Multi-modality approaches for medical support systems: A systematic review of the last decade Salvi, Massimo Loh, Hui Wen Seoni, Silvia Datta Barua, Prabal García López, Salvador Molinari, Filippo Rajendra Acharya, U. Data fusion Deep learning Multi-modality Fusion methods Diagnosis and prognosis Healthcare Healthcare traditionally relies on single-modality approaches, which limit the information available for medical decisions. However, advancements in technology and the availability of diverse data sources have made it feasible to integrate multiple modalities and gain a more comprehensive understanding of patients' conditions. Multi-modality approaches involve fusing and analyzing various data types, including medical images, biosignals, clinical records, and other relevant sources. This systematic review provides a comprehensive exploration of the multi-modality approaches in healthcare, with a specific focus on disease diagnosis and prognosis. The adoption of multi-modality approaches in healthcare is crucial for personalized medicine, as it enables a comprehensive profile of each patient, considering their genetic makeup, imaging characteristics, clinical history, and other relevant factors. The review also discusses the technical challenges associated with fusing heterogeneous multimodal data and highlights the emergence of deep learning approaches as a powerful paradigm for multimodal data integration. 2025-07-09T11:06:36Z 2025-07-09T11:06:36Z 2023-11-15 journal article Salvi, M., Loh, H. W., Seoni, S., Barua, P. D., García, S., Molinari, F., & Acharya, U. R. (2024). Multi-modality approaches for medical support systems: A systematic review of the last decade. An International Journal on Information Fusion, 103(102134), 102134. https://doi.org/10.1016/j.inffus.2023.102134 https://hdl.handle.net/10481/105150 10.1016/j.inffus.2023.102134 eng http://creativecommons.org/licenses/by-nc/4.0/ open access Atribución-NoComercial 4.0 Internacional Elsevier