This review comprehensively summarized the potential of artificial intelligence(AI)in the management of esophageal cancer.It highlighted the significance of AI-assisted endoscopy in Japan where endoscopy is central to...This review comprehensively summarized the potential of artificial intelligence(AI)in the management of esophageal cancer.It highlighted the significance of AI-assisted endoscopy in Japan where endoscopy is central to both screening and diagnosis.For the clinical adaptation of AI,several challenges remain for its effective translation.The establishment of high-quality clinical databases,such as the National Clinical Database and Japan Endoscopy Database in Japan,which covers almost all cases of esophageal cancer,is essential for validating multimodal AI models.This requires rigorous external validation using diverse datasets,including those from different endoscope manufacturers and image qualities.Furthermore,endoscopists’skills significantly affect diagnostic accuracy,suggesting that AI should serve as a supportive tool rather than a replacement.Addressing these challenges,along with country-specific legal and ethical considerations,will facilitate the successful integration of multimodal AI into the management of esophageal cancer,particularly in endoscopic diagnosis,and contribute to improved patient outcomes.Although this review focused on Japan as a case study,the challenges and solutions described are broadly applicable to other high-incidence regions.展开更多
Standard bacterial suspensions play a crucial role in microbiological diagnosis.Traditional prepar-ation methods,which rely heavily on manual operations,face challenges such as poor reproducibility,low ef-ficiency,and...Standard bacterial suspensions play a crucial role in microbiological diagnosis.Traditional prepar-ation methods,which rely heavily on manual operations,face challenges such as poor reproducibility,low ef-ficiency,and biosafety concerns.In this study,we propose a high-precision automated colony extraction and separation system that combines large-field imaging and artificial intelligence(AI)to facilitate intelligent screening and localization of colonies.Firstly,a large-field imaging system was developed to capture high-resolution images of 90 mm Petri dishes,achieving a physical resolution of 13.2μm and an imaging speed of 13 frames per second.Subsequently,AI technology was employed for the automatic recognition and localiza-tion of colonies,enabling the selection of target colonies with diameters ranging from 1.9 to 2.3 mm.Next,a three-axis motion control platform was designed,accompanied by a path planning algorithm for the efficient extraction of colonies.An electronic pipette was employed for accurate colony collection.Additionally,a bacterial suspension concentration measurement module was developed,incorporating a 650 nm laser diode as the light source,achieving a measurement accuracy of 0.01 McFarland concentration(MCF).Finally,the system’s performance was validated through the preparation of an Esckerichia coli(E.coli)suspension.After 17 hours of cultivation,E.coli was extracted four times,achieving the target concentration set by the system.This work is expected to enable rapid and accurate microbial sample preparation,significantly reducing de-tection cycles and alleviating the workload of healthcare personnel.展开更多
The regulation of signal transmission speed is one of the most important capabilities of the biological nervous system.This study explores the mechanisms and methods for regulating signal transmission speed among nonm...The regulation of signal transmission speed is one of the most important capabilities of the biological nervous system.This study explores the mechanisms and methods for regulating signal transmission speed among nonmyelinated neurons within the same brain region,starting from spike-timing-dependent plasticity(STDP)of synapses.Building upon the Hodgkin-Huxley model,the dynamic behavior of synapses is incorporated,and the adaptive growth neuron(AGN)model is proposed.Artificial synaptic structures and neuronal physical nodes are also designed.The artificial synaptic structure exhibits unidirectionality,memory capacity,and STDP,enabling it to connect neuronal physical nodes through branching and merging structures.Furthermore,the artificial synapse can adjust signal transmission speed,regulate functional competition between different regions of the neuromorphic network,and promote information interaction.The findings of this study endow neuromorphic networks with the ability to regulate signal transmission speed over the long term,providing new insights into the development of neuromorphic networks.展开更多
Generative artificial intelligence(AI),specifically large language models,such as DeepSeek,has accelerated the digital transformation of healthcare systems in both developing and developed countries.The use of AI in d...Generative artificial intelligence(AI),specifically large language models,such as DeepSeek,has accelerated the digital transformation of healthcare systems in both developing and developed countries.The use of AI in diagnostics,image processing and interpretation,treatment personalization,clinical documentation,and drug discovery is an example of the implementation of AI in Western medicine.The need for evidence-based studies and a standardized approach to scientific medicine aligns well with these applications.AI can leave a lasting impact on the Chinese medicine(CM)landscape by increasing expectations and presenting new challenges.The analogy between the CM-specific diagnostic methods and pattern differentiation,which is holistic,pattern-oriented,patient-centered,and clinical data analysis,is significant at multiple levels.These qualities pose challenges for AI usage in CM,which heavily relies on structured data and pattern recognition.Despite these adversities,AI can still be used in CM through data standardization,prediction formulation,and treatment planning,provided that the integration of this tool considers the primary principles of CM and adheres to ethical and regulatory considerations.This review examines the dichotomous approach to health and medicine in the contexts of AI and CM,highlighting the evolving potential,inherent limitations,and ethical and regulatory issues associated with the application of AI to CM.It provides a foundation for developing technologically progressive yet culturally and philosophically sensitive strategies that are in harmony with traditional clinical values.展开更多
Artificial intelligence(AI)is revolutionizing medical imaging,particularly in chronic liver diseases assessment.AI technologies,including machine learning and deep learning,are increasingly integrated with multiparame...Artificial intelligence(AI)is revolutionizing medical imaging,particularly in chronic liver diseases assessment.AI technologies,including machine learning and deep learning,are increasingly integrated with multiparametric ultrasound(US)techniques to provide more accurate,objective,and non-invasive evaluations of liver fibrosis and steatosis.Analyzing large datasets from US images,AI enhances diagnostic precision,enabling better quantification of liver stiffness and fat content,which are essential for diagnosing and staging liver fibrosis and steatosis.Combining advanced US modalities,such as elastography and doppler imaging with AI,has demonstrated improved sensitivity in identifying different stages of liver disease and distinguishing various degrees of steatotic liver.These advancements also contribute to greater reproducibility and reduced operator dependency,addressing some of the limitations of traditional methods.The clinical implications of AI in liver disease are vast,ranging from early detection to predicting disease progression and evaluating treatment response.Despite these promising developments,challenges such as the need for large-scale datasets,algorithm transparency,and clinical validation remain.The aim of this review is to explore the current applications and future potential of AI in liver fibrosis and steatosis assessment using multiparametric US,highlighting the technological advances and clinical relevance of this emerging field.展开更多
BACKGROUND Gastrointestinal stromal tumors(GISTs)are rare mesenchymal neoplasms primarily originating in the stomach or small intestine.Duodenal GISTs are particularly uncommon,accounting for only a small fraction of ...BACKGROUND Gastrointestinal stromal tumors(GISTs)are rare mesenchymal neoplasms primarily originating in the stomach or small intestine.Duodenal GISTs are particularly uncommon,accounting for only a small fraction of GIST cases.These tumors often present with nonspecific symptoms,making early detection challenging.This case discusses a duodenal GIST misdiagnosed as pancreatic cancer due to obstructive jaundice.CASE SUMMARY A 40-year-old male with jaundice and abdominal symptoms underwent imaging,which suggested a malignant periampullary tumor.Preoperative misdiagnosis of pancreatic cancer was made,and surgery was performed.Postoperative histopathology confirmed a duodenal GIST.The role of artificial intelligence in the diagnostic pathway is explored,emphasizing its potential to differentiate between duodenal GISTs and other similar conditions using advanced imaging analysis.CONCLUSION Artificial intelligence in radiomic imaging holds significant promise in enhancing the diagnostic process for rare cancers like duodenal GISTs,ensuring timely and accurate treatment.展开更多
Metabolic dysfunction-associated steatotic liver disease(MASLD)is now considered to be among the most prevalent chronic liver diseases worldwide.Its comprehensive management encompasses multiple stages,including risk ...Metabolic dysfunction-associated steatotic liver disease(MASLD)is now considered to be among the most prevalent chronic liver diseases worldwide.Its comprehensive management encompasses multiple stages,including risk assessment,early detection,stratified intervention,and long-term follow-up.Among these,improving diagnostic accuracy and optimizing individualized therapeutic strategies remain key challenges in both research and clinical practice.In recent years,artificial intelligence and smart devices have developed rapidly and have gradually been applied in the medical field,offering novel tools and pathways for MASLD risk stratification,non-invasive diagnosis,therapeutic evaluation,and patient self-management.This review summarizes the current applications of artificial intelligence and smart devices in MASLD care,highlights their benefits and limitations,and discusses future directions to support precision diagnosis and treatment strategies.展开更多
Background:Artificial intelligence medical diagnostic devices(AIMDDs)show strong potential but face barriers to clinical use,emphasizing the need for rigorous clinical research.Objective:We assessed current AIMDD rese...Background:Artificial intelligence medical diagnostic devices(AIMDDs)show strong potential but face barriers to clinical use,emphasizing the need for rigorous clinical research.Objective:We assessed current AIMDD research,key challenges,and future directions.Methods:A scoping review followed Arksey and O'Malley's methodological framework and the Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews guidelines.PubMed,Web of Science Core Collection,and the Cochrane Database of Systematic Reviews(January 2020-December 2024)were searched on AIMDD design,implementation,and evaluation.Two independent researchers screened and extracted data from the literature using predefined criteria.Results:Ninety-seven articles met the inclusion criteria.Machine learning and deep learning approaches dominated across diverse disease fields,with oncology being the most frequent(41%).The key challenges identified include insufficient quantity,quality,representativeness,and diversity of data;research designs that do not adequately address clinical needs;poor patient selection;poorly defined gold standards;lack of external and prospective validation;and a disconnect between validation strategies and clinical practice.Additionally,issues such as the“black box”phenomenon,overfitting,and data privacy concerns hinder clinical translation.Completeness and standardization of reporting were also found to be lacking.Conclusions:Significant challenges remain in the development and clinical application of AIMDD.To facilitate their clinical translation,improvements are needed in dataset optimization,clinically driven research design,development of evaluation frameworks,enhanced interpretability,and standardized reporting and validation of algorithms.展开更多
Gastrointestinal(GI)cancers remain a leading cause of cancer-related morbidity and mortality worldwide.Artificial intelligence(AI),particularly machine learning and deep learning(DL),has shown promise in enhancing can...Gastrointestinal(GI)cancers remain a leading cause of cancer-related morbidity and mortality worldwide.Artificial intelligence(AI),particularly machine learning and deep learning(DL),has shown promise in enhancing cancer detection,diagnosis,and prognostication.A narrative review of literature published from January 2015 to march 2025 was conducted using PubMed,Web of Science,and Scopus.Search terms included"gastrointestinal cancer","artificial intelligence","machine learning","deep learning","radiomics","multimodal detection"and"predictive modeling".Studies were included if they focused on clinically relevant AI applications in GI oncology.AI algorithms for GI cancer detection have achieved high performance across imaging modalities,with endoscopic DL systems reporting accuracies of 85%-97%for polyp detection and segmentation.Radiomics-based models have predicted molecular biomarkers such as programmed cell death ligand 2 expression with area under the curves up to 0.92.Large language models applied to radiology reports demonstrated diagnostic accuracy comparable to junior radiologists(78.9%vs 80.0%),though without incremental value when combined with human interpretation.Multimodal AI approaches integrating imaging,pathology,and clinical data show emerging potential for precision oncology.AI in GI oncology has reached clinically relevant accuracy levels in multiple diagnostic tasks,with multimodal approaches and predictive biomarker modeling offering new opportunities for personalized care.However,broader validation,integration into clinical workflows,and attention to ethical,legal,and social implications remain critical for widespread adoption.展开更多
As attack techniques evolve and data volumes increase,the integration of artificial intelligence-based security solutions into industrial control systems has become increasingly essential.Artificial intelligence holds...As attack techniques evolve and data volumes increase,the integration of artificial intelligence-based security solutions into industrial control systems has become increasingly essential.Artificial intelligence holds significant potential to improve the operational efficiency and cybersecurity of these systems.However,its dependence on cyber-based infrastructures expands the attack surface and introduces the risk that adversarial manipulations of artificial intelligence models may cause physical harm.To address these concerns,this study presents a comprehensive review of artificial intelligence-driven threat detection methods and adversarial attacks targeting artificial intelligence within industrial control environments,examining both their benefits and associated risks.A systematic literature review was conducted across major scientific databases,including IEEE,Elsevier,Springer Nature,ACM,MDPI,and Wiley,covering peer-reviewed journal and conference papers published between 2017 and 2026.Studies were selected based on predefined inclusion and exclusion criteria following a structured screening process.Based on an analysis of 101 selected studies,this survey categorizes artificial intelligence-based threat detection approaches across the physical,control,and application layers of industrial control systems and examines poisoning,evasion,and extraction attacks targeting industrial artificial intelligence.The findings identify key research trends,highlight unresolved security challenges,and discuss implications for the secure deployment of artificial intelligence-enabled cybersecurity solutions in industrial control systems.展开更多
Artificial intelligence(AI)is increasingly recognized as a transformative force in the field of solid organ transplantation.From enhancing donor-recipient matching to predicting clinical risks and tailoring immunosupp...Artificial intelligence(AI)is increasingly recognized as a transformative force in the field of solid organ transplantation.From enhancing donor-recipient matching to predicting clinical risks and tailoring immunosuppressive therapy,AI has the potential to improve both operational efficiency and patient outcomes.Despite these advancements,the perspectives of transplant professionals-those at the forefront of critical decision-making-remain insufficiently explored.To address this gap,this study utilizes a multi-round electronic Delphi approach to gather and analyses insights from global experts involved in organ transplantation.Participants are invited to complete structured surveys capturing demographic data,professional roles,institutional practices,and prior exposure to AI technologies.The survey also explores perceptions of AI’s potential benefits.Quantitative responses are analyzed using descriptive statistics,while open-ended qualitative responses undergo thematic analysis.Preliminary findings indicate a generally positive outlook on AI’s role in enhancing transplantation processes,particularly in areas such as donor matching and post-operative care.These mixed views reflect both optimism and caution among professionals tasked with integrating new technologies into high-stakes clinical workflows.By capturing a wide range of expert opinions,the findings will inform future policy development,regulatory considerations,and institutional readiness frameworks for the integration of AI into organ transplantation.展开更多
Nursing education is undergoing a paradigm shift from skill training to clinical thinking cultivation.The integration of artificial intelligence technology offers technical possibilities for this transformation,but it...Nursing education is undergoing a paradigm shift from skill training to clinical thinking cultivation.The integration of artificial intelligence technology offers technical possibilities for this transformation,but it also brings about a deep tension between the cultivation of humanistic qualities and a standardized training.Based on the analysis of the practical forms of nursing smart education,this paper examines the cognitive gap between the deterministic feedback of virtual simulation systems and the complexity of real clinical scenarios,reveals the potential narrowing effect of data-driven ability profiling on the all-round development of nursing students,and then proposes the design logic of intelligent teaching resources centered on real clinical problems,a hierarchical teaching model with clear human-machine division of labor,and a dynamic assessment mechanism for technology application led by professional nursing teachers,in an attempt to find a balance between technological empowerment and humanistic commitment in smart nursing education.展开更多
Breast cancer remains a global health challenge with greater than 2.3 million new cases diagnosed annually 1,according to the World Health Organization1.Management of breast cancer is shaped by a complex interplay of ...Breast cancer remains a global health challenge with greater than 2.3 million new cases diagnosed annually 1,according to the World Health Organization1.Management of breast cancer is shaped by a complex interplay of international guidelines,regional adaptations,and the rapidly evolving fields of precision medicine and artificial intelligence(AI).展开更多
Breast cancer is the most common malignant tumor among women globally and poses a major public health challenge due to limitations in traditional diagnostic and treatment processes,such as subjective interpretation bi...Breast cancer is the most common malignant tumor among women globally and poses a major public health challenge due to limitations in traditional diagnostic and treatment processes,such as subjective interpretation biases and inefficient multidimensional data integration.Artificial intelligence(AI),particularly deep learning and machine learning technologies,has emerged as a transformative tool in addressing these issues.Clinically,AI has been widely applied in imaging screening to improve detection rates and reduce reading time,digital pathology for precise tumor typing and gene mutation prediction,treatment decisionsupport systems to enhance guideline compliance,and drug research and development to accelerate target identification and virtual screening.Despite these achievements,AI implementation faces challenges,such as data standardization issues,limited model generalization,low clinical accessibility,and unclear ethical-legal responsibilities,which require targeted solutions that include national data standards,multi-center training,hierarchical physician training,and explainable AI.Future directions involve multimodal data integration,human-AI collaborative multidisciplinary team models,and extension to full-cycle health management from prevention-to-rehabilitation.This review provides a systematic overview of the role of AI in breast cancer care,offering insights for clinical practice and scientific research innovation,and supporting the transition toward personalized and intelligent medicine in oncology.展开更多
With the rapid advancements in biomedical engineering,bioprinting has emerged as a pivotal solution to address the shortage of organ transplants and advance disease model research.The evolution of bioprinting has prog...With the rapid advancements in biomedical engineering,bioprinting has emerged as a pivotal solution to address the shortage of organ transplants and advance disease model research.The evolution of bioprinting has progressed from the fabrication of simple models(1.0)to the fabrication of permanent implants(2.0),tissue engineering scaffolds(3.0),and complex biostructures utilizing living cells(4.0).Nevertheless,significant challenges remain,particularly in accurately replicating the structure and function of host tissues,selecting appropriate materials,and optimizing printing parameters.The integration of artificial intelligence(AI),especially machine learning,provides promising novel opportunities in bioprinting(5.0).This review systematically summarizes the current applications of AI in bioprinting,discussing both construction strategies and application scenarios.It also explores the potential of AI to improve bioprinting in the preparation of complex functional tissues and in situ tissue repair.Overall,the synergy between AI and bioprinting is poised to drive the development of personalized medicine,facilitate high-throughput preparation of in vitro models,and provide robust tools for regenerative medicine and precision healthcare.展开更多
The use of AI in medicine began in the 1970s,with early efforts focused on developing expert systems for diagnosis.AI in oncology specifically began with the development of algorithms to analyze large volumes of medic...The use of AI in medicine began in the 1970s,with early efforts focused on developing expert systems for diagnosis.AI in oncology specifically began with the development of algorithms to analyze large volumes of medical data,primarily focusing on cancer diagnosis and early detection through medical imaging.1–3 The evolution of AI in oncology has transitioned from early rule-based systems to the rise and subsequent pivot of high-profile platforms,such as IBM Watson,leading to today's era of deep learning and generative AI for precision medicine.Table 1 below summarizes the selected milestones associated with Oncology Research and Practice.展开更多
Background:Biliary stent placement during endoscopic retrograde cholangiopancreatography(ERCP)is important for drainage in common bile duct(CBD)strictures,while the stent length is associated with many stent-related c...Background:Biliary stent placement during endoscopic retrograde cholangiopancreatography(ERCP)is important for drainage in common bile duct(CBD)strictures,while the stent length is associated with many stent-related complications.We aimed to develop an artificial intelligence(AI)model for stent length selection during ERCP.Methods:Images of the patients who underwent ERCP and were diagnosed with CBD strictures were collected.Training involved identifying and delineating the duodenoscope,CBD and guidewire,calculating the pixel distance of the target guidewire and determining the required biliary stent length based on the diameter of the duodenoscope.The performance of the model,accuracy for length calculation and the assistance for endoscopists were validated using the testing set.Results:A total of 794 images from 431 patients were included and data augmentation was conducted.The mean intersection over union(mIoU)for duodenoscope,CBD and guidewire were 90.46%,84.79%and 84.64%,respectively.The accuracy in identifying the strictures was 97.58%(121/124).The accuracy for stent length calculation achieved 85.95%(104/121)with an error margin of±1 cm.The mean absolute error(MAE)and mean relative error(MRE)of the AI model was 0.81 cm and 0.13,respectively.The AI model could reduce approximately 202 mGycm^(2)of the radiation exposure for each patient.It significantly improved both MAE and MRE for less experienced endoscopists(P=0.01 and P=0.02,respectively).Conclusions:The AI model could accurately identify duodenoscope,CBD and guidewire,enabling accurate strictures identification and stent length selection.展开更多
The integration of machine learning(ML)into geohazard assessment has successfully instigated a paradigm shift,leading to the production of models that possess a level of predictive accuracy previously considered unatt...The integration of machine learning(ML)into geohazard assessment has successfully instigated a paradigm shift,leading to the production of models that possess a level of predictive accuracy previously considered unattainable.However,the black-box nature of these systems presents a significant barrier,hindering their operational adoption,regulatory approval,and full scientific validation.This paper provides a systematic review and synthesis of the emerging field of explainable artificial intelligence(XAI)as applied to geohazard science(GeoXAI),a domain that aims to resolve the long-standing trade-off between model performance and interpretability.A rigorous synthesis of 87 foundational studies is used to map the intellectual and methodological contours of this rapidly expanding field.The analysis reveals that current research efforts are concentrated predominantly on landslide and flood assessment.Methodologically,tree-based ensembles and deep learning models dominate the literature,with SHapley Additive exPlanations(SHAP)frequently adopted as the principal post-hoc explanation technique.More importantly,the review further documents how the role of XAI has shifted:rather than being used solely as a tool for interpreting models after training,it is increasingly integrated into the modeling cycle itself.Recent applications include its use in feature selection,adaptive sampling strategies,and model evaluation.The evidence also shows that GeoXAI extends beyond producing feature rankings.It reveals nonlinear thresholds and interaction effects that generate deeper mechanistic insights into hazard processes and mechanisms.Nevertheless,several key challenges remain unresolved within the field.These persistent issues are especially pronounced when considering the crucial necessity for interpretation stability,the demanding scholarly task of reliably distinguishing correlation from causation,and the development of appropriate methods for the treatment of complex spatio-temporal dynamics.展开更多
Background:High-mobility group box 1(HMGB1)is a critical damage-associated molecular pattern protein that participates in diverse physiological and pathological processes.However,its relevance to the prognosis of arti...Background:High-mobility group box 1(HMGB1)is a critical damage-associated molecular pattern protein that participates in diverse physiological and pathological processes.However,its relevance to the prognosis of artificial liver support therapy in patients with acute liver injury(ALF)remains unclear.Methods:Bioinformatics analyses were performed to identify HMGB1-interacting proteins and associated inflammatory signaling pathways.Peripheral blood samples were collected from ALF patients before and after artificial liver support therapy,and serum HMGB1 concentrations were quantified using ELISA.Primary mouse hepatocytes were stimulated with lipopolysaccharide(LPS)in vitro and HMGB1 expression was verified by western blot.Results:Single-cell transcriptomic profiling showed that HMGB1 is widely expressed across tissues and predominantly localized in the nucleus.In the liver,HMGB1 was primarily expressed in hepatocytes and hepatic stellate cells.STRING database analysis revealed that human HMGB1 interacts with multiple proteins,including TLR4,TP53,and BECN1.The constructed interaction network comprised 11 nodes with an average local clustering coefficient of 0.888,and the protein–protein interaction enrichment P-value was 1.42×10^(-5),indicating significant enrichment.Gene Ontology and KEGG pathway enrichment analyses demonstrated that HMGB1 is closely linked to inflammatory and injury-related signaling pathways,including the TLR and NLR pathways.Metabolomic profiling revealed significant metabolic alterations between patients with ALF and healthy controls under both positive and negative ion modes and functional analysis showed necroptosis was activated.The cell viability gradually decreased with time and dose under LPS treatment and extracellular HMGB1 was upregulated in LPS induced ALF model and patients(P<0.05).Serum HMGB1/RIPK3/MLKL levels were markedly elevated in ALF patients compared with controls(P<0.05)and progressively declined following artificial liver support therapy.Furthermore,elevated HMGB1 concentrations were positively correlated with unfavorable clinical outcomes.Conclusion:Peripheral blood HMGB1 levels are significantly increased in patients with acute liver failure,decrease following artificial liver support therapy,and are positively associated with poor clinical prognosis.展开更多
Background:Artificial intelligence(AI)is transforming healthcare,demanding reevaluation of medical education.China's“New Medical Education”initiative urgently requires a standardized AI literacy framework for me...Background:Artificial intelligence(AI)is transforming healthcare,demanding reevaluation of medical education.China's“New Medical Education”initiative urgently requires a standardized AI literacy framework for medical students to address fragmented standards,rapid technological evolution,and insufficient localized ethical norms.Objective:To establish a Chinese expert consensus defining core AI competencies and a multi-modal assessment framework for medical students.Methods:A multidisciplinary(including medical education,clinical medicine,medical AI,public health,and medical ethics)expert group(n=32)developed an initial competency list based on the“Knowledge-Skills-Attitude”Medical Competency Model.Two Delphi rounds(100%response rate;consensus threshold:mean≥4.0,CV≤0.25)refined the framework.Core competencies were prioritized via Analytic Hierarchy Process(AHP).The final consensus document was established after multiple expert group meetings.Results:The consensus defines AI literacy for medical students as a comprehensive attribute for integrating AI into profes-sional knowledge,clinical practice,research,and health management.It comprises a 21-item Competencies of AI Proficiency(CAIP)list across knowledge(eight indicators),skills(seven indicators),and attitude(six indicators)dimensions.Key com-petencies prioritized include understanding AI's role in multidisciplinary knowledge integration(CAIP3),identifying AI output biases(CAIP4),understanding health data governance(CAIP2),maintaining physician-led AI-assisted diagnosis(CAIP16),and identifying AI diagnostic biases(CAIP12).A multi-modal assessment framework is recommended,including paper-based/computerized tests for knowledge,situational judgment tests(SJTs)for attitudes,and objective structured clinical examinations(OSCEs)with a specific“AI Clinical Decision Conflict Scoring Scale”for skills.A multi-stage dynamic assessment system(“Pre-enrollment-Pre-clinical-Post-clinical”)is proposed for longitudinal tracking.Educational integration pathways emphasize embedding AI literacy modularly from early undergraduate years,constructing an integrated curriculum covering fundamental principles,advanced large model applications(e.g.,prompt engineering,agent development),and ethical considerations,supported by a"digital twin hospital platform."Conclusion:This consensus provides authoritative,China-specific guidance for defining and assessing medical students'AI literacy,adhering to national policies and regulations.It offers a core action framework for optimizing AI integration into medical education,fostering future healthcare professionals proficient in both AI technology and medical humanism,with a commitment to dynamic updating to adapt to evolving AI advancements.展开更多
基金Supported by Japan Society for the Promotion of Science,No.24K11935.
文摘This review comprehensively summarized the potential of artificial intelligence(AI)in the management of esophageal cancer.It highlighted the significance of AI-assisted endoscopy in Japan where endoscopy is central to both screening and diagnosis.For the clinical adaptation of AI,several challenges remain for its effective translation.The establishment of high-quality clinical databases,such as the National Clinical Database and Japan Endoscopy Database in Japan,which covers almost all cases of esophageal cancer,is essential for validating multimodal AI models.This requires rigorous external validation using diverse datasets,including those from different endoscope manufacturers and image qualities.Furthermore,endoscopists’skills significantly affect diagnostic accuracy,suggesting that AI should serve as a supportive tool rather than a replacement.Addressing these challenges,along with country-specific legal and ethical considerations,will facilitate the successful integration of multimodal AI into the management of esophageal cancer,particularly in endoscopic diagnosis,and contribute to improved patient outcomes.Although this review focused on Japan as a case study,the challenges and solutions described are broadly applicable to other high-incidence regions.
文摘Standard bacterial suspensions play a crucial role in microbiological diagnosis.Traditional prepar-ation methods,which rely heavily on manual operations,face challenges such as poor reproducibility,low ef-ficiency,and biosafety concerns.In this study,we propose a high-precision automated colony extraction and separation system that combines large-field imaging and artificial intelligence(AI)to facilitate intelligent screening and localization of colonies.Firstly,a large-field imaging system was developed to capture high-resolution images of 90 mm Petri dishes,achieving a physical resolution of 13.2μm and an imaging speed of 13 frames per second.Subsequently,AI technology was employed for the automatic recognition and localiza-tion of colonies,enabling the selection of target colonies with diameters ranging from 1.9 to 2.3 mm.Next,a three-axis motion control platform was designed,accompanied by a path planning algorithm for the efficient extraction of colonies.An electronic pipette was employed for accurate colony collection.Additionally,a bacterial suspension concentration measurement module was developed,incorporating a 650 nm laser diode as the light source,achieving a measurement accuracy of 0.01 McFarland concentration(MCF).Finally,the system’s performance was validated through the preparation of an Esckerichia coli(E.coli)suspension.After 17 hours of cultivation,E.coli was extracted four times,achieving the target concentration set by the system.This work is expected to enable rapid and accurate microbial sample preparation,significantly reducing de-tection cycles and alleviating the workload of healthcare personnel.
基金supported by the National Natural Science Foundation of China(Grant No.62171182)the Natural Scienceof Hunan Province(Grant No.2025JJ50345)the Postgraduate Scientific Research Innovation Project of Hunan Province(Grant No.CX20240452)。
文摘The regulation of signal transmission speed is one of the most important capabilities of the biological nervous system.This study explores the mechanisms and methods for regulating signal transmission speed among nonmyelinated neurons within the same brain region,starting from spike-timing-dependent plasticity(STDP)of synapses.Building upon the Hodgkin-Huxley model,the dynamic behavior of synapses is incorporated,and the adaptive growth neuron(AGN)model is proposed.Artificial synaptic structures and neuronal physical nodes are also designed.The artificial synaptic structure exhibits unidirectionality,memory capacity,and STDP,enabling it to connect neuronal physical nodes through branching and merging structures.Furthermore,the artificial synapse can adjust signal transmission speed,regulate functional competition between different regions of the neuromorphic network,and promote information interaction.The findings of this study endow neuromorphic networks with the ability to regulate signal transmission speed over the long term,providing new insights into the development of neuromorphic networks.
文摘Generative artificial intelligence(AI),specifically large language models,such as DeepSeek,has accelerated the digital transformation of healthcare systems in both developing and developed countries.The use of AI in diagnostics,image processing and interpretation,treatment personalization,clinical documentation,and drug discovery is an example of the implementation of AI in Western medicine.The need for evidence-based studies and a standardized approach to scientific medicine aligns well with these applications.AI can leave a lasting impact on the Chinese medicine(CM)landscape by increasing expectations and presenting new challenges.The analogy between the CM-specific diagnostic methods and pattern differentiation,which is holistic,pattern-oriented,patient-centered,and clinical data analysis,is significant at multiple levels.These qualities pose challenges for AI usage in CM,which heavily relies on structured data and pattern recognition.Despite these adversities,AI can still be used in CM through data standardization,prediction formulation,and treatment planning,provided that the integration of this tool considers the primary principles of CM and adheres to ethical and regulatory considerations.This review examines the dichotomous approach to health and medicine in the contexts of AI and CM,highlighting the evolving potential,inherent limitations,and ethical and regulatory issues associated with the application of AI to CM.It provides a foundation for developing technologically progressive yet culturally and philosophically sensitive strategies that are in harmony with traditional clinical values.
文摘Artificial intelligence(AI)is revolutionizing medical imaging,particularly in chronic liver diseases assessment.AI technologies,including machine learning and deep learning,are increasingly integrated with multiparametric ultrasound(US)techniques to provide more accurate,objective,and non-invasive evaluations of liver fibrosis and steatosis.Analyzing large datasets from US images,AI enhances diagnostic precision,enabling better quantification of liver stiffness and fat content,which are essential for diagnosing and staging liver fibrosis and steatosis.Combining advanced US modalities,such as elastography and doppler imaging with AI,has demonstrated improved sensitivity in identifying different stages of liver disease and distinguishing various degrees of steatotic liver.These advancements also contribute to greater reproducibility and reduced operator dependency,addressing some of the limitations of traditional methods.The clinical implications of AI in liver disease are vast,ranging from early detection to predicting disease progression and evaluating treatment response.Despite these promising developments,challenges such as the need for large-scale datasets,algorithm transparency,and clinical validation remain.The aim of this review is to explore the current applications and future potential of AI in liver fibrosis and steatosis assessment using multiparametric US,highlighting the technological advances and clinical relevance of this emerging field.
文摘BACKGROUND Gastrointestinal stromal tumors(GISTs)are rare mesenchymal neoplasms primarily originating in the stomach or small intestine.Duodenal GISTs are particularly uncommon,accounting for only a small fraction of GIST cases.These tumors often present with nonspecific symptoms,making early detection challenging.This case discusses a duodenal GIST misdiagnosed as pancreatic cancer due to obstructive jaundice.CASE SUMMARY A 40-year-old male with jaundice and abdominal symptoms underwent imaging,which suggested a malignant periampullary tumor.Preoperative misdiagnosis of pancreatic cancer was made,and surgery was performed.Postoperative histopathology confirmed a duodenal GIST.The role of artificial intelligence in the diagnostic pathway is explored,emphasizing its potential to differentiate between duodenal GISTs and other similar conditions using advanced imaging analysis.CONCLUSION Artificial intelligence in radiomic imaging holds significant promise in enhancing the diagnostic process for rare cancers like duodenal GISTs,ensuring timely and accurate treatment.
基金supported by the National Key Research and Development Program(2024YFA1307101).
文摘Metabolic dysfunction-associated steatotic liver disease(MASLD)is now considered to be among the most prevalent chronic liver diseases worldwide.Its comprehensive management encompasses multiple stages,including risk assessment,early detection,stratified intervention,and long-term follow-up.Among these,improving diagnostic accuracy and optimizing individualized therapeutic strategies remain key challenges in both research and clinical practice.In recent years,artificial intelligence and smart devices have developed rapidly and have gradually been applied in the medical field,offering novel tools and pathways for MASLD risk stratification,non-invasive diagnosis,therapeutic evaluation,and patient self-management.This review summarizes the current applications of artificial intelligence and smart devices in MASLD care,highlights their benefits and limitations,and discusses future directions to support precision diagnosis and treatment strategies.
基金supported by the National Key R&D Program of China(2022YFC3501000,2022YFC3502300)National Natural Science Foundation of China(82374627)+2 种基金Fundamental Research Funds for the Central public welfare research institutes(Z0876)Fundamental Research Funds for the Central Universities(2024-JYB-KYPT-01)Beijing Municipal Science and Technology Commission(Z241100007724010).
文摘Background:Artificial intelligence medical diagnostic devices(AIMDDs)show strong potential but face barriers to clinical use,emphasizing the need for rigorous clinical research.Objective:We assessed current AIMDD research,key challenges,and future directions.Methods:A scoping review followed Arksey and O'Malley's methodological framework and the Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews guidelines.PubMed,Web of Science Core Collection,and the Cochrane Database of Systematic Reviews(January 2020-December 2024)were searched on AIMDD design,implementation,and evaluation.Two independent researchers screened and extracted data from the literature using predefined criteria.Results:Ninety-seven articles met the inclusion criteria.Machine learning and deep learning approaches dominated across diverse disease fields,with oncology being the most frequent(41%).The key challenges identified include insufficient quantity,quality,representativeness,and diversity of data;research designs that do not adequately address clinical needs;poor patient selection;poorly defined gold standards;lack of external and prospective validation;and a disconnect between validation strategies and clinical practice.Additionally,issues such as the“black box”phenomenon,overfitting,and data privacy concerns hinder clinical translation.Completeness and standardization of reporting were also found to be lacking.Conclusions:Significant challenges remain in the development and clinical application of AIMDD.To facilitate their clinical translation,improvements are needed in dataset optimization,clinically driven research design,development of evaluation frameworks,enhanced interpretability,and standardized reporting and validation of algorithms.
文摘Gastrointestinal(GI)cancers remain a leading cause of cancer-related morbidity and mortality worldwide.Artificial intelligence(AI),particularly machine learning and deep learning(DL),has shown promise in enhancing cancer detection,diagnosis,and prognostication.A narrative review of literature published from January 2015 to march 2025 was conducted using PubMed,Web of Science,and Scopus.Search terms included"gastrointestinal cancer","artificial intelligence","machine learning","deep learning","radiomics","multimodal detection"and"predictive modeling".Studies were included if they focused on clinically relevant AI applications in GI oncology.AI algorithms for GI cancer detection have achieved high performance across imaging modalities,with endoscopic DL systems reporting accuracies of 85%-97%for polyp detection and segmentation.Radiomics-based models have predicted molecular biomarkers such as programmed cell death ligand 2 expression with area under the curves up to 0.92.Large language models applied to radiology reports demonstrated diagnostic accuracy comparable to junior radiologists(78.9%vs 80.0%),though without incremental value when combined with human interpretation.Multimodal AI approaches integrating imaging,pathology,and clinical data show emerging potential for precision oncology.AI in GI oncology has reached clinically relevant accuracy levels in multiple diagnostic tasks,with multimodal approaches and predictive biomarker modeling offering new opportunities for personalized care.However,broader validation,integration into clinical workflows,and attention to ethical,legal,and social implications remain critical for widespread adoption.
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(RS-2023-00242528,50%)supported by the Korea Internet&Security Agency(KISA)through the Information Security Specialized University Support Project(50%).
文摘As attack techniques evolve and data volumes increase,the integration of artificial intelligence-based security solutions into industrial control systems has become increasingly essential.Artificial intelligence holds significant potential to improve the operational efficiency and cybersecurity of these systems.However,its dependence on cyber-based infrastructures expands the attack surface and introduces the risk that adversarial manipulations of artificial intelligence models may cause physical harm.To address these concerns,this study presents a comprehensive review of artificial intelligence-driven threat detection methods and adversarial attacks targeting artificial intelligence within industrial control environments,examining both their benefits and associated risks.A systematic literature review was conducted across major scientific databases,including IEEE,Elsevier,Springer Nature,ACM,MDPI,and Wiley,covering peer-reviewed journal and conference papers published between 2017 and 2026.Studies were selected based on predefined inclusion and exclusion criteria following a structured screening process.Based on an analysis of 101 selected studies,this survey categorizes artificial intelligence-based threat detection approaches across the physical,control,and application layers of industrial control systems and examines poisoning,evasion,and extraction attacks targeting industrial artificial intelligence.The findings identify key research trends,highlight unresolved security challenges,and discuss implications for the secure deployment of artificial intelligence-enabled cybersecurity solutions in industrial control systems.
文摘Artificial intelligence(AI)is increasingly recognized as a transformative force in the field of solid organ transplantation.From enhancing donor-recipient matching to predicting clinical risks and tailoring immunosuppressive therapy,AI has the potential to improve both operational efficiency and patient outcomes.Despite these advancements,the perspectives of transplant professionals-those at the forefront of critical decision-making-remain insufficiently explored.To address this gap,this study utilizes a multi-round electronic Delphi approach to gather and analyses insights from global experts involved in organ transplantation.Participants are invited to complete structured surveys capturing demographic data,professional roles,institutional practices,and prior exposure to AI technologies.The survey also explores perceptions of AI’s potential benefits.Quantitative responses are analyzed using descriptive statistics,while open-ended qualitative responses undergo thematic analysis.Preliminary findings indicate a generally positive outlook on AI’s role in enhancing transplantation processes,particularly in areas such as donor matching and post-operative care.These mixed views reflect both optimism and caution among professionals tasked with integrating new technologies into high-stakes clinical workflows.By capturing a wide range of expert opinions,the findings will inform future policy development,regulatory considerations,and institutional readiness frameworks for the integration of AI into organ transplantation.
基金Funding Project for Ideological and Political Model Courses of“Epidemic Fighting”Courses in Henan Province(Project No.:531,2020)University-level Curriculum Ideological and Political Demonstration Course Support Project of Zhengzhou Sias University(Project No.:34,2024)+2 种基金University-level Key Discipline Support Project of Zhengzhou Sias University(Project No.:1,2022)2025 Key Scientific Research Projects of Henan Universities(Project No.:25B360003)Henan Province Private Brand Professional Support Project(Project No.:527,2019)。
文摘Nursing education is undergoing a paradigm shift from skill training to clinical thinking cultivation.The integration of artificial intelligence technology offers technical possibilities for this transformation,but it also brings about a deep tension between the cultivation of humanistic qualities and a standardized training.Based on the analysis of the practical forms of nursing smart education,this paper examines the cognitive gap between the deterministic feedback of virtual simulation systems and the complexity of real clinical scenarios,reveals the potential narrowing effect of data-driven ability profiling on the all-round development of nursing students,and then proposes the design logic of intelligent teaching resources centered on real clinical problems,a hierarchical teaching model with clear human-machine division of labor,and a dynamic assessment mechanism for technology application led by professional nursing teachers,in an attempt to find a balance between technological empowerment and humanistic commitment in smart nursing education.
文摘Breast cancer remains a global health challenge with greater than 2.3 million new cases diagnosed annually 1,according to the World Health Organization1.Management of breast cancer is shaped by a complex interplay of international guidelines,regional adaptations,and the rapidly evolving fields of precision medicine and artificial intelligence(AI).
基金supported by the National Natural Science Foundation of China(Grant No.82404074)the Science and Technology Major Project(Grant No.2024ZD0519805).
文摘Breast cancer is the most common malignant tumor among women globally and poses a major public health challenge due to limitations in traditional diagnostic and treatment processes,such as subjective interpretation biases and inefficient multidimensional data integration.Artificial intelligence(AI),particularly deep learning and machine learning technologies,has emerged as a transformative tool in addressing these issues.Clinically,AI has been widely applied in imaging screening to improve detection rates and reduce reading time,digital pathology for precise tumor typing and gene mutation prediction,treatment decisionsupport systems to enhance guideline compliance,and drug research and development to accelerate target identification and virtual screening.Despite these achievements,AI implementation faces challenges,such as data standardization issues,limited model generalization,low clinical accessibility,and unclear ethical-legal responsibilities,which require targeted solutions that include national data standards,multi-center training,hierarchical physician training,and explainable AI.Future directions involve multimodal data integration,human-AI collaborative multidisciplinary team models,and extension to full-cycle health management from prevention-to-rehabilitation.This review provides a systematic overview of the role of AI in breast cancer care,offering insights for clinical practice and scientific research innovation,and supporting the transition toward personalized and intelligent medicine in oncology.
基金financially supported by the National Natural Science Foundation of China(Nos.32471396,82230071,82172098,82201716,and 61973206)the National Key R&D Program of China(No.2023YFC2411303)+4 种基金the Integrated Project of Major Research Plan of the National Natural Science Foundation of China(No.92249303)the Shanghai Committee of Science and Technology(No.23141900600,Laboratory Animal Research Project)the Shanghai Clinical Research Plan of SHDC2023CRT01the Young Elite Scientist Sponsorship Program by the China Association for Science and Technology(No.YESS20230049)the Baoshan District Health Commission Talents(Excellent Academic Leaders)Program(No.BSWSYX-2024-05)。
文摘With the rapid advancements in biomedical engineering,bioprinting has emerged as a pivotal solution to address the shortage of organ transplants and advance disease model research.The evolution of bioprinting has progressed from the fabrication of simple models(1.0)to the fabrication of permanent implants(2.0),tissue engineering scaffolds(3.0),and complex biostructures utilizing living cells(4.0).Nevertheless,significant challenges remain,particularly in accurately replicating the structure and function of host tissues,selecting appropriate materials,and optimizing printing parameters.The integration of artificial intelligence(AI),especially machine learning,provides promising novel opportunities in bioprinting(5.0).This review systematically summarizes the current applications of AI in bioprinting,discussing both construction strategies and application scenarios.It also explores the potential of AI to improve bioprinting in the preparation of complex functional tissues and in situ tissue repair.Overall,the synergy between AI and bioprinting is poised to drive the development of personalized medicine,facilitate high-throughput preparation of in vitro models,and provide robust tools for regenerative medicine and precision healthcare.
文摘The use of AI in medicine began in the 1970s,with early efforts focused on developing expert systems for diagnosis.AI in oncology specifically began with the development of algorithms to analyze large volumes of medical data,primarily focusing on cancer diagnosis and early detection through medical imaging.1–3 The evolution of AI in oncology has transitioned from early rule-based systems to the rise and subsequent pivot of high-profile platforms,such as IBM Watson,leading to today's era of deep learning and generative AI for precision medicine.Table 1 below summarizes the selected milestones associated with Oncology Research and Practice.
基金supported by grants from the Taishan Scholars Program of Shandong Province(tsqn202312333)the National Natural Science Foundation of China(82470695).
文摘Background:Biliary stent placement during endoscopic retrograde cholangiopancreatography(ERCP)is important for drainage in common bile duct(CBD)strictures,while the stent length is associated with many stent-related complications.We aimed to develop an artificial intelligence(AI)model for stent length selection during ERCP.Methods:Images of the patients who underwent ERCP and were diagnosed with CBD strictures were collected.Training involved identifying and delineating the duodenoscope,CBD and guidewire,calculating the pixel distance of the target guidewire and determining the required biliary stent length based on the diameter of the duodenoscope.The performance of the model,accuracy for length calculation and the assistance for endoscopists were validated using the testing set.Results:A total of 794 images from 431 patients were included and data augmentation was conducted.The mean intersection over union(mIoU)for duodenoscope,CBD and guidewire were 90.46%,84.79%and 84.64%,respectively.The accuracy in identifying the strictures was 97.58%(121/124).The accuracy for stent length calculation achieved 85.95%(104/121)with an error margin of±1 cm.The mean absolute error(MAE)and mean relative error(MRE)of the AI model was 0.81 cm and 0.13,respectively.The AI model could reduce approximately 202 mGycm^(2)of the radiation exposure for each patient.It significantly improved both MAE and MRE for less experienced endoscopists(P=0.01 and P=0.02,respectively).Conclusions:The AI model could accurately identify duodenoscope,CBD and guidewire,enabling accurate strictures identification and stent length selection.
文摘The integration of machine learning(ML)into geohazard assessment has successfully instigated a paradigm shift,leading to the production of models that possess a level of predictive accuracy previously considered unattainable.However,the black-box nature of these systems presents a significant barrier,hindering their operational adoption,regulatory approval,and full scientific validation.This paper provides a systematic review and synthesis of the emerging field of explainable artificial intelligence(XAI)as applied to geohazard science(GeoXAI),a domain that aims to resolve the long-standing trade-off between model performance and interpretability.A rigorous synthesis of 87 foundational studies is used to map the intellectual and methodological contours of this rapidly expanding field.The analysis reveals that current research efforts are concentrated predominantly on landslide and flood assessment.Methodologically,tree-based ensembles and deep learning models dominate the literature,with SHapley Additive exPlanations(SHAP)frequently adopted as the principal post-hoc explanation technique.More importantly,the review further documents how the role of XAI has shifted:rather than being used solely as a tool for interpreting models after training,it is increasingly integrated into the modeling cycle itself.Recent applications include its use in feature selection,adaptive sampling strategies,and model evaluation.The evidence also shows that GeoXAI extends beyond producing feature rankings.It reveals nonlinear thresholds and interaction effects that generate deeper mechanistic insights into hazard processes and mechanisms.Nevertheless,several key challenges remain unresolved within the field.These persistent issues are especially pronounced when considering the crucial necessity for interpretation stability,the demanding scholarly task of reliably distinguishing correlation from causation,and the development of appropriate methods for the treatment of complex spatio-temporal dynamics.
基金supported by the National Natural Science Foundation of China(No.82360120)the Kunming Medical University Joint Special Project on Applied Basic Research(202401AY070001-134),and project iGandanF-1082022-RGG049+2 种基金the Open Project of Yunnan Provincial Clinical Medical Center for Digestive System Diseases(2022LCZXXF-XH07/17)the 14th Undergraduate Scientific Research Project of Mudanjiang Medical University(2024057)Yunnan Provincial Key Laboratory of Clinical Virology(No.2023A4010403-04).
文摘Background:High-mobility group box 1(HMGB1)is a critical damage-associated molecular pattern protein that participates in diverse physiological and pathological processes.However,its relevance to the prognosis of artificial liver support therapy in patients with acute liver injury(ALF)remains unclear.Methods:Bioinformatics analyses were performed to identify HMGB1-interacting proteins and associated inflammatory signaling pathways.Peripheral blood samples were collected from ALF patients before and after artificial liver support therapy,and serum HMGB1 concentrations were quantified using ELISA.Primary mouse hepatocytes were stimulated with lipopolysaccharide(LPS)in vitro and HMGB1 expression was verified by western blot.Results:Single-cell transcriptomic profiling showed that HMGB1 is widely expressed across tissues and predominantly localized in the nucleus.In the liver,HMGB1 was primarily expressed in hepatocytes and hepatic stellate cells.STRING database analysis revealed that human HMGB1 interacts with multiple proteins,including TLR4,TP53,and BECN1.The constructed interaction network comprised 11 nodes with an average local clustering coefficient of 0.888,and the protein–protein interaction enrichment P-value was 1.42×10^(-5),indicating significant enrichment.Gene Ontology and KEGG pathway enrichment analyses demonstrated that HMGB1 is closely linked to inflammatory and injury-related signaling pathways,including the TLR and NLR pathways.Metabolomic profiling revealed significant metabolic alterations between patients with ALF and healthy controls under both positive and negative ion modes and functional analysis showed necroptosis was activated.The cell viability gradually decreased with time and dose under LPS treatment and extracellular HMGB1 was upregulated in LPS induced ALF model and patients(P<0.05).Serum HMGB1/RIPK3/MLKL levels were markedly elevated in ALF patients compared with controls(P<0.05)and progressively declined following artificial liver support therapy.Furthermore,elevated HMGB1 concentrations were positively correlated with unfavorable clinical outcomes.Conclusion:Peripheral blood HMGB1 levels are significantly increased in patients with acute liver failure,decrease following artificial liver support therapy,and are positively associated with poor clinical prognosis.
基金Science and Technology Innovation 2030 Major Project,Grant/Award Number:2023ZD0508506。
文摘Background:Artificial intelligence(AI)is transforming healthcare,demanding reevaluation of medical education.China's“New Medical Education”initiative urgently requires a standardized AI literacy framework for medical students to address fragmented standards,rapid technological evolution,and insufficient localized ethical norms.Objective:To establish a Chinese expert consensus defining core AI competencies and a multi-modal assessment framework for medical students.Methods:A multidisciplinary(including medical education,clinical medicine,medical AI,public health,and medical ethics)expert group(n=32)developed an initial competency list based on the“Knowledge-Skills-Attitude”Medical Competency Model.Two Delphi rounds(100%response rate;consensus threshold:mean≥4.0,CV≤0.25)refined the framework.Core competencies were prioritized via Analytic Hierarchy Process(AHP).The final consensus document was established after multiple expert group meetings.Results:The consensus defines AI literacy for medical students as a comprehensive attribute for integrating AI into profes-sional knowledge,clinical practice,research,and health management.It comprises a 21-item Competencies of AI Proficiency(CAIP)list across knowledge(eight indicators),skills(seven indicators),and attitude(six indicators)dimensions.Key com-petencies prioritized include understanding AI's role in multidisciplinary knowledge integration(CAIP3),identifying AI output biases(CAIP4),understanding health data governance(CAIP2),maintaining physician-led AI-assisted diagnosis(CAIP16),and identifying AI diagnostic biases(CAIP12).A multi-modal assessment framework is recommended,including paper-based/computerized tests for knowledge,situational judgment tests(SJTs)for attitudes,and objective structured clinical examinations(OSCEs)with a specific“AI Clinical Decision Conflict Scoring Scale”for skills.A multi-stage dynamic assessment system(“Pre-enrollment-Pre-clinical-Post-clinical”)is proposed for longitudinal tracking.Educational integration pathways emphasize embedding AI literacy modularly from early undergraduate years,constructing an integrated curriculum covering fundamental principles,advanced large model applications(e.g.,prompt engineering,agent development),and ethical considerations,supported by a"digital twin hospital platform."Conclusion:This consensus provides authoritative,China-specific guidance for defining and assessing medical students'AI literacy,adhering to national policies and regulations.It offers a core action framework for optimizing AI integration into medical education,fostering future healthcare professionals proficient in both AI technology and medical humanism,with a commitment to dynamic updating to adapt to evolving AI advancements.
