Zia Mohammad K, Griffel Benjamin, Fridman Vladimir, Saponieri Cesare, Semmlow John L
University of Medicine and Dentistry of New Jersey – Graduate School of Biomedical Sciences and Rutgers, the State University of New Jersey, Piscataway, NJ, USA.
Annu Int Conf IEEE Eng Med Biol Soc. 2011;2011:5880-3. doi: 10.1109/IEMBS.2011.6091454.
Coronary artery disease (CAD) is the leading cause of death in the United States. Although progression of CAD can be controlled using drugs and diet, it is usually detected in advanced stages when invasive treatment is required. Current methods to detect CAD are invasive and/or costly, hence not suitable as a regular screening tool to detect CAD in early stages. Currently, we are developing a noninvasive and cost-effective system to detect CAD using the acoustic approach. This method identifies sounds generated by turbulent flow through partially narrowed coronary arteries to detect CAD. The limiting factor of this method is sensitivity to noises commonly encountered in the clinical setting. Because the CAD sounds are faint, these noises can easily obscure the CAD sounds and make detection impossible. In this paper, we propose a method to detect and eliminate noise encountered in the clinical setting using a reference channel. We show that our method is effective in detecting noise, which is essential to the success of the acoustic approach.
冠状动脉疾病（CAD）是美国主要的死亡原因。尽管可以通过药物和饮食来控制CAD的进展，但通常在需要进行侵入性治疗的晚期阶段才被检测出来。目前检测CAD的方法具有侵入性且/或成本高昂，因此不适合作为早期检测CAD的常规筛查工具。目前，我们正在开发一种使用声学方法检测CAD的非侵入性且经济高效的系统。该方法通过识别部分狭窄冠状动脉中湍流产生的声音来检测CAD。此方法的限制因素是对临床环境中常见噪声的敏感性。由于CAD声音微弱，这些噪声很容易掩盖CAD声音并导致无法检测。在本文中，我们提出了一种使用参考通道检测和消除临床环境中遇到的噪声的方法。我们表明我们的方法在检测噪声方面是有效的，这对声学方法的成功至关重要。
