Random forest prediction of Alzheimer's disease using pairwise selection from time series data
Time-dependent data collected in studies of Alzheimer's disease usually has missing and irregularly sampled data points. For this reason time series methods which assume regular sampling cannot be applied directly to the data without a pre-processing step. In this paper we use a random forest t...
| Asıl Yazarlar: | , , , |
|---|---|
| Materyal Türü: | Journal article |
| Dil: | English |
| Baskı/Yayın Bilgisi: |
Public Library of Science
2019
|
| _version_ | 1826285032658960384 |
|---|---|
| author | Moore, P Lyons, T Gallacher, J Alzheimer’S Disease Neuroimaging Initiative, |
| author_facet | Moore, P Lyons, T Gallacher, J Alzheimer’S Disease Neuroimaging Initiative, |
| author_sort | Moore, P |
| collection | OXFORD |
| description | Time-dependent data collected in studies of Alzheimer's disease usually has missing and irregularly sampled data points. For this reason time series methods which assume regular sampling cannot be applied directly to the data without a pre-processing step. In this paper we use a random forest to learn the relationship between pairs of data points at different time separations. The input vector is a summary of the time series history and it includes both demographic and non-time varying variables such as genetic data. To test the method we use data from the TADPOLE grand challenge, an initiative which aims to predict the evolution of subjects at risk of Alzheimer's disease using demographic, physical and cognitive input data. The task is to predict diagnosis, ADAS-13 score and normalised ventricles volume. While the competition proceeds, forecasting methods may be compared using a leaderboard dataset selected from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and with standard metrics for measuring accuracy. For diagnosis, we find an mAUC of 0.82, and a classification accuracy of 0.73 compared with a benchmark SVM predictor which gives mAUC = 0.62 and BCA = 0.52. The results show that the method is effective and comparable with other methods. |
| first_indexed | 2024-03-07T01:22:47Z |
| format | Journal article |
| id | oxford-uuid:90ef958e-ecfc-4cab-9c3b-c0e4211d0fb5 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T01:22:47Z |
| publishDate | 2019 |
| publisher | Public Library of Science |
| record_format | dspace |
| spelling | oxford-uuid:90ef958e-ecfc-4cab-9c3b-c0e4211d0fb52022-03-26T23:15:07ZRandom forest prediction of Alzheimer's disease using pairwise selection from time series dataJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:90ef958e-ecfc-4cab-9c3b-c0e4211d0fb5EnglishSymplectic Elements at OxfordPublic Library of Science2019Moore, PLyons, TGallacher, JAlzheimer’S Disease Neuroimaging Initiative,Time-dependent data collected in studies of Alzheimer's disease usually has missing and irregularly sampled data points. For this reason time series methods which assume regular sampling cannot be applied directly to the data without a pre-processing step. In this paper we use a random forest to learn the relationship between pairs of data points at different time separations. The input vector is a summary of the time series history and it includes both demographic and non-time varying variables such as genetic data. To test the method we use data from the TADPOLE grand challenge, an initiative which aims to predict the evolution of subjects at risk of Alzheimer's disease using demographic, physical and cognitive input data. The task is to predict diagnosis, ADAS-13 score and normalised ventricles volume. While the competition proceeds, forecasting methods may be compared using a leaderboard dataset selected from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and with standard metrics for measuring accuracy. For diagnosis, we find an mAUC of 0.82, and a classification accuracy of 0.73 compared with a benchmark SVM predictor which gives mAUC = 0.62 and BCA = 0.52. The results show that the method is effective and comparable with other methods. |
| spellingShingle | Moore, P Lyons, T Gallacher, J Alzheimer’S Disease Neuroimaging Initiative, Random forest prediction of Alzheimer's disease using pairwise selection from time series data |
| title | Random forest prediction of Alzheimer's disease using pairwise selection from time series data |
| title_full | Random forest prediction of Alzheimer's disease using pairwise selection from time series data |
| title_fullStr | Random forest prediction of Alzheimer's disease using pairwise selection from time series data |
| title_full_unstemmed | Random forest prediction of Alzheimer's disease using pairwise selection from time series data |
| title_short | Random forest prediction of Alzheimer's disease using pairwise selection from time series data |
| title_sort | random forest prediction of alzheimer s disease using pairwise selection from time series data |
| work_keys_str_mv | AT moorep randomforestpredictionofalzheimersdiseaseusingpairwiseselectionfromtimeseriesdata AT lyonst randomforestpredictionofalzheimersdiseaseusingpairwiseselectionfromtimeseriesdata AT gallacherj randomforestpredictionofalzheimersdiseaseusingpairwiseselectionfromtimeseriesdata AT alzheimersdiseaseneuroimaginginitiative randomforestpredictionofalzheimersdiseaseusingpairwiseselectionfromtimeseriesdata |