A fast and non‐invasive artificial intelligence olfactory‐like system that aids diagnosis of Parkinson's disease

• Published in: European journal of neurology Vol. 31; no. 3; pp. e16167 - n/a
• Main Authors: Cao, Yina, Jiang, Lina, Zhang, Jingxin, Fu, Yanlu, Li, Qiwei, Fu, Wei, Zhu, Junjiang, Xiang, Xiaohui, Zhao, Guohua, Kong, Dongdong, Chen, Xing, Fang, Jiajia
• Format: Journal Article
• Language: English
• Published: England John Wiley & Sons, Inc 01.03.2024
• Subjects: Artificial Intelligence; artificial intelligence olfactory; Decision trees; Diagnosis; gas chromatographic analysis; Gas chromatography; Humans; Machine Learning; Movement disorders; Neurodegenerative diseases; Organic compounds; Parkinson Disease - diagnosis; Parkinson Disease - pathology; Parkinson's disease; Pathogenesis; Sebaceous gland; Sebaceous glands; sebum; surface acoustic wave sensor; VOCs; Volatile organic compounds; United Kingdom > UK; Parkinson's disease; volatile organic compounds; surface acoustic wave sensor; diagnosis; sebum; artificial intelligence olfactory; gas chromatographic analysis
• ISSN: 1351-5101; 1468-1331; 1468-1331
• DOI: 10.1111/ene.16167

Background and purpose Several previous studies have shown that skin sebum analysis can be used to diagnose Parkinson's disease (PD). The aim of this study was to develop a portable artificial intelligence olfactory‐like (AIO) system based on gas chromatographic analysis of the volatile organic compounds (VOCs) in patient sebum and explore its application value in the diagnosis of PD. Methods The skin VOCs from 121 PD patients and 129 healthy controls were analyzed using the AIO system and three classic machine learning models were established, including the gradient boosting decision tree (GBDT), random forest and extreme gradient boosting, to assist the diagnosis of PD and predict its severity. Results A 20‐s time series of AIO system data were collected from each participant. The VOC peaks at a large number of time points roughly concentrated around 5–12 s were significantly higher in PD subjects. The gradient boosting decision tree model showed the best ability to differentiate PD from healthy controls, yielding a sensitivity of 83.33% and a specificity of 84.00%. However, the system failed to predict PD progression scored by Hoehn−Yahr stage. Conclusions This study provides a fast, low‐cost and non‐invasive method to distinguish PD patients from healthy controls. Furthermore, our study also indicates abnormal sebaceous gland secretion in PD patients, providing new evidence for exploring the pathogenesis of PD. A new fast and non‐invasive artificial intelligence olfactory system was created based on gas chromatographic analysis of the volatile organic compounds in patients’ and healthy controls' sebum and its application value in the diagnosis of Parkinson's disease was explored.