Sense and Sensibility: Sensible Quality Control and Data Decision-Making in Passive Sensing Data for Adolescent Substance Use Risk Prediction
- 1University of Pittsburgh School of Medicine
Abstract
BackgroundPassively collected smartphone and wearable data, combined with genomic information, may enable scalable early identification of youth who are at risk for substance use disorder. However, heterogeneous data collected in naturalistic settings limit researcher control over data quality, requiring substantial preprocessing. Data cleaning and feature engineering decisions can meaningfully influence analytic outcomes yet are often minimally described or omitted in published work.
ObjectivesWe provide rationales and recommendations for common preprocessing challenges in passive sensing research, including establishing inclusion criteria when "outliers" may reflect true behavioral variability, analyzing differences across smartphone operating systems, handling observations collected outside protocol windows, and engineering features for machine learning applications.
MethodsWe illustrate principled approaches to these challenges using smartphone and Fitbit data from the Adolescent Brain Cognitive DevelopmentSM Study (ABCD). The sample was drawn from the available half of the year-4 follow-up (data release 5.1; N = 4,754; ages 13-14).
ResultsExtreme outlying observations were concentrated among low-engagement participants with few observed days. Smartphone usage among Apple users appeared under-recorded relative to Android users when compared with self-report measures. Fitbit-derived behavior differed systematically between observations collected within versus outside protocol windows. We also identified potential errors in the studys default preprocessing pipeline.
ConclusionWe recommend prioritizing person-level inclusion criteria that preserve meaningful behavioral variability, examining temporal distributions rather than assuming observations are exchangeable, and thoroughly investigating and reporting data quality issues. Although illustrated using the ABCD Study, these principles broadly apply to research using smartphones, wearables, and other digital data sources.
Related
- Editorial: Adolescent smoking, alcohol consumption and psychoactive substance misuse in low-middle income countries
- Electrophysiological reactivity to emotional images and targets predicts the development of substance use disorders in adolescent girls
- Updated models of adolescent substance-related interference and problems (A-SIP) and measurement via the Substance-related Interference and Problems Identification Test (SIP-IT)
- Motivational Interviewing for Pediatric Residents: A Case-Based Workshop on Adolescent Substance Use.
- Improving behaviours, declining awareness: paradox in adolescent substance use in Ukraine during war
BibTeX
@misc{hong2026sense,
title = {{Sense and Sensibility: Sensible Quality Control and Data Decision-Making in Passive Sensing Data for Adolescent Substance Use Risk Prediction}},
author = {A. Hong and J. L. Diaz and T. M. Kennedy and F. L. Wang},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.06.26364884},
url = {https://www.medrxiv.org/content/10.64898/2026.10.06.26364884v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Sense and Sensibility: Sensible Quality Control and Data Decision-Making in Passive Sensing Data for Adolescent Substance Use Risk Prediction
AU - A. Hong
AU - J. L. Diaz
AU - T. M. Kennedy
AU - F. L. Wang
PY - 2026
DA - 2026/10/06
PB - medRxiv
DO - 10.64898/2026.10.06.26364884
UR - https://www.medrxiv.org/content/10.64898/2026.10.06.26364884v1
AB - BackgroundPassively collected smartphone and wearable data, combined with genomic information, may enable scalable early identification of youth who are at risk for substance use disorder. However, heterogeneous data collected in naturalistic settings limit researcher control over data quality, requiring substantial preprocessing. Data cleaning and feature engineering decisions can meaningfully influence analytic outcomes yet are often minimally described or omitted in published work. ObjectivesWe provide rationales and recommendations for common preprocessing challenges in passive sensing research, including establishing inclusion criteria when "outliers" may reflect true behavioral variability, analyzing differences across smartphone operating systems, handling observations collected outside protocol windows, and engineering features for machine learning applications. MethodsWe illustrate principled approaches to these challenges using smartphone and Fitbit data from the Adolescent Brain Cognitive DevelopmentSM Study (ABCD). The sample was drawn from the available half of the year-4 follow-up (data release 5.1; N = 4,754; ages 13-14). ResultsExtreme outlying observations were concentrated among low-engagement participants with few observed days. Smartphone usage among Apple users appeared under-recorded relative to Android users when compared with self-report measures. Fitbit-derived behavior differed systematically between observations collected within versus outside protocol windows. We also identified potential errors in the studys default preprocessing pipeline. ConclusionWe recommend prioritizing person-level inclusion criteria that preserve meaningful behavioral variability, examining temporal distributions rather than assuming observations are exchangeable, and thoroughly investigating and reporting data quality issues. Although illustrated using the ABCD Study, these principles broadly apply to research using smartphones, wearables, and other digital data sources.
ER -