当前位置: X-MOL 学术IEEE J. Transl. Eng. Health Med. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Early detection of Acute Chest Syndrome through electronic recording and analysis of auscultatory percussion
IEEE Journal of Translational Engineering in Health and Medicine ( IF 3.4 ) Pub Date : 2020-01-01 , DOI: 10.1109/jtehm.2020.3027802
Bekah Allen 1 , Robert Molokie 2, 3 , Thomas J Royston 1
Affiliation  

Acute chest syndrome (ACS) is the leading cause of death among people with sickle cell disease. ACS is clinically defined and diagnosed by the presence of a new pulmonary infiltrate on chest imaging with accompanying fever and respiratory symptoms like hypoxia, tachypnea, and shortness of breath. However, the characteristic chest x-ray (CXR) findings necessary for a clinical diagnosis of ACS can be difficult to detect, as is determining which patient needs a CXR. This makes early detection difficult; but it is critical in order to limit ACS severity and subsequent fatalities. This research project looks to apply percussion and auscultation techniques that can provide an immediate diagnosis of acute pulmonary conditions by using an automated standard percussive input and electronic auscultation for computational analysis of the measured signal. Measurements on sickle cell patients having ACS, vaso-occlusive crisis (VOC), and regular clinic visits (healthy) were recorded and analyzed. Average intensity of sound transmission through the chest and lungs was determined in the ACS and healthy subject groups, revealing an average of 10–14 dB decrease in sound intensity in the ACS group compared to the healthy group. A random under-sampling boosted tree classification model identified with 94% accuracy the positive ACS and healthy observations. The analysis also revealed unique measurable changes in a small number of cases clinically classified as complicated VOC, which later developed into ACS. This suggests the developed approach may also have early predictive capability, identifying patients at risk for developing ACS prior to current clinical practice.

中文翻译:

通过电子记录和听诊分析早期发现急性胸部综合征

急性胸部综合征 (ACS) 是镰状细胞病患者死亡的主要原因。ACS 的临床定义和诊断是在胸部影像学上出现新的肺部浸润,并伴有发热和呼吸系统症状,如缺氧、呼吸急促和呼吸急促。然而,临床诊断 ACS 所必需的特征性胸部 X 线 (CXR) 发现可能难以检测,正如确定哪些患者需要 CXR 一样。这使得早期检测变得困难;但它对于限制 ACS 严重性和随后的死亡至关重要。该研究项目旨在应用敲击和听诊技术,通过使用自动标准敲击输入和电子听诊对测量信号进行计算分析,可以立即诊断急性肺部疾病。记录和分析患有 ACS、血管闭塞危象 (VOC) 和定期门诊就诊(健康)的镰状细胞患者的测量结果。在 ACS 和健康受试者组中测定了通过胸部和肺部的声音传输的平均强度,与健康组相比,ACS 组的声音强度平均降低了 10-14 dB。一个随机欠采样增强树分类模型以 94% 的准确率识别出阳性 ACS 和健康观察。该分析还揭示了少数临床上归类为复杂 VOC 的病例的独特可测量变化,这些病例后来发展为 ACS。这表明开发的方法也可能具有早期预测能力,在当前临床实践之前识别出有发生 ACS 风险的患者。
更新日期:2020-01-01
down
wechat
bug