Kotb Magd Ahmed, Elmahdy Hesham Nabih, Seif El Dein Hadeel Mohamed, Mostafa Fatma Zahraa, Refaey Mohammed Ahmed, Rjoob Khaled Waleed Younis, Draz Iman H, Basanti Christine William Shaker
Department of Pediatrics, Faculty of Medicine, Cairo University, Cairo, Egypt.
Information Technology Department, Vice-Dean of Faculty of Computers and Information, Cairo University, Giza, Egypt.
Med Devices (Auckl). 2020 Jan 23;13:13-22. doi: 10.2147/MDER.S221029. eCollection 2020.
Contemporary stethoscope has limitations in diagnosis of chest conditions, necessitating further imaging modalities.
We created 2 diagnostic computer aided non-invasive machine-learning models to recognize chest sounds. Model A was interpreter independent based on hidden markov model and mel frequency cepstral coefficient (MFCC). Model B was based on MFCC, hidden markov model, and chest sound wave image interpreter dependent analysis (phonopulmonography (PPG)).
We studied 464 records of actual chest sounds belonging to 116 children diagnosed by clinicians and confirmed by other imaging diagnostic modalities. Model A had 96.7% overall correct classification rate (CCR), 100% sensitivity and 100% specificity in discrimination between normal and abnormal sounds. CCR was 100% for normal vesicular sounds, crepitations 89.1%, wheezes 97.6%, and bronchial breathing 100%. Model B's CCR was 100% for normal vesicular sounds, crepitations 97.3%, wheezes 97.6%, and bronchial breathing 100%. The overall CCR was 98.7%, sensitivity and specificity were 100%.
Both models demonstrated very high precision in the diagnosis of chest conditions and in differentiating normal from abnormal chest sounds irrespective of operator expertise. Incorporation of computer-aided models in stethoscopes promises prompt, precise, accurate, cost-effective, non-invasive, operator independent, objective diagnosis of chest conditions and reduces number of unnecessary imaging studies.
当代听诊器在胸部疾病诊断方面存在局限性，因此需要进一步的成像方式。
我们创建了两种诊断性计算机辅助非侵入性机器学习模型来识别胸部声音。模型A基于隐马尔可夫模型和梅尔频率倒谱系数（MFCC），与解释器无关。模型B基于MFCC、隐马尔可夫模型以及依赖胸部声波图像解释器的分析（肺音图（PPG））。
我们研究了464份实际胸部声音记录，这些记录来自116名经临床医生诊断并经其他成像诊断方式证实的儿童。模型A在区分正常和异常声音方面的总体正确分类率（CCR）为96.7%，敏感性和特异性均为100%。正常肺泡呼吸音的CCR为100%，湿啰音为89.1%，哮鸣音为97.6%，支气管呼吸音为100%。模型B对于正常肺泡呼吸音的CCR为100%，湿啰音为97.3%，哮鸣音为97.6%，支气管呼吸音为100%。总体CCR为98.7%，敏感性和特异性均为100%。
两种模型在胸部疾病诊断以及区分正常与异常胸部声音方面均显示出非常高的精度，且与操作者的专业知识无关。将计算机辅助模型纳入听诊器有望实现对胸部疾病的快速、精确、准确、经济高效、非侵入性、独立于操作者的客观诊断，并减少不必要的成像研究数量。
