Cargando…
Prediction of stress and drug craving ninety minutes in the future with passively collected GPS data
Just-in-time adaptive interventions (JITAIs), typically smartphone apps, learn to deliver therapeutic content when users need it. The challenge is to “push” content at algorithmically chosen moments without making users trigger it with effortful input. We trained a randomForest algorithm to predict...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7055250/ https://www.ncbi.nlm.nih.gov/pubmed/32195362 http://dx.doi.org/10.1038/s41746-020-0234-6 |
_version_ | 1783503335816429568 |
---|---|
author | Epstein, David H. Tyburski, Matthew Kowalczyk, William J. Burgess-Hull, Albert J. Phillips, Karran A. Curtis, Brenda L. Preston, Kenzie L. |
author_facet | Epstein, David H. Tyburski, Matthew Kowalczyk, William J. Burgess-Hull, Albert J. Phillips, Karran A. Curtis, Brenda L. Preston, Kenzie L. |
author_sort | Epstein, David H. |
collection | PubMed |
description | Just-in-time adaptive interventions (JITAIs), typically smartphone apps, learn to deliver therapeutic content when users need it. The challenge is to “push” content at algorithmically chosen moments without making users trigger it with effortful input. We trained a randomForest algorithm to predict heroin craving, cocaine craving, or stress (reported via smartphone app 3x/day) 90 min into the future, using 16 weeks of field data from 189 outpatients being treated for opioid-use disorder. We used only one form of continuous input (along with person-level demographic data), collected passively: an indicator of environmental exposures along the past 5 h of movement, as assessed by GPS. Our models achieved excellent overall accuracy—as high as 0.93 by the end of 16 weeks of tailoring—but this was driven mostly by correct predictions of absence. For predictions of presence, “believability” (positive predictive value, PPV) usually peaked in the high 0.70s toward the end of the 16 weeks. When the prediction target was more rare, PPV was lower. Our findings complement those of other investigators who use machine learning with more broadly based “digital phenotyping” inputs to predict or detect mental and behavioral events. When target events are comparatively subtle, like stress or drug craving, accurate detection or prediction probably needs effortful input from users, not passive monitoring alone. We discuss ways in which accuracy is difficult to achieve or even assess, and warn that high overall accuracy (including high specificity) can mask the abundance of false alarms that low PPV reveals. |
format | Online Article Text |
id | pubmed-7055250 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | Nature Publishing Group UK |
record_format | MEDLINE/PubMed |
spelling | pubmed-70552502020-03-19 Prediction of stress and drug craving ninety minutes in the future with passively collected GPS data Epstein, David H. Tyburski, Matthew Kowalczyk, William J. Burgess-Hull, Albert J. Phillips, Karran A. Curtis, Brenda L. Preston, Kenzie L. NPJ Digit Med Article Just-in-time adaptive interventions (JITAIs), typically smartphone apps, learn to deliver therapeutic content when users need it. The challenge is to “push” content at algorithmically chosen moments without making users trigger it with effortful input. We trained a randomForest algorithm to predict heroin craving, cocaine craving, or stress (reported via smartphone app 3x/day) 90 min into the future, using 16 weeks of field data from 189 outpatients being treated for opioid-use disorder. We used only one form of continuous input (along with person-level demographic data), collected passively: an indicator of environmental exposures along the past 5 h of movement, as assessed by GPS. Our models achieved excellent overall accuracy—as high as 0.93 by the end of 16 weeks of tailoring—but this was driven mostly by correct predictions of absence. For predictions of presence, “believability” (positive predictive value, PPV) usually peaked in the high 0.70s toward the end of the 16 weeks. When the prediction target was more rare, PPV was lower. Our findings complement those of other investigators who use machine learning with more broadly based “digital phenotyping” inputs to predict or detect mental and behavioral events. When target events are comparatively subtle, like stress or drug craving, accurate detection or prediction probably needs effortful input from users, not passive monitoring alone. We discuss ways in which accuracy is difficult to achieve or even assess, and warn that high overall accuracy (including high specificity) can mask the abundance of false alarms that low PPV reveals. Nature Publishing Group UK 2020-03-04 /pmc/articles/PMC7055250/ /pubmed/32195362 http://dx.doi.org/10.1038/s41746-020-0234-6 Text en © This is a U.S. government work and not under copyright protection in the U.S.; foreign copyright protection may apply 2020 Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/. |
spellingShingle | Article Epstein, David H. Tyburski, Matthew Kowalczyk, William J. Burgess-Hull, Albert J. Phillips, Karran A. Curtis, Brenda L. Preston, Kenzie L. Prediction of stress and drug craving ninety minutes in the future with passively collected GPS data |
title | Prediction of stress and drug craving ninety minutes in the future with passively collected GPS data |
title_full | Prediction of stress and drug craving ninety minutes in the future with passively collected GPS data |
title_fullStr | Prediction of stress and drug craving ninety minutes in the future with passively collected GPS data |
title_full_unstemmed | Prediction of stress and drug craving ninety minutes in the future with passively collected GPS data |
title_short | Prediction of stress and drug craving ninety minutes in the future with passively collected GPS data |
title_sort | prediction of stress and drug craving ninety minutes in the future with passively collected gps data |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7055250/ https://www.ncbi.nlm.nih.gov/pubmed/32195362 http://dx.doi.org/10.1038/s41746-020-0234-6 |
work_keys_str_mv | AT epsteindavidh predictionofstressanddrugcravingninetyminutesinthefuturewithpassivelycollectedgpsdata AT tyburskimatthew predictionofstressanddrugcravingninetyminutesinthefuturewithpassivelycollectedgpsdata AT kowalczykwilliamj predictionofstressanddrugcravingninetyminutesinthefuturewithpassivelycollectedgpsdata AT burgesshullalbertj predictionofstressanddrugcravingninetyminutesinthefuturewithpassivelycollectedgpsdata AT phillipskarrana predictionofstressanddrugcravingninetyminutesinthefuturewithpassivelycollectedgpsdata AT curtisbrendal predictionofstressanddrugcravingninetyminutesinthefuturewithpassivelycollectedgpsdata AT prestonkenziel predictionofstressanddrugcravingninetyminutesinthefuturewithpassivelycollectedgpsdata |