Self-supervised learning for graph-structured data in healthcare applications: A comprehensive review

Computers in Biology and Medicine, Год журнала: 2025, Номер 188, С. 109874 - 109874

Опубликована: Фев. 24, 2025

Язык: Английский

---

A contemporary survey of recent advances in federated learning: Taxonomies, applications, and challenges

Internet of Things, Год журнала: 2024, Номер 27, С. 101251 - 101251

Опубликована: Июнь 15, 2024

Язык: Английский

---

Data-driven prediction of spinal cord injury recovery: An exploration of current status and future perspectives

Experimental Neurology, Год журнала: 2024, Номер 380, С. 114913 - 114913

Опубликована: Авг. 2, 2024

Spinal Cord Injury (SCI) presents a significant challenge in rehabilitation medicine, with recovery outcomes varying widely among individuals. Machine learning (ML) is promising approach to enhance the prediction of trajectories, but its integration into clinical practice requires thorough understanding efficacy and applicability. We systematically reviewed current literature on data-driven models SCI prediction. The included studies were evaluated based range criteria assessing approach, implementation, input data preferences, aimed forecast. observe tendency utilize routinely acquired data, such as International Standards for Neurological Classification (ISNCSCI), imaging, demographics, functional derived from Independence Measure (SCIM) III Functional (FIM) scores focus motor ability. Although there has been an increasing interest over time, traditional machine architectures, linear regression tree-based approaches, remained overwhelmingly popular choices implementation. This implies ample opportunities exploring architectures addressing challenges predicting recovery, including techniques limited longitudinal improving generalizability, enhancing reproducibility. conclude perspective, highlighting possible future directions drawing parallels other application fields terms diverse types (imaging, tabular, sequential, multimodal), (limited, missing, data), algorithmic needs (causal inference, robustness).

Язык: Английский

---

SASD: Self-Attention for Small Datasets—A case study in smart villages

Expert Systems with Applications, Год журнала: 2025, Номер unknown, С. 126245 - 126245

Опубликована: Янв. 1, 2025

Язык: Английский

---

Inductive graph neural network framework for imputation of single-cell RNA sequencing data

Computers & Chemical Engineering, Год журнала: 2025, Номер 195, С. 109031 - 109031

Опубликована: Фев. 6, 2025

Язык: Английский

---

Hospital Network Resilience in Hatay Following the 2023 Cascading Earthquakes in Türkiye: Year-Long Investigation

Journal of Structural Engineering, Год журнала: 2025, Номер 151(5)

Опубликована: Фев. 26, 2025

Язык: Английский

---

A systematic mapping study on graph machine learning for static source code analysis

Information and Software Technology, Год журнала: 2025, Номер unknown, С. 107722 - 107722

Опубликована: Март 1, 2025

Язык: Английский

---

Brain-GCN-Net: Graph-Convolutional Neural Network for brain tumor identification

Computers in Biology and Medicine, Год журнала: 2024, Номер 180, С. 108971 - 108971

Опубликована: Авг. 5, 2024

Язык: Английский

---

Data-driven prediction of spinal cord injury recovery: an exploration of current status and future perspectives

medRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Май 4, 2024

Abstract Spinal Cord Injury (SCI) presents a significant challenge in rehabilitation medicine, with recovery outcomes varying widely among individuals. Machine learning (ML) is promising approach to enhance the prediction of trajectories, but its integration into clinical practice requires thorough understanding efficacy and applicability. We systematically reviewed current literature on data-driven models SCI prediction. The included studies were evaluated based range criteria assessing approach, implementation, input data preferences, aimed forecast. observe tendency utilize routinely acquired data, such as International Standards for Neurological Classification (ISNCSCI), imaging, demographics, functional derived from Independence Measure (SCIM) III Functional (FIM) scores focus motor ability. Although there has been an increasing interest over time, traditional machine architectures, linear regression tree-based approaches, remained overwhelmingly popular choices implementation. This implies ample opportunities exploring architectures addressing challenges predicting recovery, including techniques limited longitudinal improving generalizability, enhancing reproducibility. conclude perspective, highlighting possible future directions drawing parallels other application fields terms diverse types (imaging, tabular, sequential, multimodal), (limited, missing, data), algorithmic needs (causal inference, robustness).

Язык: Английский

---

Machine Learning Techniques for Predicting Drug-Related Side Effects: A Scoping Review

Pharmaceuticals, Год журнала: 2024, Номер 17(6), С. 795 - 795

Опубликована: Июнь 17, 2024

Background: Drug safety relies on advanced methods for timely and accurate prediction of side effects. To tackle this requirement, scoping review examines machine-learning approaches predicting drug-related effects with a particular focus chemical, biological, phenotypical features. Methods: This was in which comprehensive search conducted various databases from 1 January 2013 to 31 December 2023. Results: The results showed the widespread use Random Forest, k-nearest neighbor, support vector machine algorithms. Ensemble methods, particularly random forest, emphasized significance integrating chemical biological features Conclusions: article considering variety features, datasets, learning algorithms Forest best performance combining improved prediction. suggested that techniques have some potential improve drug development trials. Future work should specific feature types, selection techniques, graph-based even better

Язык: Английский

---