Xintian Yang, Tongxin Li, Qin Su, Yaling Liu, Chenxi Kang, Yong Lyu, Lina Zhao, Yongzhan Nie, Yanglin Pan
中华医学杂志英文版2025年 138卷 02期
DOI: 10.1097/CM9.0000000000003456
摘要
Large language models (LLMs) such as ChatGPT, Claude, Llama, and Qwen are emerging as transformative technologies for the diagnosis and treatment of various diseases. With their exceptional long-context reasoning capabilities, LLMs are proficient in clinically relevant tasks, particularly in medical text analysis and interactive dialogue. They can enhance diagnostic accuracy by processing vast amounts of patient data and medical literature and have demonstrated their utility in diagnosing common diseases and facilitating the identification of rare diseases by recognizing subtle patterns in symptoms and test results. Building on their image-recognition abilities, multimodal LLMs (MLLMs) show promising potential for diagnosis based on radiography, chest computed tomography (CT), electrocardiography (ECG), and common pathological images. These models can also assist in treatment planning by suggesting evidence-based interventions and improving clinical decision support systems through integrated analysis of patient records. Despite these promising developments, significant challenges persist regarding the use of LLMs in medicine, including concerns regarding algorithmic bias, the potential for hallucinations, and the need for rigorous clinical validation. Ethical considerations also underscore the importance of maintaining the function of supervision in clinical practice. This paper highlights the rapid advancements in research on the diagnostic and therapeutic applications of LLMs across different medical disciplines and emphasizes the importance of policymaking, ethical supervision, and multidisciplinary collaboration in promoting more effective and safer clinical applications of LLMs. Future directions include the integration of proprietary clinical knowledge, the investigation of open-source and customized models, and the evaluation of real-time effects in clinical diagnosis and treatment practices.
Ali A. Alshahrani, Evangelos Kontopantelis, Catharine Morgan, Rathi Ravindrarajah, Glen P. Martin, Mamas A. Mamas
中华医学杂志英文版2025年 138卷 02期
DOI: 10.1097/CM9.0000000000003419
摘要
This article provides an overview of the current evidence on the epidemiology, overlapping risk factors, and pathophysiology of cardiovascular disease (CVD) in patients with cancer. It explores the cardiotoxic effects of anticancer therapy and their impact on prognosis. Although cancer survival rates have improved over the last two decades, the risk of CVD has risen over time in patients with cancer. CVD and cancer share similar risk factors and a common pathophysiology involving inflammation. Many chemotherapeutic agents used to treat cancer are associated with cardiovascular complications (such as heart failure, myocardial infarction, and thrombosis). Current evidence indicates a significant burden of CVD in patients with cancer, particularly in the first year following cancer diagnosis, with elevated risk persisting beyond this period. This short- and long-term risk of CVD may vary depending on the cancer type and treatment regimen. Early identification of potential cardiovascular risk in patients with cancer, can lead to more favorable clinical and survival outcomes. Given the acute and long-term consequences, patients with cancer require increased cardiovascular care and lifestyle optimization. This article offers valuable insights into the cardiovascular burden and needs of patients with cancer. It is intended for a general medical research readership interested in the intersection of cardiology and oncology.
Wei Liu, Le Zhang, Wenhui Liao, Huiguo Liu, Wukaiyang Liang, Jinhua Yan, Yi Huang, Tao Jiang, Qian Wang, Cuntai Zhang
中华医学杂志英文版2025年 138卷 02期
DOI: 10.1097/CM9.0000000000003352
摘要
Vascular aging (VA) is a common etiology of various chronic diseases and represents a major public health concern. Intermittent hypoxia (IH) associated with obstructive sleep apnea-hypopnea syndrome (OSAHS) is a primary pathological and physiological driver of OSAHS-induced systemic complications. A substantial proportion of OSAHS patients, estimated to be between 40% and 80%, have comorbidities such as hypertension, heart failure, coronary artery disease, pulmonary hypertension, atrial fibrillation, aneurysm, and stroke, all of which are closely associated with VA. This review examines the molecular and cellular features common to both OSAHS and VA, highlighting decreased melatonin secretion, impaired autophagy, increased apoptosis, increased inflammation and pyroptosis, increased oxidative stress, accelerated telomere shortening, accelerated stem cell depletion, metabolic disorders, imbalanced protein homeostasis, epigenetic alterations, and dysregulated neurohormonal signaling. The accumulation and combination of these features may underlie the pathophysiological link between OSAHS and VA, but the exact mechanisms by which OSAHS affects VA may require further investigation. Taken together, these findings suggest that OSAHS may serve as a novel risk factor for VA and related vascular disorders, and that targeting these features may offer therapeutic potential to mitigate the vascular risks associated with OSAHS.
Xing Tu, Zixing Zou, Jiahui Li, Simiao Zeng, Zhengchao Luo, Gen Li, Yuanxu Gao, Kang Zhang
中华医学杂志英文版2025年 138卷 02期
DOI: 10.1097/CM9.0000000000003387
摘要
Background:
Retinal ganglion cell (RGC) death caused by acute ocular hypertension is an important characteristic of acute glaucoma. Receptor-interacting protein kinase 3 (RIPK3) that mediates necroptosis is a potential therapeutic target for RGC death. However, the current understanding of the targeting agents and mechanisms of RIPK3 in the treatment of glaucoma remains limited. Notably, artificial intelligence (AI) technologies have significantly advanced drug discovery. This study aimed to discover RIPK3 inhibitor with AI assistance.
Methods:
An acute ocular hypertension model was used to simulate pathological ocular hypertension in vivo. We employed a series of AI methods, including large language and graph neural network models, to identify the target compounds of RIPK3. Subsequently, these target candidates were validated using molecular simulations (molecular docking, absorption, distribution, metabolism, excretion, and toxicity [ADMET] prediction, and molecular dynamics simulations) and biological experiments (Western blotting and fluorescence staining) in vitro and in vivo.
Results:
AI-driven drug screening techniques have the potential to greatly accelerate drug development. A compound called HG9-91-01, identified using AI methods, exerted neuroprotective effects in acute glaucoma. Our research indicates that all five candidates recommended by AI were able to protect the morphological integrity of RGC cells when exposed to hypoxia and glucose deficiency, and HG9-91-01 showed a higher cell survival rate compared to the other candidates. Furthermore, HG9-91-01 was found to protect the retinal structure and reduce the loss of retinal layers in an acute glaucoma model. It was also observed that the neuroprotective effects of HG9-91-01 were highly correlated with the inhibition of PANoptosis (apoptosis, pyroptosis, and necroptosis). Finally, we found that HG9-91-01 can regulate key proteins related to PANoptosis, indicating that this compound exerts neuroprotective effects in the retina by inhibiting the expression of proteins related to apoptosis, pyroptosis, and necroptosis.
Conclusion:
AI-enabled drug discovery revealed that HG9-91-01 could serve as a potential treatment for acute glaucoma.
Background:
Skin cancer is a common skin disease whose incidence and mortality rates have been showing yearly increases. In this report, we update the most recent data on skin cancer as obtained from GLOBOCAN 2022.
Methods:
The incidence and mortality rates of skin cancer (melanoma of skin and non-melanoma skin cancer) in GLOBOCAN 2022 were reviewed. These data were analyzed and the characteristics of incidence and mortality across five continents and top five countries and regions in each continent are presented. In addition, correlations between Human Development Index (HDI) and age-standardized incidence and mortality rates of these two skin cancers are described.
Results:
The GLOBOCAN 2022 data indicated that melanoma was the 17th most common cancer. An estimated 331,722 people were diagnosed with melanoma globally and approximately 58,667 died from this disease. For non-melanoma skin cancer, it ranks as the 5th most common cancer, and an estimated 1,234,533 people were diagnosed with non-melanoma skin cancer globally and approximately 69,416 died from this disease. The incidence of skin cancer varies across geographic regions and countries, with a predominance observed in Oceania, North America, and Europe. Australia was ranked first in terms of incidence, while incidence rates in Africa and Asia were very low. Despite these regional differences in incidence, there was little geographic variation in mortality rates. Currently, the number of deaths from non-melanoma skin cancer exceeds that of melanoma of skin. HDI was positively associated with the incidence of both types of skin cancers, with a positive correlation obtained between HDI and mortality from melanoma of skin and a negative correlation between HDI and mortality from non-melanoma skin cancer.
Conclusions:
Skin cancer remains a major disease burden worldwide. Substantial variations are observed across countries and regions. Further research on skin cancer will be required to provide a rationale for more effective preventions and treatments of this condition.
Background:
Chronic kidney disease (CKD) is associated with common pathophysiological processes, such as inflammation and fibrosis, in both the heart and the kidney. However, the underlying molecular mechanisms that drive these processes are not yet fully understood. Therefore, this study focused on the molecular mechanism of heart and kidney injury in CKD.
Methods:
We generated an microRNA (miR)-26a knockout (KO) mouse model to investigate the role of miR-26a in angiotensin (Ang)-II-induced cardiac and renal injury. We performed Ang-II modeling in wild type (WT) mice and miR-26a KO mice, with six mice in each group. In addition, Ang-II-treated AC16 cells and HK2 cells were used as in vitro models of cardiac and renal injury in the context of CKD. Histological staining, immunohistochemistry, quantitative real-time polymerase chain reaction (PCR), and Western blotting were applied to study the regulation of miR-26a on Ang-II-induced cardiac and renal injury. Immunofluorescence reporter assays were used to detect downstream genes of miR-26a, and immunoprecipitation was employed to identify the interacting protein of LIM and senescent cell antigen-like domain 1 (LIMS1). We also used an adeno-associated virus (AAV) to supplement LIMS1 and explored the specific regulatory mechanism of miR-26a on Ang-II-induced cardiac and renal injury. Dunnett’s multiple comparison and t-test were used to analyze the data.
Results:
Compared with the control mice, miR-26a expression was significantly downregulated in both the kidney and the heart after Ang-II infusion. Our study identified LIMS1 as a novel target gene of miR-26a in both heart and kidney tissues. Downregulation of miR-26a activated the LIMS1/integrin-linked kinase (ILK) signaling pathway in the heart and kidney, which represents a common molecular mechanism underlying inflammation and fibrosis in heart and kidney tissues during CKD. Furthermore, knockout of miR-26a worsened inflammation and fibrosis in the heart and kidney by inhibiting the LIMS1/ILK signaling pathway; on the contrary, supplementation with exogenous miR-26a reversed all these changes.
Conclusions:
Our findings suggest that miR-26a could be a promising therapeutic target for the treatment of cardiorenal injury in CKD. This is attributed to its ability to regulate the LIMS1/ILK signaling pathway, which represents a common molecular mechanism in both heart and kidney tissues.
Background:
China is one of the countries with the highest burdens of stomach cancer. The objective of this study was to analyze long-term trends in the incidence and mortality of stomach cancer in Chinese mainland from 1990 to 2019 and to make projections until 2030.
Methods:
Data on stomach cancer were extracted from the Global Burden of Diseases Study 2019. Population data were extracted from the Global Burden of Diseases Study 2019 and World Population Prospects 2019. An age-period-cohort framework and decomposition analysis were used in this study.
Results:
The net drift for the incidence of stomach cancer was 0.2% (95% confidence interval [CI]: 0, 0.4%) per year for men and -1.8% (95% CI: -2.0%, -1.6%) for women. The net drift for mortality was -1.6% (95% CI: -1.8%, -1.3%) per year for men and -3.3% (95% CI: -3.5%, -3.1%) for women. In the last 10-15 years, the risk of stomach cancer occurrence and death has continued to decline for both sexes. Regarding birth cohorts, although the risk of stomach cancer death decreased in general among women and men born after 1920, the risk of occurrence increased in recent birth cohorts (men born after 1970 and women born after 1985). It is expected that the age-standardized incidence will increase among men and decrease among women, and age-standardized mortality will decrease for both sexes. The largest contributor to the projected increase in incident cases and deaths is population aging, and elderly individuals are projected to have an increased proportion of occurrence and death.
Conclusions:
In the past three decades, the incidence of stomach cancer among men has increased in Chinese mainland, and this trend is projected to continue. Aging will be the main contributor to future increased stomach cancer occurrence and deaths. To reduce the health impact of stomach cancer, more efforts are needed.