In recent years, the scientific community has increasingly delved into the study of the interaction between the nervous system and tumors, revealing that the nervous system not only regulates bodily functions under physiological conditions, but also assumes a vital part in the emergence and progression of tumors. Research has demonstrated that the extensive neural network directly regulates tumor progression and can influence tumors by modulating the tumor microenvironment and immune system. Moreover, tumors induce neural networks to provide favorable conditions for their proliferation and metastasis. In the above process, neurotransmitters play a vital role. They directly act or bind to their receptor, activating various classical signaling pathways, among which are PI3K/AKT, MEK/ERK, and WNT/β-catenin, to facilitate tumor advancement. Therefore, this study systematically reviews the regulatory mechanisms of neurotransmitters and their receptors in the advancement of cancer, along with the utilization of targeted drugs. At the same time, we also analyzed that targeting specific receptor subtypes may produce more significant therapeutic effects in different types of cancer. Additionally, this research further explores the limitations of neurotransmitter-based drugs currently used in clinical cancer treatment. In summary, the field of cancer neuroscience is rapidly advancing, constantly revealing the regulatory effects of neurotransmitters on tumor progression and their specific molecular mechanisms, providing broad application prospects for future clinical therapy.

Pressure injury management requires coordinated decisions on wound staging, debridement, and dressing selection, yet most computational studies focus on isolated tasks using a single data modality. This study developed a multimodal, multi-task framework integrating wound photographs and clinical text to support pressure injury stage classification, debridement necessity prediction, primary dressing recommendation, and secondary dressing recommendation. Models were trained on an expert-annotated public dataset and externally validated using an independent private cohort. We systematically compared image-only models, text-only models, large language model-based approaches, conventional image–text fusion strategies, and image–language model combinations. Among the evaluated models, ResNet-50 combined with DeepSeek-R1-Distill-Qwen-1.5B showed the best overall balance across classification performance, text-generation quality, and validation robustness. On the validation set, the final model achieved 82.92% accuracy, 81.26% macro-F1, and 99.01% area under the curve for stage classification, and 89.91% accuracy, 89.83% macro-F1, and 96.24% area under the curve for debridement prediction. For dressing recommendation, the model achieved ROUGE-1 scores of 58.30% and 61.06% for primary and secondary dressings, respectively. Interpretability analyses indicated clinically relevant image attention and text attribution patterns. These findings suggest that multimodal learning may provide a clinically aligned decision-support approach for pressure injury assessment and treatment recommendations.