICC 0.93, 95% CI 0.90 to 0.94), and for individual experts was 4.4mm (ICC 0.82, 95% CI 0.78 to 0.95). Both the experts and AI performed better in diastole than systole (precision SD AI 2.5mm vs 4.3mm, p<0.0001; experts 3.3mm vs 5.3mm, p<0.0001). Conclusions AI trained by a group of echocardiography experts was able to perform PLAX measurements which matched the reference standard more closely than any individual expert's own measurements. This open, collaborative approach may be a model for the development of AI that is explainable to, and trusted by clinicians. FUNDunding Acknowledgement Type of funding sources: Public grant(s) – National budget only. Main funding source(s): NIHR Imperil BRC ITMATDr Howard was additionally funded by Wellcome. Online collaborative platform Results of AI and experts

scholarly journals Basic values of M-mode echocardiographic parameters of the left ventricle in outbreed Wistar rats

2012 ◽  
Vol 57 (No. 1) ◽  
pp. 42-52 ◽  
Author(s):  
P. Scheer ◽  
V. Sverakova ◽  
J. Doubek ◽  
K. Janeckova ◽  
I. Uhrikova ◽  
...  
Keyword(s):  
Left Ventricle ◽  
Wistar Rats ◽  
Minimum Weight ◽  
Interventricular Septum ◽  
Posterior Wall ◽  
Left Ventricular ◽  
Regression Equations ◽  
Left Ventricular Dimension ◽  
Echocardiographic Parameters ◽  
Ventricular Dimension

This paper describes the partial results of an echocardiographic study in sixty outbreed Wistar rats. Animals of parity sex ratio were chosen for the experiment. The animals were grown up during the observation period (the minimum weight was 220 g; the maximum weight was 909 g) and were then sequentially anaesthetised (2&ndash;2.5% of isoflurane, 3 l/min O<sub>2</sub>). The second, fourth and fifth examinations were performed under anaesthesia maintained by intramuscular injections with diazepam (2 mg/kg), xylazine (5 mg/kg) and ketamine (35 mg/kg). Transthoracal examination was done using the SonoSite Titan echo system (SonoSite Ltd.) with a microconvex transducer C11 (8&ndash;5 MHz). M-mode (according to the leading-edge method of American Society of Echocardiography) echocardiography data were acquired at the papillary muscle: systolic and diastolic interventricular septum (IVSs, d) and left vetricular posterior wall (LVPWs, d) thickness, systolic and diastolic left ventricular dimension (LVDs, d), aorta (Ao) and left atrium (LA) dimensions. According to standard formulas, the following parameters were obtained: ejection fraction (EF), cardiac output (CO), stroke volume (SV), left ventricle end systolic volume (LVESV), left ventricle end diastolic volume (LVEDV), interventricular septum fractional thickening (IVSFT), left ventricular dimension fraction shortening (LVDFS), and left ventricle posterior wall fraction thickening (LVPWFS). In our study we performed 300 examinations both in male and female Wistar rats of various body weights and calculated regression equations to predict expected normal echocardiographic parameters for rats with arbitrary weights. The rats were examined by an echo scan. The first and third examinations were performed during mono-anaesthesia induced by inhalation of isoflurane. Correlations, with one exception (LVDs), were very close, which means that the results of the calculations based on regression equations are very reliable. &nbsp; &nbsp;

Comparing the performance of artificial intelligence and conventional diagnosis criteria for detecting left ventricular hypertrophy using electrocardiography

EP Europace ◽  
2019 ◽  
Vol 22 (3) ◽  
pp. 412-419 ◽  
Author(s):  
Joon-Myoung Kwon ◽  
Ki-Hyun Jeon ◽  
Hyue Mee Kim ◽  
Min Jeong Kim ◽  
Sung Min Lim ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Left Ventricular Hypertrophy ◽  
Ventricular Hypertrophy ◽  
External Validation ◽  
Left Ventricular ◽  
Machine Learning Techniques ◽  
Validation Dataset ◽  
Point System ◽  
Diagnosis Criteria

Abstract Aims  Although left ventricular hypertrophy (LVH) has a high incidence and clinical importance, the conventional diagnosis criteria for detecting LVH using electrocardiography (ECG) has not been satisfied. We aimed to develop an artificial intelligence (AI) algorithm for detecting LVH. Methods and results This retrospective cohort study involved the review of 21 286 patients who were admitted to two hospitals between October 2016 and July 2018 and underwent 12-lead ECG and echocardiography within 4 weeks. The patients in one hospital were divided into a derivation and internal validation dataset, while the patients in the other hospital were included in only an external validation dataset. An AI algorithm based on an ensemble neural network (ENN) combining convolutional and deep neural network was developed using the derivation dataset. And we visualized the ECG area that the AI algorithm used to make the decision. The area under the receiver operating characteristic curve of the AI algorithm based on ENN was 0.880 (95% confidence interval 0.877–0.883) and 0.868 (0.865–0.871) during the internal and external validations. These results significantly outperformed the cardiologist’s clinical assessment with Romhilt-Estes point system and Cornell voltage criteria, Sokolov-Lyon criteria, and interpretation of ECG machine. At the same specificity, the AI algorithm based on ENN achieved 159.9%, 177.7%, and 143.8% higher sensitivities than those of the cardiologist’s assessment, Sokolov-Lyon criteria, and interpretation of ECG machine. Conclusion  An AI algorithm based on ENN was highly able to detect LVH and outperformed cardiologists, conventional methods, and other machine learning techniques.

External validation of an electrocardiography artificial intelligence-generated algorithm to detect left ventricular systolic function in a general cardiac clinic in Uganda

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
C.K Mondo ◽  
Z.I Attia ◽  
E.D Benavente ◽  
P Friedman ◽  
P Noseworthy ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Heart Failure ◽  
Negative Predictive Value ◽  
Predictive Value ◽  
Left Ventricular Systolic Dysfunction ◽  
External Validation ◽  
Left Ventricular ◽  
Receiver Operating Curve ◽  
Left Ventricular Ejection ◽  
Ventricular Ejection Fraction

Abstract Background Left ventricular systolic dysfunction (LVSD) is associated with increased morbidity and mortality. Although there are effective treatments for patients with LVSD to prevent mortality, heart failure and to improve symptoms, many patients remain undetected and untreated. We have recently derived a deep learning algorithm to detect LVSD using the electrocardiogram (ECG) which could have an important screening role, particularly in limited resources settings. We evaluated the accuracy of this algorithm for the first time in Africa in a sample of subjects attending a cardiology clinic. Methods We conducted a retrospective study in a general cardiac clinic in Uganda. Consecutive patients ≥18 years who had a digital ECG and echocardiogram done within two days of each other were included. We excluded patients with pacemakers or missing information regarding left ventricular ejection fraction (LVEF). Routine 10-second, twelve-lead surface rest ECG were performed using an Edan PC ECG Model SE-1515, Hamburg, Germany. The probability of LVSD was estimated with the Mayo Clinic artificial intelligence (AI) ECG algorithm. LVEF was calculated by the MMode (Teichholz method) using a Philips Ultrasound system, HD7XE, Bothel, Washington, USA. LVSD was defined as a LVEF≤35%. We assessed the overall diagnostic performance of the algorithm to identify LVSD in this population with the area under the receiver operating curve (AUC), and estimated sensitivity, specificity and accuracy using a pre-specified cut-off based on the probability for LVSD generated by the algorithm. We conducted secondary analyses using different LVEF cutoff values. Results We included 634 subjects, 32% (200) of whom had hypertension and 12% (77) clinical heart failure. Mean age was 57±18.8 years, 58% were women and the overall prevalence of LVSD was 4%. The AI-ECG had an AUC of 0.866 (see figure below), sensitivity 73.08%, specificity 91.10%, negative predictive value 98.75%, positive predictive value 26.03% and an accuracy of 90.96% using the original threshold. Using the optimal cutoff based on the AUCs, the sensitivity was 80.77% and specificity was 81.05% with a negative predictive value of 98.99%. The ROC for the detection of LVEF of 40% or below was 0.821. Conclusion The Mayo AI-ECG algorithm demonstrated good accuracy, sensitivity and specificity to detect LVSD in patients seen in a clinical setting in Uganda. This tool may facilitate the identification of people at a high risk for LVSD in settings with low resources. ROC Funding Acknowledgement Type of funding source: None

Sign in / Sign up

Export Citation Format

Share Document