Diagnostic accuracy of heart auscultation for detecting valve disease: a systematic review.

OBJECTIVE: The objective of this study was to determine the diagnostic accuracy in detecting valvular heart disease (VHD) by heart auscultation, performed by medical doctors. DESIGN/METHODS: A systematic literature search for diagnostic studies comparing heart auscultation to echocardiography or angiography, to evaluate VHD in adults, was performed in MEDLINE (1947-November 2021) and EMBASE (1947-November 2021). Two reviewers screened all references by title and abstract, to select studies to be included. Disagreements were resolved by consensus meetings. Reference lists of included studies were also screened. The results are presented as a narrative synthesis, and risk of bias was assessed using Quality Assessment of Diagnostic Accuracy Studies-2. MAIN OUTCOME MEASURES: Sensitivity, specificity and likelihood ratios (LRs). RESULTS: We found 23 articles meeting the inclusion criteria. Auscultation was compared with full echocardiography in 15 of the articles; pulsed Doppler was used as reference standard in 2 articles, while aortography and ventriculography was used in 5 articles. One article used point-of-care ultrasound. The articles were published from year 1967 to 2021. Sensitivity of auscultation ranged from 30% to 100%, and specificity ranged from 28% to 100%. LRs ranged from 1.35 to 26. Most of the included studies used cardiologists or internal medicine residents or specialists as auscultators, whereas two used general practitioners and two studied several different auscultators. CONCLUSION: Sensitivity, specificity and LRs of auscultation varied considerably across the different studies. There is a sparsity of data from general practice, where auscultation of the heart is usually one of the main methods for detecting VHD. Based on this review, the diagnostic utility of auscultation is unclear and medical doctors should not rely too much on auscultation alone. More research is needed on how auscultation, together with other clinical findings and history, can be used to distinguish patients with VHD. PROSPERO REGISTRATION NUMBER: CRD42018091675.

Algorithm for predicting valvular heart disease from heart sounds in an unselected cohort.

Objective: This study aims to assess the ability of state-of-the-art machine learning algorithms to detect valvular heart disease (VHD) from digital heart sound recordings in a general population that includes asymptomatic cases and intermediate stages of disease progression. Methods: We trained a recurrent neural network to predict murmurs from heart sound audio using annotated recordings collected with digital stethoscopes from four auscultation positions in 2,124 participants from the Tromsø7 study. The predicted murmurs were used to predict VHD as determined by echocardiography. Results: The presence of aortic stenosis (AS) was detected with a sensitivity of 90.9%, a specificity of 94.5%, and an area under the curve (AUC) of 0.979 (CI: 0.963-0.995). At least moderate AS was detected with an AUC of 0.993 (CI: 0.989-0.997). Moderate or greater aortic and mitral regurgitation (AR and MR) were predicted with AUC values of 0.634 (CI: 0.565-703) and 0.549 (CI: 0.506-0.593), respectively, which increased to 0.766 and 0.677 when clinical variables were added as predictors. The AUC for predicting symptomatic cases was higher for AR and MR, 0.756 and 0.711, respectively. Screening jointly for symptomatic regurgitation or presence of stenosis resulted in an AUC of 0.86, with 97.7% of AS cases (n = 44) and all 12 MS cases detected. Conclusions: The algorithm demonstrated excellent performance in detecting AS in a general cohort, surpassing observations from similar studies on selected cohorts. The detection of AR and MR based on HS audio was poor, but accuracy was considerably higher for symptomatic cases, and the inclusion of clinical variables improved the performance of the model significantly.