Framework for fairer automated neurodevelopmental assessment using multimodal data

Neurodiversity-Aware Multimodal Affective Computing for Neurodevelopmental Assessment: From Norm-Referenced Classification to Context-Sensitive Decision Support

Human-Computer InteractionArtificial Intelligence

Summary

Automated systems try to understand neurodevelopmental conditions by analyzing things like speech, facial expressions, and eye movements. This paper suggests a new way to build these systems so they are aware of the natural variety in how people behave, rather than just labeling differences as problems. The authors propose a structure that carefully considers context, personal baselines, and uncertainty to make decisions more accurate and trustworthy. They focus mainly on autism but do not claim their ideas automatically apply to all conditions.

What this means in practice

  • For clinical software developers: Develop neurodevelopmental diagnostic tools that integrate multiple behavioral signals while accounting for individual and population diversity to improve fairness and interpretability.
  • For healthcare data engineers: Implement data processing pipelines that maintain modality quality, account for missing data, and support uncertainty-aware inference for neurodevelopmental assessments.

A position paper. It proposes an approach and reports no results.

Authors

Mateusz Pomianek, Anna Łężniak-Seruga

Abstract

Automated neurodevelopmental assessment increasingly combines computer vision, speech, eye tracking, physiology, and machine learning, yet multimodality and discrimination do not establish construct validity, clinical usefulness, or appropriate interpretation of behavioral variation. We propose a testable architecture for neurodiversity-aware multimodal affective computing in which population-relative deviation is not treated as sufficient evidence of adverse functioning. This conceptual article reports neither a new participant-level study nor a trained predictive system, and no predictive or clinical superiority is claimed. The framework keeps observable signals, modality quality and availability, context, population-relative information, pooled within-person references and, when sufficiently supported, context-conditioned within person references, and predictive uncertainty distinguishable throughout inference. It defines structured decision-support outputs and auditable requirements for target validity, temporal integrity, contextual leakage, missing-modality robustness, calibration, subgroup evaluation, interpretability, privacy, and human decision boundaries. The contribution is architectural rather than algorithmic: it specifies empirically testable constraints that can be instantiated with different multimodal learning methods. Autism provides the principal motivating evidence base, without assuming unchanged transfer to other neurodevelopmental conditions.
View PDFOpen arXiv