Detecting Bipolar Depression from Geographic Location Data
Objective: This work aims to identify periods of depression using geolocation movements recorded from mobile phones in a prospective community study of individuals with bipolar disorder (BD). <br/>Methods: Anonymised geographic location recordings from 22 BD participants and 14 healthy contro...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Journal article |
| Published: |
Institute of Electrical and Electronics Engineers
2016
|
| _version_ | 1826265823030804480 |
|---|---|
| author | De Vos, M Geddes, J Goodwin, G Tsanas, A Saunders, K Bilderbeck, A Palmius, N |
| author_facet | De Vos, M Geddes, J Goodwin, G Tsanas, A Saunders, K Bilderbeck, A Palmius, N |
| author_sort | De Vos, M |
| collection | OXFORD |
| description | Objective: This work aims to identify periods of depression using geolocation movements recorded from mobile phones in a prospective community study of individuals with bipolar disorder (BD). <br/>Methods: Anonymised geographic location recordings from 22 BD participants and 14 healthy controls (HC) were collected over 3 months. Participants reported their depressive symptomatology using a weekly questionnaire (QIDS-SR16). Recorded location data were pre-processed by detecting and removing imprecise data points and features were extracted to assess the level and regularity of geographic movements of the participant. A subset of features were selected using a wrapper feature selection method and presented to (a) a linear regression model and a quadratic generalised linear model with a logistic link function for questionnaire score estimation; and (b) a quadratic discriminant analysis classifier for depression detection in BD participants based on their questionnaire responses. <br/>Results: HC participants did not report depressive symptoms and their features showed similar distributions to nondepressed BD participants. Questionnaire score estimation using geolocation-derived features from BD participants demonstrated an optimal mean absolute error rate of 3.73 while depression detection demonstrated an optimal (median±IQR) F1 score of 0.857±0.022 using 5 features (classification accuracy: 0.849±0.016; sensitivity: 0.839±0.014; specificity: 0.872±0.047). <br/>Conclusion: These results demonstrate a strong link between geographic movements and depression in bipolar disorder. <br/>Significance: To our knowledge this is the first community study of passively recorded objective markers of depression in bipolar disorder of this scale. The techniques could help individuals monitor their depression and enable healthcare providers to detect those in need of care or treatment. |
| first_indexed | 2024-03-06T20:29:39Z |
| format | Journal article |
| id | oxford-uuid:309eced3-45d8-4e1e-b92e-dcd780643a6e |
| institution | University of Oxford |
| last_indexed | 2024-03-06T20:29:39Z |
| publishDate | 2016 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | oxford-uuid:309eced3-45d8-4e1e-b92e-dcd780643a6e2022-03-26T13:02:33ZDetecting Bipolar Depression from Geographic Location DataJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:309eced3-45d8-4e1e-b92e-dcd780643a6eSymplectic Elements at OxfordInstitute of Electrical and Electronics Engineers2016De Vos, MGeddes, JGoodwin, GTsanas, ASaunders, KBilderbeck, APalmius, NObjective: This work aims to identify periods of depression using geolocation movements recorded from mobile phones in a prospective community study of individuals with bipolar disorder (BD). <br/>Methods: Anonymised geographic location recordings from 22 BD participants and 14 healthy controls (HC) were collected over 3 months. Participants reported their depressive symptomatology using a weekly questionnaire (QIDS-SR16). Recorded location data were pre-processed by detecting and removing imprecise data points and features were extracted to assess the level and regularity of geographic movements of the participant. A subset of features were selected using a wrapper feature selection method and presented to (a) a linear regression model and a quadratic generalised linear model with a logistic link function for questionnaire score estimation; and (b) a quadratic discriminant analysis classifier for depression detection in BD participants based on their questionnaire responses. <br/>Results: HC participants did not report depressive symptoms and their features showed similar distributions to nondepressed BD participants. Questionnaire score estimation using geolocation-derived features from BD participants demonstrated an optimal mean absolute error rate of 3.73 while depression detection demonstrated an optimal (median±IQR) F1 score of 0.857±0.022 using 5 features (classification accuracy: 0.849±0.016; sensitivity: 0.839±0.014; specificity: 0.872±0.047). <br/>Conclusion: These results demonstrate a strong link between geographic movements and depression in bipolar disorder. <br/>Significance: To our knowledge this is the first community study of passively recorded objective markers of depression in bipolar disorder of this scale. The techniques could help individuals monitor their depression and enable healthcare providers to detect those in need of care or treatment. |
| spellingShingle | De Vos, M Geddes, J Goodwin, G Tsanas, A Saunders, K Bilderbeck, A Palmius, N Detecting Bipolar Depression from Geographic Location Data |
| title | Detecting Bipolar Depression from Geographic Location Data |
| title_full | Detecting Bipolar Depression from Geographic Location Data |
| title_fullStr | Detecting Bipolar Depression from Geographic Location Data |
| title_full_unstemmed | Detecting Bipolar Depression from Geographic Location Data |
| title_short | Detecting Bipolar Depression from Geographic Location Data |
| title_sort | detecting bipolar depression from geographic location data |
| work_keys_str_mv | AT devosm detectingbipolardepressionfromgeographiclocationdata AT geddesj detectingbipolardepressionfromgeographiclocationdata AT goodwing detectingbipolardepressionfromgeographiclocationdata AT tsanasa detectingbipolardepressionfromgeographiclocationdata AT saundersk detectingbipolardepressionfromgeographiclocationdata AT bilderbecka detectingbipolardepressionfromgeographiclocationdata AT palmiusn detectingbipolardepressionfromgeographiclocationdata |