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

Abstract

ObjectiveThe objective of this study was to determine the diagnostic accuracy in detecting valvular heart disease (VHD) by heart auscultation, performed by medical doctors.Design/methodsA 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 measuresSensitivity, specificity and likelihood ratios (LRs).ResultsWe 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.ConclusionSensitivity, 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 numberCRD42018091675.

The Virtual Cardiologist: Three Deep Learning Pipelines in an Inexpensive Portable Device and Web/Mobile Application for Rapid Cardiovascular Diagnosis and Clinical Decision-Making

“…Microsoft Swin Transformer models were modified to analyze cardiac ultrasound video containing left ventricular motion in the following steps: [1] echo frames were pre-processed into a fixed length sequence to be used as training data. [2] a hierarchy of Swin transformers were implemented to a single Transformers Encoders (TE) module to extract spatio-temporal features from the input video frames. [3] The transformers use the shifted window attention technique (Figure 2) to capture both local and global context.…”

“…Multiple studies have shown diagnostic accuracy for auscultation among doctors have eroded significantly (27-68% accuracy). 2 Point of Care Ultrasound devices can record 2-D Echo images and are often a first line tool to assess cardiac anatomy and function, including wall motion, valve disease and enlargement of heart chambers. A routine echocardiogram takes approximately 10-30 videos and 2000 images, and physicians have extremely limited time to interpret the data.…”

A Role For Electrocardiograms in Aortic Stenosis Screening: A Retrospective Trial

“…Aortic stenosis (AS) is the most common valvular heart disease in developed countries, affecting 1 in 50 adults over age 65 and portending significant morbidity and mortality. 1 The majority of patients with AS are asymptomatic, and detection of AS by auscultation has been shown in recent meta-analysis to be highly variable 2 , hence adjunctive methods are needed. Recently, machine learning has identified an association between right-sided precordial U waves (RSPUW) on electrocardiograms (ECG) and moderate to severe aortic stenosis.…”

Improving Valvular Pathologies and Ventricular Dysfunction Diagnostic Efficiency Using Combined Auscultation and Electrocardiography Data: A Multimodal AI Approach

“…Recent research has increasingly highlighted the efficacy of artificial intelligence (AI) in diagnostic processes utilizing simple testing methods [ 5 , 6 , 7 ]. Nevertheless, these studies typically focus on singular modalities.…”