Behavioral motion patterns to predict child mobile device use: Evaluating model performance across a standardized screen time protocol - Scorecard - MDSpire
Clinical Scorecard: Using Behavioral Motion Patterns to Predict Children’s Mobile Device Use: Model Performance Under a Standardized Screen-Time Protocol
At a Glance
Category
Detail
Condition
Behavioral biometrics for identifying children using shared mobile devices
Key Mechanisms
Machine-learning models use built-in accelerometer and gyroscope data to learn individualized motion patterns and identify the target child user.
Target Population
Children and parents in parent–child dyads; the supplied excerpt does not state the number recruited.
Care Setting
The study examines model performance under a standardized screen-time protocol; the supplied excerpt does not specify the location or protocol details.
Key Highlights
The study examines whether models trained on motion-sensor data can distinguish a child from their parent.
The authors identify standardized games and evaluation on games excluded from training as questions for further study.
The authors identify comparison of child-only versus child-and-parent training data as a question for further study.
The excerpt describes the study rationale and aims but does not provide results.
Guideline-Based Recommendations
Diagnosis
Management
Monitoring & Follow-up
Risks
Patient & Prescribing Data
The study concerns children and parents in parent–child dyads. The supplied excerpt does not state the number recruited or further participant characteristics.
Not applicable: the excerpt describes a study of behavioral biometrics, not a treatment or prescribing study.
by Olivia L. Finnegan, Bridget Armstrong, Elizabeth L. Adams, Sarah Burkart, Michael W. Beets, James W. White, III, Joshua Culverhouse, Srihari Nelakuditi, Zifei Zhong, Hongpeng Yang, Keagan P. Kiely, Rahul Ghosal, Robert G. Weaver
