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.
Humans ; Large Language Models ; Tomography, X-Ray Computed

Objective To explore the traditional Chinese medicine(TCM)syndrome characteristics of patients with Chikungunya hemorrhagic fever and to provide empirical data to support the application of TCM in diagnosing and treating Chikungunya hemorrhagic fever.Methods A cross-sectional survey was conducted to collect clinical data(sex,age,days since onset,and comorbidity underlying disease conditions)and TCM with four-examination information(symptoms,tongue manifestations,and pulse manifestations)from 255 patients with Chikungunya hemorrhagic fever who visited Lecong Hospital of Shunde,Foshan,the Third People's Hospital of Shunde District of Foshan,Shunde Hospital of Southern Medical University Affiliated Chencun Hospital between July 23 and July 29,2025.Factor and cluster analyses were used to summarize TCM syndrome characteristics and analyze core pathogenesis in conjunction with clinical features.Results Among the 255 patients with Chikungunya hemorrhagic fever,131 were male and 124 were female,with a age of(49.05±17.93)years and a disease duration of(3.26±1.78)days.Among the four types of examination information in TCM,35 items exhibited a frequency exceeding 10%.The most prevalent symptoms were arthralgia(180 patients,70.59%),exanthem(153 patients,60.00%),fatigue(99 patients,38.82%),anhidrosis(98 patients,38.43%),pruritus(96 patients,37.65%),and fever(92 patients,36.08%).Tongue and pulse manifestations were primarily white fur(155 patients,60.78%),pink tongue(111 patients,43.53%),slippery pulse(143 patients,56.08%),and greasy fur(134 patients,52.53%).Patients with disease onset≤3 d had a higher incidence of arthralgia,fatigue,fever,aversion to cold,generalized muscle pain,aversion to wind,insomnia,headache,sweating,low-grade fever,poor appetite,loose stool,hyperhidrosis,and red tongue than those with disease onset≥4 d(P<0.05).Patients with disease onset≥4 d had a higher incidence of pink tongue and thick fur than those with disease onset≤3 d(P<0.05).The syndrome elements in patients with Chikungunya hemorrhagic fever predominantly manifested on the defensive exterior,with involvement of the sinew-bone joints,skin-muscle,and spleen.Pathogenic factors were primarily characterized by external winds,dampness,and heat.Factor and cluster analysis result indicated three TCM pathogenesis progression patterns:imbalance of the defensive exterior with wind-dampness conflict and heat transformation;dampness-heat flowing into muscles and meridians causing joint obstruction and qi blood stasis;and dampness-heat congelation resulting in qi mechanism obstruction,consumption of body fluids,and infiltration of the skin.Conclusion Patients with Chikungunya hemorrhagic fever primarily present with fever,joint pain,and rashes.In TCM,this condition falls under the category of"dampness-warmth"syndrome.Its etiology is attributed to pathogens,with transmission occurring through mosquito bites.The core pathogenesis of TCM is the invasion of the defensive exterior and dampness-toxic heat accumulation.The therapeutic principles focus on clearing heat pathogens,resolving dampness pathogens,dispersing wind pathogens,and promoting the resolution of rashes.

Objective To explore the traditional Chinese medicine(TCM)syndrome characteristics of patients with Chikungunya hemorrhagic fever and to provide empirical data to support the application of TCM in diagnosing and treating Chikungunya hemorrhagic fever.Methods A cross-sectional survey was conducted to collect clinical data(sex,age,days since onset,and comorbidity underlying disease conditions)and TCM with four-examination information(symptoms,tongue manifestations,and pulse manifestations)from 255 patients with Chikungunya hemorrhagic fever who visited Lecong Hospital of Shunde,Foshan,the Third People's Hospital of Shunde District of Foshan,Shunde Hospital of Southern Medical University Affiliated Chencun Hospital between July 23 and July 29,2025.Factor and cluster analyses were used to summarize TCM syndrome characteristics and analyze core pathogenesis in conjunction with clinical features.Results Among the 255 patients with Chikungunya hemorrhagic fever,131 were male and 124 were female,with a age of(49.05±17.93)years and a disease duration of(3.26±1.78)days.Among the four types of examination information in TCM,35 items exhibited a frequency exceeding 10%.The most prevalent symptoms were arthralgia(180 patients,70.59%),exanthem(153 patients,60.00%),fatigue(99 patients,38.82%),anhidrosis(98 patients,38.43%),pruritus(96 patients,37.65%),and fever(92 patients,36.08%).Tongue and pulse manifestations were primarily white fur(155 patients,60.78%),pink tongue(111 patients,43.53%),slippery pulse(143 patients,56.08%),and greasy fur(134 patients,52.53%).Patients with disease onset≤3 d had a higher incidence of arthralgia,fatigue,fever,aversion to cold,generalized muscle pain,aversion to wind,insomnia,headache,sweating,low-grade fever,poor appetite,loose stool,hyperhidrosis,and red tongue than those with disease onset≥4 d(P<0.05).Patients with disease onset≥4 d had a higher incidence of pink tongue and thick fur than those with disease onset≤3 d(P<0.05).The syndrome elements in patients with Chikungunya hemorrhagic fever predominantly manifested on the defensive exterior,with involvement of the sinew-bone joints,skin-muscle,and spleen.Pathogenic factors were primarily characterized by external winds,dampness,and heat.Factor and cluster analysis result indicated three TCM pathogenesis progression patterns:imbalance of the defensive exterior with wind-dampness conflict and heat transformation;dampness-heat flowing into muscles and meridians causing joint obstruction and qi blood stasis;and dampness-heat congelation resulting in qi mechanism obstruction,consumption of body fluids,and infiltration of the skin.Conclusion Patients with Chikungunya hemorrhagic fever primarily present with fever,joint pain,and rashes.In TCM,this condition falls under the category of"dampness-warmth"syndrome.Its etiology is attributed to pathogens,with transmission occurring through mosquito bites.The core pathogenesis of TCM is the invasion of the defensive exterior and dampness-toxic heat accumulation.The therapeutic principles focus on clearing heat pathogens,resolving dampness pathogens,dispersing wind pathogens,and promoting the resolution of rashes.

ObjectiveTo investigate the objective characteristics of tongue manifestations in patients with coronary heart disease （CHD）. MethodsA total of 315 participants with CHD were recruited in the CHD group， and 211 healthy participants who underwent physical examination were recruited as the healthy control group. In addition， according to the common comorbidities （primary hypertension， carotid atherosclerosis， type 2 diabetes mellitus， fatty liver， hyperlipidaemia， heart failure， and cerebral infarction） in 315 participants with CHD， each comorbidity was classified into a group of comorbidities with that disease and a group of non-comorbidities. Tongue images were captured using a TFDA-1 tongue diagnostic instrument to characterise the tongue body （TB） and tongue coating （TC）， comparing the RGB， HIS， and Lab colour spaces in the chromaticity index （R， red； G， green； B， blue； H， hue； I， intensity； S， saturation； L， lightness； a， red-green axis； b， yellow-blue axis）， the tongue coating thickness index （per-All）， contrast （CON）， angular second moment （ASM）， entropy （ENT）， and mean （MEAN） in texture metrics. ResultsCompared with the healthy control group， the characteristic indexes of tongue body in CHD group showed lower TB-R， TB-G， TB-B， TB-I， TB-L and higher TB-H， TB-b； and the characteristic indexes of tongue coating in CHD group showed lower TC-R， TC-B and higher TC-CON， TC-MEAN， TC-H， TC-b （P＜0.05 or P＜0.01）. Compared with non-combined primary hypertension group， CHD combined primary hypertension group showed higher per-All， TB-G， TB-L， and lower TB-a， TC-a （P＜0.05）； compared with the non-combined carotid atherosclerosis group， CHD combined carotid atherosclerosis group showed higher TB-CON， TB-ENT， TB-MEAN， and lower TB-ASM （P＜0.05 or P＜0.01）； compared with the non-combined type 2 diabetes mellitus group， CHD combined type 2 diabetes mellitus group showed lower per-All and higher TB-H （P＜0.05 or P＜0.01）； compared with the non-combined fatty liver group， CHD combined fatty liver group showed higher TB-CON， TB-MEAN， TB-ENT， and lower TB-ASM and TC-S （P＜0.05 or P＜0.01）； compared with the non-combined hyperlipidaemia group， CHD combined hyperlipidaemia group showed lower TB-S and TB-a （P＜0.05）； compared with non-combined heart failure group， CHD combined heart failure group showed lower TB-R， TB-G， TB-I， TB-L， and higher TB-a （P＜0.05 or P＜0.01）； compared with non-combined cerebral infarction group， CHD combined cerebral infarction group showed higher TC-CON， TC-ENT， TC-MEAN， and lower TC-ASM （P＜0.05 or P＜0.01）. ConclusionCompared to healthy individuals， patients with CHD tend to have darker tongue colours and rougher TC textures. Compared with non-comorbidity participants， those with primary hypertension tended to be lighter tongue colour and thicker tongue coating， those with carotid atherosclerosis had paler tongue body， those with type 2 diabetes mellitus had thinner tongue coating， those with fatty liver disease had paler tongue body and whiter tongue colour， those with hyperlipidaemia and heart failure had paler tongue colour， and those with cerebral infarction had rougher tongue texture.

A novel technology is proposed for non-contact and real-time detection of atrial fibrillation using millimeter-wave radar.A 60 GHz PCR millimeter wave radar is used to continuously detect the chest echo signal of the subject.After signal acquisition,I-Q signal is generated through I-Q demodulation,and the signal phase information is extracted using effective points phase trend evaluation for obtaining the signals from oscillations in the chest wall,from which the respiratory signals and cardiac signals are extracted through digital filtering for the analysis of cardiac movement.Whether the atrial fibrillation occurs or not is determined by the characteristics of atrial fibrillation wave in the time domain.The effective points phase trend evaluation for extracting more accurate signal phase information and the time-domain method for real-time atrial fibrillation detection are the innovations of the study.The experimental results show that the proposed method achieves a detection accuracy of 99.2%in clinic.

Objective To analyze the blood concentration monitoring results of 7 new antiepileptic drugs levetiracetam(LEV),oxcarbazepine(OXC),lamotrigine(LTG),topiramate(TPM),lacosamide(LCM),zonisamide(ZNS)and perampanel(PER)and provide a basis for clinical rational drug use.Methods Aretrospective analysis was conducted on the blood concentration monitoring results of 7 new antiepileptic drugs in a grade-A tertiary hospital in Beijing from November 2021 to March 2023,with a total of 6 537 valid concentration data collected.The patients were grouped according to age,gender and concomitant medication,and the blood drug concentration levels and compliance rates among the groups were analyzed and compared.Results The male to female patient ratio was 1.35∶1.There were statistically significant differences in the blood concentration distribution of OXC,LEV,LCM and TPM between genders(P<0.05).The blood concentration of LEV showed statistically significant differences between the pediatric group and the elderly group,as well as between the young adult group and the elderly group(P<0.05).The blood concentrations of OXC,ZNS and TPM showed statistically significant differences between the pediatric group and the young and middle-aged group,between the young and middle-aged group and the elderly group,and between the pediatric group and the young and middle-aged group,respectively(P<0.05).The highest and lowest overall compliance rates of blood concentration were observed for OXC and LCM,respectively.The compliance rates of OXC and TPM in the pediatric group were significantly higher than those in the young-middle-aged group,with statistically significant differences(P<0.05),while the compliance rate of LEV in the elderly group was significantly higher than that in the pediatric group and the young-middle-aged group,with a statistically significant difference(P<0.05).There were a total of 2 133 cases with combined drug use.LEV,OXC and LTG are frequently used and have good efficacy and weak interactions when added to treatment.Conclusion New antiepileptic drugs show a promising prospect in treatment,and therapeutic drug monitoring can further improve the effectiveness of individualized clinical treatment.

This study explored the feasibility of mineral element content and ratios of nitrogen isotopes to discriminate the cultivation mode of Dendrobium nobile in order to provide theoretical support for the discrimination of the cultivation mode of D. nobile. The content of 11 mineral elements(N, K, Ca, P, Mg, Na, Fe, Cu, Zn, Mn, and B) and nitrogen isotope ratios in D. nobile and its substrate samples in three cultivation methods(greenhouse cultivation, tree-attached cultivation, and stone-attached cultivation) were determined. According to the analysis of variance, principal component analysis, and stepwise discriminant analysis, the samples of different cultivation types were classified. The results showed that the nitrogen isotope ratios and the content of elements except for Zn were significantly different among different cultivation types of D. nobile(P<0.05). The results of correlation analysis showed that the nitrogen isotope ratios, mineral element content, and effective component content in D. nobile were correlated with the nitrogen isotope ratio and mineral element content in the corresponding substrate samples to varying degrees. Principal component analysis can preliminarily classify the samples of D. nobile, but some samples overlapped. Through stepwise discriminant analysis, six indicators, including δ~(15)N, K, Cu, P, Na, and Ca, were screened out, which could be used to establish the discriminant model of D. nobile cultivation methods, and the overall correct discrimination rates after back-substitution test, cross-check, and external validation were all 100%. Therefore, nitrogen isotope ratios and mineral element fingerprints combined with multivariate statistical analysis could effectively discriminate the cultivation types of D. nobile. The results of this study provide a new method for the identification of the cultivation type and production area of D. nobile and an experimental basis for the quality evaluation and quality control of D. nobile.
Dendrobium ; Minerals ; Discriminant Analysis ; Multivariate Analysis ; Nitrogen Isotopes

Objective: To observe the effect of Mo-Rubbing abdomen manipulation on glucose metabolism and inflammatory factors in rats with type 2 diabetes mellitus (T2DM). Methods: Sixty Sprague-Dawley rats were randomly divided into a normal group (n=10) and a group for modeling (n=50) using the random number table method. Rats in the group for modeling were induced to form T2DM models by a high-sugar and high-fat diet combined with intraperitoneal injection of streptozotocin. Thirty successfully modeled rats were randomly divided into a model group, a Mo-Rubbing abdomen group, and a metformin group, with 10 rats in each group. Rats in the normal group and the model group received no intervention, those in the Mo-Rubbing abdomen group received Mo-Rubbing abdomen manipulation, and those in the metformin group received metformin by gavage. After 8-week intervention, fasting insulin (FINS), fasting plasma glucose (FPG), homeostasis model assessment for insulin resistance (HOMA-IR) and area under the curve at the oral glucose tolerance test (AUC-OGTT), as well as serum inflammatory factors interleukin (IL)-1β, IL-6, and tumor necrosis factor (TNF)-α were detected, and the morphological changes of the pancreas were also observed. Results: After the 8-week intervention, the levels of FINS, FPG, HOMA-IR, and AUC-OGTT of rats in the Mo-Rubbing abdomen group were significantly lower than those in the model group (P<0.05); the pancreatic injury degree in the Mo-Rubbing abdomen group and the metformin group was lower than that in the model group. Compared with the model group, the serum IL-1β, IL-6, and TNF-α levels of rats in the Mo-Rubbing abdomen group were significantly decreased (P<0.05), and the serum IL-1β and TNF-α levels of the metformin group showed a downward trend; the serum IL-6 and TNF-α levels in the Mo-Rubbing abdomen group were significantly lower than those in the metformin group (P<0.01). There was a significant positive correlation between FPG with IL-1β, IL-6, and TNF-α in the T2DM rats (P<0.01). Conclusion: Mo-Rubbing abdomen manipulation reduces the inflammatory response and improves the morphological changes of the pancreas in T2DM rats, thereby achieving the effect of lowering blood glucose.

Polymer hydrophilic lubricating coatings for medical catheters refer to highly hydrophilic coating films fixed on the surface of catheters with binding force, which can reduce the surface friction with human tissues during the use of interventional catheters, improve the patient comfort of and effectively reduce the incidence of infection. Based on the development process of medical catheter coating, this review summarizes recent advances in the field of polymer hydrophilic lubricating coatings for medical catheters from types of hydrophilic coating polymer, development of coating technology and establishment of coating performance evaluation method. Main problems in this field are analyzed and development trends in the future are prospected.
Catheters ; Humans ; Hydrophobic and Hydrophilic Interactions ; Polymers

OBJECTIVE：To provide referenc e for selectin g antitumor drugs economic evaluation models and improving the quality of evidence for antitumor drugs economics evaluation in China. METHODS ：A systematic search of the antitumor drug health technology evaluation （pCODR）reports were conducted on the official website of the Canadian Agency for Drugs and Technologies in Health （CADTH）. The search time was limited to Jan. 1st，2015 to Sep. 6th，2020. The basic information ，model types and structure ，and key limitations were extracted and summarized. RESULTS & CONCLUSIONS ：A total of 185 pCODR reports were finally retrieved ，involving 114 types of tumor indications and 98 types of antitumor drugs. The number of CADTH antitumor drugs economics evaluations in the past 5 years had shown an increasing trend. Among 137 pCODR reports with final economic guidance report ，98 reports（71.5％）adopted the PartSA model ，21 reports（15.3％）used the Markov model ，and some reports（6 reports，4.3％）used both PartSA and Markov models to explore the uncertainty of the model structure. In terms of model health status setting ，86 reports（62.8％）used three-state models to evaluate the economy of different anti tumor drugs ，and 16 reports（11.7％）used no less than four health states to simulate the outcome of disease state. However ，there were still some problems in CADTH models ，such as the unreasonable choice of research time limit ，the unreasonable extrapolation method or uncertain extrapolation results of efficacy （survival）data，the uncertainty of efficacy data obtained by indirect comparison ，and some assumptions or parameter settings did not conform to the actual diagnosis and treatment environment. In view of the advantages of PartSA model ，it is suggested that PartSA model or Markov model combined with PartSA model should be used first to verify the uncertainty of model structure in the future economic evaluation of antitumor drugs ；reasonable settings of key model parameters should be considered to improve the quality of evidence for antitumor drugs economics evaluation in China.