Dataset Information

Deep Learning Algorithm for Automated Cardiac Murmur Detection via a Digital Stethoscope Platform.

ABSTRACT: Background Clinicians vary markedly in their ability to detect murmurs during cardiac auscultation and identify the underlying pathological features. Deep learning approaches have shown promise in medicine by transforming collected data into clinically significant information. The objective of this research is to assess the performance of a deep learning algorithm to detect murmurs and clinically significant valvular heart disease using recordings from a commercial digital stethoscope platform. Methods and Results Using >34 hours of previously acquired and annotated heart sound recordings, we trained a deep neural network to detect murmurs. To test the algorithm, we enrolled 962 patients in a clinical study and collected recordings at the 4 primary auscultation locations. Ground truth was established using patient echocardiograms and annotations by 3 expert cardiologists. Algorithm performance for detecting murmurs has sensitivity and specificity of 76.3% and 91.4%, respectively. By omitting softer murmurs, those with grade 1 intensity, sensitivity increased to 90.0%. Application of the algorithm at the appropriate anatomic auscultation location detected moderate-to-severe or greater aortic stenosis, with sensitivity of 93.2% and specificity of 86.0%, and moderate-to-severe or greater mitral regurgitation, with sensitivity of 66.2% and specificity of 94.6%. Conclusions The deep learning algorithm's ability to detect murmurs and clinically significant aortic stenosis and mitral regurgitation is comparable to expert cardiologists based on the annotated subset of our database. The findings suggest that such algorithms would have utility as front-line clinical support tools to aid clinicians in screening for cardiac murmurs caused by valvular heart disease. Registration URL: https://clinicaltrials.gov; Unique Identifier: NCT03458806.

SUBMITTER: Chorba JS

PROVIDER: S-EPMC8200722 | biostudies-literature | 2021 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep Learning Algorithm for Automated Cardiac Murmur Detection via a Digital Stethoscope Platform.

Chorba John S JS Shapiro Avi M AM Le Le L Maidens John J Prince John J Pham Steve S Kanzawa Mia M MM Barbosa Daniel N DN Currie Caroline C Brooks Catherine C White Brent E BE Huskin Anna A Paek Jason J Geocaris Jack J Elnathan Dinatu D Ronquillo Ria R Kim Roy R Alam Zenith H ZH Mahadevan Vaikom S VS Fuller Sophie G SG Stalker Grant W GW Bravo Sara A SA Jean Dina D Lee John J JJ Gjergjindreaj Medeona M Mihos Christos G CG Forman Steven T ST Venkatraman Subramaniam S McCarthy Patrick M PM Thomas James D JD

Journal of the American Heart Association 20210426 9

Background Clinicians vary markedly in their ability to detect murmurs during cardiac auscultation and identify the underlying pathological features. Deep learning approaches have shown promise in medicine by transforming collected data into clinically significant information. The objective of this research is to assess the performance of a deep learning algorithm to detect murmurs and clinically significant valvular heart disease using recordings from a commercial digital stethoscope platform. ...[more]

PMID: 33899504

Similar Datasets

Project description:IntroductionRheumatic heart diseases (RHDs) contribute significant morbidity and mortality globally. To reduce the burden of RHD, timely initiation of secondary prophylaxis is important. The objectives of this study are to determine the frequency of subclinical RHD and to train a deep learning (DL) algorithm using waveform data from the digital auscultatory stethoscope (DAS) in predicting subclinical RHD.Methods and analysisWe aim to recruit 1700 children from a group of schools serving the underprivileged over a 12-month period in Karachi (Pakistan). All consenting students within the age of 5-15 years with no underlying congenital heart disease will be eligible for the study. We will gather information regarding sociodemographics, anthropometric data, history of symptoms or diagnosis of rheumatic fever, phonocardiogram (PCG) and electrocardiography (ECG) data obtained from DAS. Handheld echocardiogram will be performed on each study participant to assess the presence of a mitral regurgitation (MR) jet (>1.5 cm), or the presence of aortic regurgitation (AR) in any view. If any of these findings are present, a confirmatory standard echocardiogram using the World Heart Federation (WHF) will be performed to confirm the diagnosis of subclinical RHD. The auscultatory data from digital stethoscope will be used to train the deep neural network for the automatic identification of patients with subclinical RHD. The proposed neural network will be trained in a supervised manner using labels from standard echocardiogram of the participants. Once trained, the neural network will be able to automatically classify the DAS data in one of the three major categories-patient with definite RHD, patient with borderline RHD and normal subject. The significance of the results will be confirmed by standard statistical methods for hypothesis testing.Ethics and disseminationEthics approval has been taken from the Aga Khan University, Pakistan. Findings will be disseminated through scientific publications and to collaborators.Article focusThis study focuses on determining the frequency of subclinical RHD in school-going children in Karachi, Pakistan and developing a DL algorithm to screen for this condition using a digital stethoscope.

Project description:ImportanceInterpretation of chest radiographs is a challenging task prone to errors, requiring expert readers. An automated system that can accurately classify chest radiographs may help streamline the clinical workflow.ObjectivesTo develop a deep learning-based algorithm that can classify normal and abnormal results from chest radiographs with major thoracic diseases including pulmonary malignant neoplasm, active tuberculosis, pneumonia, and pneumothorax and to validate the algorithm's performance using independent data sets.Design, setting, and participantsThis diagnostic study developed a deep learning-based algorithm using single-center data collected between November 1, 2016, and January 31, 2017. The algorithm was externally validated with multicenter data collected between May 1 and July 31, 2018. A total of 54 221 chest radiographs with normal findings from 47 917 individuals (21 556 men and 26 361 women; mean [SD] age, 51 [16] years) and 35 613 chest radiographs with abnormal findings from 14 102 individuals (8373 men and 5729 women; mean [SD] age, 62 [15] years) were used to develop the algorithm. A total of 486 chest radiographs with normal results and 529 with abnormal results (1 from each participant; 628 men and 387 women; mean [SD] age, 53 [18] years) from 5 institutions were used for external validation. Fifteen physicians, including nonradiology physicians, board-certified radiologists, and thoracic radiologists, participated in observer performance testing. Data were analyzed in August 2018.ExposuresDeep learning-based algorithm.Main outcomes and measuresImage-wise classification performances measured by area under the receiver operating characteristic curve; lesion-wise localization performances measured by area under the alternative free-response receiver operating characteristic curve.ResultsThe algorithm demonstrated a median (range) area under the curve of 0.979 (0.973-1.000) for image-wise classification and 0.972 (0.923-0.985) for lesion-wise localization; the algorithm demonstrated significantly higher performance than all 3 physician groups in both image-wise classification (0.983 vs 0.814-0.932; all P < .005) and lesion-wise localization (0.985 vs 0.781-0.907; all P < .001). Significant improvements in both image-wise classification (0.814-0.932 to 0.904-0.958; all P < .005) and lesion-wise localization (0.781-0.907 to 0.873-0.938; all P < .001) were observed in all 3 physician groups with assistance of the algorithm.Conclusions and relevanceThe algorithm consistently outperformed physicians, including thoracic radiologists, in the discrimination of chest radiographs with major thoracic diseases, demonstrating its potential to improve the quality and efficiency of clinical practice.

Project description:Rationale and objectivesProstate MRI improves detection of clinically significant prostate cancer; however, its diagnostic performance has wide variation. Artificial intelligence (AI) has the potential to assist radiologists in the detection and classification of prostatic lesions. Herein, we aimed to develop and test a cascaded deep learning detection and classification system trained on biparametric prostate MRI using PI-RADS for assisting radiologists during prostate MRI read out.Materials and methodsT2-weighted, diffusion-weighted (ADC maps, high b value DWI) MRI scans obtained at 3 Tesla from two institutions (n = 1043 in-house and n = 347 Prostate-X, respectively) acquired between 2015 to 2019 were used for model training, validation, testing. All scans were retrospectively reevaluated by one radiologist. Suspicious lesions were contoured and assigned a PI-RADS category. A 3D U-Net-based deep neural network was used to train an algorithm for automated detection and segmentation of prostate MRI lesions. Two 3D residual neural network were used for a 4-class classification task to predict PI-RADS categories 2 to 5 and BPH. Training and validation used 89% (n = 1290 scans) of the data using 5 fold cross-validation, the remaining 11% (n = 150 scans) were used for independent testing. Algorithm performance at lesion level was assessed using sensitivities, positive predictive values (PPV), false discovery rates (FDR), classification accuracy, Dice similarity coefficient (DSC). Additional analysis was conducted to compare AI algorithm's lesion detection performance with targeted biopsy results.ResultsMedian age was 66 years (IQR = 60-71), PSA 6.7 ng/ml (IQR = 4.7-9.9) from in-house cohort. In the independent test set, algorithm correctly detected 111 of 198 lesions leading to 56.1% (49.3%-62.6%) sensitivity. PPV was 62.7% (95% CI 54.7%-70.7%) with FDR of 37.3% (95% CI 29.3%-45.3%). Of 79 true positive lesions, 82.3% were tumor positive at targeted biopsy, whereas of 57 false negative lesions, 50.9% were benign at targeted biopsy. Median DSC for lesion segmentation was 0.359. Overall PI-RADS classification accuracy was 30.8% (95% CI 24.6%-37.8%).ConclusionOur cascaded U-Net, residual network architecture can detect, classify cancer suspicious lesions at prostate MRI with good detection, reasonable classification performance metrics.

Project description:Purpose: To assess the accuracy and efficacy of a semi-automated deep learning algorithm (DLA) assisted approach to detect vision-threatening diabetic retinopathy (DR). Methods: We developed a two-step semi-automated DLA-assisted approach to grade fundus photographs for vision-threatening referable DR. Study images were obtained from the Lingtou Cohort Study, and captured at participant enrollment in 2009-2010 ("baseline images") and annual follow-up between 2011 and 2017. To begin, a validated DLA automatically graded baseline images for referable DR and classified them as positive, negative, or ungradable. Following, each positive image, all other available images from patients who had a positive image, and a 5% random sample of all negative images were selected and regraded by trained human graders. A reference standard diagnosis was assigned once all graders achieved consistent grading outcomes or with a senior ophthalmologist's final diagnosis. The semi-automated DLA assisted approach combined initial DLA screening and subsequent human grading for images identified as high-risk. This approach was further validated within the follow-up image datasets and its time and economic costs evaluated against fully human grading. Results: For evaluation of baseline images, a total of 33,115 images were included and automatically graded by the DLA. 2,604 images (480 positive results, 624 available other images from participants with a positive result, and 1500 random negative samples) were selected and regraded by graders. The DLA achieved an area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy of 0.953, 0.970, 0.879, and 88.6%, respectively. In further validation within the follow-up image datasets, a total of 88,363 images were graded using this semi-automated approach and human grading was performed on 8975 selected images. The DLA achieved an AUC, sensitivity, and specificity of 0.914, 0.852, 0.853, respectively. Compared against fully human grading, the semi-automated DLA-assisted approach achieved an estimated 75.6% time and 90.1% economic cost saving. Conclusions: The DLA described in this study was able to achieve high accuracy, sensitivity, and specificity in grading fundus images for referable DR. Validated against long-term follow-up datasets, a semi-automated DLA-assisted approach was able to accurately identify suspect cases, and minimize misdiagnosis whilst balancing safety, time, and economic cost.

Dataset Information

Deep Learning Algorithm for Automated Cardiac Murmur Detection via a Digital Stethoscope Platform.

Publications

Deep Learning Algorithm for Automated Cardiac Murmur Detection via a Digital Stethoscope Platform.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets