Application of Multimodal Data and Artificial Intelligence in Pulmonary Diseases Volume II

In the era of big data, the growing diversity, dimensionality, and volume of data have accelerated the development of artificial intelligence (AI). In turn, AI technologies have provided new tools and approaches for medical diagnosis. By performing in-depth mining and learning on multimodal disease-related big data, AI can identify latent diagnostic evidence and potential pathological mechanisms from multi-source data. This can support clinicians in diagnosis, improve diagnostic accuracy and efficiency, help elucidate disease pathogenesis, and reduce diagnostic costs.In primary healthcare, pulmonary diseases such as tuberculosis, pneumonia, and bronchitis are characterized by rapid transmission, diverse routes of infection, high infection and rapid mutation, often leading to regionally concentrated outbreaks. However, medical resources vary substantially across regions. In resource-limited settings, shortages in basic healthcare infrastructure can lead to difficulties in conducting large-scale community screening, delayed medical services, high medical costs, low diagnostic accuracy, and risks to patient privacy during the management of pulmonary disease outbreaks.To address these challenges, this Special Issue invites high-quality submissions from academic and industry researchers in big data, data fusion, machine learning, and artificial intelligence. The Special Issue aims to present advanced methods and applications that integrate AI with multimodal data to enhance primary healthcare, with a particular focus on strengthening community-based diagnosis and treatment capacity for pulmonary diseases.Submitted manuscripts should be original, unpublished, and provide novel contributions. Topics of interest include, but are not limited to:• Large language models for pulmonary diseases• Large vision models for pulmonary diseases• Big data fusion and its applications for pulmonary diseases• Multimodal methods for early screening of pulmonary diseases• Methods for early warning of pulmonary disease risk• Large language models for primary healthcare• Large vision models for primary healthcare• Big data fusion and its applications for primary healthcare• Methods for medical image analysis• Theory and methods for incomplete multimodal data in medicine• Theory and methods for mismatched multimodal data in medicine• Methods for the design and implementation of medical virtual assistants• Methods for predicting drug response• Methods for designing clinical treatment plans• Unsupervised learning methods in medicine• Supervised learning methods in medicine• Mixed-supervision learning methods in medicine• Semi-supervised learning methods in medicine• Contrastive learning methods in medicine Topic editors: Liang Zhao, Qingchen Zhang, Jianzhe Lin Source: https://www.frontiersin.org/research-topics/78320/application-of-multimodal-data-and-artificial-intelligence-in-pulmonary-diseases-volume-ii