Hongcheng Liu1, Guangwei Du2, Lijun Zhang3, Mechelle M Lewis4, Xue Wang1, Tao Yao5, Runze Li6, Xuemei Huang7. 1. Department of Industrial and Manufacturing Engineering, The Pennsylvania State University, University Park, PA 16802, United States. 2. Departments of Neurology, Milton S. Hershey College of Medicine, The Pennsylvania State University, Hershey, PA 17033, United States. 3. Departments of Biochemistry and Molecular Biology, Milton S. Hershey College of Medicine, The Pennsylvania State University, Hershey, PA 17033, United States. 4. Departments of Neurology, Milton S. Hershey College of Medicine, The Pennsylvania State University, Hershey, PA 17033, United States; Departments of Pharmacology, Milton S. Hershey College of Medicine, The Pennsylvania State University, Hershey, PA 17033, United States. 5. Department of Industrial and Manufacturing Engineering, The Pennsylvania State University, University Park, PA 16802, United States. Electronic address: taoyao@psu.edu. 6. Department of Statistics, The Pennsylvania State University, University Park, PA 16802, United States. Electronic address: rzli@psu.edu. 7. Departments of Neurology, Milton S. Hershey College of Medicine, The Pennsylvania State University, Hershey, PA 17033, United States; Departments of Pharmacology, Milton S. Hershey College of Medicine, The Pennsylvania State University, Hershey, PA 17033, United States; Department of Radiology, Milton S. Hershey College of Medicine, The Pennsylvania State University, Hershey, PA 17033, United States; Department of Neurosurgery, Milton S. Hershey College of Medicine, The Pennsylvania State University, Hershey, PA 17033, United States; Department of Kinesiology, Milton S. Hershey College of Medicine, The Pennsylvania State University, Hershey, PA 17033, United States. Electronic address: Xuemei@psu.edu.
Abstract
BACKGROUND: Brain MRI holds promise to gauge different aspects of Parkinson's disease (PD)-related pathological changes. Its analysis, however, is hindered by the high-dimensional nature of the data. NEW METHOD: This study introduces folded concave penalized (FCP) sparse logistic regression to identify biomarkers for PD from a large number of potential factors. The proposed statistical procedures target the challenges of high-dimensionality with limited data samples acquired. The maximization problem associated with the sparse logistic regression model is solved by local linear approximation. The proposed procedures then are applied to the empirical analysis of multimodal MRI data. RESULTS: From 45 features, the proposed approach identified 15 MRI markers and the UPSIT, which are known to be clinically relevant to PD. By combining the MRI and clinical markers, we can enhance substantially the specificity and sensitivity of the model, as indicated by the ROC curves. COMPARISON TO EXISTING METHODS: We compare the folded concave penalized learning scheme with both the Lasso penalized scheme and the principle component analysis-based feature selection (PCA) in the Parkinson's biomarker identification problem that takes into account both the clinical features and MRI markers. The folded concave penalty method demonstrates a substantially better clinical potential than both the Lasso and PCA in terms of specificity and sensitivity. CONCLUSIONS: For the first time, we applied the FCP learning method to MRI biomarker discovery in PD. The proposed approach successfully identified MRI markers that are clinically relevant. Combining these biomarkers with clinical features can substantially enhance performance.
BACKGROUND: Brain MRI holds promise to gauge different aspects of Parkinson's disease (PD)-related pathological changes. Its analysis, however, is hindered by the high-dimensional nature of the data. NEW METHOD: This study introduces folded concave penalized (FCP) sparse logistic regression to identify biomarkers for PD from a large number of potential factors. The proposed statistical procedures target the challenges of high-dimensionality with limited data samples acquired. The maximization problem associated with the sparse logistic regression model is solved by local linear approximation. The proposed procedures then are applied to the empirical analysis of multimodal MRI data. RESULTS: From 45 features, the proposed approach identified 15 MRI markers and the UPSIT, which are known to be clinically relevant to PD. By combining the MRI and clinical markers, we can enhance substantially the specificity and sensitivity of the model, as indicated by the ROC curves. COMPARISON TO EXISTING METHODS: We compare the folded concave penalized learning scheme with both the Lasso penalized scheme and the principle component analysis-based feature selection (PCA) in the Parkinson's biomarker identification problem that takes into account both the clinical features and MRI markers. The folded concave penalty method demonstrates a substantially better clinical potential than both the Lasso and PCA in terms of specificity and sensitivity. CONCLUSIONS: For the first time, we applied the FCP learning method to MRI biomarker discovery in PD. The proposed approach successfully identified MRI markers that are clinically relevant. Combining these biomarkers with clinical features can substantially enhance performance.
Authors: Ramon Casanova; Christopher T Whitlow; Benjamin Wagner; Jeff Williamson; Sally A Shumaker; Joseph A Maldjian; Mark A Espeland Journal: Front Neuroinform Date: 2011-10-14 Impact factor: 4.081
Authors: Katrina Gwinn; Karen K David; Christine Swanson-Fischer; Roger Albin; Coryse St Hillaire-Clarke; Beth-Anne Sieber; Codrin Lungu; F DuBois Bowman; Roy N Alcalay; Debra Babcock; Ted M Dawson; Richard B Dewey; Tatiana Foroud; Dwight German; Xuemei Huang; Vlad Petyuk; Judith A Potashkin; Rachel Saunders-Pullman; Margaret Sutherland; David R Walt; Andrew B West; Jing Zhang; Alice Chen-Plotkin; Clemens R Scherzer; David E Vaillancourt; Liana S Rosenthal Journal: Biomark Med Date: 2017-06-23 Impact factor: 2.851
Authors: George Markousis-Mavrogenis; Loukia Koutsogeorgopoulou; Gikas Katsifis; Theodoros Dimitroulas; Genovefa Kolovou; George D Kitas; Petros P Sfikakis; Sophie I Mavrogeni Journal: Diagnostics (Basel) Date: 2020-05-24
Authors: George Markousis-Mavrogenis; Aikaterini Giannakopoulou; Nikolaos Andreou; George Papadopoulos; Vasiliki Vartela; Genovefa Kolovou; Flora Bacopoulou; Konstantinos Tsarouhas; Christina Kanaka-Gantenbein; Demetrios A Spandidos; Sophie I Mavrogeni Journal: Exp Ther Med Date: 2020-04-29 Impact factor: 2.447
Authors: George Markousis-Mavrogenis; Dimos D Mitsikostas; Loukia Koutsogeorgopoulou; Theodoros Dimitroulas; Gikas Katsifis; Panayiotis Argyriou; Dimitrios Apostolou; Stella Velitsista; Vasiliki Vartela; Dionysia Manolopoulou; Maria G Tektonidou; Genovefa Kolovou; George D Kitas; Petros P Sfikakis; Sophie I Mavrogeni Journal: J Clin Med Date: 2020-02-06 Impact factor: 4.241