Optimising classification of Parkinson’s disease based on motor, olfactory, neuropsychiatric and sleep features
Abstract Olfactory loss, motor impairment, anxiety/depression, and REM-sleep behaviour disorder (RBD) are prodromal Parkinson’s disease (PD) features. PD risk prediction models typically dichotomize test results and apply likelihood ratios (LRs) to scores above and below cut-offs. We investigate whe...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2021-09-01
|
| Series: | npj Parkinson's Disease |
| Online Access: | https://doi.org/10.1038/s41531-021-00226-2 |
| _version_ | 1827776727852515328 |
|---|---|
| author | Jonathan P. Bestwick Stephen D. Auger Anette E. Schrag Donald G. Grosset Sofia Kanavou Gavin Giovannoni Andrew J. Lees Jack Cuzick Alastair J. Noyce |
| author_facet | Jonathan P. Bestwick Stephen D. Auger Anette E. Schrag Donald G. Grosset Sofia Kanavou Gavin Giovannoni Andrew J. Lees Jack Cuzick Alastair J. Noyce |
| author_sort | Jonathan P. Bestwick |
| collection | DOAJ |
| description | Abstract Olfactory loss, motor impairment, anxiety/depression, and REM-sleep behaviour disorder (RBD) are prodromal Parkinson’s disease (PD) features. PD risk prediction models typically dichotomize test results and apply likelihood ratios (LRs) to scores above and below cut-offs. We investigate whether LRs for specific test values could enhance classification between PD and controls. PD patient data on smell (UPSIT), possible RBD (RBD Screening Questionnaire), and anxiety/depression (LADS) were taken from the Tracking Parkinson’s study (n = 1046). For motor impairment (BRAIN test) in PD cases, published data were supplemented (n = 87). Control data (HADS for anxiety/depression) were taken from the PREDICT-PD pilot study (n = 1314). UPSIT, RBDSQ, and anxiety/depression data were analysed using logistic regression to determine which items were associated with PD. Gaussian distributions were fitted to BRAIN test scores. LRs were calculated from logistic regression models or score distributions. False-positive rates (FPRs) for specified detection rates (DRs) were calculated. Sixteen odours were associated with PD; LRs for this set ranged from 0.005 to 5511. Six RBDSQ and seven anxiety/depression questions were associated with PD; LRs ranged from 0.35 to 69 and from 0.002 to 402, respectively. BRAIN test LRs ranged from 0.16 to 1311. For a 70% DR, the FPR was 2.4% for the 16 odours, 4.6% for anxiety/depression, 16.0% for the BRAIN test, and 20.0% for the RBDSQ. Specific selections of (prodromal) PD marker features rather than dichotomized marker test results optimize PD classification. Such optimized classification models could improve the ability of algorithms to detect prodromal PD; however, prospective studies are needed to investigate their value for PD-prediction models. |
| first_indexed | 2024-03-11T14:09:12Z |
| format | Article |
| id | doaj.art-65468704213a42c5a5966766f07c7b64 |
| institution | Directory Open Access Journal |
| issn | 2373-8057 |
| language | English |
| last_indexed | 2024-03-11T14:09:12Z |
| publishDate | 2021-09-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Parkinson's Disease |
| spelling | doaj.art-65468704213a42c5a5966766f07c7b642023-11-02T00:42:59ZengNature Portfolionpj Parkinson's Disease2373-80572021-09-017111110.1038/s41531-021-00226-2Optimising classification of Parkinson’s disease based on motor, olfactory, neuropsychiatric and sleep featuresJonathan P. Bestwick0Stephen D. Auger1Anette E. Schrag2Donald G. Grosset3Sofia Kanavou4Gavin Giovannoni5Andrew J. Lees6Jack Cuzick7Alastair J. Noyce8Preventive Neurology Unit, Wolfson Institute of Population Health, Barts and the London School of Medicine and Dentistry, Queen Mary University of LondonPreventive Neurology Unit, Wolfson Institute of Population Health, Barts and the London School of Medicine and Dentistry, Queen Mary University of LondonDepartment of Clinical and Movement Neuroscience, UCL Institute of Neurology, University College LondonDepartment of Neurology, Institute of Neurological Sciences, Queen Elizabeth University HospitalPopulation Health Sciences, University of BristolPreventive Neurology Unit, Wolfson Institute of Population Health, Barts and the London School of Medicine and Dentistry, Queen Mary University of LondonDepartment of Clinical and Movement Neuroscience, UCL Institute of Neurology, University College LondonPreventive Neurology Unit, Wolfson Institute of Population Health, Barts and the London School of Medicine and Dentistry, Queen Mary University of LondonPreventive Neurology Unit, Wolfson Institute of Population Health, Barts and the London School of Medicine and Dentistry, Queen Mary University of LondonAbstract Olfactory loss, motor impairment, anxiety/depression, and REM-sleep behaviour disorder (RBD) are prodromal Parkinson’s disease (PD) features. PD risk prediction models typically dichotomize test results and apply likelihood ratios (LRs) to scores above and below cut-offs. We investigate whether LRs for specific test values could enhance classification between PD and controls. PD patient data on smell (UPSIT), possible RBD (RBD Screening Questionnaire), and anxiety/depression (LADS) were taken from the Tracking Parkinson’s study (n = 1046). For motor impairment (BRAIN test) in PD cases, published data were supplemented (n = 87). Control data (HADS for anxiety/depression) were taken from the PREDICT-PD pilot study (n = 1314). UPSIT, RBDSQ, and anxiety/depression data were analysed using logistic regression to determine which items were associated with PD. Gaussian distributions were fitted to BRAIN test scores. LRs were calculated from logistic regression models or score distributions. False-positive rates (FPRs) for specified detection rates (DRs) were calculated. Sixteen odours were associated with PD; LRs for this set ranged from 0.005 to 5511. Six RBDSQ and seven anxiety/depression questions were associated with PD; LRs ranged from 0.35 to 69 and from 0.002 to 402, respectively. BRAIN test LRs ranged from 0.16 to 1311. For a 70% DR, the FPR was 2.4% for the 16 odours, 4.6% for anxiety/depression, 16.0% for the BRAIN test, and 20.0% for the RBDSQ. Specific selections of (prodromal) PD marker features rather than dichotomized marker test results optimize PD classification. Such optimized classification models could improve the ability of algorithms to detect prodromal PD; however, prospective studies are needed to investigate their value for PD-prediction models.https://doi.org/10.1038/s41531-021-00226-2 |
| spellingShingle | Jonathan P. Bestwick Stephen D. Auger Anette E. Schrag Donald G. Grosset Sofia Kanavou Gavin Giovannoni Andrew J. Lees Jack Cuzick Alastair J. Noyce Optimising classification of Parkinson’s disease based on motor, olfactory, neuropsychiatric and sleep features npj Parkinson's Disease |
| title | Optimising classification of Parkinson’s disease based on motor, olfactory, neuropsychiatric and sleep features |
| title_full | Optimising classification of Parkinson’s disease based on motor, olfactory, neuropsychiatric and sleep features |
| title_fullStr | Optimising classification of Parkinson’s disease based on motor, olfactory, neuropsychiatric and sleep features |
| title_full_unstemmed | Optimising classification of Parkinson’s disease based on motor, olfactory, neuropsychiatric and sleep features |
| title_short | Optimising classification of Parkinson’s disease based on motor, olfactory, neuropsychiatric and sleep features |
| title_sort | optimising classification of parkinson s disease based on motor olfactory neuropsychiatric and sleep features |
| url | https://doi.org/10.1038/s41531-021-00226-2 |
| work_keys_str_mv | AT jonathanpbestwick optimisingclassificationofparkinsonsdiseasebasedonmotorolfactoryneuropsychiatricandsleepfeatures AT stephendauger optimisingclassificationofparkinsonsdiseasebasedonmotorolfactoryneuropsychiatricandsleepfeatures AT anetteeschrag optimisingclassificationofparkinsonsdiseasebasedonmotorolfactoryneuropsychiatricandsleepfeatures AT donaldggrosset optimisingclassificationofparkinsonsdiseasebasedonmotorolfactoryneuropsychiatricandsleepfeatures AT sofiakanavou optimisingclassificationofparkinsonsdiseasebasedonmotorolfactoryneuropsychiatricandsleepfeatures AT gavingiovannoni optimisingclassificationofparkinsonsdiseasebasedonmotorolfactoryneuropsychiatricandsleepfeatures AT andrewjlees optimisingclassificationofparkinsonsdiseasebasedonmotorolfactoryneuropsychiatricandsleepfeatures AT jackcuzick optimisingclassificationofparkinsonsdiseasebasedonmotorolfactoryneuropsychiatricandsleepfeatures AT alastairjnoyce optimisingclassificationofparkinsonsdiseasebasedonmotorolfactoryneuropsychiatricandsleepfeatures |