The presented study analyses the impact of hysteresis on the response of mechanical systems.The main objective is to determine how the hysteretic models influence the system behaviour and if they can be utilised to de...The presented study analyses the impact of hysteresis on the response of mechanical systems.The main objective is to determine how the hysteretic models influence the system behaviour and if they can be utilised to describe a damaged or a faulty system.The hysteretic models are able to describe various types of nonlinear behaviour that can reflect the wear or damage of the system components.The data obtained from these models can possibly serve as a basis for the advanced approaches,such as digital twin modelling and predictive maintenance.All the results presented in this study were obtained in the MATLAB environment.The first part of the study provides a concise review of hysteretic models and compares them under the condition of equal energy dissipation per loading cycle.The models considered include the linear,bilinear,Bouc-Wen,Wang-Wen,and generalised Bouc-Wen models.The second part focuses on the development of a mechanical model and the implementation of the mentioned hysteretic models.The stochastic modelling of the driving forces is carried out using the Kanai-Tajimi differential model.The results show that the hysteretic models noticeably influence the treated model.This is also reflected in the frequency domain.The behaviour of hysteretic systems suggests increased energy dissipation combined with the changes in stiffness of the suspension components.Among the presented models,the asymmetric models can be considered as the most suitable for further modelling of damaged systems.展开更多
While conventional FISH and IHC methods struggle to decode complex tissue heterogeneity and comprehensive molecular diagnosis due to low-throughput spatial information,spatial omics technologies enable high-throughput...While conventional FISH and IHC methods struggle to decode complex tissue heterogeneity and comprehensive molecular diagnosis due to low-throughput spatial information,spatial omics technologies enable high-throughput molecular mapping across tissue microenvironments.These technologies are emerging as transformative tools in molecular diagnostics and medical research.By integrating histopathological morphology with spatial multi-omics profiling(genome,transcriptome,epigenome,and proteome),spatial omics technologies open an avenue for understanding disease progression,therapeutic resistance mechanisms,and precise diagnosis.It particularly enhances tumor microenvironment analysis by mapping immune cell distributions and functional states,which may greatly facilitate tumor molecular subtyping,prognostic assessment,and prediction of the radiotherapy and chemotherapy efficacy.Despite the substantial advancements in spatial omics,the translation of spatial omics into clinical applications remains challenging due to robustness,efficacy,clinical validation,and cost constraints.In this review,we summarize the current progress and prospects of spatial omics technologies,particularly in medical research and diagnostic applications.展开更多
Understanding the complex plasma dynamics in ultra-intense relativistic laser-solid interactions is of fundamental importance for applications of laser-plasma-based particle accelerators,the creation of high-energy-de...Understanding the complex plasma dynamics in ultra-intense relativistic laser-solid interactions is of fundamental importance for applications of laser-plasma-based particle accelerators,the creation of high-energy-density matter,understanding planetary science,and laser-driven fusion energy.However,experimental efforts in this regime have been limited by the lack of accessibility of over-critical densities and the poor spatiotemporal resolution of conventional diagnostics.Over the last decade,the advent of femtosecond brilliant hard X-ray free-electron lasers(XFELs)has opened new horizons to overcome these limitations.Here,for the first time,we present full-scale spatiotemporal measurements of solid-density plasma dynamics,including preplasma generation with tens of nanometer scale length driven by the leading edge of a relativistic laser pulse,ultrafast heating and ionization at the main pulse arrival,the laser-driven blast wave,and transient surface return current-induced compression dynamics up to hundreds of picoseconds after interaction.These observations are enabled by utilizing a novel combination of advanced X-ray diagnostics including small-angle X-ray scattering,resonant X-ray emission spectroscopy,and propagation-based X-ray phase-contrast imaging simultaneously at the European XFEL-HED beamline station.展开更多
This article provides a short review on the importance of the detailed analysis of a Langmuir probe I-V trace in a multi-Maxwellian plasma,and discuss proper procedures analyzing Langmuir probe I-V traces in bi-Maxwel...This article provides a short review on the importance of the detailed analysis of a Langmuir probe I-V trace in a multi-Maxwellian plasma,and discuss proper procedures analyzing Langmuir probe I-V traces in bi-Maxwellian and triple-Maxwellian Electron Energy Distribution Function(EEDF)plasmas.Discus⁃sion and demonstration of procedures include the treatment of the ion saturation current,electron saturation cur⁃rent,space-charge effects on the I-V trace,and most importantly how to properly isolate and fit for each electron group present in an I-V trace reflecting a mult-Maxwellian EEDF,as well as how having a multi-Maxwellian EEDF affects the procedures of treating the ion and electron saturation currents.Shortcomings of common improp⁃er procedures are discussed and demonstrated with simulated I-V traces to show how these procedures gives false measurements.展开更多
Multimodal deep learning has emerged as a key paradigm in contemporary medical diagnostics,advancing precision medicine by enabling integration and learning from diverse data sources.The exponential growth of high-dim...Multimodal deep learning has emerged as a key paradigm in contemporary medical diagnostics,advancing precision medicine by enabling integration and learning from diverse data sources.The exponential growth of high-dimensional healthcare data,encompassing genomic,transcriptomic,and other omics profiles,as well as radiological imaging and histopathological slides,makes this approach increasingly important because,when examined separately,these data sources only offer a fragmented picture of intricate disease processes.Multimodal deep learning leverages the complementary properties of multiple data modalities to enable more accurate prognostic modeling,more robust disease characterization,and improved treatment decision-making.This review provides a comprehensive overview of the current state of multimodal deep learning approaches in medical diagnosis.We classify and examine important application domains,such as(1)radiology,where automated report generation and lesion detection are facilitated by image-text integration;(2)histopathology,where fusion models improve tumor classification and grading;and(3)multi-omics,where molecular subtypes and latent biomarkers are revealed through cross-modal learning.We provide an overview of representative research,methodological advancements,and clinical consequences for each domain.Additionally,we critically analyzed the fundamental issues preventing wider adoption,including computational complexity(particularly in training scalable,multi-branch networks),data heterogeneity(resulting from modality-specific noise,resolution variations,and inconsistent annotations),and the challenge of maintaining significant cross-modal correlations during fusion.These problems impede interpretability,which is crucial for clinical trust and use,in addition to performance and generalizability.Lastly,we outline important areas for future research,including the development of standardized protocols for harmonizing data,the creation of lightweight and interpretable fusion architectures,the integration of real-time clinical decision support systems,and the promotion of cooperation for federated multimodal learning.Our goal is to provide researchers and clinicians with a concise overview of the field’s present state,enduring constraints,and exciting directions for further research through this review.展开更多
In a recent case report in the World Journal of Clinical Cases,emphasized the crucial role of rapidly and accurately identifying pathogens to optimize patient treatment outcomes.Laboratory-on-a-chip(LOC)technology has...In a recent case report in the World Journal of Clinical Cases,emphasized the crucial role of rapidly and accurately identifying pathogens to optimize patient treatment outcomes.Laboratory-on-a-chip(LOC)technology has emerged as a transformative tool in health care,offering rapid,sensitive,and specific identification of microorganisms.This editorial provides a comprehensive overview of LOC technology,highlighting its principles,advantages,applications,challenges,and future directions.Success studies from the field have demonstrated the practical benefits of LOC devices in clinical diagnostics,epidemiology,and food safety.Comparative studies have underscored the superiority of LOC technology over traditional methods,showcasing improvements in speed,accuracy,and portability.The future integration of LOC with biosensors,artificial intelligence,and data analytics promises further innovation and expansion.This call to action emphasizes the importance of continued research,investment,and adoption to realize the full potential of LOC technology in improving healthcare outcomes worldwide.展开更多
Artificial Intelligence(AI)is fundamentally transforming medical diagnostics,driving advancements that enhance accuracy,efficiency,and personalized patient care.This narrative review explores AI integration across var...Artificial Intelligence(AI)is fundamentally transforming medical diagnostics,driving advancements that enhance accuracy,efficiency,and personalized patient care.This narrative review explores AI integration across various diagnostic domains,emphasizing its role in improving clinical decision-making.The evolution of medical diagnostics from traditional observational methods to sophisticated imaging,laboratory tests,and molecular diagnostics lays the foundation for understanding AI’s impact.Modern diagnostics are inherently complex,influenced by multifactorial disease presentations,patient variability,cognitive biases,and systemic factors like data overload and interdisciplinary collaboration.AI-enhanced clinical decision support systems utilize both knowledge-based and non-knowledge-based approaches,employing machine learning and deep learning algorithms to analyze vast datasets,identify patterns,and generate accurate differential diagnoses.AI’s potential in diagnostics is demonstrated through applications in genomics,predictive analytics,and early disease detection,with successful case studies in oncology,radiology,pathology,ophthalmology,dermatology,gastroenterology,and psychiatry.These applications demonstrate AI’s ability to process complex medical data,facilitate early intervention,and extend specialized care to underserved populations.However,integrating AI into diagnostics faces significant limitations,including technical challenges related to data quality and system integration,regulatory hurdles,ethical concerns about transparency and bias,and risks of misinformation and overreliance.Addressing these challenges requires robust regulatory frameworks,ethical guidelines,and continuous advancements in AI technology.The future of AI in diagnostics promises further innovations in multimodal AI,genomic data integration,and expanding access to high-quality diagnostic services globally.Responsible and ethical implementation of AI will be crucial to fully realize its potential,ensuring AI serves as a powerful ally in achieving diagnostic excellence and improving global health care outcomes.This narrative review emphasizes AI’s pivotal role in shaping the future of medical diagnostics,advocating for sustained investment and collaborative efforts to harness its benefits effectively.展开更多
Electrochemical impedance spectroscopy(EIS)offers valuable insights into the dynamic behaviors of lithium-ion batteries,making it a powerful and non-invasive tool for evaluating battery health.However,EIS falls short ...Electrochemical impedance spectroscopy(EIS)offers valuable insights into the dynamic behaviors of lithium-ion batteries,making it a powerful and non-invasive tool for evaluating battery health.However,EIS falls short in quantitatively determining the degree of specific degradation modes,which are essential for improving battery lifespan.This study introduces a novel approach employing deep neural networks enhanced by an attention mechanism to identify the degree of degradation modes.The proposed method can automatically determine the most relevant frequency ranges for each degradation mode,which can link impedance characteristics to battery degradation.To overcome the limitation of scarce labeled experimental data,simulation results derived from mechanistic models are incorporated into the model.Validation results demonstrate that the proposed method could achieve root mean square errors below 3%for estimating loss of lithium inventory and loss of active material of the positive electrode,and below 4%for estimating loss of active material of the negative electrode while requiring only 25%of early-stage experimental degradation data.By integrating simulation results,the proposed method achieves a reduction in maximum estimation error ranging from 42.92%to 66.30%across different temperatures and operating conditions compared to the baseline model trained solely on experimental data.展开更多
In Unani medicine,Bawl(urine)is recognized as a key diagnostic tool,with humoural imbalances assessed via parameters like color,consistency,sediment,clarity,froth,odor,and volume.This conceptual review explores how th...In Unani medicine,Bawl(urine)is recognized as a key diagnostic tool,with humoural imbalances assessed via parameters like color,consistency,sediment,clarity,froth,odor,and volume.This conceptual review explores how these classical diagnostic indicators may be contextualized alongside modern urinalysis markers(e.g.,bilirubin,protein,ketones,and sedimentation)and examined through emerging artificial intelligence(AI)frameworks.Potential applications include ResNet-18 for color classification,You Only Look Once version 8(YOLOv8)for sediment detection,long short-term memory(LSTM)for viscosity estimation,and EfficientDet for froth analysis,with standardized urine images/videos forming the basis of future datasets.Additionally,a comparative ontology is proposed to align Unani perspectives with diagnostic approaches in traditional Chinese medicine,encouraging cross-system integration.By synthesizing classical epistemology with computational intelligence,this review highlights pathways for developing AI-based decision support systems to promote personalized,accessible,and telemedicine-enabled healthcare.展开更多
Accurate real-time monitoring of internal temperature in lithium-ion batteries remains critical for preventing thermal runaway,as conventional approaches sacrifice either computational efficiency or cross-scenario rob...Accurate real-time monitoring of internal temperature in lithium-ion batteries remains critical for preventing thermal runaway,as conventional approaches sacrifice either computational efficiency or cross-scenario robustness.We present a generalized fuzzy physics-informed framework that distills thermally sensitive electrochemical processes while circumventing redundant physical constraints,thereby establishing an explicit mechanism-constrained mapping between frequency-domain signals and internal temperature.This framework facilitates online thermal estimation,with dynamic validations in LiFePO_4/graphite 18650-type cells confirming real-time capability with near-instantaneous acquisition(~6 s per measurement),exceptional accuracy(±0.5℃) within the operational temperature range(30-50℃),and operational resilience across 20 %-80 % state-of-charge.The framework maintains predictive fidelity(±1.0℃ at 30℃ and ±4.0℃ at 60℃,95 % prediction intervals) across 80 %-100 % state-of-health while demonstrating adaptability to cathode materials and structural architectures.This strategy resolves the competing imperatives of physical interpretability,computational efficiency,and crossscenario generalizability,offering a universal paradigm for embedded thermal management in safetycritical applications.展开更多
As a critical technology for industrial system reliability and safety,machine monitoring and fault diagnostics have advanced transformatively with large language models(LLMs).This paper reviews LLM-based monitoring an...As a critical technology for industrial system reliability and safety,machine monitoring and fault diagnostics have advanced transformatively with large language models(LLMs).This paper reviews LLM-based monitoring and diagnostics methodologies,categorizing them into in-context learning,fine-tuning,retrievalaugmented generation,multimodal learning,and time series approaches,analyzing advances in diagnostics and decision support.It identifies bottlenecks like limited industrial data and edge deployment issues,proposing a three-stage roadmap to highlight LLMs’potential in shaping adaptive,interpretable PHM frameworks.展开更多
Background:Head and neck cancers(HNC)account for a significant global health burden,with increasing incidence rates and complex treatment requirements.Traditional diagnostic and therapeutic approaches,while effective,...Background:Head and neck cancers(HNC)account for a significant global health burden,with increasing incidence rates and complex treatment requirements.Traditional diagnostic and therapeutic approaches,while effective,often result in substantial morbidity and limitations in personalized care.This review provides a comprehensive overview of the latest innovations in diagnostics and therapeutic strategies for HNC from 2015 to 2024.Methods:A review of literature focused on pe-reviewed journals,clinical trial databases,and oncology conference proceedings.Key areas include molecular diagnostics,imaging technologies,minimally invasive surgeries,and innovative therapeutic strategies.Results:Technologies like liquid biopsy next-generation sequencing(NGS)have greatly improved diagnostic accuracy and personalization in HNC care.These advancements have improved survival rates and enhanced patients’quality of life.Personalized therapeutic approaches,including immune checkpoint inhibitors,precision radiation therapy,and surgery,have led to enhanced treatment efficacy while reducing side effects.The integration of AI and machine learning into diagnostics and treatment planning shows promise in optimizing clinical decision-making and predicting treatment outcomes.Conclusion:The current innovations in diagnostics and therapeutics are reshaping the management of head and neck cancer,offering more tailored and effective approaches to care.Overall,the continuous integration of these innovations in clinical practice is reshaping HNC treatment and improving patient outcomes and survival rates.Future research should focus on further refining these technologies,addressing challenges related to accessibility,and exploring their long-term clinical benefits in diverse patient populations.展开更多
Radiation doses to patients in diagnostics and interventional radiology need to be optimized to comply with the principles of radiation protection in medical practice. This involves using specific detectors with respe...Radiation doses to patients in diagnostics and interventional radiology need to be optimized to comply with the principles of radiation protection in medical practice. This involves using specific detectors with respective diagnostic beams to carry out quality control/quality assurance tests needed to optimize patient doses in the hospital. Semiconductor detectors are used in dosimetry to verify the equipment performance and dose to patients. This work aims to assess the performance, energy dependence, and response of five commercially available semiconductor detectors in RQR, RQR-M, RQA, and RQT at Secondary Standard Dosimetry for clinical applications. The diagnostic beams were generated using Exradin A4 reference ion chamber and PTW electrometer. The ambient temperature and pressure were noted for KTP correction. The detectors designed for RQR showed good performance in RQT beams and vice versa. The detectors designed for RQR-M displayed high energy dependency in other diagnostic beams. The type of diagnostic beam quality determines the response of semiconductor detectors. Therefore, a detector should be calibrated according to the beam qualities to be measured.展开更多
With the rapid development of science and technology,the application of artificial intelligence(AI)technology in medical education has become increasingly widespread in the digital age,bringing new opportunities and c...With the rapid development of science and technology,the application of artificial intelligence(AI)technology in medical education has become increasingly widespread in the digital age,bringing new opportunities and challenges to China’s higher education of traditional Chinese medicine(TCM).In the context of digital education,it is of great significance to construct a teaching model that integrates AI technology with the characteristics of the diagnostics of traditional Chinese medicine,in order to improve the quality of curriculum teaching in the future.This article aims to introduce how to organically integrate AI technology with diagnostics of traditional Chinese medicine teaching based on the characteristics of the discipline,to achieve teaching mode reform,therefore to improve the teaching quality of traditional Chinese medicine education,and cultivate high-quality TCM talents that meet the needs of the new era.展开更多
基金supported by projects KEGA,Nos.002ŽU-4/2023,and 005ŽU-4/2024,and by the project VEGA,No.1/0423/23.
文摘The presented study analyses the impact of hysteresis on the response of mechanical systems.The main objective is to determine how the hysteretic models influence the system behaviour and if they can be utilised to describe a damaged or a faulty system.The hysteretic models are able to describe various types of nonlinear behaviour that can reflect the wear or damage of the system components.The data obtained from these models can possibly serve as a basis for the advanced approaches,such as digital twin modelling and predictive maintenance.All the results presented in this study were obtained in the MATLAB environment.The first part of the study provides a concise review of hysteretic models and compares them under the condition of equal energy dissipation per loading cycle.The models considered include the linear,bilinear,Bouc-Wen,Wang-Wen,and generalised Bouc-Wen models.The second part focuses on the development of a mechanical model and the implementation of the mentioned hysteretic models.The stochastic modelling of the driving forces is carried out using the Kanai-Tajimi differential model.The results show that the hysteretic models noticeably influence the treated model.This is also reflected in the frequency domain.The behaviour of hysteretic systems suggests increased energy dissipation combined with the changes in stiffness of the suspension components.Among the presented models,the asymmetric models can be considered as the most suitable for further modelling of damaged systems.
基金supported by the National Natural Science Foundation of China(32171022,32221005,and 32401246).
文摘While conventional FISH and IHC methods struggle to decode complex tissue heterogeneity and comprehensive molecular diagnosis due to low-throughput spatial information,spatial omics technologies enable high-throughput molecular mapping across tissue microenvironments.These technologies are emerging as transformative tools in molecular diagnostics and medical research.By integrating histopathological morphology with spatial multi-omics profiling(genome,transcriptome,epigenome,and proteome),spatial omics technologies open an avenue for understanding disease progression,therapeutic resistance mechanisms,and precise diagnosis.It particularly enhances tumor microenvironment analysis by mapping immune cell distributions and functional states,which may greatly facilitate tumor molecular subtyping,prognostic assessment,and prediction of the radiotherapy and chemotherapy efficacy.Despite the substantial advancements in spatial omics,the translation of spatial omics into clinical applications remains challenging due to robustness,efficacy,clinical validation,and cost constraints.In this review,we summarize the current progress and prospects of spatial omics technologies,particularly in medical research and diagnostic applications.
基金funding from Grant No. HIDSS-0002 DASHH (Data Science in Hamburg-Helmholtz Graduate School for the Structure of Matter)partially supported by the Helmholtz Imaging platform through the project “Smart Phase.”
文摘Understanding the complex plasma dynamics in ultra-intense relativistic laser-solid interactions is of fundamental importance for applications of laser-plasma-based particle accelerators,the creation of high-energy-density matter,understanding planetary science,and laser-driven fusion energy.However,experimental efforts in this regime have been limited by the lack of accessibility of over-critical densities and the poor spatiotemporal resolution of conventional diagnostics.Over the last decade,the advent of femtosecond brilliant hard X-ray free-electron lasers(XFELs)has opened new horizons to overcome these limitations.Here,for the first time,we present full-scale spatiotemporal measurements of solid-density plasma dynamics,including preplasma generation with tens of nanometer scale length driven by the leading edge of a relativistic laser pulse,ultrafast heating and ionization at the main pulse arrival,the laser-driven blast wave,and transient surface return current-induced compression dynamics up to hundreds of picoseconds after interaction.These observations are enabled by utilizing a novel combination of advanced X-ray diagnostics including small-angle X-ray scattering,resonant X-ray emission spectroscopy,and propagation-based X-ray phase-contrast imaging simultaneously at the European XFEL-HED beamline station.
文摘This article provides a short review on the importance of the detailed analysis of a Langmuir probe I-V trace in a multi-Maxwellian plasma,and discuss proper procedures analyzing Langmuir probe I-V traces in bi-Maxwellian and triple-Maxwellian Electron Energy Distribution Function(EEDF)plasmas.Discus⁃sion and demonstration of procedures include the treatment of the ion saturation current,electron saturation cur⁃rent,space-charge effects on the I-V trace,and most importantly how to properly isolate and fit for each electron group present in an I-V trace reflecting a mult-Maxwellian EEDF,as well as how having a multi-Maxwellian EEDF affects the procedures of treating the ion and electron saturation currents.Shortcomings of common improp⁃er procedures are discussed and demonstrated with simulated I-V traces to show how these procedures gives false measurements.
文摘Multimodal deep learning has emerged as a key paradigm in contemporary medical diagnostics,advancing precision medicine by enabling integration and learning from diverse data sources.The exponential growth of high-dimensional healthcare data,encompassing genomic,transcriptomic,and other omics profiles,as well as radiological imaging and histopathological slides,makes this approach increasingly important because,when examined separately,these data sources only offer a fragmented picture of intricate disease processes.Multimodal deep learning leverages the complementary properties of multiple data modalities to enable more accurate prognostic modeling,more robust disease characterization,and improved treatment decision-making.This review provides a comprehensive overview of the current state of multimodal deep learning approaches in medical diagnosis.We classify and examine important application domains,such as(1)radiology,where automated report generation and lesion detection are facilitated by image-text integration;(2)histopathology,where fusion models improve tumor classification and grading;and(3)multi-omics,where molecular subtypes and latent biomarkers are revealed through cross-modal learning.We provide an overview of representative research,methodological advancements,and clinical consequences for each domain.Additionally,we critically analyzed the fundamental issues preventing wider adoption,including computational complexity(particularly in training scalable,multi-branch networks),data heterogeneity(resulting from modality-specific noise,resolution variations,and inconsistent annotations),and the challenge of maintaining significant cross-modal correlations during fusion.These problems impede interpretability,which is crucial for clinical trust and use,in addition to performance and generalizability.Lastly,we outline important areas for future research,including the development of standardized protocols for harmonizing data,the creation of lightweight and interpretable fusion architectures,the integration of real-time clinical decision support systems,and the promotion of cooperation for federated multimodal learning.Our goal is to provide researchers and clinicians with a concise overview of the field’s present state,enduring constraints,and exciting directions for further research through this review.
文摘In a recent case report in the World Journal of Clinical Cases,emphasized the crucial role of rapidly and accurately identifying pathogens to optimize patient treatment outcomes.Laboratory-on-a-chip(LOC)technology has emerged as a transformative tool in health care,offering rapid,sensitive,and specific identification of microorganisms.This editorial provides a comprehensive overview of LOC technology,highlighting its principles,advantages,applications,challenges,and future directions.Success studies from the field have demonstrated the practical benefits of LOC devices in clinical diagnostics,epidemiology,and food safety.Comparative studies have underscored the superiority of LOC technology over traditional methods,showcasing improvements in speed,accuracy,and portability.The future integration of LOC with biosensors,artificial intelligence,and data analytics promises further innovation and expansion.This call to action emphasizes the importance of continued research,investment,and adoption to realize the full potential of LOC technology in improving healthcare outcomes worldwide.
文摘Artificial Intelligence(AI)is fundamentally transforming medical diagnostics,driving advancements that enhance accuracy,efficiency,and personalized patient care.This narrative review explores AI integration across various diagnostic domains,emphasizing its role in improving clinical decision-making.The evolution of medical diagnostics from traditional observational methods to sophisticated imaging,laboratory tests,and molecular diagnostics lays the foundation for understanding AI’s impact.Modern diagnostics are inherently complex,influenced by multifactorial disease presentations,patient variability,cognitive biases,and systemic factors like data overload and interdisciplinary collaboration.AI-enhanced clinical decision support systems utilize both knowledge-based and non-knowledge-based approaches,employing machine learning and deep learning algorithms to analyze vast datasets,identify patterns,and generate accurate differential diagnoses.AI’s potential in diagnostics is demonstrated through applications in genomics,predictive analytics,and early disease detection,with successful case studies in oncology,radiology,pathology,ophthalmology,dermatology,gastroenterology,and psychiatry.These applications demonstrate AI’s ability to process complex medical data,facilitate early intervention,and extend specialized care to underserved populations.However,integrating AI into diagnostics faces significant limitations,including technical challenges related to data quality and system integration,regulatory hurdles,ethical concerns about transparency and bias,and risks of misinformation and overreliance.Addressing these challenges requires robust regulatory frameworks,ethical guidelines,and continuous advancements in AI technology.The future of AI in diagnostics promises further innovations in multimodal AI,genomic data integration,and expanding access to high-quality diagnostic services globally.Responsible and ethical implementation of AI will be crucial to fully realize its potential,ensuring AI serves as a powerful ally in achieving diagnostic excellence and improving global health care outcomes.This narrative review emphasizes AI’s pivotal role in shaping the future of medical diagnostics,advocating for sustained investment and collaborative efforts to harness its benefits effectively.
基金supported by the National Key R&D Program of China(2024YFB2505003).
文摘Electrochemical impedance spectroscopy(EIS)offers valuable insights into the dynamic behaviors of lithium-ion batteries,making it a powerful and non-invasive tool for evaluating battery health.However,EIS falls short in quantitatively determining the degree of specific degradation modes,which are essential for improving battery lifespan.This study introduces a novel approach employing deep neural networks enhanced by an attention mechanism to identify the degree of degradation modes.The proposed method can automatically determine the most relevant frequency ranges for each degradation mode,which can link impedance characteristics to battery degradation.To overcome the limitation of scarce labeled experimental data,simulation results derived from mechanistic models are incorporated into the model.Validation results demonstrate that the proposed method could achieve root mean square errors below 3%for estimating loss of lithium inventory and loss of active material of the positive electrode,and below 4%for estimating loss of active material of the negative electrode while requiring only 25%of early-stage experimental degradation data.By integrating simulation results,the proposed method achieves a reduction in maximum estimation error ranging from 42.92%to 66.30%across different temperatures and operating conditions compared to the baseline model trained solely on experimental data.
文摘In Unani medicine,Bawl(urine)is recognized as a key diagnostic tool,with humoural imbalances assessed via parameters like color,consistency,sediment,clarity,froth,odor,and volume.This conceptual review explores how these classical diagnostic indicators may be contextualized alongside modern urinalysis markers(e.g.,bilirubin,protein,ketones,and sedimentation)and examined through emerging artificial intelligence(AI)frameworks.Potential applications include ResNet-18 for color classification,You Only Look Once version 8(YOLOv8)for sediment detection,long short-term memory(LSTM)for viscosity estimation,and EfficientDet for froth analysis,with standardized urine images/videos forming the basis of future datasets.Additionally,a comparative ontology is proposed to align Unani perspectives with diagnostic approaches in traditional Chinese medicine,encouraging cross-system integration.By synthesizing classical epistemology with computational intelligence,this review highlights pathways for developing AI-based decision support systems to promote personalized,accessible,and telemedicine-enabled healthcare.
基金supported by the National Natural Science Foundation of China (Grant No.22109008)。
文摘Accurate real-time monitoring of internal temperature in lithium-ion batteries remains critical for preventing thermal runaway,as conventional approaches sacrifice either computational efficiency or cross-scenario robustness.We present a generalized fuzzy physics-informed framework that distills thermally sensitive electrochemical processes while circumventing redundant physical constraints,thereby establishing an explicit mechanism-constrained mapping between frequency-domain signals and internal temperature.This framework facilitates online thermal estimation,with dynamic validations in LiFePO_4/graphite 18650-type cells confirming real-time capability with near-instantaneous acquisition(~6 s per measurement),exceptional accuracy(±0.5℃) within the operational temperature range(30-50℃),and operational resilience across 20 %-80 % state-of-charge.The framework maintains predictive fidelity(±1.0℃ at 30℃ and ±4.0℃ at 60℃,95 % prediction intervals) across 80 %-100 % state-of-health while demonstrating adaptability to cathode materials and structural architectures.This strategy resolves the competing imperatives of physical interpretability,computational efficiency,and crossscenario generalizability,offering a universal paradigm for embedded thermal management in safetycritical applications.
文摘As a critical technology for industrial system reliability and safety,machine monitoring and fault diagnostics have advanced transformatively with large language models(LLMs).This paper reviews LLM-based monitoring and diagnostics methodologies,categorizing them into in-context learning,fine-tuning,retrievalaugmented generation,multimodal learning,and time series approaches,analyzing advances in diagnostics and decision support.It identifies bottlenecks like limited industrial data and edge deployment issues,proposing a three-stage roadmap to highlight LLMs’potential in shaping adaptive,interpretable PHM frameworks.
文摘Background:Head and neck cancers(HNC)account for a significant global health burden,with increasing incidence rates and complex treatment requirements.Traditional diagnostic and therapeutic approaches,while effective,often result in substantial morbidity and limitations in personalized care.This review provides a comprehensive overview of the latest innovations in diagnostics and therapeutic strategies for HNC from 2015 to 2024.Methods:A review of literature focused on pe-reviewed journals,clinical trial databases,and oncology conference proceedings.Key areas include molecular diagnostics,imaging technologies,minimally invasive surgeries,and innovative therapeutic strategies.Results:Technologies like liquid biopsy next-generation sequencing(NGS)have greatly improved diagnostic accuracy and personalization in HNC care.These advancements have improved survival rates and enhanced patients’quality of life.Personalized therapeutic approaches,including immune checkpoint inhibitors,precision radiation therapy,and surgery,have led to enhanced treatment efficacy while reducing side effects.The integration of AI and machine learning into diagnostics and treatment planning shows promise in optimizing clinical decision-making and predicting treatment outcomes.Conclusion:The current innovations in diagnostics and therapeutics are reshaping the management of head and neck cancer,offering more tailored and effective approaches to care.Overall,the continuous integration of these innovations in clinical practice is reshaping HNC treatment and improving patient outcomes and survival rates.Future research should focus on further refining these technologies,addressing challenges related to accessibility,and exploring their long-term clinical benefits in diverse patient populations.
文摘Radiation doses to patients in diagnostics and interventional radiology need to be optimized to comply with the principles of radiation protection in medical practice. This involves using specific detectors with respective diagnostic beams to carry out quality control/quality assurance tests needed to optimize patient doses in the hospital. Semiconductor detectors are used in dosimetry to verify the equipment performance and dose to patients. This work aims to assess the performance, energy dependence, and response of five commercially available semiconductor detectors in RQR, RQR-M, RQA, and RQT at Secondary Standard Dosimetry for clinical applications. The diagnostic beams were generated using Exradin A4 reference ion chamber and PTW electrometer. The ambient temperature and pressure were noted for KTP correction. The detectors designed for RQR showed good performance in RQT beams and vice versa. The detectors designed for RQR-M displayed high energy dependency in other diagnostic beams. The type of diagnostic beam quality determines the response of semiconductor detectors. Therefore, a detector should be calibrated according to the beam qualities to be measured.
文摘With the rapid development of science and technology,the application of artificial intelligence(AI)technology in medical education has become increasingly widespread in the digital age,bringing new opportunities and challenges to China’s higher education of traditional Chinese medicine(TCM).In the context of digital education,it is of great significance to construct a teaching model that integrates AI technology with the characteristics of the diagnostics of traditional Chinese medicine,in order to improve the quality of curriculum teaching in the future.This article aims to introduce how to organically integrate AI technology with diagnostics of traditional Chinese medicine teaching based on the characteristics of the discipline,to achieve teaching mode reform,therefore to improve the teaching quality of traditional Chinese medicine education,and cultivate high-quality TCM talents that meet the needs of the new era.
