Ocular-Induced Abnormal Head Posture: Diagnosis and Missing Data Imputation

2025-10-07

AI Summary

Early diagnosis of abnormal head posture (AHP) in ocular disorders suffers from subjective clinical assessment and unreliable diagnostic outcomes due to missing clinical data. To address these challenges, we propose a dual-module deep learning framework: (1) AHP-CADNet, which integrates ocular keypoint features, head pose estimation, and multimodal clinical variables to enable interpretable automated AHP diagnosis; and (2) a novel imputation module that jointly leverages curriculum learning and PubMedBERT to explicitly model clinical dependencies—uniquely incorporating both structured variables and unstructured clinical text for robust missing-value imputation. Our framework introduces hierarchical attention-based feature fusion and clinical-dependency-driven imputation. Evaluated on the PoseGaze-AHP dataset, it achieves diagnostic accuracy of 96.9%–99.0%, continuous prediction MAE of 0.103–0.199 (R² > 0.93), and imputation accuracy of 93.46%–99.78%, all significantly outperforming baselines (p < 0.001).

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Calibration & Uncertainty Quantification
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Ocular-induced abnormal head posture (AHP) is a compensatory mechanism that arises from ocular misalignment conditions, such as strabismus, enabling patients to reduce diplopia and preserve binocular vision. Early diagnosis minimizes morbidity and secondary complications such as facial asymmetry; however, current clinical assessments remain largely subjective and are further complicated by incomplete medical records. This study addresses both challenges through two complementary deep learning frameworks. First, AHP-CADNet is a multi-level attention fusion framework for automated diagnosis that integrates ocular landmarks, head pose features, and structured clinical attributes to generate interpretable predictions. Second, a curriculum learning-based imputation framework is designed to mitigate missing data by progressively leveraging structured variables and unstructured clinical notes to enhance diagnostic robustness under realistic data conditions. Evaluation on the PoseGaze-AHP dataset demonstrates robust diagnostic performance. AHP-CADNet achieves 96.9-99.0 percent accuracy across classification tasks and low prediction errors for continuous variables, with MAE ranging from 0.103 to 0.199 and R2 exceeding 0.93. The imputation framework maintains high accuracy across all clinical variables (93.46-99.78 percent with PubMedBERT), with clinical dependency modeling yielding significant improvements (p < 0.001). These findings confirm the effectiveness of both frameworks for automated diagnosis and recovery from missing data in clinical settings.

Problem

• Automating diagnosis of ocular-induced abnormal head posture
• Imputing missing data in clinical records for diagnosis
• Enhancing diagnostic robustness with deep learning frameworks

Innovation

• Multi-level attention fusion for automated diagnosis
• Curriculum learning-based imputation for missing data
• Integration of structured variables and clinical notes