Different intelligence models are used by researchers for an easy and successful diagnosis of neurodegenerative diseases like Parkinson’s disease (PD) but none of the adopted methods is efficient. Early-stage identification of disease and diagnosis based upon vocal measurements is important to enhance the productive lives of the patient. An innovative intelligence model with a combination of a chaos-mapped bat algorithm (CMBA) and a support vector machine (SVM) called CMBA-SVM is introduced. The coordination of the CMBA method effectively resolved the SVM parameter tuning issues. CMBA is used for the identification of featured and consider input for SVM to develop an intelligence model. The effectiveness and performance of the proposed model are compared to ECFA-SVM and CFA-SVM. The performance of the proposed model was tested with considering various parameters in terms of accuracy, sensitivity, specificity, and AUC by taking two sets of PD data set (from UCI repository and Istanbul collected data set). The performance results and perspective of this study were compared with the different intelligence methods described literature study that used the same data, and the CMBA-SVM showed better efficiency than the other. The CMBA-SVM has a very good prospect, which may provide huge expediency to the clinicians to improve quality during PD diagnosis.

研究人员使用不同的智能模型来轻松，成功地诊断神经退行性疾病，如帕金森氏病（PD），但所采用的方法均无效。基于声音测量的疾病的早期识别和诊断对于延长患者的生产寿命很重要。介绍了一种创新的智能模型，该模型结合了混沌映射蝙蝠算法（CMBA）和支持向量机（SVM），称为CMBA-SVM。CMBA方法的协调有效地解决了SVM参数调整问题。CMBA用于识别特征并考虑输入支持SVM以开发智能模型。将该模型的有效性和性能与ECFA-SVM和CFA-SVM进行了比较。通过考虑两组PD数据集（来自UCI资料库和Istanbul收集的数据集），在考虑准确性，敏感性，特异性和AUC方面的各种参数的情况下测试了建议模型的性能。将本研究的性能结果和前景与文献研究中使用相同数据的不同智能方法进行了比较，CMBA-SVM的效率要优于其他方法。CMBA-SVM的前景非常好，这可能为临床医生在PD诊断期间提高质量提供极大的便利。将本研究的性能结果和前景与文献研究中使用相同数据的不同智能方法进行了比较，CMBA-SVM的效率要优于其他方法。CMBA-SVM的前景非常好，这可能为临床医生在PD诊断期间提高质量提供极大的便利。将本研究的性能结果和前景与文献研究中使用相同数据的不同智能方法进行了比较，CMBA-SVM的效率要优于其他方法。CMBA-SVM的前景非常好，这可能为临床医生在PD诊断期间提高质量提供极大的便利。