MAL-Net: A Multi-Label Deep Learning Framework Integrating LSTM and Multi-Head Attention for Enhanced Classification of IgA Nephropathy Subtypes Using Clinical Sensor Data
MAL-Net provides a robust solution for multi-label IgAN subtype classification, tackling challenges such as data heterogeneity, class imbalance, and feature interdependencies. By integrating clinical sensor data, MAL-Net enhances IgAN subtype prediction, supporting early diagnosis, personalized treatment, and improved prognosis evaluation.
Authors
- Yuehui Liao (ORCID: https://orcid.org/0009-0006-0785-4596)
- Bin Fu (ORCID: https://orcid.org/0000-0003-2041-1678)
- Xiaobo Lai (ORCID: https://orcid.org/0000-0002-1305-5057)
- Panfei Li
- Junwei Huang
- Hongyan Wang (ORCID: https://orcid.org/0000-0003-4623-1878)
- Qin Zhu (ORCID: https://orcid.org/0000-0003-2186-3828)
- Li Gao (ORCID: https://orcid.org/0000-0001-9190-0562)
- Peng Xu (ORCID: https://orcid.org/0000-0002-6431-1110)
Institutions
- Zhejiang Chinese Medical University (CN)
- The Third Affiliated Hospital of Zhejiang Chinese Medical University (CN)
Publication Details
- Journal
- Sensors
- Published
- 2025-03-19
- DOI
- https://doi.org/10.3390/s25061916
- Citations
- 5
- Primary Topic
- Renal Diseases and Glomerulopathies
- Type
- article
- Field-Weighted Citation Impact
- 7.15