Favour Nerrise

All Publications

• Data-driven discovery of movement-linked heterogeneity in neurodegenerative diseases NATURE MACHINE INTELLIGENCE Endo, M., Nerrise, F., Zhao, Q., Sullivan, E. V., Fei-Fei, L., Henderson, V. W., Pohl, K. M., Poston, K. L., Adeli, E. 2024

  View details for DOI 10.1038/s42256-024-00882-y

  View details for Web of Science ID 001287474600001

• An Explainable Geometric-Weighted Graph Attention Network for Identifying Functional Networks Associated with Gait Impairment. Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention Nerrise, F., Zhao, Q., Poston, K. L., Pohl, K. M., Adeli, E. 2023; 14221: 723-733

  Abstract

  One of the hallmark symptoms of Parkinson's Disease (PD) is the progressive loss of postural reflexes, which eventually leads to gait difficulties and balance problems. Identifying disruptions in brain function associated with gait impairment could be crucial in better understanding PD motor progression, thus advancing the development of more effective and personalized therapeutics. In this work, we present an explainable, geometric, weighted-graph attention neural network (xGW-GAT) to identify functional networks predictive of the progression of gait difficulties in individuals with PD. xGW-GAT predicts the multi-class gait impairment on the MDS-Unified PD Rating Scale (MDS-UPDRS). Our computational- and data-efficient model represents functional connectomes as symmetric positive definite (SPD) matrices on a Riemannian manifold to explicitly encode pairwise interactions of entire connectomes, based on which we learn an attention mask yielding individual- and group-level explainability. Applied to our resting-state functional MRI (rs-fMRI) dataset of individuals with PD, xGW-GAT identifies functional connectivity patterns associated with gait impairment in PD and offers interpretable explanations of functional subnetworks associated with motor impairment. Our model successfully outperforms several existing methods while simultaneously revealing clinically-relevant connectivity patterns. The source code is available at https://github.com/favour-nerrise/xGW-GAT.

  View details for DOI 10.1007/978-3-031-43895-0_68

  View details for PubMedID 37982132

  View details for PubMedCentralID PMC10657737

• An Explainable Geometric-Weighted Graph Attention Network for Identifying Functional Networks Associated with Gait Impairment. ArXiv Nerrise, F., Zhao, Q., Poston, K. L., Pohl, K. M., Adeli, E. 2023

  Abstract

  One of the hallmark symptoms of Parkinson's Disease (PD) is the progressive loss of postural reflexes, which eventually leads to gait difficulties and balance problems. Identifying disruptions in brain function associated with gait impairment could be crucial in better understanding PD motor progression, thus advancing the development of more effective and personalized therapeutics. In this work, we present an explainable, geometric, weighted-graph attention neural network (xGW-GAT) to identify functional networks predictive of the progression of gait difficulties in individuals with PD. xGW-GAT predicts the multi-class gait impairment on the MDS-Unified PD Rating Scale (MDS-UPDRS). Our computational- and data-efficient model represents functional connectomes as symmetric positive definite (SPD) matrices on a Riemannian manifold to explicitly encode pairwise interactions of entire connectomes, based on which we learn an attention mask yielding individual- and group-level explain-ability. Applied to our resting-state functional MRI (rs-fMRI) dataset of individuals with PD, xGW-GAT identifies functional connectivity patterns associated with gait impairment in PD and offers interpretable explanations of functional subnetworks associated with motor impairment. Our model successfully outperforms several existing methods while simultaneously revealing clinically-relevant connectivity patterns. The source code is available at https://github.com/favour-nerrise/xGW-GAT.

  View details for PubMedID 37547656

  View details for PubMedCentralID PMC10402187

• User-Driven Support for Visualization Prototyping in D3 Bako, H. K., Varma, A., Faboro, A., Haider, M., Nerrise, F., Kenah, B., Dickerson, J. P., Battle, L., ACM ASSOC COMPUTING MACHINERY. 2023: 958-972

  View details for DOI 10.1145/3581641.3584041

  View details for Web of Science ID 001302573800066

• Predictive Agent-Based Modeling of Natural Disasters Using Machine Learning Nerrise, F., Assoc Advancement Artificial Intelligence ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2021: 15976-15977

  View details for Web of Science ID 000681269807185