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.

Yttrium-90(90Y)selective internal radiation therapy(SIRT)is an emerging modality for the treatment of hepatocellular carcinoma(HCC),leveraging the nuclide 90Y to deliver targeted radiation therapy.90Y has a long half-life and can be used to selectively ablate tumor cells by high-energy beta rays.It has high biological effectiveness and robust local control capabilities.In recent years,with the continuous advancement of basic and clinical research,the application of 90Y-SIRT in the conversion treatment of unresectable HCC(uHCC)has made significant progress.However,challenges remain in the clinical application of 90Y-SIRT,including how to improve the efficacy of conversion therapy and how to optimize therapy regimens.This review aims to summarize the research progress of90Y-SIRT in the conversion therapy of uHCC.

Objective To construct an automatic segmentation model to segment female urine control anatomy on MRI images based on deep learning methods in order to improve the segmentation efficiency and accuracy.Methods A dataset comprising 49 female pelvic floor muscle MRI images[30 women with varying degrees of pelvic organ prolapse(POP)and 19 healthy individuals],obtained from Faculty of Biomedical Engineering and Medical Imaging in Army Medical University,was used for model training and testing.The dataset was split into a training set(17 normal cases and 22 POP cases)and a testing set(4 normal cases and 6 POP cases)in a ratio of 8∶2.The training set was used to train UNet,UNet+++,Dense UNet,and UNet++models separately,and then input into each network.The model achieving the highest testing accuracy was selected as the backbone network.Results Under the training of UNet,UNet+++,Dense UNet,and UNet++,the 4 models achieved average Dice similarity coefficients of 61.82%,57.94%,57.63%,and 62.76%,respectively,for the segmentation of 5 anatomical structures(compressor urethrae,urethra sphincter body,bladder wall,bladder cavity and urethra submucosa).The corresponding Intersection over Union(IoU)score was 49.74%,46.59%,46.07%,and 49.44%,while the accuracy rate was 61.74%,55.03%,59.23%,and 61.91%,respectively for the 4 models.Notably,UNet++consistently outperformed UNet,UNet+++,and Dense UNet across the 3 metrics,indicating that UNet++achieved the highest overall segmentation accuracy.Conclusion In UNet,UNet++,Dense UNet and UNet++for automatic segmentation of 5 female urine control anatomical elements,UNet++achieves the best overall segmentation accuracy.

The morphological characteristics of hepatocellular carcinoma(HCC)tumor margins are pivotal in influencing patient's prognosis and the selection of therapeutic strategies.This paper re-viewed the classification methods of HCC tumor margins,ranging from traditional macroscopic classifi-cations to refined classification systems based on multi-omics analysis,and analyzed the role of these classification methods in guiding the formulation of personalized treatment plans.Additionally,this paper emphasized the crucial role of three-dimensional imaging techniques in assessing tumor margin morphology and outlined future research directions,including validating the effectiveness of multi-omics classification systems and developing new imaging and molecular biomarkers to achieve more precise treatment plans and prolong patient survival.

Objective To evaluate the reporting quality and influencing factors of patient-reported outcome (PRO) data in randomized controlled trials (RCTs) of lung cancer. Methods RCTs of lung cancer with PRO as either primary or secondary endpoints were searched from PubMed, EMbase, Medline, CNKI, Wanfang Data, and VIP databases between January 1, 2010 and April 20, 2024. Reporting quality of included RCTs were assessed based on the CONSORT-PRO extension. Descriptive statistics and bivariate regression analysis were used to describe the reporting quality and analyze the factors influencing the reporting quality. Results A total of 740 articles were retrieved. After screening, 53 eligible RCTs of lung cancer with 22 780 patients were included. The patients were mainly with non-small cell lung cancer (84.91%), with the median sample size of the included studies was 364.0 (160.5, 599.5) patients. The primary PRO tool used was the EORTC QLQ-C30 (60.38%). There were 52 (98.11%) studies whose PRO measured the domain of "symptom management of cough, dyspnea, fatigue, pain, etc.", and 45 (84.91%) studies measured "health-related quality of life". Multicenter studies accounted for 84.91%, and randomized non-blind trials accounted for 62.26%. PRO was used as the primary endpoint in 33.96% of the studies and as secondary endpoints in 66.04%. The reliability and validity of the PRO tools were explicitly mentioned in 11.32% and 7.55% of the studies, respectively. The average completeness of reporting according to the CONSORT-PRO guidelines was 60.00%, ranging from 25.00% to 93.00%. The main factors affecting the completeness of CONSORT-PRO reporting included sample size and publication year. For every increment in sample size, the completeness of reporting increased by 27.5% (SE=0.00, t=2.040, P=0.046). Additionally, studies published after 2018 had a 67.2% higher completeness of reporting compared to those published in or before 2018 (SE=17.8, t=–3.273, P=0.006). Conclusion The study reveals that the overall reporting quality of PRO in lung cancer RCTs is poor. Particularly, the reporting of PRO measures reliability and validity, PRO assumptions, applicability, and handling of missing data need further improvement. Future research should emphasize comprehensive adherence to the CONSORT-PRO guidelines.

This article systematically analyzes the historical evolution of the name， origin， quality evaluation， harvesting， processing and other aspects of Picrorhizae Rhizoma by referring to the medical books， prescription books， and other documents of the past dynasties， combined with relevant modern research materials， in order to provide a basis for the development and utilization of famous classical formulas containing this medicinal herb. The research results indicate that Picrorhizae Rhizoma was first recorded in New Revised Materia Medica from the Tang dynasty. Throughout history， Huhuanglian has been used as its official name， and there are also aliases such as Gehu Luze， Jiahuanglian and Hulian. The main source of past dynasties is the the rhizomes of Picrorhiza kurrooa and P. scrophulariiflora. In ancient times， Picrorhizae Rhizoma was mainly imported by foreign traders via Guangzhou and other regions， and also produced in China， mainly in Xizang. In ancient times， it was harvested and dried in early August of the lunar calendar， while in modern times， it is mostly harvested from July to September， with the best quality being those with thick and crispy rhizomes without impurities， and bitter taste. Throughout history， Picrorhizae Rhizoma was collected， washed， sliced， and dried before being used as a raw material for medicine， it has a bitter and cold taste， mainly used to treat bone steaming， hot flashes， infantile chancre fever， and dysentery. There is no significant difference in taste and efficacy between ancient and modern times. Based on the research results， it is recommended that the rhizomes of P. scrophulariiflora in the 2020 edition of Chinese Pharmacopoeia， or the rhizomes of P. kurrooa， can be used in famous classical formulas containing this medicinal herb， which can be processed according to the processing requirements marked by the original formula. For those without clear processing requirements， the dried raw products are used as medicine.

The immunomodulatory， repair， and regeneration-promoting functions of mesenchymal stem cells make them one of the potential treatment methods for liver diseases. At present， viral and non-viral delivery methods have been developed to genetically modify mesenchymal stem cells， and gene modification can promote the survival， homing， and cytokine secretion of mesenchymal stem cells， thereby enhancing the ability of mesenchymal stem cells to treat liver diseases. This article mainly summarizes the research advances in gene-modified mesenchymal stem cells in the treatment of liver diseases， in order to provide new insights and strategies for the clinical treatment of liver diseases.

The Consolidated Standards of Reporting Trials (CONSORT) statement aims to enhance the quality of reporting for randomized controlled trial (RCT) by providing a minimum item checklist. It was first published in 1996, and updated in 2001 and 2010, respectively. The latest version was released in April 2025, continuously reflecting new evidence, methodological advancements, and user feedback. CONSORT 2025 includes 30 essential checklist items and a template for a participant flow diagram. The main changes to the checklist include the addition of 7 items, revision of 3 items, and deletion of 1 item, as well as the integration of multiple key extensions. This article provides a comprehensive interpretation of the statement, aiming to help clinical trial staff, journal editors, and reviewers fully understand the essence of CONSORT 2025, correctly apply it in writing RCT reports and evaluating RCT quality, and provide guidance for conducting high-level RCT research in China.

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.

Radiation-induced thrombocytopenia (RIT) faces a perplexing challenge in the clinical treatment of cancer patients, and current therapeutic approaches are inadequate in the clinical settings. In this research, oxymatrine, a new molecule capable of healing RIT was screened out, and the underlying regulatory mechanism associated with magakaryocyte (MK) differentiation and thrombopoiesis was demonstrated. The capacity of oxymatrine to induce MK differentiation was verified in K-562 and Meg-01 cells in vitro. The ability to induce thrombopoiesis was subsequently demonstrated in Tg (cd41:enhanced green fluorescent protein (eGFP)) zebrafish and RIT model mice. In addition, we carried out network pharmacological prediction, drug affinity responsive target stability assay (DARTS) and cellular thermal shift assay (CETSA) analyses to explore the potential targets of oxymatrine. Moreover, the pathway underlying the effects of oxymatrine was determined by Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses, Western blot (WB), and immunofluorescence. Oxymatrine markedly promoted MK differentiation and maturation in vitro. Moreover, oxymatrine induced thrombopoiesis in Tg (cd41:eGFP) zebrafish and accelerated thrombopoiesis and platelet function recovery in RIT model mice. Mechanistically, oxymatrine directly binds to toll-like receptor 2 (TLR2) and further regulates the downstream pathway stimulator of interferon genes (STING)/nuclear factor-kappaB (NF-κB), which can be blocked by C29 and C-176, which are specific inhibitors of TLR2 and STING, respectively. Taken together, we demonstrated that oxymatrine, a novel TLR2 agonist, plays a critical role in accelerating MK differentiation and thrombopoiesis via the STING/NF-κB axis, suggesting that oxymatrine is a promising candidate for RIT therapy.