This comprehensive review systematically explores the multifaceted applications, inherent challenges, and promising future directions of artificial intelligence (AI) within the medical domain. It meticulously examines AI's specific contributions to basic medical research, disease prevention, intelligent diagnosis, treatment, rehabilitation, nursing, and health management. Furthermore, the review delves into AI's innovative practices and pivotal roles in clinical trials, hospital administration, medical education, as well as the realms of medical ethics and policy formulation. Notably, the review identifies several key challenges confronting AI in healthcare, encompassing issues such as inadequate algorithm transparency, data privacy concerns, absent regulatory standards, and incomplete risk assessment frameworks. Looking ahead, the future trajectory of AI in healthcare encompasses enhancing algorithm interpretability, propelling generative AI applications, establishing robust data-sharing mechanisms, refining regulatory policies and standards, nurturing interdisciplinary talent, fostering collaboration among industry, academia, and medical institutions, and advancing inclusive, personalized precision medicine. Emphasizing the synergy between AI and emerging technologies like 5G, big data, and cloud computing, this review anticipates a new era of intelligent collaboration and inclusive sharing in healthcare. Through a multidimensional analysis, it presents a holistic overview of AI's medical applications and development prospects, catering to researchers, practitioners, and policymakers in the healthcare sector. Ultimately, this review aims to catalyze the deep integration and innovative deployment of AI technology in healthcare, thereby driving the sustainable advancement of smart healthcare.

OBJECTIVE To establish population pharmacokinetic model of levetiracetam （Lev） for Chinese patients with post- stroke epilepsy （PSE）， and provide reference for formulating individualized dosing regimens for Lev therapy in this specific population. METHODS Blood concentration data and clinical diagnosis and treatment information of PSE patients meeting the inclusion criteria were retrospectively collected and divided into model group and validation group at an 8∶2 ratio using a random number method. Based on the model group data， a population pharmacokinetic model was developed using nonlinear mixed-effects modeling. Internal evaluation was performed through goodness-of-fit tests and bootstrap analysis， while external validation was conducted using the validation group data. RESULTS A total of 75 blood concentration measurements from 70 PSE patients were collected， with 60 measurements from 55 patients used for model development and 15 measurements from 15 patients reserved for external validation. The final model estimated a population typical value of clearance at 2.98 L/h. Estimated glomerular filtration rate， daily dose， and homocysteine level significantly influenced clearance of Lev （P＜0.01）. The model demonstrated satisfactory predictive performance， as evidenced by goodness-of-fit tests， bootstrap analysis， and external validation results. CONCLUSIONS Daily dose， estimated glomerular filtration rate， and homocysteine level are identified as significant covariates influencing Lev clearance in Chinese PSE patients. When making clinical decisions， comprehensive consideration should be given to the patient’s treatment response， physiological and pathological conditions， and the occurrence of adverse reactions， etc. The dosage of Lev should be adjusted based on the results of population pharmacokinetic model.

As the volume of medical research using large language models (LLM) surges, the need for standardized and transparent reporting standards becomes increasingly critical. In January 2025, Nature Medicine published statement titled by TRIPOD-LLM reporting guideline for studies using large language models. This represents the first comprehensive reporting framework specifically tailored for studies that develop prediction models based on LLM. It comprises a checklist with 19 main items (encompassing 50 sub-items), a flowchart, and an abstract checklist (containing 12 items). This article provides an interpretation of TRIPOD-LLM’s development methods, primary content, scope, and the specific details of its items. The goal is to help researchers, clinicians, editors, and healthcare decision-makers to deeply understand and correctly apply TRIPOD-LLM, thereby improving the quality and transparency of LLM medical research reporting and promoting the standardized and ethical integration of LLM into healthcare.

Gentianopsis barbata (G. barbata) represents a significant plant species with considerable ornamental and medicinal value in China. This investigation sought to elucidate the primary constituents within the plant and investigate their pharmacological properties. Fifty triterpenoids (1-50), including nine previously undescribed compounds (1, 2, 7, 10, 20, 28, 29, 37, and 41) were isolated and characterized from the whole plants of G. barbata. Notably, compounds 1 and 2 exhibited the novel 3,4;9,10-diseco-24-homo-cycloartane triterpenoid skeleton. The isolated triterpenoids demonstrated substantial anti-inflammatory activity through inhibition of tumor necrosis factor α (TNF-α) and interleukin-6 (IL-6) cytokine secretion in LPS-induced RAW264.7 macrophages, and hepatoprotective effects by preventing tert-butyl hydroperoxide (t-BHP)-induced oxidative injury in HepG2 cells. These results demonstrate both the presence of diverse triterpenoids in G. barbata and their therapeutic potential for inflammatory and hepatic conditions, providing scientific evidence supporting the clinical application of this traditional Mongolian medicinal plant.
Triterpenes/isolation & purification* ; Mice ; Anti-Inflammatory Agents/isolation & purification* ; Animals ; Humans ; RAW 264.7 Cells ; Hep G2 Cells ; Interleukin-6/genetics* ; Tumor Necrosis Factor-alpha/genetics* ; Medicine, Mongolian Traditional ; Macrophages/immunology* ; Protective Agents/isolation & purification* ; Liver/drug effects* ; Gentianaceae/chemistry* ; Plant Extracts/chemistry* ; Molecular Structure

Objective: To investigate the prevalence of Dengue virus (DENV) infection among voluntary blood donors in Xishuangbanna Dai Autonomous Prefecture, and to evaluate the necessity of implementing nucleic acid testing (NAT) for blood donors during the rainy season (May-October). Methods: Prior to initiating donor screening, the Xishuangbanna Central Blood Center conducted in-house validation of reagent performance and participated in external quality assessment (EQA) organized by the National Center for Clinical Laboratories (NCCL). During the surveillance period (August-October 2024), a total of 2 919 donor samples were screened using a 6-sample mini-pool NAT strategy. Daily internal quality controls were recorded. Samples that tested positive in pooled screening were deconvoluted and retested in duplicate; only those reactive in both replicate wells were sent to the NCCL for confirmatory testing. At NCCL, samples underwent re-testing using five domestic NAT reagents, as well as serological assays for NS1 antigen and DENV-specific IgG/IgM. Confirmed positive samples were further characterized by serotyping, envelope (E) gene sequencing, and phylogenetic analysis using the maximum likelihood method. Results: The DENV NAT reagent demonstrated consistent detection of 40 copies/mL controls in individual donor (ID)-NAT test (mean CT: 35.61±0.40). During the 63-day quality control monitoring, DENV detection remained stable (mean CT: 22.53±0.72). The center achieved full marks in EQA assessments for 2023 and 2024. Three reactive pools were identified in initial screening, and subsequent individual testing confirmed three DENV RNA-positive donors (sample numbers: 2401, 2402, and 2403). The confirmatory test results from NCCL were: all five NAT platforms consistently detected DENV RNA in the three samples; for serological tests, 2 samples (2402, 2403) were positive for NS1 antigen, while all three samples were negative for both IgG and IgM antibodies. DENV serotyping reagents identified DENV-2 in all cases, which were further confirmed as DENV-2 Genotype Ⅱ-Cosmopolitan by E gene sequencing. Phylogenetic analysis indicated that samples 2401 and 2402 clustered with Southeast Asian strains (Thailand/MZ636802.1, Laos/PQ775621.1), while sample 2403 closely matched a previously reported local Yunnan strain (PV544686.1). Conclusion: DENV-2 infection was detected among blood donors in Xishuangbanna during the rainy season, indicating concurrent risks of imported and local transmission. We recommend implementing pooled NAT screening for blood donors in high-risk areas during dengue epidemic seasons, along with strengthened laboratory quality control, to enhance blood safety.

Objective:To investigate the association between frailty and prognosis of elderly patients in the emergency department, and to validate frailty screening tools suitable for the emergency department.Methods:This was a prospective cohort study. Clinical data of elderly patients over 60 years old treated in the emergency department of Beijing Bo'Ai Hospital from January to December 2021 were collected. The Frailty Screening Questionnaire (FSQ), FRAIL Scale (FRAIL) and Clinical Frailty Scale (CFS) were used to score patients, and patients were divided into frail or non-frail group according to the criteria of the above three scales. Twelve-month all-cause mortality was the primary endpoint, dependence and re-admission to the emergency department within 12 months were secondary outcomes. Receiver operating characteristic curves were used to evaluate the ability of the FSQ, FRAIL and CFS scores to predict the primary and secondary endpoints, and the areas under the curve (AUC) were calculated and compared. Survival analysis was performed using Cox hazard proportional regression model, and relative risk was expressed as hazard ratio ( HR) and 95% CI. Results:A total of 406 patients were included in the study. The AUCs (95% CI) of FSQ, FRAIL and CFS scores for predicting 12-month all-cause mortality were 0.879 (0.844-0.909), 0.838 (0.798-0.872), 0.906 (0.873-0.933), respectively (all P<0.001). The AUCs of 3 scores for predicting secondary endpoints ranged from 0.820 to 0.889 (all P<0.001). Pairwise comparisons of the AUCs showed that the CFS was superior to one or both of the other frailty screening scales in predicting 12-month all-cause mortality and dependence except for re-admission to emergency room within 12 months after discharge (all P<0.05). Cox regression analysis revealed that, after adjusting for sex, age, body mass index and comorbidities, frailty as defined by the FSQ, FRAIL, and CFS scales was independently associated with 12-month all-cause mortality, with the HRadj of 3.267 (95% CI: 2.406-4.435), 2.465 (95% CI: 1.819-3.341), 3.523 (95% CI: 2.648-4.687), respectively (all P<0.001). Conclusions:FSQ, FRAIL and CFS scores can predict adverse outcomes, the CFS is a practical frailty screening tool in the emergency department, and frailty screening can improve the risk stratification of older patients.

Objective:To develop and validate a prediction model by combining clinical data and biomarkers to evaluate the probability of frailty among older emergency patients.Methods:A cross-sectional study was conducted. From January 2021 to December 2021, patients aged 60 years and older admitted to the emergency department of China Rehabilitation Research Center were enrolled. Data of patient's clinical information were collected. The patients were divided into frail group and non-frail group according to the Fried's frailty phenotype and clinical data were compared between the two groups. LASSO regression was used to deal with dimension reduction and multivariate logistic regression was employed to construct a prediction model based on variables selected by the LASSO regression. Nomogram was used to visualize the prediction model. The area under the receiver operating characteristic curve, calibration curve, decision curve analysis and bootstrap were used to evaluate the discrimination, calibration, clinical applicability, and internal validity of the model respectively.Results:A total of 348 patients were enrolled, and the incidence of frailty was 53.74% (187/348). Education, coronary heart disease, chronic obstructive pulmonary disease, albumin, fibrinogen, N-terminal pro-brain natriuretic peptide, decreased creatinine, and underweight were independent predictors for frailty in older emergency patients ( P < 0.05). A nomogram model was built based on the above predictors and the model showed good discrimination, calibration and clinical applicability. Conclusions:The study utilized objective clinical data and biomarkers to establish a predictive model for the occurrence of frailty in elderly emergency department patients. This model aids in risk stratification and targeted intervention for elderly emergency patients, thereby improving patient outcomes.

Tafamidis is a selective stabilizer for transthyretin （TTR）， used for the treatment of transthyretin amyloidosis with cardiomyopathy （ATTR-CM） and transthyretin amyloidosis with polyneuropathy （ATTR-PN）. This article provides a review of the basic information and clinical studies on the efficacy and safety of tafamidis. It is found that tafamidis slows down or prevents the progression of TTR amyloidosis by inhibiting the dissociation of TTR tetramers. Multiple clinical studies have shown that tafamidis has good efficacy and safety， significantly reducing all-cause mortality and cardiovascular-related hospitalization rates in patients with amyloidosis， and delaying disease progression. Although tafamidis treatment may have certain limitations， it is still a key drug for the treatment of TTR amyloidosis， and the first drug approved for the treatment of ATTR-CM.

The clinical practice guidelines of traditional Chinese medicine （TCM） have problems such as limited clinical application and unclear implementation effects， which may be related to the lack of clinical practice evidence. To provide reliable and precise evidence for clinical practice， this article proposes a model of combining TCM guidelines with real-world study， which includes 4 steps. Firstly， during the implementation process of the guidelines， a high-quality research database is established. Secondly， the recommendations in the guidelines are evaluated based on the established database in multiple dimensions， including applicability， effectiveness， safety， and cost-effectiveness， and thus their effectiveness in practical applications can be determined. Thirdly， based on the established database， core prescriptions are identified， and the targeted populations and medication plans are determined. That is， the best treatment regimen is established based on the analysis of abundant clinical data regarding the effects of different medication frequencies， dosages， and duration on efficacy. Fourthly， the guidelines are updated according to the real-world evidence. The research based on this model can provide real-world evidence for ancient and empirical prescriptions， improving their application in clinical practice. Moreover， this model can reduce research costs and improve research efficiency. When applying this model， researchers need to pay attention to the quality of real-world evidence， ensuring that it can truly reflect the situation in clinical practice. In addition， importance should be attached to the clinical application of guideline recommendations， ensuring that doctors can conduct standardized diagnosis and treatment according to the guidelines. Finally， full-process participation of multidisciplinary experts is encouraged to ensure the comprehensiveness and scientificity of the study. In conclusion， the application of this model will contribute to the development of TCM guidelines responsive to the needs of clinical practice and achieve the goal of promoting the homogenization of TCM clinical diagnosis and treatment.

As a supplement to randomized controlled trials， observational studies can provide evidence for the effectiveness of traditional Chinese medicine （TCM） treatment measures. They can also study influencing factors of diseases， etiology， and prognosis. However， there is a confounding effect due to the lack of randomization， which seriously affects the causal inference between the study factors and the outcome， resulting in confounding bias. Therefore， identifying and controlling confounding factors are key issues to be addressed in TCM observational studies. According to the causal network and the characteristics of TCM theory， confounding factors can be categorized into measured and unmeasured confounding factors. In addition， attention must be paid to identifying confounding factors and intermediate variables， as well as the interaction between confounding factors and study factors. For methods of controlling confounding factors， measured confounding factors can be controlled by stratification， multifactor analysis， propensity scores， and disease risk scores. Unmeasured and unknown confounding factors can be corrected using instrumental variable methods， difference-in-difference methods， and correction for underlying event rate ratios. Correcting and controlling confounding factors can ensure a balance between groups， and confounding bias can be reduced. In addition， methods such as sensitivity analysis and determination of interactions make the control of confounding factors more comprehensive. Due to the unique characteristics of TCM， observational studies of TCM face unique challenges in identifying and controlling confounding factors， including the ever-changing TCM treatment measures received by patients， the often-overlooked confounding effects in the four diagnostic information of TCM， and the lack of objective criteria for TCM evidence-based diagnosis. Some scholars have already conducted innovative explorations to address these issues， providing a methodological basis for conducting higher-quality TCM observational studies， so as to obtain more rigorous real-world evidence of TCM and gradually develop quality evaluation criteria for OS that are consistent with the characteristics of TCM.