# Interpreting Deep Learning based Cerebral Palsy Prediction with Channel Attention

arXiv: https://arxiv.org/abs/2106.04471 · HTML: https://mlsanity.com/paper/2106.04471/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 10 references that are in the map.
- First posted on arXiv 8 Jun 2021.

## Builds on (most cited first, 2 of 2)

- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models](https://mlsanity.com/paper/1708.08296/) (2017)

## Built on by (most cited first, 8 of 8)

- [Cerebral Palsy Prediction with Frequency Attention Informed Graph Convolutional Networks](https://mlsanity.com/paper/2204.10997/) (2022)
- [CP-AGCN: Pytorch-based Attention Informed Graph Convolutional Network for Identifying Infants at Risk of Cerebral Palsy](https://mlsanity.com/paper/2209.02824/) (2022)
- [Weakly Supervised Online Action Detection for Infant General Movements](https://mlsanity.com/paper/2208.03648/) (2022)
- [UDF-GMA: Uncertainty Disentanglement and Fusion for General Movement Assessment](https://mlsanity.com/paper/2507.04814/) (2025)
- [A Hybrid Machine Learning Model for Cerebral Palsy Detection](https://mlsanity.com/paper/2603.06803/) (2026)
- [A Two-stream Convolutional Network for Musculoskeletal and Neurological Disorders Prediction](https://mlsanity.com/paper/2208.08848/) (2022)
- [Explainability of Deep Neural Networks for Brain Tumor Detection](https://mlsanity.com/paper/2410.07613/) (2024)
- [Uncertainty-Aware Federated Learning for Infant Movement Analysis](https://mlsanity.com/paper/2609.31463/) (2026)

## Abstract (arXiv)

Early prediction of cerebral palsy is essential as it leads to early treatment and monitoring. Deep learning has shown promising results in biomedical engineering thanks to its capacity of modelling complicated data with its non-linear architecture. However, due to their complex structure, deep learning models are generally not interpretable by humans, making it difficult for clinicians to rely on the findings. In this paper, we propose a channel attention module for deep learning models to predict cerebral palsy from infants' body movements, which highlights the key features (i.e. body joints) the model identifies as important, thereby indicating why certain diagnostic results are found. To highlight the capacity of the deep network in modelling input features, we utilize raw joint positions instead of hand-crafted features. We validate our system with a real-world infant movement dataset. Our proposed channel attention module enables the visualization of the vital joints to this disease that the network considers. Our system achieves 91.67% accuracy, suppressing other state-of-the-art deep learning methods.