Emergence of digital biomarkers to predict and modify treatment efficacy: machine learning study

Objectives Development of digital biomarkers to predict treatment response to a digital behavioural intervention.Design Machine learning using random forest classifiers on data generated through the use of a digital therapeutic which delivers behavioural therapy to treat cardiometabolic disease. Dat...

Full description

Saved in:
Bibliographic Details
Main Authors: Nicole L Guthrie, Jason Carpenter, Katherine L Edwards, Kevin J Appelbaum, Sourav Dey, David M Eisenberg, David L Katz, Mark A Berman
Format: Article
Language:English
Published: BMJ Publishing Group 2019-07-01
Series:BMJ Open
Online Access:https://bmjopen.bmj.com/content/9/7/e030710.full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850178694698500096
author Nicole L Guthrie
Jason Carpenter
Katherine L Edwards
Kevin J Appelbaum
Sourav Dey
David M Eisenberg
David L Katz
Mark A Berman
author_facet Nicole L Guthrie
Jason Carpenter
Katherine L Edwards
Kevin J Appelbaum
Sourav Dey
David M Eisenberg
David L Katz
Mark A Berman
author_sort Nicole L Guthrie
collection DOAJ
description Objectives Development of digital biomarkers to predict treatment response to a digital behavioural intervention.Design Machine learning using random forest classifiers on data generated through the use of a digital therapeutic which delivers behavioural therapy to treat cardiometabolic disease. Data from 13 explanatory variables (biometric and engagement in nature) generated in the first 28 days of a 12-week intervention were used to train models. Two levels of response to treatment were predicted: (1) systolic change ≥10 mm Hg (SC model), and (2) shift down to a blood pressure category of elevated or better (ER model). Models were validated using leave-one-out cross validation and evaluated using area under the curve receiver operating characteristics (AUROC) and specificity- sensitivity. Ability to predict treatment response with a subset of nine variables, including app use and baseline blood pressure, was also tested (models SC-APP and ER-APP).Setting Data generated through ad libitum use of a digital therapeutic in the USA.Participants Deidentified data from 135 adults with a starting blood pressure ≥130/80, who tracked blood pressure for at least 7 weeks using the digital therapeutic.Results The SC model had an AUROC of 0.82 and a sensitivity of 58% at a specificity of 90%. The ER model had an AUROC of 0.69 and a sensitivity of 32% at a specificity at 91%. Dropping explanatory variables related to blood pressure resulted in an AUROC of 0.72 with a sensitivity of 42% at a specificity of 90% for the SC-APP model and an AUROC of 0.53 for the ER-APP model.Conclusions Machine learning was used to transform data from a digital therapeutic into digital biomarkers that predicted treatment response in individual participants. Digital biomarkers have potential to improve treatment outcomes in a digital behavioural intervention.
format Article
id doaj-art-d1175a7c79834bbabe36bd17c5372782
institution OA Journals
issn 2044-6055
language English
publishDate 2019-07-01
publisher BMJ Publishing Group
record_format Article
series BMJ Open
spelling doaj-art-d1175a7c79834bbabe36bd17c53727822025-08-20T02:18:39ZengBMJ Publishing GroupBMJ Open2044-60552019-07-019710.1136/bmjopen-2019-030710Emergence of digital biomarkers to predict and modify treatment efficacy: machine learning studyNicole L Guthrie0Jason Carpenter1Katherine L Edwards2Kevin J Appelbaum3Sourav Dey4David M Eisenberg5David L Katz6Mark A Berman71 Better Therapeutics LLC, San Francisco, California, USA2 Manifold, Inc, Oakland, California, USA1 Better Therapeutics LLC, San Francisco, California, USA1 Better Therapeutics LLC, San Francisco, California, USA2 Manifold, Inc, Oakland, California, USA3 Nutrition, Harvard T.H. Chan School of Public Health, Boston, Massachusetts, USA1 Better Therapeutics LLC, San Francisco, California, USA1 Better Therapeutics LLC, San Francisco, California, USAObjectives Development of digital biomarkers to predict treatment response to a digital behavioural intervention.Design Machine learning using random forest classifiers on data generated through the use of a digital therapeutic which delivers behavioural therapy to treat cardiometabolic disease. Data from 13 explanatory variables (biometric and engagement in nature) generated in the first 28 days of a 12-week intervention were used to train models. Two levels of response to treatment were predicted: (1) systolic change ≥10 mm Hg (SC model), and (2) shift down to a blood pressure category of elevated or better (ER model). Models were validated using leave-one-out cross validation and evaluated using area under the curve receiver operating characteristics (AUROC) and specificity- sensitivity. Ability to predict treatment response with a subset of nine variables, including app use and baseline blood pressure, was also tested (models SC-APP and ER-APP).Setting Data generated through ad libitum use of a digital therapeutic in the USA.Participants Deidentified data from 135 adults with a starting blood pressure ≥130/80, who tracked blood pressure for at least 7 weeks using the digital therapeutic.Results The SC model had an AUROC of 0.82 and a sensitivity of 58% at a specificity of 90%. The ER model had an AUROC of 0.69 and a sensitivity of 32% at a specificity at 91%. Dropping explanatory variables related to blood pressure resulted in an AUROC of 0.72 with a sensitivity of 42% at a specificity of 90% for the SC-APP model and an AUROC of 0.53 for the ER-APP model.Conclusions Machine learning was used to transform data from a digital therapeutic into digital biomarkers that predicted treatment response in individual participants. Digital biomarkers have potential to improve treatment outcomes in a digital behavioural intervention.https://bmjopen.bmj.com/content/9/7/e030710.full
spellingShingle Nicole L Guthrie
Jason Carpenter
Katherine L Edwards
Kevin J Appelbaum
Sourav Dey
David M Eisenberg
David L Katz
Mark A Berman
Emergence of digital biomarkers to predict and modify treatment efficacy: machine learning study
BMJ Open
title Emergence of digital biomarkers to predict and modify treatment efficacy: machine learning study
title_full Emergence of digital biomarkers to predict and modify treatment efficacy: machine learning study
title_fullStr Emergence of digital biomarkers to predict and modify treatment efficacy: machine learning study
title_full_unstemmed Emergence of digital biomarkers to predict and modify treatment efficacy: machine learning study
title_short Emergence of digital biomarkers to predict and modify treatment efficacy: machine learning study
title_sort emergence of digital biomarkers to predict and modify treatment efficacy machine learning study
url https://bmjopen.bmj.com/content/9/7/e030710.full
work_keys_str_mv AT nicolelguthrie emergenceofdigitalbiomarkerstopredictandmodifytreatmentefficacymachinelearningstudy
AT jasoncarpenter emergenceofdigitalbiomarkerstopredictandmodifytreatmentefficacymachinelearningstudy
AT katherineledwards emergenceofdigitalbiomarkerstopredictandmodifytreatmentefficacymachinelearningstudy
AT kevinjappelbaum emergenceofdigitalbiomarkerstopredictandmodifytreatmentefficacymachinelearningstudy
AT souravdey emergenceofdigitalbiomarkerstopredictandmodifytreatmentefficacymachinelearningstudy
AT davidmeisenberg emergenceofdigitalbiomarkerstopredictandmodifytreatmentefficacymachinelearningstudy
AT davidlkatz emergenceofdigitalbiomarkerstopredictandmodifytreatmentefficacymachinelearningstudy
AT markaberman emergenceofdigitalbiomarkerstopredictandmodifytreatmentefficacymachinelearningstudy