Predicting motor, cognitive and functional impairment in Parkinson's
<strong>Objective</strong> We recently demonstrated that 998 features derived from a simple 7‐minute smartphone test could distinguish between controls, people with Parkinson's and people with idiopathic Rapid Eye Movement sleep behavior disorder, with mean sensitivity/specificity v...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Wiley
2019
|
| _version_ | 1826266920941256704 |
|---|---|
| author | Lo, C Arora, S Baig, F Lawton, M El Mouden, C Barber, T Ruffmann, C Klein, J Brown, P Ben‐Shlomo, Y Vos, M Hu, M |
| author_facet | Lo, C Arora, S Baig, F Lawton, M El Mouden, C Barber, T Ruffmann, C Klein, J Brown, P Ben‐Shlomo, Y Vos, M Hu, M |
| author_sort | Lo, C |
| collection | OXFORD |
| description | <strong>Objective</strong> We recently demonstrated that 998 features derived from a simple 7‐minute smartphone test could distinguish between controls, people with Parkinson's and people with idiopathic Rapid Eye Movement sleep behavior disorder, with mean sensitivity/specificity values of 84.6‐91.9%. Here, we investigate whether the same smartphone features can be used to predict future clinically relevant outcomes in early Parkinson's. <br/><br/> <strong>Methods</strong> A total of 237 participants with Parkinson's (mean (SD) disease duration 3.5 (2.2) years) in the Oxford Discovery cohort performed smartphone tests in clinic and at home. Each test assessed voice, balance, gait, reaction time, dexterity, rest, and postural tremor. In addition, standard motor, cognitive and functional assessments and questionnaires were administered in clinic. Machine learning algorithms were trained to predict the onset of clinical outcomes provided at the next 18‐month follow‐up visit using baseline smartphone recordings alone. The accuracy of model predictions was assessed using 10‐fold and subject‐wise cross validation schemes. <br/><br/> <strong>Results</strong> Baseline smartphone tests predicted the new onset of falls, freezing, postural instability, cognitive impairment, and functional impairment at 18 months. For all outcome predictions AUC values were greater than 0.90 for 10‐fold cross validation using all smartphone features. Using only the 30 most salient features, AUC values greater than 0.75 were obtained. <br/><br/> <strong>Interpretation</strong> We demonstrate the ability to predict key future clinical outcomes using a simple smartphone test. This work has the potential to introduce individualized predictions to routine care, helping to target interventions to those most likely to benefit, with the aim of improving their outcome. |
| first_indexed | 2024-03-06T20:46:16Z |
| format | Journal article |
| id | oxford-uuid:360725c0-cd43-4807-994b-1cf1eaa1a156 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T20:46:16Z |
| publishDate | 2019 |
| publisher | Wiley |
| record_format | dspace |
| spelling | oxford-uuid:360725c0-cd43-4807-994b-1cf1eaa1a1562022-03-26T13:35:18ZPredicting motor, cognitive and functional impairment in Parkinson'sJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:360725c0-cd43-4807-994b-1cf1eaa1a156EnglishSymplectic Elements at OxfordWiley2019Lo, CArora, SBaig, FLawton, MEl Mouden, CBarber, TRuffmann, CKlein, JBrown, PBen‐Shlomo, YVos, MHu, M<strong>Objective</strong> We recently demonstrated that 998 features derived from a simple 7‐minute smartphone test could distinguish between controls, people with Parkinson's and people with idiopathic Rapid Eye Movement sleep behavior disorder, with mean sensitivity/specificity values of 84.6‐91.9%. Here, we investigate whether the same smartphone features can be used to predict future clinically relevant outcomes in early Parkinson's. <br/><br/> <strong>Methods</strong> A total of 237 participants with Parkinson's (mean (SD) disease duration 3.5 (2.2) years) in the Oxford Discovery cohort performed smartphone tests in clinic and at home. Each test assessed voice, balance, gait, reaction time, dexterity, rest, and postural tremor. In addition, standard motor, cognitive and functional assessments and questionnaires were administered in clinic. Machine learning algorithms were trained to predict the onset of clinical outcomes provided at the next 18‐month follow‐up visit using baseline smartphone recordings alone. The accuracy of model predictions was assessed using 10‐fold and subject‐wise cross validation schemes. <br/><br/> <strong>Results</strong> Baseline smartphone tests predicted the new onset of falls, freezing, postural instability, cognitive impairment, and functional impairment at 18 months. For all outcome predictions AUC values were greater than 0.90 for 10‐fold cross validation using all smartphone features. Using only the 30 most salient features, AUC values greater than 0.75 were obtained. <br/><br/> <strong>Interpretation</strong> We demonstrate the ability to predict key future clinical outcomes using a simple smartphone test. This work has the potential to introduce individualized predictions to routine care, helping to target interventions to those most likely to benefit, with the aim of improving their outcome. |
| spellingShingle | Lo, C Arora, S Baig, F Lawton, M El Mouden, C Barber, T Ruffmann, C Klein, J Brown, P Ben‐Shlomo, Y Vos, M Hu, M Predicting motor, cognitive and functional impairment in Parkinson's |
| title | Predicting motor, cognitive and functional impairment in Parkinson's |
| title_full | Predicting motor, cognitive and functional impairment in Parkinson's |
| title_fullStr | Predicting motor, cognitive and functional impairment in Parkinson's |
| title_full_unstemmed | Predicting motor, cognitive and functional impairment in Parkinson's |
| title_short | Predicting motor, cognitive and functional impairment in Parkinson's |
| title_sort | predicting motor cognitive and functional impairment in parkinson s |
| work_keys_str_mv | AT loc predictingmotorcognitiveandfunctionalimpairmentinparkinsons AT aroras predictingmotorcognitiveandfunctionalimpairmentinparkinsons AT baigf predictingmotorcognitiveandfunctionalimpairmentinparkinsons AT lawtonm predictingmotorcognitiveandfunctionalimpairmentinparkinsons AT elmoudenc predictingmotorcognitiveandfunctionalimpairmentinparkinsons AT barbert predictingmotorcognitiveandfunctionalimpairmentinparkinsons AT ruffmannc predictingmotorcognitiveandfunctionalimpairmentinparkinsons AT kleinj predictingmotorcognitiveandfunctionalimpairmentinparkinsons AT brownp predictingmotorcognitiveandfunctionalimpairmentinparkinsons AT benshlomoy predictingmotorcognitiveandfunctionalimpairmentinparkinsons AT vosm predictingmotorcognitiveandfunctionalimpairmentinparkinsons AT hum predictingmotorcognitiveandfunctionalimpairmentinparkinsons |