Evaluating the predictability of medical conditions from social media posts.
We studied whether medical conditions across 21 broad categories were predictable from social media content across approximately 20 million words written by 999 consenting patients. Facebook language significantly improved upon the prediction accuracy of demographic variables for 18 of the 21 diseas...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2019-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0215476 |
| _version_ | 1818725059932454912 |
|---|---|
| author | Raina M Merchant David A Asch Patrick Crutchley Lyle H Ungar Sharath C Guntuku Johannes C Eichstaedt Shawndra Hill Kevin Padrez Robert J Smith H Andrew Schwartz |
| author_facet | Raina M Merchant David A Asch Patrick Crutchley Lyle H Ungar Sharath C Guntuku Johannes C Eichstaedt Shawndra Hill Kevin Padrez Robert J Smith H Andrew Schwartz |
| author_sort | Raina M Merchant |
| collection | DOAJ |
| description | We studied whether medical conditions across 21 broad categories were predictable from social media content across approximately 20 million words written by 999 consenting patients. Facebook language significantly improved upon the prediction accuracy of demographic variables for 18 of the 21 disease categories; it was particularly effective at predicting diabetes and mental health conditions including anxiety, depression and psychoses. Social media data are a quantifiable link into the otherwise elusive daily lives of patients, providing an avenue for study and assessment of behavioral and environmental disease risk factors. Analogous to the genome, social media data linked to medical diagnoses can be banked with patients' consent, and an encoding of social media language can be used as markers of disease risk, serve as a screening tool, and elucidate disease epidemiology. In what we believe to be the first report linking electronic medical record data with social media data from consenting patients, we identified that patients' Facebook status updates can predict many health conditions, suggesting opportunities to use social media data to determine disease onset or exacerbation and to conduct social media-based health interventions. |
| first_indexed | 2024-12-17T21:36:18Z |
| format | Article |
| id | doaj.art-3d1528f4d9d342ab88d5b8f67adf08af |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-17T21:36:18Z |
| publishDate | 2019-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-3d1528f4d9d342ab88d5b8f67adf08af2022-12-21T21:31:43ZengPublic Library of Science (PLoS)PLoS ONE1932-62032019-01-01146e021547610.1371/journal.pone.0215476Evaluating the predictability of medical conditions from social media posts.Raina M MerchantDavid A AschPatrick CrutchleyLyle H UngarSharath C GuntukuJohannes C EichstaedtShawndra HillKevin PadrezRobert J SmithH Andrew SchwartzWe studied whether medical conditions across 21 broad categories were predictable from social media content across approximately 20 million words written by 999 consenting patients. Facebook language significantly improved upon the prediction accuracy of demographic variables for 18 of the 21 disease categories; it was particularly effective at predicting diabetes and mental health conditions including anxiety, depression and psychoses. Social media data are a quantifiable link into the otherwise elusive daily lives of patients, providing an avenue for study and assessment of behavioral and environmental disease risk factors. Analogous to the genome, social media data linked to medical diagnoses can be banked with patients' consent, and an encoding of social media language can be used as markers of disease risk, serve as a screening tool, and elucidate disease epidemiology. In what we believe to be the first report linking electronic medical record data with social media data from consenting patients, we identified that patients' Facebook status updates can predict many health conditions, suggesting opportunities to use social media data to determine disease onset or exacerbation and to conduct social media-based health interventions.https://doi.org/10.1371/journal.pone.0215476 |
| spellingShingle | Raina M Merchant David A Asch Patrick Crutchley Lyle H Ungar Sharath C Guntuku Johannes C Eichstaedt Shawndra Hill Kevin Padrez Robert J Smith H Andrew Schwartz Evaluating the predictability of medical conditions from social media posts. PLoS ONE |
| title | Evaluating the predictability of medical conditions from social media posts. |
| title_full | Evaluating the predictability of medical conditions from social media posts. |
| title_fullStr | Evaluating the predictability of medical conditions from social media posts. |
| title_full_unstemmed | Evaluating the predictability of medical conditions from social media posts. |
| title_short | Evaluating the predictability of medical conditions from social media posts. |
| title_sort | evaluating the predictability of medical conditions from social media posts |
| url | https://doi.org/10.1371/journal.pone.0215476 |
| work_keys_str_mv | AT rainammerchant evaluatingthepredictabilityofmedicalconditionsfromsocialmediaposts AT davidaasch evaluatingthepredictabilityofmedicalconditionsfromsocialmediaposts AT patrickcrutchley evaluatingthepredictabilityofmedicalconditionsfromsocialmediaposts AT lylehungar evaluatingthepredictabilityofmedicalconditionsfromsocialmediaposts AT sharathcguntuku evaluatingthepredictabilityofmedicalconditionsfromsocialmediaposts AT johannesceichstaedt evaluatingthepredictabilityofmedicalconditionsfromsocialmediaposts AT shawndrahill evaluatingthepredictabilityofmedicalconditionsfromsocialmediaposts AT kevinpadrez evaluatingthepredictabilityofmedicalconditionsfromsocialmediaposts AT robertjsmith evaluatingthepredictabilityofmedicalconditionsfromsocialmediaposts AT handrewschwartz evaluatingthepredictabilityofmedicalconditionsfromsocialmediaposts |