The effective early warning of surrounding rock mass deformation is crucial in geotechnical engineering for ensuring the safety and stability of underground constructions.This study introduces a novel risk early warni...The effective early warning of surrounding rock mass deformation is crucial in geotechnical engineering for ensuring the safety and stability of underground constructions.This study introduces a novel risk early warning model based on multi-parameter fuzzy comprehensive evaluation,which quantitatively assesses the risk state of the surrounding rock mass.The microseismic(MS)monitoring system is set up for the underground powerhouse.The spatial and temporal distribution of MS events and the frequency characteristics of MS signals are analyzed during the top arch excavation.The early warning indices for characterizing MS spatial aggregation and frequency-energy dispersion are proposed based on the octree theory to assess the deformation of the surrounding rock mass.The risk warning model for the surrounding rock mass in underground engineering is developed through the integration of the formulated index and the frequency characteristics of MS signals.The results indicate that the multiparameter fuzzy comprehensive assessment model can achieve three-dimensional visualization of risk warnings for the surrounding rock mass.The quantitative results regarding warning time and potential deformation areas are highly consistent with the characteristics of MS precursors.These research results can provide an important reference for early warning of surrounding rock mass risk in similar underground projects.展开更多
Background:Despite the promise shown by large language models(LLMs)for standardized tasks,their multidimensional performance in real-world oncology decision-making remains unevaluated.This study aims to introduce a fr...Background:Despite the promise shown by large language models(LLMs)for standardized tasks,their multidimensional performance in real-world oncology decision-making remains unevaluated.This study aims to introduce a framework for evaluating LLMs and physician decisions in challenging lung cancer cases.Methods:We curated 50 challenging lung cancer cases(25 local and 25 published)classified as complex,rare,or refractory.Blinded three-dimensional,five-point Likert evaluations(1–5 for comprehensiveness,specificity,and readability)compared standalone LLMs(DeepSeek R1,Claude 3.5,Gemini 1.5,and GPT-4o),physicians by experience level(junior,intermediate,and senior),and AI-assisted juniors;intergroup differences and augmentation effects were analyzed statistically.Results:Of 50 challenging cases(18 complex,17 rare,and 15 refractory)rated by three experts,DeepSeek R1 achieved scores of 3.95±0.33,3.71±0.53,and 4.26±0.18 for comprehensiveness,specificity,and readability,respectively,positioning it between intermediate(3.68,3.68,3.75)and senior(4.50,4.64,4.53)physicians.GPT-4o and Claude 3.5 reached intermediate physician–level comprehensiveness(3.76±0.39,3.60±0.39)but junior-to-intermediate physician–level specificity(3.39±0.39,3.39±0.49).All LLMs scored higher on rare cases than intermediate physicians but fell below junior physicians in refractory-case specificity.AIassisted junior physicians showed marked gains in rare cases,with comprehensiveness rising from 2.32 to 4.29(84.8%),specificity from 2.24 to 4.26(90.8%),and readability from 2.76 to 4.59(66.0%),while specificity declined by 3.2%(3.17 to 3.07)in refractory cases.Error analysis showed complementary strengths,with physicians demonstrating reasoning stability and LLMs excelling in knowledge updating and risk management.Conclusions:LLMs performed variably in clinical decision-making tasks depending on case type,performing better in rare cases and worse in refractory cases requiring longitudinal reasoning.Complementary strengths between LLMs and physicians support case-and task-tailored human–AI collaboration.展开更多
Environmental problems are intensifying due to the rapid growth of the population,industry,and urban infrastructure.This expansion has resulted in increased air and water pollution,intensified urban heat island effect...Environmental problems are intensifying due to the rapid growth of the population,industry,and urban infrastructure.This expansion has resulted in increased air and water pollution,intensified urban heat island effects,and greater runoff from parks and other green spaces.Addressing these challenges requires prioritizing green infrastructure and other sustainable urban development strategies.This study introduces a novel Integrated Decision Support System that combines Pythagorean Fuzzy Sets with the Advanced Alternative Ranking Order Method allowing for Two-Step Normalization(AAROM-TN),enhanced by a dual weighting strategy.The weighting approach integrates the Criteria Importance Through Intercriteria Correlation(CRITIC)method with the Criteria Importance through Means and Standard Deviation(CIMAS)technique.The originality of the proposed framework lies in its ability to objectively quantify criteria importance using CRITIC,incorporate decision-makers’preferences through CIMAS,and capture the uncertainty and hesitation inherent in human judgment via Pythagorean Fuzzy Sets.A case study evaluating green infrastructure alternatives in metropolitan regions demonstrates the applicability and effectiveness of the framework.A sensitivity analysis is conducted to examine how variations in criteria weights affect the rankings and to evaluate the robustness of the results.Furthermore,a comparative analysis highlights the practical and financial implications of each alternative by assessing their respective strengths and weaknesses.展开更多
With the rapid development of artificial intelligence,intelligent air combat maneuver decision-making(ACMD)has garnered global attention.Although deep reinforcement learning provides a promising approach to ACMD,exist...With the rapid development of artificial intelligence,intelligent air combat maneuver decision-making(ACMD)has garnered global attention.Although deep reinforcement learning provides a promising approach to ACMD,existing methods often suffer from rigid reward functions and limited adaptability to evolving adversarial strategies.Moreover,most research assumes open airspace,overlooking the influence of potential obstacles.In this paper,we address one-on-one within-visual-range ACMD in obstructed environments,and propose an improved Soft Actor-Critic(SAC)algorithm trained under a curriculum self-play framework.A maneuver strategy mirroring inference module is integrated to estimate each other's likely positions when visual obstruction occurs.By leveraging curriculum learning to guide progressive experience accumulation and self-play for adversarial evolution,our method enhances both training efficiency and tactical diversity.We further integrate an attention mechanism that dynamically adjusts the weights of sub-rewards,enabling the learned policy to adapt to rapidly changing air combat situations.Numerical simulations demonstrate that our enhanced SAC converges more quickly and achieves higher win rates than other baseline methods.An animation is available at bilibili.com/video/BV1BHVszHE98 for better illustration.展开更多
With the increasing complexity of industrial automation,planetary gearboxes play a vital role in largescale equipment transmission systems,directly impacting operational efficiency and safety.Traditional maintenance s...With the increasing complexity of industrial automation,planetary gearboxes play a vital role in largescale equipment transmission systems,directly impacting operational efficiency and safety.Traditional maintenance strategies often struggle to accurately predict the degradation process of equipment,leading to excessive maintenance costs or potential failure risks.However,existing prediction methods based on statistical models are difficult to adapt to nonlinear degradation processes.To address these challenges,this study proposes a novel condition-based maintenance framework for planetary gearboxes.A comprehensive full-lifecycle degradation experiment was conducted to collect raw vibration signals,which were then processed using a temporal convolutional network autoencoder with multi-scale perception capability to extract deep temporal degradation features,enabling the collaborative extraction of longperiod meshing frequencies and short-term impact features from the vibration signals.Kernel principal component analysis was employed to fuse and normalize these features,enhancing the characterization of degradation progression.A nonlinear Wiener process was used to model the degradation trajectory,with a threshold decay function introduced to dynamically adjust maintenance strategies,and model parameters optimized through maximum likelihood estimation.Meanwhile,the maintenance strategy was optimized to minimize costs per unit time,determining the optimal maintenance timing and preventive maintenance threshold.The comprehensive indicator of degradation trends extracted by this method reaches 0.756,which is 41.2%higher than that of traditional time-domain features;the dynamic threshold strategy reduces the maintenance cost per unit time to 55.56,which is 8.9%better than that of the static threshold optimization.Experimental results demonstrate significant reductions in maintenance costs while enhancing system reliability and safety.This study realizes the organic integration of deep learning and reliability theory in the maintenance of planetary gearboxes,provides an interpretable solution for the predictive maintenance of complex mechanical systems,and promotes the development of condition-based maintenance strategies for planetary gearboxes.展开更多
0 INTRODUCTION Due to the sudden and highly destructive nature of slope rock collapse,developing effective early warning systems has become an urgent challenge in geotechnical engineering(Cai and Detournay,2024;Loew e...0 INTRODUCTION Due to the sudden and highly destructive nature of slope rock collapse,developing effective early warning systems has become an urgent challenge in geotechnical engineering(Cai and Detournay,2024;Loew et al.,2017).Traditional monitoring methods primarily target the acceleration stage preceding disasters(such as displacement monitoring for landslides and debris flows),which is effective for early warning of plastic collapse disasters but often inadequate for brittle failure modes(Walter et al.,2019;Chao et al.,2018;Crosta et al.,2017).展开更多
Iced transmission line galloping poses a significant threat to the safety and reliability of power systems,leading directly to line tripping,disconnections,and power outages.Existing early warning methods of iced tran...Iced transmission line galloping poses a significant threat to the safety and reliability of power systems,leading directly to line tripping,disconnections,and power outages.Existing early warning methods of iced transmission line galloping suffer from issues such as reliance on a single data source,neglect of irregular time series,and lack of attention-based closed-loop feedback,resulting in high rates of missed and false alarms.To address these challenges,we propose an Internet of Things(IoT)empowered early warning method of transmission line galloping that integrates time series data from optical fiber sensing and weather forecast.Initially,the method applies a primary adaptive weighted fusion to the IoT empowered optical fiber real-time sensing data and weather forecast data,followed by a secondary fusion based on a Back Propagation(BP)neural network,and uses the K-medoids algorithm for clustering the fused data.Furthermore,an adaptive irregular time series perception adjustment module is introduced into the traditional Gated Recurrent Unit(GRU)network,and closed-loop feedback based on attentionmechanism is employed to update network parameters through gradient feedback of the loss function,enabling closed-loop training and time series data prediction of the GRU network model.Subsequently,considering various types of prediction data and the duration of icing,an iced transmission line galloping risk coefficient is established,and warnings are categorized based on this coefficient.Finally,using an IoT-driven realistic dataset of iced transmission line galloping,the effectiveness of the proposed method is validated through multi-dimensional simulation scenarios.展开更多
The critical role of patient-reported outcome measures(PROMs)in enhancing clinical decision-making and promoting patient-centered care has gained a profound significance in scientific research.PROMs encapsulate a pati...The critical role of patient-reported outcome measures(PROMs)in enhancing clinical decision-making and promoting patient-centered care has gained a profound significance in scientific research.PROMs encapsulate a patient's health status directly from their perspective,encompassing various domains such as symptom severity,functional status,and overall quality of life.By integrating PROMs into routine clinical practice and research,healthcare providers can achieve a more nuanced understanding of patient experiences and tailor treatments accordingly.The deployment of PROMs supports dynamic patient-provider interactions,fostering better patient engagement and adherence to tre-atment plans.Moreover,PROMs are pivotal in clinical settings for monitoring disease progression and treatment efficacy,particularly in chronic and mental health conditions.However,challenges in implementing PROMs include data collection and management,integration into existing health systems,and acceptance by patients and providers.Overcoming these barriers necessitates technological advancements,policy development,and continuous education to enhance the acceptability and effectiveness of PROMs.The paper concludes with recommendations for future research and policy-making aimed at optimizing the use and impact of PROMs across healthcare settings.展开更多
In order to solve the problems of high coupling and poor scalability of the traditional monomer early warning release system architecture,multi-level deployment in a complex network environment will lead to high inves...In order to solve the problems of high coupling and poor scalability of the traditional monomer early warning release system architecture,multi-level deployment in a complex network environment will lead to high investment in software and hardware and cannot achieve intensive multi-level deployment.This paper realizes the goal of system scalability by introducing micro service architecture and technology stack and realizes the goal of resource intensification by introducing the idea of a data forwarding agent.The designed architecture scheme has been practically applied in the“Jiangxi emergency early warning information release system software platform(phase I)project”(hereinafter referred to as“provincial emergency”),which meets the needs of flexible deployment of multi-level applications across meteorological wide area network(WAN),business private network of other commissions,offices,and bureaus,government extranet,Internet and other complex networks,and fully verifies the scientificity and rationality of the scheme.It has achieved the goal of intensive and scalable construction of provincial emergencies under the complex network environment,greatly improved the early warning capacity and communication capacity of emergencies and comprehensive disasters,provided a reliable guarantee for disaster prevention and reduction,and provided a reference for the construction of current and future early warning release system and capacity improvement project.展开更多
BACKGROUND Emphysematous pyelonephritis(EPN)is a life-threatening necrotizing renal parenchyma infection characterized by gas formation due to severe bacterial infection,predominantly affecting diabetic and immunocomp...BACKGROUND Emphysematous pyelonephritis(EPN)is a life-threatening necrotizing renal parenchyma infection characterized by gas formation due to severe bacterial infection,predominantly affecting diabetic and immunocompromised patients.It carries high morbidity and mortality,requiring early diagnosis and timely intervention.Various prognostic scoring systems help in triaging critically ill patients.The National Early Warning Score 2(NEWS 2)scoring system is a widely used physiological assessment tool that evaluates clinical deterioration based on vital parameters,but its standard form lacks specificity for risk stratification in EPN,necessitating modifications to improve treatment decisionmaking and prognostic accuracy in this critical condition.AIM To highlight the need to modify the NEWS 2 score to enable more intense monitoring and better treatment outcomes.METHODS This prospective study was done on all EPN patients admitted to our hospital over the past 12 years.A weighted average risk-stratification index was calculated for each of the three groups,mortality risk was calculated for each of the NEWS 2 scores,and the need for intervention for each of the three groups was calculated.The NEWS 2 score was subsequently modified with 0-6,7-14 and 15-20 scores included in groups 1,2 and 3,respectively.RESULTS A total of 171 patients with EPN were included in the study,with a predominant association with diabetes(90.6%)and a female-to-male ratio of 1.5:1.The combined prognostic scoring of the three groups was 10.7,13.0,and 21.9,respectively(P<0.01).All patients managed conservatively belonged to group 1(P<0.01).Eight patients underwent early nephrectomy,with six from group 3(P<0.01).Overall mortality was 8(4.7%),with seven from group 3(87.5%).The cutoff NEWS 2 score for mortality was identified to be 15,with a sensitivity of 87.5%,specificity of 96.9%,and an overall accuracy rate of 96.5%.The area under the curve to predict mortality based on the NEWS 2 score was 0.98,with a confidence interval of(0.97,1.0)and P<0.001.CONCLUSION Modified NEWS 2(mNEWS 2)score dramatically aids in the appropriate assessment of treatment-related outcomes.MNEWS 2 scores should become the practice standard to reduce the morbidity and mortality associated with this dreaded illness.展开更多
To solve problems of poor security guarantee and insufficient training efficiency in the conventional reinforcement learning methods for decision-making,this study proposes a hybrid framework to combine deep reinforce...To solve problems of poor security guarantee and insufficient training efficiency in the conventional reinforcement learning methods for decision-making,this study proposes a hybrid framework to combine deep reinforcement learning with rule-based decision-making methods.A risk assessment model for lane-change maneuvers considering uncertain predictions of surrounding vehicles is established as a safety filter to improve learning efficiency while correcting dangerous actions for safety enhancement.On this basis,a Risk-fused DDQN is constructed utilizing the model-based risk assessment and supervision mechanism.The proposed reinforcement learning algorithm sets up a separate experience buffer for dangerous trials and punishes such actions,which is shown to improve the sampling efficiency and training outcomes.Compared with conventional DDQN methods,the proposed algorithm improves the convergence value of cumulated reward by 7.6%and 2.2%in the two constructed scenarios in the simulation study and reduces the number of training episodes by 52.2%and 66.8%respectively.The success rate of lane change is improved by 57.3%while the time headway is increased at least by 16.5%in real vehicle tests,which confirms the higher training efficiency,scenario adaptability,and security of the proposed Risk-fused DDQN.展开更多
The traditional academic warning methods for students in higher vocational colleges are relatively backward,single,and have many influencing factors,which have a limited effect on improving their learning ability.A da...The traditional academic warning methods for students in higher vocational colleges are relatively backward,single,and have many influencing factors,which have a limited effect on improving their learning ability.A data set was established by collecting academic warning data of students in a certain university.The importance of the school,major,grade,and warning level for the students was analyzed using the Pearson correlation coefficient,random forest variable importance,and permutation importance.It was found that the characteristic of the major has a great impact on the academic warning level.Countermeasures such as dynamic adjustment of majors,reform of cognitive adaptation of courses,full-cycle academic support,and data-driven precise intervention were proposed to provide theoretical support and practical paths for universities to improve the efficiency of academic warning and enhance students’learning ability.展开更多
Due to batteries inconsistencies and potential faults in battery management systems,slight overcharging remains a common yet insufficiently understood safety risk,lacking effective warning methods.To illuminate the de...Due to batteries inconsistencies and potential faults in battery management systems,slight overcharging remains a common yet insufficiently understood safety risk,lacking effective warning methods.To illuminate the degradation behavior and failure mechanism of various overcharged states(100%SOC,105%SOC,110%SOC,and 115%SOC),multiple advanced in-situ characterization techniques(accelerating rate calorimeter,electrochemical impedance spectroscopy,ultrasonic scanning,and expansion instrument)were utilized.Additionally,re-overcharge-induced thermal runaway(TR)tests were conducted,with a specific emphasis on the evolution of the expansion force signal.Results indicated significant degradation at 110%SOC including conductivity loss,loss of lithium inventory,and loss of active material accompanied by internal gas generation.These failure behaviors slow down the expansion force rate during reovercharging,reducing the efficacy of active warnings that depend on rate thresholds of expansion force.Specifically,the warning time for 115%SOC battery is only 144 s,which is 740 s shorter than that for fresh battery,and the time to TR is advanced by 9 min.Moreover,the initial self-heating temperature(T1)is reduced by 62.4℃compared to that of fresh battery,reaching only 70.8℃.To address the low safety of overcharged batteries,a passive overcharge warning method utilizing relaxation expansion force was proposed,based on the continued gas generation after stopping charging,leading to a sustained increase in force.Compared to active methods that rely on thresholds of expansion force rate,the passive method can issue warnings 115 s earlier.By combining the passive and active warning methods,guaranteed effective overcharge warning can be issued 863-884 s before TR.This study introduces a novel perspective for enhancing the safety of batteries.展开更多
Coating microdefects and localized corrosion in coating/metal system are inevitable,accelerating the degradation of metal infrastructure.Early evaluating coating microdefects and detecting corrosion sites are urgent y...Coating microdefects and localized corrosion in coating/metal system are inevitable,accelerating the degradation of metal infrastructure.Early evaluating coating microdefects and detecting corrosion sites are urgent yet remain challenge to achieve.Herein,we propose a robust,universal and efficient fluorescence-based strategy for hierarchical warning of coating damage and metal corrosion by introducing the concepts of damage-induced fluorescence enhancement effect(DIE)and ionic-recognition induced quenching effect(RIQ).The coatings with dualresponsiveness for coating defect and steel corrosion are constructed by incorporating synthesized nanoprobes composed of metal organic frameworks(Ni–Zn-MOFs)loaded with Rhodamine B(RhB@MOFs).The initial damage to the coating causes an immediate intensification of fluorescence,while the specific ionic-recognition characteristic of RhB with Fe3t results in an evident fluorescence quenching,enabling the detection of coating damage and corrosion.Importantly,this nanoprobes are insensitive to the coating matrix and exhibit stable corrosion warning capability across various coating systems.Meanwhile,electrochemical investigations indicate that the impedance values of RM/EP maintain above 10^(8)Ωcm^(2)even after 60 days of immersion.Therefore,the incorporation of fluorescent nanoprobes greatly inhibits the intrusion of electrolytes into polymer and improves the corrosion protection performance of the coating.This powerful strategy towards dual-level damage warning provides insights for the development of long-term smart protective materials.展开更多
As oil and gas exploration continues to progress into deeper and unconventional reservoirs,the likelihood of kick risk increases,making kick warning a critical factor in ensuring drilling safety and efficiency.Due to ...As oil and gas exploration continues to progress into deeper and unconventional reservoirs,the likelihood of kick risk increases,making kick warning a critical factor in ensuring drilling safety and efficiency.Due to the scarcity of kick samples,traditional supervised models perform poorly,and significant fluctuations in field data lead to high false alarm rates.This study proposes an unsupervised graph autoencoder(GAE)-based kick warning method,which effectively reduces false alarms by eliminating the influence of field engineer operations and incorporating real-time model updates.The method utilizes the GAE model to process time-series data during drilling,accurately identifying kick risk while overcoming challenges related to small sample sizes and missing features.To further reduce false alarms,the weighted dynamic time warping(WDTW)algorithm is introduced to identify fluctuations in logging data caused by field engineer operations during drilling,with real-time updates applied to prevent normal conditions from being misclassified as kick risk.Experimental results show that the GAE-based kick warning method achieves an accuracy of 92.7%and significantly reduces the false alarm rate.The GAE model continues to operate effectively even under conditions of missing features and issues kick warnings 4 min earlier than field engineers,demonstrating its high sensitivity and robustness.After integrating the WDTW algorithm and real-time updates,the false alarm rate is reduced from 17.3%to 5.6%,further improving the accuracy of kick warnings.The proposed method provides an efficient and reliable approach for kick warning in drilling operations,offering strong practical value and technical support for the intelligent management of future drilling operations.展开更多
One of the primary tasks of earthquake early warning(EEW)systems is to predict potential earthquake damage rapidly and accurately.Cumulative absolute velocity(CAV),Arias intensity(I_(A)),and spectrum intensity(SI)are ...One of the primary tasks of earthquake early warning(EEW)systems is to predict potential earthquake damage rapidly and accurately.Cumulative absolute velocity(CAV),Arias intensity(I_(A)),and spectrum intensity(SI)are important parameters for measuring ground motion intensity and assessing earthquake damage.Due to the limited available information in EEW,CAV,I_(A),and SI cannot be accurately predicted using traditional EEW methods.In this paper,we propose an end-to-end deep learning-based Ground motion Intensity prediction Network(ENGINet)for on-site EEW.The aim of the ENGINet is to predict CAV,I_(A),and SI rapidly and reliably.ENGINet is based on a convolutional neural network and recurrent neural network.The inputs of the network are three-component acceleration records,three-component velocity records,and three-component displacement records obtained by a single station.The results from the test dataset show that at 3 s after the P-wave arrival,compared with the baseline models and other traditional methods,ENGINet has better performance in predicting CAV,I_(A),and SI.Our results indicate that ENGINet can quickly and accurately predict CAV,I_(A),and SI to some extent and has good potential in EEW efforts.展开更多
Due to the numerous variables to take into account as well as the inherent ambiguity and uncertainty,evaluating educational institutions can be difficult.The concept of a possibility Pythagorean fuzzy hypersoft set(pP...Due to the numerous variables to take into account as well as the inherent ambiguity and uncertainty,evaluating educational institutions can be difficult.The concept of a possibility Pythagorean fuzzy hypersoft set(pPyFHSS)is more flexible in this regard than other theoretical fuzzy set-like models,even though some attempts have been made in the literature to address such uncertainties.This study investigates the elementary notions of pPyFHSS including its set-theoretic operations union,intersection,complement,OR-and AND-operations.Some results related to these operations are also modified for pPyFHSS.Additionally,the similarity measures between pPyFHSSs are formulated with the assistance of numerical examples and results.Lastly,an intelligent decision-assisted mechanism is developed with the proposal of a robust algorithm based on similarity measures for solving multi-attribute decision-making(MADM)problems.A case study that helps the decision-makers assess the best educational institution is discussed to validate the suggested system.The algorithmic results are compared with the most pertinent model to evaluate the adaptability of pPyFHSS,as it generalizes the classical possibility fuzzy set-like theoretical models.Similarly,while considering significant evaluating factors,the flexibility of pPyFHSS is observed through structural comparison.展开更多
Accurate medical diagnosis,which involves identifying diseases based on patient symptoms,is often hindered by uncertainties in data interpretation and retrieval.Advanced fuzzy set theories have emerged as effective to...Accurate medical diagnosis,which involves identifying diseases based on patient symptoms,is often hindered by uncertainties in data interpretation and retrieval.Advanced fuzzy set theories have emerged as effective tools to address these challenges.In this paper,new mathematical approaches for handling uncertainty in medical diagnosis are introduced using q-rung orthopair fuzzy sets(q-ROFS)and interval-valued q-rung orthopair fuzzy sets(IVq-ROFS).Three aggregation operators are proposed in our methodologies:the q-ROF weighted averaging(q-ROFWA),the q-ROF weighted geometric(q-ROFWG),and the q-ROF weighted neutrality averaging(qROFWNA),which enhance decision-making under uncertainty.These operators are paired with ranking methods such as the similarity measure,score function,and inverse score function to improve the accuracy of disease identification.Additionally,the impact of varying q-rung values is explored through a sensitivity analysis,extending the analysis beyond the typical maximum value of 3.The Basic Uncertain Information(BUI)method is employed to simulate expert opinions,and aggregation operators are used to combine these opinions in a group decisionmaking context.Our results provide a comprehensive comparison of methodologies,highlighting their strengths and limitations in diagnosing diseases based on uncertain patient data.展开更多
Background:Multiparametric magnetic resonance imaging(mpMRI)has significantly advanced prostate cancer(PCa)detection,yet decisions on invasive biopsy with moderate prostate imaging reporting and data system(PI-RADS)sc...Background:Multiparametric magnetic resonance imaging(mpMRI)has significantly advanced prostate cancer(PCa)detection,yet decisions on invasive biopsy with moderate prostate imaging reporting and data system(PI-RADS)scores remain ambiguous.Methods:To explore the decision-making capacity of Generative Pretrained Transformer-4(GPT-4)for automated prostate biopsy recommendations,we included 2299 individuals who underwent prostate biopsy from 2018 to 2023 in 3 large medical centers,with available mpMRI before biopsy and documented clinical-histopathological records.GPT-4 generated structured reports with given prompts.The performance of GPT-4 was quantified using confusion matrices,and sensitivity,specificity,as well as area under the curve were calculated.Multiple artificial evaluation procedures were conducted.Wilcoxon’s rank sum test,Fisher’s exact test,and Kruskal-Wallis tests were used for comparisons.Results:Utilizing the largest sample size in the Chinese population,patients with moderate PI-RADS scores(scores 3 and 4)accounted for 39.7%(912/2299),defined as the subset-of-interest(SOI).The detection rates of clinically significant PCa corresponding to PI-RADS scores 2-5 were 9.4%,27.3%,49.2%,and 80.1%,respectively.Nearly 47.5%(433/912)of SOI patients were histopathologically proven to have undergone unnecessary prostate biopsies.With the assistance of GPT-4,20.8%(190/912)of the SOI population could avoid unnecessary biopsies,and it performed even better[28.8%(118/410)]in the most heterogeneous subgroup of PI-RADS score 3.More than 90.0%of GPT-4-generated reports were comprehensive and easy to understand,but less satisfied with the accuracy(82.8%).GPT-4 also demonstrated cognitive potential for handling complex problems.Additionally,the Chain of Thought method enabled us to better understand the decision-making logic behind GPT-4.Eventually,we developed a ProstAIGuide platform to facilitate accessibility for both doctors and patients.Conclusions:This multi-center study highlights the clinical utility of GPT-4 for prostate biopsy decision-making and advances our understanding of the latest artificial intelligence implementation in various medical scenarios.展开更多
BACKGROUND Understanding a patient's clinical status and setting priorities for their care are two aspects of the constantly changing process of clinical decision-making.One analytical technique that can be helpfu...BACKGROUND Understanding a patient's clinical status and setting priorities for their care are two aspects of the constantly changing process of clinical decision-making.One analytical technique that can be helpful in uncertain situations is clinical judgment.Clinicians must deal with contradictory information,lack of time to make decisions,and long-term factors when emergencies occur.AIM To examine the ethical issues healthcare professionals faced during the coronavirus disease 2019(COVID-19)pandemic and the factors affecting clinical decision-making.METHODS This pilot study,which means it was a preliminary investigation to gather information and test the feasibility of a larger investigation was conducted over 6 months and we invited responses from clinicians worldwide who managed patients with COVID-19.The survey focused on topics related to their professional roles and personal relationships.We examined five core areas influencing critical care decision-making:Patients'personal factors,family-related factors,informed consent,communication and media,and hospital administrative policies on clinical decision-making.The collected data were analyzed using the χ^(2) test for categorical variables.RESULTS A total of 102 clinicians from 23 specialties and 17 countries responded to the survey.Age was a significant factor in treatment planning(n=88)and ventilator access(n=78).Sex had no bearing on how decisions were made.Most doctors reported maintaining patient confidentiality regarding privacy and informed consent.Approximately 50%of clinicians reported a moderate influence of clinical work,with many citing it as one of the most important factors affecting their health and relationships.Clinicians from developing countries had a significantly higher score for considering a patient's financial status when creating a treatment plan than their counterparts from developed countries.Regarding personal experiences,some respondents noted that treatment plans and preferences changed from wave to wave,and that there was a rapid turnover of studies and evidence.Hospital and government policies also played a role in critical decision-making.Rather than assessing the appropriateness of treatment,some doctors observed that hospital policies regarding medications were driven by patient demand.CONCLUSION Factors other than medical considerations frequently affect management choices.The disparity in treatment choices,became more apparent during the pandemic.We highlight the difficulties and contradictions between moral standards and the realities physicians encountered during this medical emergency.False information,large patient populations,and limited resources caused problems for clinicians.These factors impacted decision-making,which,in turn,affected patient care and healthcare staff well-being.展开更多
基金support from the Sichuan Science and Technology Program(Grant No.2023NSFSC0812).
文摘The effective early warning of surrounding rock mass deformation is crucial in geotechnical engineering for ensuring the safety and stability of underground constructions.This study introduces a novel risk early warning model based on multi-parameter fuzzy comprehensive evaluation,which quantitatively assesses the risk state of the surrounding rock mass.The microseismic(MS)monitoring system is set up for the underground powerhouse.The spatial and temporal distribution of MS events and the frequency characteristics of MS signals are analyzed during the top arch excavation.The early warning indices for characterizing MS spatial aggregation and frequency-energy dispersion are proposed based on the octree theory to assess the deformation of the surrounding rock mass.The risk warning model for the surrounding rock mass in underground engineering is developed through the integration of the formulated index and the frequency characteristics of MS signals.The results indicate that the multiparameter fuzzy comprehensive assessment model can achieve three-dimensional visualization of risk warnings for the surrounding rock mass.The quantitative results regarding warning time and potential deformation areas are highly consistent with the characteristics of MS precursors.These research results can provide an important reference for early warning of surrounding rock mass risk in similar underground projects.
文摘Background:Despite the promise shown by large language models(LLMs)for standardized tasks,their multidimensional performance in real-world oncology decision-making remains unevaluated.This study aims to introduce a framework for evaluating LLMs and physician decisions in challenging lung cancer cases.Methods:We curated 50 challenging lung cancer cases(25 local and 25 published)classified as complex,rare,or refractory.Blinded three-dimensional,five-point Likert evaluations(1–5 for comprehensiveness,specificity,and readability)compared standalone LLMs(DeepSeek R1,Claude 3.5,Gemini 1.5,and GPT-4o),physicians by experience level(junior,intermediate,and senior),and AI-assisted juniors;intergroup differences and augmentation effects were analyzed statistically.Results:Of 50 challenging cases(18 complex,17 rare,and 15 refractory)rated by three experts,DeepSeek R1 achieved scores of 3.95±0.33,3.71±0.53,and 4.26±0.18 for comprehensiveness,specificity,and readability,respectively,positioning it between intermediate(3.68,3.68,3.75)and senior(4.50,4.64,4.53)physicians.GPT-4o and Claude 3.5 reached intermediate physician–level comprehensiveness(3.76±0.39,3.60±0.39)but junior-to-intermediate physician–level specificity(3.39±0.39,3.39±0.49).All LLMs scored higher on rare cases than intermediate physicians but fell below junior physicians in refractory-case specificity.AIassisted junior physicians showed marked gains in rare cases,with comprehensiveness rising from 2.32 to 4.29(84.8%),specificity from 2.24 to 4.26(90.8%),and readability from 2.76 to 4.59(66.0%),while specificity declined by 3.2%(3.17 to 3.07)in refractory cases.Error analysis showed complementary strengths,with physicians demonstrating reasoning stability and LLMs excelling in knowledge updating and risk management.Conclusions:LLMs performed variably in clinical decision-making tasks depending on case type,performing better in rare cases and worse in refractory cases requiring longitudinal reasoning.Complementary strengths between LLMs and physicians support case-and task-tailored human–AI collaboration.
基金supported by the Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2026R259)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.Ashit Kumar Dutta would like to thank AlMaarefa University for supporting this research under project number MHIRSP2025017.
文摘Environmental problems are intensifying due to the rapid growth of the population,industry,and urban infrastructure.This expansion has resulted in increased air and water pollution,intensified urban heat island effects,and greater runoff from parks and other green spaces.Addressing these challenges requires prioritizing green infrastructure and other sustainable urban development strategies.This study introduces a novel Integrated Decision Support System that combines Pythagorean Fuzzy Sets with the Advanced Alternative Ranking Order Method allowing for Two-Step Normalization(AAROM-TN),enhanced by a dual weighting strategy.The weighting approach integrates the Criteria Importance Through Intercriteria Correlation(CRITIC)method with the Criteria Importance through Means and Standard Deviation(CIMAS)technique.The originality of the proposed framework lies in its ability to objectively quantify criteria importance using CRITIC,incorporate decision-makers’preferences through CIMAS,and capture the uncertainty and hesitation inherent in human judgment via Pythagorean Fuzzy Sets.A case study evaluating green infrastructure alternatives in metropolitan regions demonstrates the applicability and effectiveness of the framework.A sensitivity analysis is conducted to examine how variations in criteria weights affect the rankings and to evaluate the robustness of the results.Furthermore,a comparative analysis highlights the practical and financial implications of each alternative by assessing their respective strengths and weaknesses.
基金support of the National Key Research and Development Plan(No.2021YFB3302501)the financial support of the National Science Foundation of China(No.12161076)the financial support of the Fundamental Research Funds for the Central Universities(No.DUT25GF207).
文摘With the rapid development of artificial intelligence,intelligent air combat maneuver decision-making(ACMD)has garnered global attention.Although deep reinforcement learning provides a promising approach to ACMD,existing methods often suffer from rigid reward functions and limited adaptability to evolving adversarial strategies.Moreover,most research assumes open airspace,overlooking the influence of potential obstacles.In this paper,we address one-on-one within-visual-range ACMD in obstructed environments,and propose an improved Soft Actor-Critic(SAC)algorithm trained under a curriculum self-play framework.A maneuver strategy mirroring inference module is integrated to estimate each other's likely positions when visual obstruction occurs.By leveraging curriculum learning to guide progressive experience accumulation and self-play for adversarial evolution,our method enhances both training efficiency and tactical diversity.We further integrate an attention mechanism that dynamically adjusts the weights of sub-rewards,enabling the learned policy to adapt to rapidly changing air combat situations.Numerical simulations demonstrate that our enhanced SAC converges more quickly and achieves higher win rates than other baseline methods.An animation is available at bilibili.com/video/BV1BHVszHE98 for better illustration.
基金funded by scientific research projects under Grant JY2024B011.
文摘With the increasing complexity of industrial automation,planetary gearboxes play a vital role in largescale equipment transmission systems,directly impacting operational efficiency and safety.Traditional maintenance strategies often struggle to accurately predict the degradation process of equipment,leading to excessive maintenance costs or potential failure risks.However,existing prediction methods based on statistical models are difficult to adapt to nonlinear degradation processes.To address these challenges,this study proposes a novel condition-based maintenance framework for planetary gearboxes.A comprehensive full-lifecycle degradation experiment was conducted to collect raw vibration signals,which were then processed using a temporal convolutional network autoencoder with multi-scale perception capability to extract deep temporal degradation features,enabling the collaborative extraction of longperiod meshing frequencies and short-term impact features from the vibration signals.Kernel principal component analysis was employed to fuse and normalize these features,enhancing the characterization of degradation progression.A nonlinear Wiener process was used to model the degradation trajectory,with a threshold decay function introduced to dynamically adjust maintenance strategies,and model parameters optimized through maximum likelihood estimation.Meanwhile,the maintenance strategy was optimized to minimize costs per unit time,determining the optimal maintenance timing and preventive maintenance threshold.The comprehensive indicator of degradation trends extracted by this method reaches 0.756,which is 41.2%higher than that of traditional time-domain features;the dynamic threshold strategy reduces the maintenance cost per unit time to 55.56,which is 8.9%better than that of the static threshold optimization.Experimental results demonstrate significant reductions in maintenance costs while enhancing system reliability and safety.This study realizes the organic integration of deep learning and reliability theory in the maintenance of planetary gearboxes,provides an interpretable solution for the predictive maintenance of complex mechanical systems,and promotes the development of condition-based maintenance strategies for planetary gearboxes.
基金supported by the National Key R&D Program of China(No.2023YFC3081400)the National Natural Science Foundation of China(No.41702371)+3 种基金the Open Fund Project of State Key Laboratory of Mining Response and Disaster Prevention in Deep Coal Mines(No.SKLMRDPC22KF13)the Supported by State key Laboratory of Mining Disaster Prevention and Control(Shandong University of Science and Technology),Ministry of Education(No.DPEPM202502)the Open Fund Research Project Supported by State Key Laboratory of Strata Intelligent Control and Green Mining Co-founded by Shandong Province and the Ministry of Science and Technology(No.SICGM202503)the Fund of Chongqing Key Laboratory of Facility Damage Mechanism and Protection in Highland Mountain Environment(No.LQ24KFJJ09)。
文摘0 INTRODUCTION Due to the sudden and highly destructive nature of slope rock collapse,developing effective early warning systems has become an urgent challenge in geotechnical engineering(Cai and Detournay,2024;Loew et al.,2017).Traditional monitoring methods primarily target the acceleration stage preceding disasters(such as displacement monitoring for landslides and debris flows),which is effective for early warning of plastic collapse disasters but often inadequate for brittle failure modes(Walter et al.,2019;Chao et al.,2018;Crosta et al.,2017).
基金research was funded by Science and Technology Project of State Grid Corporation of China under grant number 5200-202319382A-2-3-XG.
文摘Iced transmission line galloping poses a significant threat to the safety and reliability of power systems,leading directly to line tripping,disconnections,and power outages.Existing early warning methods of iced transmission line galloping suffer from issues such as reliance on a single data source,neglect of irregular time series,and lack of attention-based closed-loop feedback,resulting in high rates of missed and false alarms.To address these challenges,we propose an Internet of Things(IoT)empowered early warning method of transmission line galloping that integrates time series data from optical fiber sensing and weather forecast.Initially,the method applies a primary adaptive weighted fusion to the IoT empowered optical fiber real-time sensing data and weather forecast data,followed by a secondary fusion based on a Back Propagation(BP)neural network,and uses the K-medoids algorithm for clustering the fused data.Furthermore,an adaptive irregular time series perception adjustment module is introduced into the traditional Gated Recurrent Unit(GRU)network,and closed-loop feedback based on attentionmechanism is employed to update network parameters through gradient feedback of the loss function,enabling closed-loop training and time series data prediction of the GRU network model.Subsequently,considering various types of prediction data and the duration of icing,an iced transmission line galloping risk coefficient is established,and warnings are categorized based on this coefficient.Finally,using an IoT-driven realistic dataset of iced transmission line galloping,the effectiveness of the proposed method is validated through multi-dimensional simulation scenarios.
文摘The critical role of patient-reported outcome measures(PROMs)in enhancing clinical decision-making and promoting patient-centered care has gained a profound significance in scientific research.PROMs encapsulate a patient's health status directly from their perspective,encompassing various domains such as symptom severity,functional status,and overall quality of life.By integrating PROMs into routine clinical practice and research,healthcare providers can achieve a more nuanced understanding of patient experiences and tailor treatments accordingly.The deployment of PROMs supports dynamic patient-provider interactions,fostering better patient engagement and adherence to tre-atment plans.Moreover,PROMs are pivotal in clinical settings for monitoring disease progression and treatment efficacy,particularly in chronic and mental health conditions.However,challenges in implementing PROMs include data collection and management,integration into existing health systems,and acceptance by patients and providers.Overcoming these barriers necessitates technological advancements,policy development,and continuous education to enhance the acceptability and effectiveness of PROMs.The paper concludes with recommendations for future research and policy-making aimed at optimizing the use and impact of PROMs across healthcare settings.
文摘In order to solve the problems of high coupling and poor scalability of the traditional monomer early warning release system architecture,multi-level deployment in a complex network environment will lead to high investment in software and hardware and cannot achieve intensive multi-level deployment.This paper realizes the goal of system scalability by introducing micro service architecture and technology stack and realizes the goal of resource intensification by introducing the idea of a data forwarding agent.The designed architecture scheme has been practically applied in the“Jiangxi emergency early warning information release system software platform(phase I)project”(hereinafter referred to as“provincial emergency”),which meets the needs of flexible deployment of multi-level applications across meteorological wide area network(WAN),business private network of other commissions,offices,and bureaus,government extranet,Internet and other complex networks,and fully verifies the scientificity and rationality of the scheme.It has achieved the goal of intensive and scalable construction of provincial emergencies under the complex network environment,greatly improved the early warning capacity and communication capacity of emergencies and comprehensive disasters,provided a reliable guarantee for disaster prevention and reduction,and provided a reference for the construction of current and future early warning release system and capacity improvement project.
文摘BACKGROUND Emphysematous pyelonephritis(EPN)is a life-threatening necrotizing renal parenchyma infection characterized by gas formation due to severe bacterial infection,predominantly affecting diabetic and immunocompromised patients.It carries high morbidity and mortality,requiring early diagnosis and timely intervention.Various prognostic scoring systems help in triaging critically ill patients.The National Early Warning Score 2(NEWS 2)scoring system is a widely used physiological assessment tool that evaluates clinical deterioration based on vital parameters,but its standard form lacks specificity for risk stratification in EPN,necessitating modifications to improve treatment decisionmaking and prognostic accuracy in this critical condition.AIM To highlight the need to modify the NEWS 2 score to enable more intense monitoring and better treatment outcomes.METHODS This prospective study was done on all EPN patients admitted to our hospital over the past 12 years.A weighted average risk-stratification index was calculated for each of the three groups,mortality risk was calculated for each of the NEWS 2 scores,and the need for intervention for each of the three groups was calculated.The NEWS 2 score was subsequently modified with 0-6,7-14 and 15-20 scores included in groups 1,2 and 3,respectively.RESULTS A total of 171 patients with EPN were included in the study,with a predominant association with diabetes(90.6%)and a female-to-male ratio of 1.5:1.The combined prognostic scoring of the three groups was 10.7,13.0,and 21.9,respectively(P<0.01).All patients managed conservatively belonged to group 1(P<0.01).Eight patients underwent early nephrectomy,with six from group 3(P<0.01).Overall mortality was 8(4.7%),with seven from group 3(87.5%).The cutoff NEWS 2 score for mortality was identified to be 15,with a sensitivity of 87.5%,specificity of 96.9%,and an overall accuracy rate of 96.5%.The area under the curve to predict mortality based on the NEWS 2 score was 0.98,with a confidence interval of(0.97,1.0)and P<0.001.CONCLUSION Modified NEWS 2(mNEWS 2)score dramatically aids in the appropriate assessment of treatment-related outcomes.MNEWS 2 scores should become the practice standard to reduce the morbidity and mortality associated with this dreaded illness.
基金Supported by National Key Research and Development Program of China(Grant No.2022YFE0117100)National Science Foundation of China(Grant No.52102468,52325212)Fundamental Research Funds for the Central Universities。
文摘To solve problems of poor security guarantee and insufficient training efficiency in the conventional reinforcement learning methods for decision-making,this study proposes a hybrid framework to combine deep reinforcement learning with rule-based decision-making methods.A risk assessment model for lane-change maneuvers considering uncertain predictions of surrounding vehicles is established as a safety filter to improve learning efficiency while correcting dangerous actions for safety enhancement.On this basis,a Risk-fused DDQN is constructed utilizing the model-based risk assessment and supervision mechanism.The proposed reinforcement learning algorithm sets up a separate experience buffer for dangerous trials and punishes such actions,which is shown to improve the sampling efficiency and training outcomes.Compared with conventional DDQN methods,the proposed algorithm improves the convergence value of cumulated reward by 7.6%and 2.2%in the two constructed scenarios in the simulation study and reduces the number of training episodes by 52.2%and 66.8%respectively.The success rate of lane change is improved by 57.3%while the time headway is increased at least by 16.5%in real vehicle tests,which confirms the higher training efficiency,scenario adaptability,and security of the proposed Risk-fused DDQN.
基金supported by the Basic Ability Improvement Project of Young and Middle-Aged Teachers in Colleges and Universities of Guangxi(2022KY1922,2021KY1938).
文摘The traditional academic warning methods for students in higher vocational colleges are relatively backward,single,and have many influencing factors,which have a limited effect on improving their learning ability.A data set was established by collecting academic warning data of students in a certain university.The importance of the school,major,grade,and warning level for the students was analyzed using the Pearson correlation coefficient,random forest variable importance,and permutation importance.It was found that the characteristic of the major has a great impact on the academic warning level.Countermeasures such as dynamic adjustment of majors,reform of cognitive adaptation of courses,full-cycle academic support,and data-driven precise intervention were proposed to provide theoretical support and practical paths for universities to improve the efficiency of academic warning and enhance students’learning ability.
基金supported by the National Natural Science Foundation of China(52476200,52106244)the Guangdong Basic and Applied Basic Research Foundation(2024A1515030124)+1 种基金the Science and Technology Project of China Southern Power Grid under Grant GDKJXM20230246(030100KC23020017)the Fundamental Research Funds for the Central Universities。
文摘Due to batteries inconsistencies and potential faults in battery management systems,slight overcharging remains a common yet insufficiently understood safety risk,lacking effective warning methods.To illuminate the degradation behavior and failure mechanism of various overcharged states(100%SOC,105%SOC,110%SOC,and 115%SOC),multiple advanced in-situ characterization techniques(accelerating rate calorimeter,electrochemical impedance spectroscopy,ultrasonic scanning,and expansion instrument)were utilized.Additionally,re-overcharge-induced thermal runaway(TR)tests were conducted,with a specific emphasis on the evolution of the expansion force signal.Results indicated significant degradation at 110%SOC including conductivity loss,loss of lithium inventory,and loss of active material accompanied by internal gas generation.These failure behaviors slow down the expansion force rate during reovercharging,reducing the efficacy of active warnings that depend on rate thresholds of expansion force.Specifically,the warning time for 115%SOC battery is only 144 s,which is 740 s shorter than that for fresh battery,and the time to TR is advanced by 9 min.Moreover,the initial self-heating temperature(T1)is reduced by 62.4℃compared to that of fresh battery,reaching only 70.8℃.To address the low safety of overcharged batteries,a passive overcharge warning method utilizing relaxation expansion force was proposed,based on the continued gas generation after stopping charging,leading to a sustained increase in force.Compared to active methods that rely on thresholds of expansion force rate,the passive method can issue warnings 115 s earlier.By combining the passive and active warning methods,guaranteed effective overcharge warning can be issued 863-884 s before TR.This study introduces a novel perspective for enhancing the safety of batteries.
基金support by the National Natural Science Foundation of China(52201077)the Natural Science Foundation of Shandong Province(ZR2022QE191)+1 种基金Elite Scheme of Shandong University of Science and Technology(0104060541123)Talent introduction and Research Start-up Fund of Shandong University of Science and Technology(0104060510124).
文摘Coating microdefects and localized corrosion in coating/metal system are inevitable,accelerating the degradation of metal infrastructure.Early evaluating coating microdefects and detecting corrosion sites are urgent yet remain challenge to achieve.Herein,we propose a robust,universal and efficient fluorescence-based strategy for hierarchical warning of coating damage and metal corrosion by introducing the concepts of damage-induced fluorescence enhancement effect(DIE)and ionic-recognition induced quenching effect(RIQ).The coatings with dualresponsiveness for coating defect and steel corrosion are constructed by incorporating synthesized nanoprobes composed of metal organic frameworks(Ni–Zn-MOFs)loaded with Rhodamine B(RhB@MOFs).The initial damage to the coating causes an immediate intensification of fluorescence,while the specific ionic-recognition characteristic of RhB with Fe3t results in an evident fluorescence quenching,enabling the detection of coating damage and corrosion.Importantly,this nanoprobes are insensitive to the coating matrix and exhibit stable corrosion warning capability across various coating systems.Meanwhile,electrochemical investigations indicate that the impedance values of RM/EP maintain above 10^(8)Ωcm^(2)even after 60 days of immersion.Therefore,the incorporation of fluorescent nanoprobes greatly inhibits the intrusion of electrolytes into polymer and improves the corrosion protection performance of the coating.This powerful strategy towards dual-level damage warning provides insights for the development of long-term smart protective materials.
基金Youth Foundation of National Natural Science Foundation of China (No. 52204020)Distinguished Young Foundation of National Natural Science Foundation of China (No. 52125401).
文摘As oil and gas exploration continues to progress into deeper and unconventional reservoirs,the likelihood of kick risk increases,making kick warning a critical factor in ensuring drilling safety and efficiency.Due to the scarcity of kick samples,traditional supervised models perform poorly,and significant fluctuations in field data lead to high false alarm rates.This study proposes an unsupervised graph autoencoder(GAE)-based kick warning method,which effectively reduces false alarms by eliminating the influence of field engineer operations and incorporating real-time model updates.The method utilizes the GAE model to process time-series data during drilling,accurately identifying kick risk while overcoming challenges related to small sample sizes and missing features.To further reduce false alarms,the weighted dynamic time warping(WDTW)algorithm is introduced to identify fluctuations in logging data caused by field engineer operations during drilling,with real-time updates applied to prevent normal conditions from being misclassified as kick risk.Experimental results show that the GAE-based kick warning method achieves an accuracy of 92.7%and significantly reduces the false alarm rate.The GAE model continues to operate effectively even under conditions of missing features and issues kick warnings 4 min earlier than field engineers,demonstrating its high sensitivity and robustness.After integrating the WDTW algorithm and real-time updates,the false alarm rate is reduced from 17.3%to 5.6%,further improving the accuracy of kick warnings.The proposed method provides an efficient and reliable approach for kick warning in drilling operations,offering strong practical value and technical support for the intelligent management of future drilling operations.
基金Scientific Research Fund of Institute of Engineering Mechanics,China Earthquake Administration under Grant No.2024B08。
文摘One of the primary tasks of earthquake early warning(EEW)systems is to predict potential earthquake damage rapidly and accurately.Cumulative absolute velocity(CAV),Arias intensity(I_(A)),and spectrum intensity(SI)are important parameters for measuring ground motion intensity and assessing earthquake damage.Due to the limited available information in EEW,CAV,I_(A),and SI cannot be accurately predicted using traditional EEW methods.In this paper,we propose an end-to-end deep learning-based Ground motion Intensity prediction Network(ENGINet)for on-site EEW.The aim of the ENGINet is to predict CAV,I_(A),and SI rapidly and reliably.ENGINet is based on a convolutional neural network and recurrent neural network.The inputs of the network are three-component acceleration records,three-component velocity records,and three-component displacement records obtained by a single station.The results from the test dataset show that at 3 s after the P-wave arrival,compared with the baseline models and other traditional methods,ENGINet has better performance in predicting CAV,I_(A),and SI.Our results indicate that ENGINet can quickly and accurately predict CAV,I_(A),and SI to some extent and has good potential in EEW efforts.
基金supported by the Deanship of Graduate Studies and Scientific Research at Qassim University(QU-APC-2024-9/1).
文摘Due to the numerous variables to take into account as well as the inherent ambiguity and uncertainty,evaluating educational institutions can be difficult.The concept of a possibility Pythagorean fuzzy hypersoft set(pPyFHSS)is more flexible in this regard than other theoretical fuzzy set-like models,even though some attempts have been made in the literature to address such uncertainties.This study investigates the elementary notions of pPyFHSS including its set-theoretic operations union,intersection,complement,OR-and AND-operations.Some results related to these operations are also modified for pPyFHSS.Additionally,the similarity measures between pPyFHSSs are formulated with the assistance of numerical examples and results.Lastly,an intelligent decision-assisted mechanism is developed with the proposal of a robust algorithm based on similarity measures for solving multi-attribute decision-making(MADM)problems.A case study that helps the decision-makers assess the best educational institution is discussed to validate the suggested system.The algorithmic results are compared with the most pertinent model to evaluate the adaptability of pPyFHSS,as it generalizes the classical possibility fuzzy set-like theoretical models.Similarly,while considering significant evaluating factors,the flexibility of pPyFHSS is observed through structural comparison.
文摘Accurate medical diagnosis,which involves identifying diseases based on patient symptoms,is often hindered by uncertainties in data interpretation and retrieval.Advanced fuzzy set theories have emerged as effective tools to address these challenges.In this paper,new mathematical approaches for handling uncertainty in medical diagnosis are introduced using q-rung orthopair fuzzy sets(q-ROFS)and interval-valued q-rung orthopair fuzzy sets(IVq-ROFS).Three aggregation operators are proposed in our methodologies:the q-ROF weighted averaging(q-ROFWA),the q-ROF weighted geometric(q-ROFWG),and the q-ROF weighted neutrality averaging(qROFWNA),which enhance decision-making under uncertainty.These operators are paired with ranking methods such as the similarity measure,score function,and inverse score function to improve the accuracy of disease identification.Additionally,the impact of varying q-rung values is explored through a sensitivity analysis,extending the analysis beyond the typical maximum value of 3.The Basic Uncertain Information(BUI)method is employed to simulate expert opinions,and aggregation operators are used to combine these opinions in a group decisionmaking context.Our results provide a comprehensive comparison of methodologies,highlighting their strengths and limitations in diagnosing diseases based on uncertain patient data.
基金supported by the Beijing Key Clinical Specialty Project(20240930)the National Natural Science Foundation of China(NSFC 82373436)+7 种基金the Beijing Hospitals Authority’Youth Program(BHAYP,QML20230114)the Beijing Natural Science Foundation(BNSF Z200027)the Beijing Chaoyang Hospital Multi-disciplinary Team Program(CYDXK202204),the NSFC(62331001)the BNSF(Z200027)the NSFC(82202097)the BHAYP(QML20230113)the Training Fund for Open Projects at Clinical Institutes and Departments of Capital Medical University(CCMU2022ZKYXY010)the Beijing Scholars Program(No.[2015]160).
文摘Background:Multiparametric magnetic resonance imaging(mpMRI)has significantly advanced prostate cancer(PCa)detection,yet decisions on invasive biopsy with moderate prostate imaging reporting and data system(PI-RADS)scores remain ambiguous.Methods:To explore the decision-making capacity of Generative Pretrained Transformer-4(GPT-4)for automated prostate biopsy recommendations,we included 2299 individuals who underwent prostate biopsy from 2018 to 2023 in 3 large medical centers,with available mpMRI before biopsy and documented clinical-histopathological records.GPT-4 generated structured reports with given prompts.The performance of GPT-4 was quantified using confusion matrices,and sensitivity,specificity,as well as area under the curve were calculated.Multiple artificial evaluation procedures were conducted.Wilcoxon’s rank sum test,Fisher’s exact test,and Kruskal-Wallis tests were used for comparisons.Results:Utilizing the largest sample size in the Chinese population,patients with moderate PI-RADS scores(scores 3 and 4)accounted for 39.7%(912/2299),defined as the subset-of-interest(SOI).The detection rates of clinically significant PCa corresponding to PI-RADS scores 2-5 were 9.4%,27.3%,49.2%,and 80.1%,respectively.Nearly 47.5%(433/912)of SOI patients were histopathologically proven to have undergone unnecessary prostate biopsies.With the assistance of GPT-4,20.8%(190/912)of the SOI population could avoid unnecessary biopsies,and it performed even better[28.8%(118/410)]in the most heterogeneous subgroup of PI-RADS score 3.More than 90.0%of GPT-4-generated reports were comprehensive and easy to understand,but less satisfied with the accuracy(82.8%).GPT-4 also demonstrated cognitive potential for handling complex problems.Additionally,the Chain of Thought method enabled us to better understand the decision-making logic behind GPT-4.Eventually,we developed a ProstAIGuide platform to facilitate accessibility for both doctors and patients.Conclusions:This multi-center study highlights the clinical utility of GPT-4 for prostate biopsy decision-making and advances our understanding of the latest artificial intelligence implementation in various medical scenarios.
文摘BACKGROUND Understanding a patient's clinical status and setting priorities for their care are two aspects of the constantly changing process of clinical decision-making.One analytical technique that can be helpful in uncertain situations is clinical judgment.Clinicians must deal with contradictory information,lack of time to make decisions,and long-term factors when emergencies occur.AIM To examine the ethical issues healthcare professionals faced during the coronavirus disease 2019(COVID-19)pandemic and the factors affecting clinical decision-making.METHODS This pilot study,which means it was a preliminary investigation to gather information and test the feasibility of a larger investigation was conducted over 6 months and we invited responses from clinicians worldwide who managed patients with COVID-19.The survey focused on topics related to their professional roles and personal relationships.We examined five core areas influencing critical care decision-making:Patients'personal factors,family-related factors,informed consent,communication and media,and hospital administrative policies on clinical decision-making.The collected data were analyzed using the χ^(2) test for categorical variables.RESULTS A total of 102 clinicians from 23 specialties and 17 countries responded to the survey.Age was a significant factor in treatment planning(n=88)and ventilator access(n=78).Sex had no bearing on how decisions were made.Most doctors reported maintaining patient confidentiality regarding privacy and informed consent.Approximately 50%of clinicians reported a moderate influence of clinical work,with many citing it as one of the most important factors affecting their health and relationships.Clinicians from developing countries had a significantly higher score for considering a patient's financial status when creating a treatment plan than their counterparts from developed countries.Regarding personal experiences,some respondents noted that treatment plans and preferences changed from wave to wave,and that there was a rapid turnover of studies and evidence.Hospital and government policies also played a role in critical decision-making.Rather than assessing the appropriateness of treatment,some doctors observed that hospital policies regarding medications were driven by patient demand.CONCLUSION Factors other than medical considerations frequently affect management choices.The disparity in treatment choices,became more apparent during the pandemic.We highlight the difficulties and contradictions between moral standards and the realities physicians encountered during this medical emergency.False information,large patient populations,and limited resources caused problems for clinicians.These factors impacted decision-making,which,in turn,affected patient care and healthcare staff well-being.
