Time-Lagged Prediction of Food Craving With Qualitative Distinct Predictor Types: An Application of BISCWIT

Food craving (FC) peaks are highly context-dependent and variable. Accurate prediction of FC might help preventing disadvantageous eating behavior. Here, we examine whether data from 2 weeks of ecological momentary assessment (EMA) questionnaires on stress and emotions (active EMA, aEMA) alongside t...

Full description

Bibliographic Details
Main Authors: Tim Kaiser, Björn Butter, Samuel Arzt, Björn Pannicke, Julia Reichenberger, Simon Ginzinger, Jens Blechert
Format: Article
Language:English
Published: Frontiers Media S.A. 2021-09-01
Series:Frontiers in Digital Health
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fdgth.2021.694233/full
_version_ 1818922753753874432
author Tim Kaiser
Björn Butter
Samuel Arzt
Björn Pannicke
Björn Pannicke
Julia Reichenberger
Julia Reichenberger
Simon Ginzinger
Jens Blechert
Jens Blechert
author_facet Tim Kaiser
Björn Butter
Samuel Arzt
Björn Pannicke
Björn Pannicke
Julia Reichenberger
Julia Reichenberger
Simon Ginzinger
Jens Blechert
Jens Blechert
author_sort Tim Kaiser
collection DOAJ
description Food craving (FC) peaks are highly context-dependent and variable. Accurate prediction of FC might help preventing disadvantageous eating behavior. Here, we examine whether data from 2 weeks of ecological momentary assessment (EMA) questionnaires on stress and emotions (active EMA, aEMA) alongside temporal features and smartphone sensor data (passive EMA, pEMA) are able to predict FCs ~2.5 h into the future in N = 46 individuals. A logistic prediction approach with feature dimension reduction via Best Item Scale that is Cross-Validated, Weighted, Informative and Transparent (BISCWIT) was performed. While overall prediction accuracy was acceptable, passive sensing data alone was equally predictive to psychometric data. The frequency of which single predictors were considered for a model was rather balanced, indicating that aEMA and pEMA models were fully idiosyncratic.
first_indexed 2024-12-20T01:58:33Z
format Article
id doaj.art-34a2529678bd43e5b6b24f78d13baeb5
institution Directory Open Access Journal
issn 2673-253X
language English
last_indexed 2024-12-20T01:58:33Z
publishDate 2021-09-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Digital Health
spelling doaj.art-34a2529678bd43e5b6b24f78d13baeb52022-12-21T19:57:24ZengFrontiers Media S.A.Frontiers in Digital Health2673-253X2021-09-01310.3389/fdgth.2021.694233694233Time-Lagged Prediction of Food Craving With Qualitative Distinct Predictor Types: An Application of BISCWITTim Kaiser0Björn Butter1Samuel Arzt2Björn Pannicke3Björn Pannicke4Julia Reichenberger5Julia Reichenberger6Simon Ginzinger7Jens Blechert8Jens Blechert9Clinical Psychology and Psychotherapy, Department of Psychology, University of Greifswald, Greifswald, GermanyEating Behavior Laboratory, Department of Psychology, Paris-Lodron-University of Salzburg, Salzburg, AustriaMultiMediaTechnology, University of Applied Sciences Salzburg, Salzburg, AustriaEating Behavior Laboratory, Department of Psychology, Paris-Lodron-University of Salzburg, Salzburg, AustriaDepartment of Psychology, Centre for Cognitive Neuroscience, Paris-Lodron-University of Salzburg, Salzburg, AustriaEating Behavior Laboratory, Department of Psychology, Paris-Lodron-University of Salzburg, Salzburg, AustriaDepartment of Psychology, Centre for Cognitive Neuroscience, Paris-Lodron-University of Salzburg, Salzburg, AustriaMultiMediaTechnology, University of Applied Sciences Salzburg, Salzburg, AustriaEating Behavior Laboratory, Department of Psychology, Paris-Lodron-University of Salzburg, Salzburg, AustriaDepartment of Psychology, Centre for Cognitive Neuroscience, Paris-Lodron-University of Salzburg, Salzburg, AustriaFood craving (FC) peaks are highly context-dependent and variable. Accurate prediction of FC might help preventing disadvantageous eating behavior. Here, we examine whether data from 2 weeks of ecological momentary assessment (EMA) questionnaires on stress and emotions (active EMA, aEMA) alongside temporal features and smartphone sensor data (passive EMA, pEMA) are able to predict FCs ~2.5 h into the future in N = 46 individuals. A logistic prediction approach with feature dimension reduction via Best Item Scale that is Cross-Validated, Weighted, Informative and Transparent (BISCWIT) was performed. While overall prediction accuracy was acceptable, passive sensing data alone was equally predictive to psychometric data. The frequency of which single predictors were considered for a model was rather balanced, indicating that aEMA and pEMA models were fully idiosyncratic.https://www.frontiersin.org/articles/10.3389/fdgth.2021.694233/fullfood cravingstime-laggedidiographic modelsBISCWITecological momentary assessmentpassive sensing
spellingShingle Tim Kaiser
Björn Butter
Samuel Arzt
Björn Pannicke
Björn Pannicke
Julia Reichenberger
Julia Reichenberger
Simon Ginzinger
Jens Blechert
Jens Blechert
Time-Lagged Prediction of Food Craving With Qualitative Distinct Predictor Types: An Application of BISCWIT
Frontiers in Digital Health
food cravings
time-lagged
idiographic models
BISCWIT
ecological momentary assessment
passive sensing
title Time-Lagged Prediction of Food Craving With Qualitative Distinct Predictor Types: An Application of BISCWIT
title_full Time-Lagged Prediction of Food Craving With Qualitative Distinct Predictor Types: An Application of BISCWIT
title_fullStr Time-Lagged Prediction of Food Craving With Qualitative Distinct Predictor Types: An Application of BISCWIT
title_full_unstemmed Time-Lagged Prediction of Food Craving With Qualitative Distinct Predictor Types: An Application of BISCWIT
title_short Time-Lagged Prediction of Food Craving With Qualitative Distinct Predictor Types: An Application of BISCWIT
title_sort time lagged prediction of food craving with qualitative distinct predictor types an application of biscwit
topic food cravings
time-lagged
idiographic models
BISCWIT
ecological momentary assessment
passive sensing
url https://www.frontiersin.org/articles/10.3389/fdgth.2021.694233/full
work_keys_str_mv AT timkaiser timelaggedpredictionoffoodcravingwithqualitativedistinctpredictortypesanapplicationofbiscwit
AT bjornbutter timelaggedpredictionoffoodcravingwithqualitativedistinctpredictortypesanapplicationofbiscwit
AT samuelarzt timelaggedpredictionoffoodcravingwithqualitativedistinctpredictortypesanapplicationofbiscwit
AT bjornpannicke timelaggedpredictionoffoodcravingwithqualitativedistinctpredictortypesanapplicationofbiscwit
AT bjornpannicke timelaggedpredictionoffoodcravingwithqualitativedistinctpredictortypesanapplicationofbiscwit
AT juliareichenberger timelaggedpredictionoffoodcravingwithqualitativedistinctpredictortypesanapplicationofbiscwit
AT juliareichenberger timelaggedpredictionoffoodcravingwithqualitativedistinctpredictortypesanapplicationofbiscwit
AT simonginzinger timelaggedpredictionoffoodcravingwithqualitativedistinctpredictortypesanapplicationofbiscwit
AT jensblechert timelaggedpredictionoffoodcravingwithqualitativedistinctpredictortypesanapplicationofbiscwit
AT jensblechert timelaggedpredictionoffoodcravingwithqualitativedistinctpredictortypesanapplicationofbiscwit