Mike A Nalls1, Cory Y McLean2, Jacqueline Rick3, Shirley Eberly4, Samantha J Hutten5, Katrina Gwinn6, Margaret Sutherland6, Maria Martinez7, Peter Heutink8, Nigel M Williams9, John Hardy10, Thomas Gasser11, Alexis Brice12, T Ryan Price1, Aude Nicolas1, Margaux F Keller13, Cliona Molony13, J Raphael Gibbs1, Alice Chen-Plotkin3, Eunran Suh14, Christopher Letson1, Massimo S Fiandaca15, Mark Mapstone16, Howard J Federoff15, Alastair J Noyce10, Huw Morris10, Vivianna M Van Deerlin14, Daniel Weintraub17, Cyrus Zabetian18, Dena G Hernandez1, Suzanne Lesage12, Meghan Mullins2, Emily Drabant Conley2, Carrie A M Northover2, Mark Frasier5, Ken Marek19, Aaron G Day-Williams20, David J Stone13, John P A Ioannidis21, Andrew B Singleton22. 1. Laboratory of Neurogenetics, National Institute on Aging, National Institutes of Health, Bethesda, MD, USA. 2. 23andMe, Mountain View, CA, USA. 3. Department of Neurology, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA, USA. 4. Deptartment of Biostatistics and Computational Biology, University of Rochester Medical Center, Rochester, NY, USA. 5. The Michael J Fox Foundation for Parkinson's Research, New York, NY 10018, USA. 6. National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD, USA. 7. INSERM, UMR 1043, Centre de Physiopathologie de Toulouse-Purpan, Toulouse, France; Paul Sabatier University, Toulouse, France. 8. Genome Biology of Neurodegenerative Diseases, German Center for Neurodegenerative Diseases, Tübingen, Germany. 9. Institute of Psychological Medicine and Clinical Neurosciences, MRCCentre for Neuropsychiatric Genetics and Genomics, Cardiff University, Cardiff, UK. 10. Reta Lila Weston Institute, University College London Institute of Neurology, London, UK. 11. Department for Neurodegenerative Diseases, Hertie Institute for Clinical Brain Research, University of Tübingen, Tübingen, Germany. 12. Sorbonne Université, UPMC Univ Paris 06, UM 1127, ICM, Paris, France; INSERM, U 1127, and CNRS, UMR 7225, Institut du Cerveau et de la Moelle Epinière, Paris, France; AP-HP, Hôpital de la Salpêtrière, Département de Génétique et Cytogénétique, Paris, France. 13. Genetics and Pharmacogenomics, Merck Research Laboratories, West Point, PA, USA; Merck Research Laboratories, Boston, MA, USA. 14. Center for Neurodegenerative Disease Research, Department of Pathology and Laboratory Medicine, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA, USA. 15. Department of Neurology, Georgetown University Medical Center, Washington, DC, USA. 16. Department of Neurology, University of Rochester Medical Center, Rochester, NY, USA. 17. Department of Neurology, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA, USA; Department of Psychiatry, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA, USA. 18. Department of Neurology, Division of Neurogenetics, VA Puget Sound Health Care System, Seattle, WA, USA. 19. Institute for Neurodegenerative Disorders, New Haven, CT, USA. 20. Precision Medicine, Biogen, Cambridge, MA, USA. 21. Meta-Research Innovation Center at Stanford (METRICS), Stanford University, Stanford, CA, USA; Department of Medicine, Stanford Prevention Research Center, Stanford, CA, USA; Department of Health Research and Policy, Stanford University School of Medicine, Stanford, CA, USA; Department of Statistics, Stanford University School of Humanities and Sciences, Stanford, CA, USA. 22. Laboratory of Neurogenetics, National Institute on Aging, National Institutes of Health, Bethesda, MD, USA. Electronic address: singleta@mail.nih.gov.
Abstract
BACKGROUND: Accurate diagnosis and early detection of complex diseases, such as Parkinson's disease, has the potential to be of great benefit for researchers and clinical practice. We aimed to create a non-invasive, accurate classification model for the diagnosis of Parkinson's disease, which could serve as a basis for future disease prediction studies in longitudinal cohorts. METHODS: We developed a model for disease classification using data from the Parkinson's Progression Marker Initiative (PPMI) study for 367 patients with Parkinson's disease and phenotypically typical imaging data and 165 controls without neurological disease. Olfactory function, genetic risk, family history of Parkinson's disease, age, and gender were algorithmically selected by stepwise logistic regression as significant contributors to our classifying model. We then tested the model with data from 825 patients with Parkinson's disease and 261 controls from five independent cohorts with varying recruitment strategies and designs: the Parkinson's Disease Biomarkers Program (PDBP), the Parkinson's Associated Risk Study (PARS), 23andMe, the Longitudinal and Biomarker Study in PD (LABS-PD), and the Morris K Udall Parkinson's Disease Research Center of Excellence cohort (Penn-Udall). Additionally, we used our model to investigate patients who had imaging scans without evidence of dopaminergic deficit (SWEDD). FINDINGS: In the population from PPMI, our initial model correctly distinguished patients with Parkinson's disease from controls at an area under the curve (AUC) of 0·923 (95% CI 0·900-0·946) with high sensitivity (0·834, 95% CI 0·711-0·883) and specificity (0·903, 95% CI 0·824-0·946) at its optimum AUC threshold (0·655). All Hosmer-Lemeshow simulations suggested that when parsed into random subgroups, the subgroup data matched that of the overall cohort. External validation showed good classification of Parkinson's disease, with AUCs of 0·894 (95% CI 0·867-0·921) in the PDBP cohort, 0·998 (0·992-1·000) in PARS, 0·955 (no 95% CI available) in 23andMe, 0·929 (0·896-0·962) in LABS-PD, and 0·939 (0·891-0·986) in the Penn-Udall cohort. Four of 17 SWEDD participants who our model classified as having Parkinson's disease converted to Parkinson's disease within 1 year, whereas only one of 38 SWEDD participants who were not classified as having Parkinson's disease underwent conversion (test of proportions, p=0·003). INTERPRETATION: Our model provides a potential new approach to distinguish participants with Parkinson's disease from controls. If the model can also identify individuals with prodromal or preclinical Parkinson's disease in prospective cohorts, it could facilitate identification of biomarkers and interventions. FUNDING: National Institute on Aging, National Institute of Neurological Disorders and Stroke, and the Michael J Fox Foundation.
BACKGROUND: Accurate diagnosis and early detection of complex diseases, such as Parkinson's disease, has the potential to be of great benefit for researchers and clinical practice. We aimed to create a non-invasive, accurate classification model for the diagnosis of Parkinson's disease, which could serve as a basis for future disease prediction studies in longitudinal cohorts. METHODS: We developed a model for disease classification using data from the Parkinson's Progression Marker Initiative (PPMI) study for 367 patients with Parkinson's disease and phenotypically typical imaging data and 165 controls without neurological disease. Olfactory function, genetic risk, family history of Parkinson's disease, age, and gender were algorithmically selected by stepwise logistic regression as significant contributors to our classifying model. We then tested the model with data from 825 patients with Parkinson's disease and 261 controls from five independent cohorts with varying recruitment strategies and designs: the Parkinson's Disease Biomarkers Program (PDBP), the Parkinson's Associated Risk Study (PARS), 23andMe, the Longitudinal and Biomarker Study in PD (LABS-PD), and the Morris K Udall Parkinson's Disease Research Center of Excellence cohort (Penn-Udall). Additionally, we used our model to investigate patients who had imaging scans without evidence of dopaminergic deficit (SWEDD). FINDINGS: In the population from PPMI, our initial model correctly distinguished patients with Parkinson's disease from controls at an area under the curve (AUC) of 0·923 (95% CI 0·900-0·946) with high sensitivity (0·834, 95% CI 0·711-0·883) and specificity (0·903, 95% CI 0·824-0·946) at its optimum AUC threshold (0·655). All Hosmer-Lemeshow simulations suggested that when parsed into random subgroups, the subgroup data matched that of the overall cohort. External validation showed good classification of Parkinson's disease, with AUCs of 0·894 (95% CI 0·867-0·921) in the PDBP cohort, 0·998 (0·992-1·000) in PARS, 0·955 (no 95% CI available) in 23andMe, 0·929 (0·896-0·962) in LABS-PD, and 0·939 (0·891-0·986) in the Penn-Udall cohort. Four of 17 SWEDD participants who our model classified as having Parkinson's disease converted to Parkinson's disease within 1 year, whereas only one of 38 SWEDD participants who were not classified as having Parkinson's disease underwent conversion (test of proportions, p=0·003). INTERPRETATION: Our model provides a potential new approach to distinguish participants with Parkinson's disease from controls. If the model can also identify individuals with prodromal or preclinical Parkinson's disease in prospective cohorts, it could facilitate identification of biomarkers and interventions. FUNDING: National Institute on Aging, National Institute of Neurological Disorders and Stroke, and the Michael J Fox Foundation.
Authors: N Sobel; M E Thomason; I Stappen; C M Tanner; J W Tetrud; J M Bower; E V Sullivan; J D Gabrieli Journal: Proc Natl Acad Sci U S A Date: 2001-03-20 Impact factor: 11.205
Authors: Ronald B Postuma; Dag Aarsland; Paolo Barone; David J Burn; Christopher H Hawkes; Wolfgang Oertel; Tjalf Ziemssen Journal: Mov Disord Date: 2012-04-15 Impact factor: 10.338
Authors: Andrew Siderowf; Danna Jennings; James Connolly; Richard L Doty; Kenneth Marek; Matthew B Stern Journal: Mov Disord Date: 2007-11-15 Impact factor: 10.338
Authors: Mike A Nalls; Nathan Pankratz; Christina M Lill; Chuong B Do; Dena G Hernandez; Mohamad Saad; Anita L DeStefano; Eleanna Kara; Jose Bras; Manu Sharma; Claudia Schulte; Margaux F Keller; Sampath Arepalli; Christopher Letson; Connor Edsall; Hreinn Stefansson; Xinmin Liu; Hannah Pliner; Joseph H Lee; Rong Cheng; M Arfan Ikram; John P A Ioannidis; Georgios M Hadjigeorgiou; Joshua C Bis; Maria Martinez; Joel S Perlmutter; Alison Goate; Karen Marder; Brian Fiske; Margaret Sutherland; Georgia Xiromerisiou; Richard H Myers; Lorraine N Clark; Kari Stefansson; John A Hardy; Peter Heutink; Honglei Chen; Nicholas W Wood; Henry Houlden; Haydeh Payami; Alexis Brice; William K Scott; Thomas Gasser; Lars Bertram; Nicholas Eriksson; Tatiana Foroud; Andrew B Singleton Journal: Nat Genet Date: 2014-07-27 Impact factor: 38.330
Authors: Sara Bandrés-Ciga; Timothy Ryan Price; Francisco Javier Barrero; Francisco Escamilla-Sevilla; Javier Pelegrina; Sampath Arepalli; Dena Hernández; Blanca Gutiérrez; Jorge Cervilla; Margarita Rivera; Alberto Rivera; Jing-Hui Ding; Francisco Vives; Michael Nalls; Andrew Singleton; Raquel Durán Journal: Neurobiol Aging Date: 2016-06-11 Impact factor: 4.673
Authors: Joanna A Korecka; Ria Thomas; Dan P Christensen; Anthony J Hinrich; Eliza J Ferrari; Simon A Levy; Michelle L Hastings; Penelope J Hallett; Ole Isacson Journal: Hum Mol Genet Date: 2019-10-01 Impact factor: 6.150