Da Liu

Arrhythmia poses a severe health risk, necessitating long-term monitoring to prevent complications like stroke. However, existing radar monitoring solutions fail to detect concurrent arrhythmias and lack clinical interpretability. In this paper, we bridge the gap by proposing READ (Radar Evidence-based Arrhythmia Diagnosis). Unlike previous “black-box” approaches, READ integrates mmWave radar with Large Language Models (LLMs) to deliver transparent, evidence-based diagnoses. However, training such a reasoning-capable model is hindered by the scarcity of mmWave datasets with detailed diagnostic annotations. To tackle this challenge, we first pretrain on large-scale ECG data to learn robust physiological patterns and then transfer this knowledge to radar domain using our proposed Cross-Physics Knowledge Distillation (CPKD) framework. Furthermore, we design a Morphological Grouping Tokenizer and a Morphology-Anchored Clinical Reasoning module, which parse raw signals into semantic tokens to guide step-by-step diagnostic inference. Empirical evaluation on a real-world dataset of 205 patients, collected in collaboration with medical institutions, demonstrates READ 's superior performance, achieving a 90.12% exact match ratio and a 0.9625 F ₁ score. Our framework significantly outperforms state-of-the-art baselines while providing interpretable clinical reports.

Large language models (LLMs) are rapidly advancing medical artificial intelligence, offering revolutionary changes in health care. These models excel in natural language processing (NLP), enhancing clinical support, diagnosis, treatment, and medical research. Breakthroughs, like GPT-4 and BERT (Bidirectional Encoder Representations from Transformer), demonstrate LLMs’ evolution through improved computing power and data. However, their high hardware requirements are being addressed through technological advancements. LLMs are unique in processing multimodal data, thereby improving emergency, elder care, and digital medical procedures. Challenges include ensuring their empirical reliability, addressing ethical and societal implications, especially data privacy, and mitigating biases while maintaining privacy and accountability. The paper emphasizes the need for human-centric, bias-free LLMs for personalized medicine and advocates for equitable development and access. LLMs hold promise for transformative impacts in health care.

UNSTRUCTURED Large language models (LLMs) are rapidly advancing medical artificial intelligence, offering revolutionary changes in health care. These models excel in natural language processing (NLP), enhancing clinical support, diagnosis, treatment, and medical research. Breakthroughs, like GPT-4 and BERT (Bidirectional Encoder Representations from Transformer), demonstrate LLMs’ evolution through improved computing power and data. However, their high hardware requirements are being addressed through technological advancements. LLMs are unique in processing multimodal data, thereby improving emergency, elder care, and digital medical procedures. Challenges include ensuring their empirical reliability, addressing ethical and societal implications, especially data privacy, and mitigating biases while maintaining privacy and accountability. The paper emphasizes the need for human-centric, bias-free LLMs for personalized medicine and advocates for equitable development and access. LLMs hold promise for transformative impacts in health care.

Background G-protein-coupled ER (GPR30) plays an important role in cardioprotection. Recent studies have shown that the GPR30-specific agonist G-1 reduces the degree of myocardial fibrosis in rats with myocardial infarction, reduces the morbidity associated with atrial fibrillation, and inhibits the proliferation of cardiac fibroblasts in animal experiments. Nevertheless, the underlying mechanism of myocardial fibrosis and atrial fibrillation remains unclear. In this study, we explored the mechanism underlying the effect of GPR30 on atrial fibrosis and atrial fibrillation in OVX mice. Methods We established an animal model of atrial fibrillation induced by Ang II (derived from OVX C57BL/6 female mice) and observed the role of G-1 in cardiac function by echocardiography, hemodynamics, morphology and fibrosis-related and apoptosis-related protein expression by Masson's trichrome, immunofluorescence, western blotting and TUNEL staining. Results Echocardiography and body surface ECG showed that G-1 combined with Ang II significantly reduced atrial fibrosis and atrial fibrillation compared to Ang II alone. The G-1 treatment group exhibited changes in the mRNA and protein expression of apoptosis-related genes. Moreover, G-1 treatment also altered the levels of inflammation-related proteins and mRNAs. In primary cultured cardiac fibroblasts (CFSs), proliferation was significantly increased in response to Ang II, and G-1 inhibited cell proliferation and apoptosis. Conclusion GPR30 is a potential therapeutic target for alleviating atrial fibrosis in OVX mice by upregulating Smad7 expression to inhibit the TGF-β/Smad pathway.