Advances in Multimodal Machine Learning in Medical Research

Dear Colleagues,

There has been a rise in the adoption of single modal data machine learning (ML) models in the health sector over the past decade. ML models using a single input type (e.g., image only or text only) is common in medical research. However, the use of multimodal ML methods is emerging as a new frontier in medical research. ML models can benefit from integrating information from different modalities by providing a more comprehensive view. This comprehensive view is especially important in medical research, where it aims to mimic a clinician who often reviews more than one mode to formulate a diagnosis (e.g., radiology reports and images). Some studies have compared unimodal to multimodal ML models and have found an improvement in predictive accuracy with the fusing of multimodal inputs. Advances are being made in the type of multimodal fusion strategy (e.g., early, intermediate, late, and hybrid fusion) and the handling of modality dropout.

This Special Issue aims to showcase advances in multimodal machine learning (ML) in medical research, with a strong emphasis on the development of novel mathematical models, sophisticated algorithms, and theoretical frameworks. We invite contributions focusing on cutting-edge methods such as multimodal transformers, multimodal deep Boltzmann machines, and other advanced mathematical models for data integration. Special attention will be given to innovative approaches in fusion strategies (e.g., early, intermediate, late, and hybrid fusion), efficient optimization algorithms, and robust handling of missing modalities. Applications may include the deep learning fusion of medical imaging, genomic data, electronic health records, and other heterogeneous data sources, with a focus on both theoretical contributions and empirical validations.

Dr. Joanna Dipnall
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• multimodal
• data fusion
• transformer
• machine learning
• deep learning
• graph network