The EPIDIA4Kids protocol for a digital epidemiology study on brain functioning in children, based on a multimodality
Vanessa Douet Vannucci1,2, Théo Marchand1,3, Alexandre Hennequin1
1R&D Lab, O-Kidia, Nice, France.
Insights
This study introduces a new digital approach for assessing neurodevelopmental disorders (NDDs) in children. It uses AI and tablet-based assessments to better understand brain function and identify early symptoms more accessibly.
Area of Science:
- Neuroscience
- Digital Epidemiology
- Child Psychology
Background:
- Neurodevelopmental disorders (NDDs) present complex phenotypes with significant overlap, complicating diagnosis and treatment.
- Digital epidemiology offers a novel approach to study health dynamics using real-world data streams.
- A transdiagnostic framework is needed to better understand brain function and NDDs.
Purpose of the Study:
- To propose and evaluate a novel transdiagnostic approach for examining brain function in children.
- To combine AI-based multimodality biometry with clinical e-assessments on a tablet.
- To characterize cognition, emotion, and behavior using data-driven methods in an ecological context.
Main Methods:
- The EPIDIA4Kids study is an uncontrolled, open-label trial with 786 participants aged 7-12.
- Data collection includes online questionnaires, paper-pencil neuro-assessments, and a 30-min gamified tablet assessment.
- Multimodality biometrics are generated using machine and deep learning from video, audio, and digit-tracking data.
Main Results:
- The study hypothesizes that digital biomarkers will detect early neurodevelopmental symptoms more effectively than traditional methods.
- It is anticipated that this digital approach will be as or more accessible in real-life practice.
Conclusions:
- This digital epidemiology approach holds promise for a more effective and accessible transdiagnostic understanding of NDDs in children.
- The findings could lead to improved early detection and intervention strategies for neurodevelopmental disorders.
Introduction:
Neurodevelopment and related mental disorders (NDDs) are one of the most frequent disabilities among young people. They have complex clinical phenotypes often associated with transnosographic dimensions, such as emotion dysregulation and executive dysfunction, that lead to adverse impacts in personal, social, academic, and occupational functioning. Strong overlap exists then across NDDs phenotypes that are challenging for diagnosis and therapeutic intervention. Recently, digital epidemiology uses the rapidly growing data streams from various devices to advance our understanding of health's and disorders' dynamics, both in individuals and the general population, once coupled with computational science. An alternative transdiagnostic approach using digital epidemiology may thus better help understanding brain functioning and hereby NDDs in the general population.
Objective:
The EPIDIA4Kids study aims to propose and evaluate in children, a new transdiagnostic approach for brain functioning examination, combining AI-based multimodality biometry and clinical e-assessments on an unmodified tablet. We will examine this digital epidemiology approach in an ecological context through data-driven methods to characterize cognition, emotion, and behavior, and ultimately the potential of transdiagnostic models of NDDs for children in real-life practice.
Methods And Analysis:
The EPIDIA4Kids is an uncontrolled open-label study. 786 participants will be recruited and enrolled if eligible: they are (1) aged 7 to 12 years and (2) are French speaker/reader; (3) have no severe intellectual deficiencies. Legal representative and children will complete online demographic, psychosocial and health assessments. During the same visit, children will perform additionally a paper/pencil neuro-assessments followed by a 30-min gamified assessment on a touch-screen tablet. Multi-stream data including questionnaires, video, audio, digit-tracking, will be collected, and the resulting multimodality biometrics will be generated using machine- and deep-learning algorithms. The trial will start in March 2023 and is expected to end by December 2024.
Discussion:
We hypothesize that the biometrics and digital biomarkers will be capable of detecting early onset symptoms of neurodevelopment compared to paper-based screening while as or more accessible in real-life practice.
