Kevin P Nguyen1, Vyom Raval2, Alex Treacher1, Cooper Mellema1, Fang Frank Yu3, Marco C Pinho3, Rathan M Subramaniam4, Richard B Dewey5, Albert A Montillo6. 1. Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, TX, USA. 2. University of Texas at Dallas, Dallas, TX, USA. 3. Department of Radiology, University of Texas Southwestern Medical Center, Dallas, TX, USA; Advanced Imaging Research Center, University of Texas Southwestern Medical Center, Dallas, TX, USA. 4. Department of Radiology, University of Texas Southwestern Medical Center, Dallas, TX, USA; Department of Data Sciences, University of Texas Southwestern Medical Center, Dallas, TX, USA; Otago Medical School, University of Otago, New Zealand. 5. Department of Neurology, University of Texas Southwestern Medical Center, Dallas, TX, USA. 6. Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, TX, USA; Department of Radiology, University of Texas Southwestern Medical Center, Dallas, TX, USA; Advanced Imaging Research Center, University of Texas Southwestern Medical Center, Dallas, TX, USA; University of Texas at Dallas, Dallas, TX, USA. Electronic address: Albert.Montillo@UTSouthwestern.edu.
Abstract
INTRODUCTION: Predictive biomarkers of Parkinson's Disease progression are needed to expedite neuroprotective treatment development and facilitate prognoses for patients. This work uses measures derived from resting-state functional magnetic resonance imaging, including regional homogeneity (ReHo) and fractional amplitude of low frequency fluctuations (fALFF), to predict an individual's current and future severity over up to 4 years and to elucidate the most prognostic brain regions. METHODS: ReHo and fALFF are measured for 82 Parkinson's Disease subjects and used to train machine learning predictors of baseline clinical and future severity at 1 year, 2 years, and 4 years follow-up as measured by the Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS). Predictive performance is measured with nested cross-validation, validated on an external dataset, and again validated through leave-one-site-out cross-validation. Important predictive features are identified. RESULTS: The models explain up to 30.4% of the variance in current MDS-UPDRS scores, 55.8% of the variance in year 1 scores, and 47.1% of the variance in year 2 scores (p < 0.0001). For distinguishing high and low-severity individuals at each timepoint (MDS-UPDRS score above or below the median, respectively), the models achieve positive predictive values up to 79% and negative predictive values up to 80%. Higher ReHo and fALFF in several regions, including components of the default motor network, predicted lower severity across current and future timepoints. CONCLUSION: These results identify an accurate prognostic neuroimaging biomarker which may be used to better inform enrollment in trials of neuroprotective treatments and enable physicians to counsel their patients.
INTRODUCTION: Predictive biomarkers of Parkinson's Disease progression are needed to expedite neuroprotective treatment development and facilitate prognoses for patients. This work uses measures derived from resting-state functional magnetic resonance imaging, including regional homogeneity (ReHo) and fractional amplitude of low frequency fluctuations (fALFF), to predict an individual's current and future severity over up to 4 years and to elucidate the most prognostic brain regions. METHODS: ReHo and fALFF are measured for 82 Parkinson's Disease subjects and used to train machine learning predictors of baseline clinical and future severity at 1 year, 2 years, and 4 years follow-up as measured by the Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS). Predictive performance is measured with nested cross-validation, validated on an external dataset, and again validated through leave-one-site-out cross-validation. Important predictive features are identified. RESULTS: The models explain up to 30.4% of the variance in current MDS-UPDRS scores, 55.8% of the variance in year 1 scores, and 47.1% of the variance in year 2 scores (p < 0.0001). For distinguishing high and low-severity individuals at each timepoint (MDS-UPDRS score above or below the median, respectively), the models achieve positive predictive values up to 79% and negative predictive values up to 80%. Higher ReHo and fALFF in several regions, including components of the default motor network, predicted lower severity across current and future timepoints. CONCLUSION: These results identify an accurate prognostic neuroimaging biomarker which may be used to better inform enrollment in trials of neuroprotective treatments and enable physicians to counsel their patients.
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: Y Y Fathy; A J Jonker; E Oudejans; F J J de Jong; A-M W van Dam; A J M Rozemuller; W D J van de Berg Journal: Neuropathol Appl Neurobiol Date: 2018-06-26 Impact factor: 8.090
Authors: Maxwell L Elliott; Annchen R Knodt; Megan Cooke; M Justin Kim; Tracy R Melzer; Ross Keenan; David Ireland; Sandhya Ramrakha; Richie Poulton; Avshalom Caspi; Terrie E Moffitt; Ahmad R Hariri Journal: Neuroimage Date: 2019-01-29 Impact factor: 6.556