Hayek C Scott, Thompson W Reid, Tuchinda Charles, Wojcik Richard A, Lombardo Joseph S
Johns Hopkins Applied Physics Laboratory, 11100 Johns Hopkins Road, Laurel, MD 20723-6099, USA.
Biomed Instrum Technol. 2003 Jul-Aug;37(4):263-70. doi: 10.2345/0899-8205(2003)37[263:WPOSMT]2.0.CO;2.
Despite advances in imaging technologies for the heart, screening of patients for cardiac pathology continues to include the use of traditional stethoscope auscultation. Detection of heart murmurs by the primary care physician often results in the ordering of additional expensive testing or referral to cardiology subspecialists, although many of the patients are eventually found to have no pathologic condition. In contrast, auscultation by an experienced cardiologist is highly sensitive and specific for detecting heart disease. Although attempts have been made to automate screening by auscultation, no device is currently available to fulfill this function. Multiple indicators of pathology are nonetheless available from heart sounds and can be elicited using certain signal processing techniques such as wavelet analysis. Results presented here show that a signal of pathology, the systolic murmur, can reliably be detected and classified as pathologic using a portable electrocardiogram and heart sound measurement unit combined with a wavelet-based algorithm. Wavelet decomposition holds promise for extending these results to detection and evaluation of other audible pathologic indicators.
尽管心脏成像技术取得了进展，但对患者进行心脏病理筛查仍继续采用传统的听诊器听诊。初级保健医生检测到心脏杂音后，往往会安排额外的昂贵检查或转诊给心脏病专科医生，尽管最终发现许多患者并无病理状况。相比之下，经验丰富的心脏病专家进行听诊对检测心脏病具有高度的敏感性和特异性。虽然已经尝试通过听诊实现筛查自动化，但目前尚无设备能履行这一功能。不过，从心音中可以获得多个病理指标，并且可以使用某些信号处理技术（如小波分析）来提取这些指标。此处呈现的结果表明，使用便携式心电图和心音测量单元结合基于小波的算法，可以可靠地检测到病理信号——收缩期杂音，并将其分类为病理性杂音。小波分解有望将这些结果扩展到其他可听病理指标的检测和评估。
