Joint detection and clinical score prediction in Parkinson's disease via multi-modal sparse learning

• Published in: Expert systems with applications Vol. 80; pp. 284 - 296
• Main Authors: Lei, Haijun, Huang, Zhongwei, Zhang, Jian, Yang, Zhang, Tan, Ee-Leng, Zhou, Feng, Lei, Baiying
• Format: Journal Article
• Language: English
• Published: New York Elsevier Ltd 01.09.2017; Elsevier BV
• Subjects: Artificial intelligence; Classification; Comparative analysis; Diagnosis; Dopamine; Feature selection; Machine learning; Mathematical models; Medical imaging; Mental depression; Modal data; Multi-modal data; Neurology; Parkinson's disease; Performance enhancement; Prediction; Predictions; Regression analysis; Rigidity; Sleep; Support vector machines; Multi-modal data; Feature selection; Parkinson's disease; Classification; Prediction
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2017.03.038

•A novel framework for joint PD detection and clinical score prediction is proposed.•A effective feature selection method for PD detection and prediction is proposed.•Multi-modal neuroimaging data enhances performance of PD detection. Parkinson's disease (PD) is the world's second most common progressive neurodegenerative disease. This disease is characterized by a combination of various non-motor symptoms (e.g., depression, olfactory, and sleep disturbance) and motor symptoms (e.g., bradykinesia, tremor, rigidity), therefore diagnosis and treatment of PD are usually complex. There are some machine learning techniques that automate PD diagnosis and predict clinical scores. These techniques are promising in assisting assessment of stage of pathology and predicting PD progression. However, existing PD research mainly focuses on single-function model (i.e., only classification or prediction) using one modality, which limits performance. In this work, we propose a novel feature selection framework based on multi-modal neuroimaging data for joint PD detection and clinical score prediction. Specifically, a unique objective function is designed to capture discriminative features which are used to train a support vector regression (SVR) model for predicting clinical score (e.g., sleep scores and olfactory scores), and a support vector classification (SVC) model for class label identification. We evaluate our method using a dataset of 208 subjects, which includes 56 normal controls (NC), 123 PD and 29 scans without evidence of dopamine deficit (SWEDD) via a 10-fold cross-validation strategy. Our experimental results demonstrate that multi-modal data effectively improves the performance in disease status identification and clinical scores prediction as compared to one single modality. Comparative analysis reveals that the proposed method outperforms state-of-art methods.