Deep Learning-Enabled Interpretable Down Syndrome Detection Model
Journal of Disability Research · vol. 4 (3) · 2025
Abstract
Down syndrome (DS) is a genetic condition characterized by distinct facial features and developmental challenges, making early and accurate detection crucial for timely intervention and support. Traditional diagnostic methods often require specialized expertise, which can be resource intensive and inaccessible in many settings. In this study, we propose a novel artificial intelligence (AI)-driven approach to detecting DS using facial images, leveraging advancements in deep learning and machine learning for accurate and scalable diagnostics. A dataset of 168 facial images was curated from publicly accessible platforms, comprising 95 images of individuals without DS and 73 with the condition. The model was implemented using TensorFlow/PyTorch and employs RegNet X and Shifted Window Transformer (SWIN Transformer) for feature extraction, capturing both local and global facial features. To enhance feature representation, an attention-based fusion mechanism was applied, prioritizing the most discriminative patterns while filtering redundant information. For classification, an Extremely Randomized Tree (ExtraTrees) model was employed, known for its ability to efficiently handle high-dimensional data with strong generalization capabilities. The model was fine-tuned using Bayesian Optimization and Hyperband (BOHB), which optimized hyperparameters by balancing exploration and exploitation, thereby improving predictive performance. The final classification achieved a 99.2% accuracy with an area under the curve (AUC) of 1.00, demonstrating exceptional reliability in distinguishing DS from normal cases. By combining advanced feature extraction, fusion, and classification techniques, this study highlights the potential of AI to revolutionize DS diagnostics, offering a non-invasive, efficient, and scalable solution for early detection.
Details
- Journal
- Journal of Disability Research
- Publisher
- —
- Volume
- 4
- Issue
- 3
- Pages
- —
- ISSN
- 1658-9912
- Year
- 2025
- Language
- en
- License
- cc-by
- Open access
- diamond
- Citations
- 2
- Source
- scopus
Keywords
Topics
Face recognition and analysis (Computer Science) · Down syndrome and intellectual disability research (Medicine) · Artificial Intelligence in Healthcare (Health Professions)
Cite this
Shaikh, M. A., Al-Rawashdeh, H. S. (2025). Deep Learning-Enabled Interpretable Down Syndrome Detection Model. Journal of Disability Research, 4(3). https://doi.org/10.57197/jdr-2025-0011
Shaikh, M. A., Al-Rawashdeh, H. S. 2025, 'Deep Learning-Enabled Interpretable Down Syndrome Detection Model', Journal of Disability Research, vol. 4(3). Available at: https://doi.org/10.57197/jdr-2025-0011
Shaikh MA, Al-Rawashdeh HS. Deep Learning-Enabled Interpretable Down Syndrome Detection Model. Journal of Disability Research. 2025;4(3).
@article{shaikh2025967,
title = {Deep Learning-Enabled Interpretable Down Syndrome Detection Model},
author = {Mujeeb Ahmed Shaikh and Hazim Saleh Al-Rawashdeh},
year = {2025},
journal = {Journal of Disability Research},
volume = {4},
number = {3},
doi = {10.57197/jdr-2025-0011},
url = {https://doi.org/10.57197/jdr-2025-0011}
}TY - JOUR AU - Mujeeb Ahmed Shaikh AU - Hazim Saleh Al-Rawashdeh TI - Deep Learning-Enabled Interpretable Down Syndrome Detection Model PY - 2025 JO - Journal of Disability Research VL - 4 IS - 3 DO - 10.57197/jdr-2025-0011 UR - https://doi.org/10.57197/jdr-2025-0011 ER -
