Supplementary materials for statistical and machine learning analyses demonstrate test-retest reliability assessment is misled by focusing on total duration of mobility tasks in Parkinson's disease
| dc.contributor.advisor | Cummings, Michael P. | |
| dc.contributor.author | Khalil, Rana M. | |
| dc.contributor.author | Shulman, Lisa M. | |
| dc.contributor.author | Gruber-Baldini, Ann L. | |
| dc.contributor.author | Shakya, Sunita | |
| dc.contributor.author | Hausdorff, Jeffrey M. | |
| dc.contributor.author | von Coelln, Rainer | |
| dc.contributor.author | Cummings, Michael P. | |
| dc.date.accessioned | 2023-12-27T04:39:34Z | |
| dc.date.available | 2023-12-27T04:39:34Z | |
| dc.date.issued | 2023 | |
| dc.description | 1. data: folder with quantitative measures derived from two trials of TUG, cogTUG, and 16-foot walk. 2. code notebook: notebook with the code used to generate the results provided in the manuscript. To view the notebook open the file index.html in a web browser or open the file notebook.pdf. 3. rdata: folder with intermediate R objects. tug_cogtug_durations.RData saves the total duration and the subtask duration of all participants for both trials of TUG and cogTUG. 16ft_durations.RData saves the total duration and the subtask duration of all participants for 16-foot walk. ids.RData: saves the ids of the mild, moderate, and severe PD participants. HY_early_phys_dfs.RData: saves the quantitative measures of the mild PD participants. HY_mild_phys_dfs.RData: saves the quantitative measures of the moderate PD participants. HY_severe_phys_dfs.RData: saves the quantitative measures of the severe PD participants. HY_control_early_tug1.RData: save a data frame with rows corresponding to mild PD participants and controls and columns corresponding to the quantitative measures derived from the first TUG trial and selected by the feature reduction technique. HY_control_early_tug2.RData: save a data frame with rows corresponding to mild PD participants and controls and columns corresponding to the quantitative measures derived from the second TUG trial and selected by the feature reduction technique. HY_control_early_tug_phys.RData: save a data frame with rows corresponding to mild PD participants and controls and columns corresponding to the quantitative measures derived from both TUG trials and selected by the feature reduction technique. HY_control_early_cogtug1.RData: save a data frame with rows corresponding to mild PD participants and controls and columns corresponding to the quantitative measures derived from the first cogTUG trial and selected by the feature reduction technique. HY_control_early_cogtug2.RData: save a data frame with rows corresponding to mild PD participants and controls and columns corresponding to the quantitative measures derived from the second cogTUG trial and selected by the feature reduction technique. HY_control_early_cogtug_phys.RData: save a data frame with rows corresponding to mild PD participants and controls and columns corresponding to the quantitative measures derived from both cogTUG trials and selected by the feature reduction technique. HY_control_early_trial1_32ft.RData: save a data frame with rows corresponding to mild PD participants and controls and columns corresponding to the quantitative measures derived from the first 16-foot walk trial and selected by the feature reduction technique. HY_control_early_trial2_32ft.RData: save a data frame with rows corresponding to mild PD participants and controls and columns corresponding to the quantitative measures derived from the second 16-foot walk trial and selected by the feature reduction technique. HY_control_early_trial_32ft_phys.RData: save a data frame with rows corresponding to mild PD participants and controls and columns corresponding to the quantitative measures derived from both 16-foot walk trials and selected by the feature reduction technique. HY_control_mild_tug1.RData: save a data frame with rows corresponding to moderate PD participants and controls and columns corresponding to the quantitative measures derived from the first TUG trial and selected by the feature reduction technique. HY_control_mild_tug2.RData: save a data frame with rows corresponding to moderate PD participants and controls and columns corresponding to the quantitative measures derived from the second TUG trial and selected by the feature reduction technique. HY_control_mild_tug_phys.RData: save a data frame with rows corresponding to moderate PD participants and controls and columns corresponding to the quantitative measures derived from both TUG trials and selected by the feature reduction technique. HY_control_mild_cogtug1.RData: save a data frame with rows corresponding to moderate PD participants and controls and columns corresponding to the quantitative measures derived from the first cogTUG trial and selected by the feature reduction technique. HY_control_mild_cogtug2.RData: save a data frame with rows corresponding to moderate PD participants and controls and columns corresponding to the quantitative measures derived from the second cogTUG trial and selected by the feature reduction technique. HY_control_mild_cogtug_phys.RData: save a data frame with rows corresponding to moderate PD participants and controls and columns corresponding to the quantitative measures derived from both cogTUG trials and selected by the feature reduction technique. HY_control_mild_trial1_32ft.RData: save a data frame with rows corresponding to moderate PD participants and controls and columns corresponding to the quantitative measures derived from the first 16-foot walk trial and selected by the feature reduction technique. HY_control_mild_trial2_32ft.RData: save a data frame with rows corresponding to moderate PD participants and controls and columns corresponding to the quantitative measures derived from the second 16-foot walk trial and selected by the feature reduction technique. HY_control_mild_trial_32ft_phys.RData: save a data frame with rows corresponding to moderate PD participants and controls and columns corresponding to the quantitative measures derived from both 16-foot walk trials and selected by the feature reduction technique. HY_control_severe_tug1.RData: save a data frame with rows corresponding to severe PD participants and controls and columns corresponding to the quantitative measures derived from the first TUG trial and selected by the feature reduction technique. HY_control_severe_tug2.RData: save a data frame with rows corresponding to severe PD participants and controls and columns corresponding to the quantitative measures derived from the second TUG trial and selected by the feature reduction technique. HY_control_severe_tug_phys.RData: save a data frame with rows corresponding to severe PD participants and controls and columns corresponding to the quantitative measures derived from both TUG trials and selected by the feature reduction technique. HY_control_severe_cogtug1.RData: save a data frame with rows corresponding to severe PD participants and controls and columns corresponding to the quantitative measures derived from the first cogTUG trial and selected by the feature reduction technique. HY_control_severe_cogtug2.RData: save a data frame with rows corresponding to severe PD participants and controls and columns corresponding to the quantitative measures derived from the second cogTUG trial and selected by the feature reduction technique. HY_control_severe_cogtug_phys.RData: save a data frame with rows corresponding to severe PD participants and controls and columns corresponding to the quantitative measures derived from both cogTUG trials and selected by the feature reduction technique. HY_control_severe_trial1_32ft.RData: save a data frame with rows corresponding to severe PD participants and controls and columns corresponding to the quantitative measures derived from the first 16-foot walk trial and selected by the feature reduction technique. HY_control_severe_trial2_32ft.RData: save a data frame with rows corresponding to severe PD participants and controls and columns corresponding to the quantitative measures derived from the second 16-foot walk trial and selected by the feature reduction technique. HY_control_severe_trial_32ft_phys.RData: save a data frame with rows corresponding to severe PD participants and controls and columns corresponding to the quantitative measures derived from both 16-foot walk trials and selected by the feature reduction technique. 4. quantitative_measures.csv: a file with all sensor-derived quantitative measures included in the analysis of the manuscript, along with a brief description of each. 5. README: file with detailed instructions on how to set up and run the code, as well as any dependencies or requirements. | |
| dc.description.abstract | Mobility tasks like the Timed Up and Go test (TUG), cognitive TUG (cogTUG), and walking with turns provide insight into dynamic motor control, balance, and cognitive functions affected by Parkinson’s disease (PD). We evaluate the test-retest reliability of these tasks by assessing the performance of machine learning models based on quantitative sensor-derived measures, and statistical measures to examine total duration, subtask duration, and other quantitative measures across both trials. We show that the diagnostic accuracy of differentiating between PD and control participants decreases from the first to the second trial of our mobility tasks, suggesting that mobility testing can be simplified by not repeating tasks without losing relevant information. Although the total duration remains relatively consistent between trials, there is more variability in subtask duration and sensor-derived measures, evident in the differences in machine learning model performance and statistical metrics. Relying solely on total task duration and conventional statistical metrics to gauge the reliability of mobility tasks overlooks the nuanced variations in movement captured by other quantitative measures. | |
| dc.description.sponsorship | Funding was provided by a University of Maryland MPower Seed Grant Award (R.v.C. and M.P.C), the Rosalyn Newman Foundation (L.M.S), and the University of Maryland Claude D. Pepper Older Americans Independence Center (R.v.C). | |
| dc.identifier | https://doi.org/10.13016/dspace/yngi-n7m4 | |
| dc.identifier.uri | http://hdl.handle.net/1903/31553 | |
| dc.language.iso | en_US | |
| dc.relation.isAvailableAt | Digital Repository at the University of Maryland | |
| dc.relation.isAvailableAt | University of Maryland (College Park, Md) | |
| dc.rights | CC0 1.0 Universal | * |
| dc.rights.uri | http://creativecommons.org/publicdomain/zero/1.0/ | * |
| dc.title | Supplementary materials for statistical and machine learning analyses demonstrate test-retest reliability assessment is misled by focusing on total duration of mobility tasks in Parkinson's disease | |
| dc.type | Dataset | |
| local.equitableAccessSubmission | Yes |
Files
Original bundle
1 - 5 of 5
No Thumbnail Available
- Name:
- quantitative_measures.csv
- Size:
- 6.85 KB
- Format:
- Comma-Separated Values
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.55 KB
- Format:
- Item-specific license agreed upon to submission
- Description: