Objective:To rapidly assess the effectiveness,safety,economy,and applicability of Shaoma Zhijing granule(SZG)for the treatment of children with tic disorders(TD),and provide currently available best evidence for decis...Objective:To rapidly assess the effectiveness,safety,economy,and applicability of Shaoma Zhijing granule(SZG)for the treatment of children with tic disorders(TD),and provide currently available best evidence for decision-makers of health policies.Methods:We conducted a rapid health technology assessment(RHTA)to explore the value of SZG.A systematic literature search in eight literature databases and on three clinical trial registration platforms was performed.The literature was screened according to eligibility criteria.The screening process and data extraction were conducted by two reviewers,and the quality of the literature was also assessed.The results were summarized,analyzed,and presented in tables or figures.Results:A total of five randomized controlled trials(RCTs)were included in this study,of which one was published in English(in the Journal of Child Psychology and Psychiatry)and four in Chinese journals.The overall risk of bias for the five RCTs was evaluated as“some concerns.”SZG monotherapy or in combi-nation with tiapride was better than tiapride alone in improving traditional Chinese medicine(TCM)syndromes and tic symptoms,with a daily cost of¥67.50e107.22.Adverse events were mainly related to the digestive,respiratory,and neurological systems,but all were mild.Conclusion:Overall,the current RHTA of published,peer-reviewed literature has located a small body of evidence evaluating the use of SZG for the treatment of TD in children.SZG has effects on improving TCM syndromes and tic symptoms;the daily cost is¥67.50e107.22;and all adverse events are mild.High-quality studies with long-term follow-up should be conducted,so as to provide local evidence and consistently guide and improve scientific decision-making.展开更多
Although a key tenant of the Sustainable Development Goals is to achieve universal health coverage,the global drug gap persists-cver a third of the global population lack access to essential medicines.Without access t...Although a key tenant of the Sustainable Development Goals is to achieve universal health coverage,the global drug gap persists-cver a third of the global population lack access to essential medicines.Without access to affordable drugs,people have worse health outcomes,higher medical expenses,and productivity loss,pushing them into poverty.Health technology assessments(HTAs)offer an opportunity to decrease the global drug gap and increase access to essential medicines by overcoming barriers to medicine access.These barriers include drug procurement,drug affordability for payers and patients,a patienfs ability to obtain essential medicines,and health system capacity.Using HTAs can therefore close the global drug gap by increasing access to affordable essential medicines.In turn,people have better health outcomes,spend less money on medical care,and can have better productivity.Ultimately,use of HTAs can lift the population out of poverty and force fewer people into poverty by creating better health outcomes at affordable prices.展开更多
Purpose-Nowadays successful organizations need to be masters at leadership by values to play in a constantly changing and transforming environment.But how can leaders and organizations effectively convene strategic an...Purpose-Nowadays successful organizations need to be masters at leadership by values to play in a constantly changing and transforming environment.But how can leaders and organizations effectively convene strategic and culture development based on values?This paper presents the Tri-Intersectional Model of Leadership by Values(TMLV)in which leaders and organizations can integrate a sustainable strategy,as well as a culture and value-based management system that simultaneously leverages human,financial,and social resources.With its three essential axes of values(economic-pragmatic,emotional-development,and ethical-social)at their intersection points,it allows leaders to focus on the strategy linkages:innovation-intersection between the economic-pragmatic values axis and the emotional-development values axis-allows them to develop sustainable innovations;survival-intersection between the economic-pragmatic values axis and the ethical-social values axis-enhances their organization’s survival;finally,sensibility-intersection between the economic-pragmatic values axis and the ethical-social values axis-makes them more humane and more socially-responsible.The application of the TMLV,using the Fuzzy Multi-Criteria Decision Making Open Technology Assessment System,can be a great inspiration for stimulating and working with values in organizations,as well as allowing leaders to develop a values-based,high-involvement,and performance-oriented culture.Methodology/Approach-This research considers empirical data analysis of the 37 case studies of the EU-InnovatE project(http//www.euinnovate.com)-a pioneering initiative to align innovation values to integrate the end user into the process of innovation and entrepreneurship related to a sustainable lifestyle and the green economy in Europe-using a fuzzy multiple-criteria decision making method and open technologies system,such as server-side PHP language,MariaDB Database,fork of MYSQL Database Management System,and JavaScript libraries to perform operation directly on the user’s browser.Findings-The application of the TMLV model,considering empirical analysis of the extracted values from the case studies,using the Fuzzy Multi-Criteria Decision Making Open Technology Assessment System,can be a great inspiration for stimulating and working with values in João organizations,as well as allowing leaders to develop suitable strategies and interventions for shaping a sustainable high-performance culture.Research implications-This research can be a starting point for further research to assess the effectiveness of the leadership model based on a decision-making open technology system in any given organization,as well as to invite researchers who have positive passion about working with values to participate in the improvement of this tool.Originality/value-The Tri-Intersectional Model of Leadership by Values using the Fuzzy Multi-Criteria Decision Making Open Technology Assessment System is presented as an evolution in leadership models that may be used to fuel innovation,survival,and a sensibility strategic focus that is necessary to optimize human and organizational performance and deliver effective solutions to the massive array of human,financial,and social problems we face today.展开更多
Objectives:Economic growth and rapid development of health technology in China have created opportunities to strengthen health technology assessment (HTA) capacity.Over the time,HTA institutions have been established ...Objectives:Economic growth and rapid development of health technology in China have created opportunities to strengthen health technology assessment (HTA) capacity.Over the time,HTA institutions have been established to conduct HTA related work.This study reviewed the current status of HTA in China and analysed the challenges of HTA development in the context of health reform under'new normal'economy.Methods:Literature review and webpage searches were used to document the development of HTA in China.An institutional survey has also been conducted to collect information on the HTA research institutions in China.Results:The number of articles and research projects on HTA were rising and are continuing to rise.HTA development has made substantial progress in China in terms of growing number of research institutions and qualified HTA workforce.However,HTA has notable weaknesses such as low capacity for conducting HTA research,limited experience in HTA researchers,and lack of knowledge translation.Conclusion:Currently,the translation of HTA findings to policy-making is limited and the integration of HTA in the policy-making processes is still in its infancy.The HTA development in China has had opportunities due to demands of health care,health insurance,and health technology as a result of health reform.Capacity building and institutionalization of HTA are urgently needed for further development of HTA in China.展开更多
Objectives:The widespread usage of traditional Chinese medicine(TCM)and the government's emphasis on TCM in China have created a positive macro-environment and great opportunities to develop and strengthen health ...Objectives:The widespread usage of traditional Chinese medicine(TCM)and the government's emphasis on TCM in China have created a positive macro-environment and great opportunities to develop and strengthen health technology assessment(HTA)in TCM.Over the past ten years,a series of policies have been issued by the government to promote the application of HTA and the development of TCM in China.This study reviews the concepts and characteristics of TCM,summarizes the current status of HTA in TCM,and analyzes the opportunities and challenges faced by HTA development in TCM with respect to deepening of healthcare reforms.Methods:Literature review and website searches were used to acquire information regarding the basic theories of TCM and the current status,opportunities,and challenges for HTA in TCM.Results:The number of articles on HTA in TCM rose substantially,especially those published in China National Knowledge Infrastructure(CNKI).With the optimistic policy environment and huge market demand for TCM,the development of HTA in TCM is expected to flourish in China.However,HTA in TCM also faces numerous challenges such as the absence of a clinical efficacy evaluation system for TCM and insufficient basic research evidence and qualified personnel.Conclusions:TCM has unique characteristic that distinguishes it from Western medicine.Currently,it is important to take all measures to address the existing main challenges and thereby take advantage of the present opportunities to develop and improve HTA in TCM.展开更多
Hospital-based health technology assessment(HB-HTA)is highly valuable in the application of hospital medical technology,cost control,improvement of medical quality,and protection of medical safety,and its use is incre...Hospital-based health technology assessment(HB-HTA)is highly valuable in the application of hospital medical technology,cost control,improvement of medical quality,and protection of medical safety,and its use is increasing daily globally.However,in China,HB-HTA is still in its infancy,and it is yet to be adopted in traditional Chinese medicine(TCM).Therefore,this article introduces the application and development of HB-HTA,as well as discusses the current situation of TCM and related future development strategies to provide ideas and references for the development of HB-HTA in TCM.We conclude and recommend that all major stakeholders,including the state,health departments,and hospital leaders,support and promote the exploration and development of HB-HTA in TCM hospitals and integrative medicine hospitals.We also suggest the utilization of existing talents and introduction of other necessary talents to promote better and faster organizational development,as well as suggest the formation of a national and internationally recognized HB-HTA guidance manual and toolkit for TCM hospitals based on both the national HTA guidelines and the evaluation of TCM hospitals pilot projects.Moreover,we recommend that HB-HTA pilot study should be executed with Chinese patent medicine as the starting point to form the implementation process and framework in the TCM arena.展开更多
The life cycle of technology is one of the most important indexes to weigh up the risk of the investment to neo tech.There are so many uncertainties because it is conditioned by a lot of factors,we can not make a rati...The life cycle of technology is one of the most important indexes to weigh up the risk of the investment to neo tech.There are so many uncertainties because it is conditioned by a lot of factors,we can not make a rational forecasting by traditional assessment method.So this paper gives a comprehensive consideration to the factors that influence production and makes some modification to production function, and establishes the life cycle of technology assessmet model by the method of fuzzy mathematics. So it quantifies the risk of investment.We can take it as one foundational index for the decision making of the investment.展开更多
Acute pancreatitis(AP)is a potentially life-threatening inflammatory disease of the pancreas,with clinical management determined by the severity of the disease.Diagnosis,severity prediction,and prognosis assessment of...Acute pancreatitis(AP)is a potentially life-threatening inflammatory disease of the pancreas,with clinical management determined by the severity of the disease.Diagnosis,severity prediction,and prognosis assessment of AP typically involve the use of imaging technologies,such as computed tomography,magnetic resonance imaging,and ultrasound,and scoring systems,including Ranson,Acute Physiology and Chronic Health Evaluation II,and Bedside Index for Severity in AP scores.Computed tomography is considered the gold standard imaging modality for AP due to its high sensitivity and specificity,while magnetic resonance imaging and ultrasound can provide additional information on biliary obstruction and vascular complications.Scoring systems utilize clinical and laboratory parameters to classify AP patients into mild,moderate,or severe categories,guiding treatment decisions,such as intensive care unit admission,early enteral feeding,and antibiotic use.Despite the central role of imaging technologies and scoring systems in AP management,these methods have limitations in terms of accuracy,reproducibility,practicality and economics.Recent advancements of artificial intelligence(AI)provide new opportunities to enhance their performance by analyzing vast amounts of clinical and imaging data.AI algorithms can analyze large amounts of clinical and imaging data,identify scoring system patterns,and predict the clinical course of disease.AI-based models have shown promising results in predicting the severity and mortality of AP,but further validation and standardization are required before widespread clinical application.In addition,understanding the correlation between these three technologies will aid in developing new methods that can accurately,sensitively,and specifically be used in the diagnosis,severity prediction,and prognosis assessment of AP through complementary advantages.展开更多
Extreme storm events in coastal zones play significant roles in shaping the morphology of boulder beaches.However,boulder displacement and the geomorphological evolution of boulder beaches driven by different extreme ...Extreme storm events in coastal zones play significant roles in shaping the morphology of boulder beaches.However,boulder displacement and the geomorphological evolution of boulder beaches driven by different extreme storm events,especially typhoon events,remain poorly understood.Thus,boulder displacement and the geomorphic response on a boulder beach in Fujian,southeastern China,were explored before,during and after a cold wave event(Dec.1–7,2020)and before and after Typhoon In-Fa(Jul.19–27,2021),a large tropical storm.This was achieved by tracking 42 tagged boulders distributed in the intertidal and supratidal zones using Radio Frequency Identification(RFID)and topographic surveys using real-time kinematic techniques,respectively.The results showed obvious disparities in boulder displacement in different geomorphic zones due to cold wave and typhoon events that were mainly characterized by migration magnitude,range,direction,and mode of transport.The typhoon event led to rapid and substantial changes in the overall morphology of the boulder beach,while the cold wave event impacted the intertidal morphology of the boulder beach to only a small extent.The surrounding structure of boulders,beach slope and beach elevation had a combined dominant effect on boulder displacement under the same extreme event.Hydrodynamic factors(effective wave energy fluxes,incident wave direction,storm surge and water level)had dominant effects on boulder displacement during different extreme events.In terms of a single event,the magnitude of the boulder displacement driven by the typhoon was much greater than that driven by the cold wave.However,considering the frequency and duration of cold waves in winter,the impact of multiple consecutive cold waves on the geomorphology of the boulder beach cannot be ignored in this study area.Alternating and repeated interactions between these two processes constitute the complete geomorphic evolution of the boulder beach.This study contributes to improved predictions of the morphodynamic response of boulder beaches to future storms,especially large tropical storms,and facilitates better coastal management.展开更多
The aim of the study is to comparatively assess the concentrations of lead, zinc and iron in Rivers Ase, Warri and Ethiope, in Nigeria. Monthly water samples were collected from six randomly selected sites along the r...The aim of the study is to comparatively assess the concentrations of lead, zinc and iron in Rivers Ase, Warri and Ethiope, in Nigeria. Monthly water samples were collected from six randomly selected sites along the rivers course. 72 water samples were collected from each river at 0 - 15 cm depths. Samples were analysed based on the standard methods recommended by the WHO for testing lead, zinc and iron. The assessment of the water quality was done using the Water Quality Index (WQI) of the Canadian Council of Ministers of the Environment (CCME-WQI). While hypotheses were tested using ANOVA. Findings indicated that CCME-WQI values were 47.3, 66.52 and 78.7. This meant that the water quality of River Ase is impaired and departed from desirable levels, while that of Warri and Ethiope were considered to occasionally be impaired and depart from desirable levels. The ANOVA model showed that there is a significant variation in heavy metal load in the selected rivers at P < 0.05. River water was put to domestic uses such as drinking (20.5%) preparing food (17.8%), bathing (19.8%), washing clothes and dishes (21.3%), brushing teeth (13.3%), and catering for domestic animals (7.5%). Poverty (49.5%) was the major reason for the use of river water for domestic purposes. The locals highlighted that they usually suffer from cholera (26.8%), diarrhoea (25.8%), dysentery (24%) and typhoid (23.5%) as a result of using the river water. The study recommended routine monitoring of anthropogenic and geologic activities, testing of the water regularly amongst others.展开更多
The global ionosphere maps(GIM)provided by the International GNSS Service(IGS)are extensively utilized for ionospheric morphology monitoring,scientific research,and practical application.Assessing the credibility of G...The global ionosphere maps(GIM)provided by the International GNSS Service(IGS)are extensively utilized for ionospheric morphology monitoring,scientific research,and practical application.Assessing the credibility of GIM products in data-sparse regions is of paramount importance.In this study,measurements from the Crustal Movement Observation Network of China(CMONOC)are leveraged to evaluate the suitability of IGS-GIM products over China region in 2013-2014.The indices of mean error(ME),root mean square error(RMSE),and normalized RMSE(NRMSE)are then utilized to quantify the accuracy of IGS-GIM products.Results revealed distinct local time and latitudinal dependencies in IGS-GIM errors,with substantially high errors at nighttime(NRMSE:39%)and above 40°latitude(NRMSE:49%).Seasonal differences also emerged,with larger equinoctial deviations(NRMSE:33.5%)compared with summer(20%).A preliminary analysis implied that the irregular assimilation of sparse IGS observations,compounded by China’s distinct geomagnetic topology,may manifest as error variations.These results suggest that modeling based solely on IGS-GIM observations engenders inadequate representations across China and that a thorough examination would proffer the necessary foundation for advancing regional total electron content(TEC)constructions.展开更多
Cancer patients are at high risk of malnutrition,which can lead to adverse health outcomes such as prolonged hospitalization,increased complications,and increased mortality.Accurate and timely nutritional assessment p...Cancer patients are at high risk of malnutrition,which can lead to adverse health outcomes such as prolonged hospitalization,increased complications,and increased mortality.Accurate and timely nutritional assessment plays a critical role in effectively managing malnutrition in these patients.However,while many tools exist to assess malnutrition,there is no universally accepted standard.Although different tools have their own strengths and limitations,there is a lack of narrative reviews on nutritional assessment tools for cancer patients.To address this knowledge gap,we conducted a non-systematic literature search using PubMed,Embase,Web of Science,and the Cochrane Library from their inception until May 2023.A total of 90 studies met our selection criteria and were included in our narrative review.We evaluated the applications,strengths,and limitations of 4 commonly used nutritional assessment tools for cancer patients:the Subjective Global Assessment(SGA),Patient-Generated Subjective Global Assessment(PG-SGA),Mini Nutritional Assessment(MNA),and Global Leadership Initiative on Malnutrition(GLIM).Our findings revealed that malnutrition was associated with adverse health outcomes.Each of these 4 tools has its applications,strengths,and limitations.Our findings provide medical staff with a foundation for choosing the optimal tool to rapidly and accurately assess malnutrition in cancer patients.It is essential for medical staff to be familiar with these common tools to ensure effective nutritional management of cancer patients.展开更多
Machine learning is currently one of the research hotspots in the field of landslide prediction.To clarify and evaluate the differences in characteristics and prediction effects of different machine learning models,Co...Machine learning is currently one of the research hotspots in the field of landslide prediction.To clarify and evaluate the differences in characteristics and prediction effects of different machine learning models,Conghua District,which is the most prone to landslide disasters in Guangzhou,was selected for landslide susceptibility evaluation.The evaluation factors were selected by using correlation analysis and variance expansion factor method.Applying four machine learning methods namely Logistic Regression(LR),Random Forest(RF),Support Vector Machines(SVM),and Extreme Gradient Boosting(XGB),landslide models were constructed.Comparative analysis and evaluation of the model were conducted through statistical indices and receiver operating characteristic(ROC)curves.The results showed that LR,RF,SVM,and XGB models have good predictive performance for landslide susceptibility,with the area under curve(AUC)values of 0.752,0.965,0.996,and 0.998,respectively.XGB model had the highest predictive ability,followed by RF model,SVM model,and LR model.The frequency ratio(FR)accuracy of LR,RF,SVM,and XGB models was 0.775,0.842,0.759,and 0.822,respectively.RF and XGB models were superior to LR and SVM models,indicating that the integrated algorithm has better predictive ability than a single classification algorithm in regional landslide classification problems.展开更多
As a basic technology at physical layer of mobile communications,non-orthogonal multiple access has been attracting wide attention across the academia and the industry.During the standardization of the fifth-generatio...As a basic technology at physical layer of mobile communications,non-orthogonal multiple access has been attracting wide attention across the academia and the industry.During the standardization of the fifth-generation(5G)of mobile communications,3GPP conducted preliminary study on non-orthogonal multiple access without reaching the consensus to standardize the technology.展开更多
The Nigerian oil sands represent the largest oil sand deposit in Africa, yet there is little published information on the distribution and potential health and ecological risks of trace elements in the oil resource. I...The Nigerian oil sands represent the largest oil sand deposit in Africa, yet there is little published information on the distribution and potential health and ecological risks of trace elements in the oil resource. In the present study, we investigated the distribution pattern of 18trace elements(including biophile and chalcophile elements) as well as the estimated risks associated with exposure to these elements. The results of the study indicated that Fe was the most abundant element, with a mean concentration of 22,131 mg/kg while Br had the lowest mean concentration of 48 mg/kg. The high occurrence of Fe and Ti suggested a possible occurrence of ilmenite(Fe TiO_(3)) in the oil sands. Source apportionment using positive matrix factorization showed that the possible sources of detected elements in the oil sands were geogenic, metal production, and crustal. The contamination factor, geo-accumulation index, modified degree of contamination, pollution load index, and Nemerow pollution index indicated that the oil sands are heavily polluted by the elements. Health risk assessment showed that children were relatively more susceptible to the potentially toxic elements in the oil sands principally via ingestion exposure route(HQ > 1E-04). Cancer risks from inhalation are unlikely due to CR < 1E-06 but ingestion and dermal contact pose severe risks(CR > 1E-04). The high concentrations of the elements pose serious threats due to the potential for atmospheric transport, bioaccessibility, and bioavailability.展开更多
Quantitative assessment of the impact of climate variability and human activities on runoff plays a pivotal role in water resource management and maintaining ecosystem integrity.This study considered six sub-basins in...Quantitative assessment of the impact of climate variability and human activities on runoff plays a pivotal role in water resource management and maintaining ecosystem integrity.This study considered six sub-basins in the upper reaches of the Yangtze River basin,China,to reveal the trend of the runoff evolution and clarify the driving factors of the changes during 1956–2020.Linear regression,Mann-Kendall test,and sliding t-test were used to study the trend of the hydrometeorological elements,while cumulative distance level and ordered clustering methods were applied to identify mutation points.The contributions of climate change and human disturbance to runoff changes were quantitatively assessed using three methods,i.e.,the rainfall-runoff relationship method,slope variation method,and variable infiltration capacity(Budyko)hypothesis method.Then,the availability and stability of the three methods were compared.The results showed that the runoff in the upper reaches of the Yangtze River basin exhibited a decreasing trend from 1956 to 2020,with an abrupt change in 1985.For attribution analysis,the runoff series could be divided into two phases,i.e.,1961–1985(baseline period)and 1986–2020(changing period);and it was found that the rainfall-runoff relationship method with precipitation as the representative of climate factors had limited usability compared with the other two methods,while the slope variation and Budyko hypothesis methods had highly consistent results.Different factors showed different effects in the sub-basins of the upper reaches of the Yangtze River basin.Moreover,human disturbance was the main factor that contributed to the runoff changes,accounting for 53.0%–82.0%;and the contribution of climate factors to the runoff change was 17.0%–47.0%,making it the secondary factor,in which precipitation was the most representative climate factor.These results provide insights into how climate and anthropogenic changes synergistically influence the runoff of the upper reaches of the Yangtze River basin.展开更多
Cancer is a leading cause of death worldwide, with breast cancer being the most common (2.26 million new cases and 685,000 deaths). In Saudi Arabia, breast cancer ranked the first among females in 2014, accounting for...Cancer is a leading cause of death worldwide, with breast cancer being the most common (2.26 million new cases and 685,000 deaths). In Saudi Arabia, breast cancer ranked the first among females in 2014, accounting for 15.9% of all cancers reported among Saudi nationals and 28.7% of all cancers reported among females of all ages. Early detection of breast cancer could decrease the risks, have a better prognosis, and have better outcomes/more successful treatments. Prevalence of breast cancer reached more than 25% of all diagnosed cancer in the kingdom among women. Aim: This study aims to assess the knowledge and performance of women attending primary care centers about breast self-examination and mammogram screening for prevention and early detection of breast cancer in Abha city primary healthcare centers, Kingdom of Saudi Arabia. Research Method: cross sectional design was conducted by using questionnaire, which was distributed to primary care center nurses. The collected data was statistically analyzed using the Statistical Package for Social Sciences, version 25. Results: The study found that participants had poor awareness and knowledge about breast self-examination, risk factors for breast cancer, and trends and practices in early diagnosis of breast cancer. Conclusion and Recommendations: It recommends increasing awareness campaigns and providing educational programs to improve knowledge and practices.展开更多
Cardiovascular disease(CVD)has gradually become one of the main causes of harm to the life and health of residents.Exploring the influencing factors and risk assessment methods of CVD has become a general trend.In thi...Cardiovascular disease(CVD)has gradually become one of the main causes of harm to the life and health of residents.Exploring the influencing factors and risk assessment methods of CVD has become a general trend.In this paper,a machine learning-based decision-making mechanism for risk assessment of CVD is designed.In this mechanism,the logistics regression analysismethod and factor analysismodel are used to select age,obesity degree,blood pressure,blood fat,blood sugar,smoking status,drinking status,and exercise status as the main pathogenic factors of CVD,and an index systemof risk assessment for CVD is established.Then,a two-stage model combining K-means cluster analysis and random forest(RF)is proposed to evaluate and predict the risk of CVD,and the predicted results are compared with the methods of Bayesian discrimination,K-means cluster analysis and RF.The results show that thepredictioneffect of theproposedtwo-stagemodel is better than that of the comparedmethods.Moreover,several suggestions for the government,the medical industry and the public are provided based on the research results.展开更多
With the development of the integration of aviation safety and artificial intelligence,research on the combination of risk assessment and artificial intelligence is particularly important in the field of risk manageme...With the development of the integration of aviation safety and artificial intelligence,research on the combination of risk assessment and artificial intelligence is particularly important in the field of risk management,but searching for an efficient and accurate risk assessment algorithm has become a challenge for the civil aviation industry.Therefore,an improved risk assessment algorithm(PS-AE-LSTM)based on long short-term memory network(LSTM)with autoencoder(AE)is proposed for the various supervised deep learning algorithms in flight safety that cannot adequately address the problem of the quality on risk level labels.Firstly,based on the normal distribution characteristics of flight data,a probability severity(PS)model is established to enhance the quality of risk assessment labels.Secondly,autoencoder is introduced to reconstruct the flight parameter data to improve the data quality.Finally,utilizing the time-series nature of flight data,a long and short-termmemory network is used to classify the risk level and improve the accuracy of risk assessment.Thus,a risk assessment experimentwas conducted to analyze a fleet landing phase dataset using the PS-AE-LSTMalgorithm to assess the risk level associated with aircraft hard landing events.The results show that the proposed algorithm achieves an accuracy of 86.45%compared with seven baseline models and has excellent risk assessment capability.展开更多
Stroke is a chronic cerebrovascular disease that carries a high risk.Stroke risk assessment is of great significance in preventing,reversing and reducing the spread and the health hazards caused by stroke.Aiming to ob...Stroke is a chronic cerebrovascular disease that carries a high risk.Stroke risk assessment is of great significance in preventing,reversing and reducing the spread and the health hazards caused by stroke.Aiming to objectively predict and identify strokes,this paper proposes a new stroke risk assessment decision-making model named Logistic-AdaBoost(Logistic-AB)based on machine learning.First,the categorical boosting(CatBoost)method is used to perform feature selection for all features of stroke,and 8 main features are selected to form a new index evaluation system to predict the risk of stroke.Second,the borderline synthetic minority oversampling technique(SMOTE)algorithm is applied to transform the unbalanced stroke dataset into a balanced dataset.Finally,the stroke risk assessment decision-makingmodel Logistic-AB is constructed,and the overall prediction performance of this new model is evaluated by comparing it with ten other similar models.The comparison results show that the new model proposed in this paper performs better than the two single algorithms(logistic regression and AdaBoost)on the four indicators of recall,precision,F1 score,and accuracy,and the overall performance of the proposed model is better than that of common machine learning algorithms.The Logistic-AB model presented in this paper can more accurately predict patients’stroke risk.展开更多
基金This study was supported by the National Natural Science Foundation of China(82174239)China Academy of Chinese Med-ical Sciences Innovation Fund(CI2021A00701-3 and CI2021A05503)China Center for Evidence Based Traditional Chinese Medicine(2020YJSZX-2).
文摘Objective:To rapidly assess the effectiveness,safety,economy,and applicability of Shaoma Zhijing granule(SZG)for the treatment of children with tic disorders(TD),and provide currently available best evidence for decision-makers of health policies.Methods:We conducted a rapid health technology assessment(RHTA)to explore the value of SZG.A systematic literature search in eight literature databases and on three clinical trial registration platforms was performed.The literature was screened according to eligibility criteria.The screening process and data extraction were conducted by two reviewers,and the quality of the literature was also assessed.The results were summarized,analyzed,and presented in tables or figures.Results:A total of five randomized controlled trials(RCTs)were included in this study,of which one was published in English(in the Journal of Child Psychology and Psychiatry)and four in Chinese journals.The overall risk of bias for the five RCTs was evaluated as“some concerns.”SZG monotherapy or in combi-nation with tiapride was better than tiapride alone in improving traditional Chinese medicine(TCM)syndromes and tic symptoms,with a daily cost of¥67.50e107.22.Adverse events were mainly related to the digestive,respiratory,and neurological systems,but all were mild.Conclusion:Overall,the current RHTA of published,peer-reviewed literature has located a small body of evidence evaluating the use of SZG for the treatment of TD in children.SZG has effects on improving TCM syndromes and tic symptoms;the daily cost is¥67.50e107.22;and all adverse events are mild.High-quality studies with long-term follow-up should be conducted,so as to provide local evidence and consistently guide and improve scientific decision-making.
基金support from“A Demonstration Program on Health Technology Assessment in China”by China Medical Board(Grant 19-318).
文摘Although a key tenant of the Sustainable Development Goals is to achieve universal health coverage,the global drug gap persists-cver a third of the global population lack access to essential medicines.Without access to affordable drugs,people have worse health outcomes,higher medical expenses,and productivity loss,pushing them into poverty.Health technology assessments(HTAs)offer an opportunity to decrease the global drug gap and increase access to essential medicines by overcoming barriers to medicine access.These barriers include drug procurement,drug affordability for payers and patients,a patienfs ability to obtain essential medicines,and health system capacity.Using HTAs can therefore close the global drug gap by increasing access to affordable essential medicines.In turn,people have better health outcomes,spend less money on medical care,and can have better productivity.Ultimately,use of HTAs can lift the population out of poverty and force fewer people into poverty by creating better health outcomes at affordable prices.
文摘Purpose-Nowadays successful organizations need to be masters at leadership by values to play in a constantly changing and transforming environment.But how can leaders and organizations effectively convene strategic and culture development based on values?This paper presents the Tri-Intersectional Model of Leadership by Values(TMLV)in which leaders and organizations can integrate a sustainable strategy,as well as a culture and value-based management system that simultaneously leverages human,financial,and social resources.With its three essential axes of values(economic-pragmatic,emotional-development,and ethical-social)at their intersection points,it allows leaders to focus on the strategy linkages:innovation-intersection between the economic-pragmatic values axis and the emotional-development values axis-allows them to develop sustainable innovations;survival-intersection between the economic-pragmatic values axis and the ethical-social values axis-enhances their organization’s survival;finally,sensibility-intersection between the economic-pragmatic values axis and the ethical-social values axis-makes them more humane and more socially-responsible.The application of the TMLV,using the Fuzzy Multi-Criteria Decision Making Open Technology Assessment System,can be a great inspiration for stimulating and working with values in organizations,as well as allowing leaders to develop a values-based,high-involvement,and performance-oriented culture.Methodology/Approach-This research considers empirical data analysis of the 37 case studies of the EU-InnovatE project(http//www.euinnovate.com)-a pioneering initiative to align innovation values to integrate the end user into the process of innovation and entrepreneurship related to a sustainable lifestyle and the green economy in Europe-using a fuzzy multiple-criteria decision making method and open technologies system,such as server-side PHP language,MariaDB Database,fork of MYSQL Database Management System,and JavaScript libraries to perform operation directly on the user’s browser.Findings-The application of the TMLV model,considering empirical analysis of the extracted values from the case studies,using the Fuzzy Multi-Criteria Decision Making Open Technology Assessment System,can be a great inspiration for stimulating and working with values in João organizations,as well as allowing leaders to develop suitable strategies and interventions for shaping a sustainable high-performance culture.Research implications-This research can be a starting point for further research to assess the effectiveness of the leadership model based on a decision-making open technology system in any given organization,as well as to invite researchers who have positive passion about working with values to participate in the improvement of this tool.Originality/value-The Tri-Intersectional Model of Leadership by Values using the Fuzzy Multi-Criteria Decision Making Open Technology Assessment System is presented as an evolution in leadership models that may be used to fuel innovation,survival,and a sensibility strategic focus that is necessary to optimize human and organizational performance and deliver effective solutions to the massive array of human,financial,and social problems we face today.
文摘Objectives:Economic growth and rapid development of health technology in China have created opportunities to strengthen health technology assessment (HTA) capacity.Over the time,HTA institutions have been established to conduct HTA related work.This study reviewed the current status of HTA in China and analysed the challenges of HTA development in the context of health reform under'new normal'economy.Methods:Literature review and webpage searches were used to document the development of HTA in China.An institutional survey has also been conducted to collect information on the HTA research institutions in China.Results:The number of articles and research projects on HTA were rising and are continuing to rise.HTA development has made substantial progress in China in terms of growing number of research institutions and qualified HTA workforce.However,HTA has notable weaknesses such as low capacity for conducting HTA research,limited experience in HTA researchers,and lack of knowledge translation.Conclusion:Currently,the translation of HTA findings to policy-making is limited and the integration of HTA in the policy-making processes is still in its infancy.The HTA development in China has had opportunities due to demands of health care,health insurance,and health technology as a result of health reform.Capacity building and institutionalization of HTA are urgently needed for further development of HTA in China.
文摘Objectives:The widespread usage of traditional Chinese medicine(TCM)and the government's emphasis on TCM in China have created a positive macro-environment and great opportunities to develop and strengthen health technology assessment(HTA)in TCM.Over the past ten years,a series of policies have been issued by the government to promote the application of HTA and the development of TCM in China.This study reviews the concepts and characteristics of TCM,summarizes the current status of HTA in TCM,and analyzes the opportunities and challenges faced by HTA development in TCM with respect to deepening of healthcare reforms.Methods:Literature review and website searches were used to acquire information regarding the basic theories of TCM and the current status,opportunities,and challenges for HTA in TCM.Results:The number of articles on HTA in TCM rose substantially,especially those published in China National Knowledge Infrastructure(CNKI).With the optimistic policy environment and huge market demand for TCM,the development of HTA in TCM is expected to flourish in China.However,HTA in TCM also faces numerous challenges such as the absence of a clinical efficacy evaluation system for TCM and insufficient basic research evidence and qualified personnel.Conclusions:TCM has unique characteristic that distinguishes it from Western medicine.Currently,it is important to take all measures to address the existing main challenges and thereby take advantage of the present opportunities to develop and improve HTA in TCM.
基金This study was supported by China Center for Evidence Based Traditional Chinese Medicine,CCEBTCM(2020YJSZX-2).
文摘Hospital-based health technology assessment(HB-HTA)is highly valuable in the application of hospital medical technology,cost control,improvement of medical quality,and protection of medical safety,and its use is increasing daily globally.However,in China,HB-HTA is still in its infancy,and it is yet to be adopted in traditional Chinese medicine(TCM).Therefore,this article introduces the application and development of HB-HTA,as well as discusses the current situation of TCM and related future development strategies to provide ideas and references for the development of HB-HTA in TCM.We conclude and recommend that all major stakeholders,including the state,health departments,and hospital leaders,support and promote the exploration and development of HB-HTA in TCM hospitals and integrative medicine hospitals.We also suggest the utilization of existing talents and introduction of other necessary talents to promote better and faster organizational development,as well as suggest the formation of a national and internationally recognized HB-HTA guidance manual and toolkit for TCM hospitals based on both the national HTA guidelines and the evaluation of TCM hospitals pilot projects.Moreover,we recommend that HB-HTA pilot study should be executed with Chinese patent medicine as the starting point to form the implementation process and framework in the TCM arena.
文摘The life cycle of technology is one of the most important indexes to weigh up the risk of the investment to neo tech.There are so many uncertainties because it is conditioned by a lot of factors,we can not make a rational forecasting by traditional assessment method.So this paper gives a comprehensive consideration to the factors that influence production and makes some modification to production function, and establishes the life cycle of technology assessmet model by the method of fuzzy mathematics. So it quantifies the risk of investment.We can take it as one foundational index for the decision making of the investment.
基金Fujian Provincial Health Technology Project,No.2020GGA079Natural Science Foundation of Fujian Province,No.2021J011380National Natural Science Foundation of China,No.62276146.
文摘Acute pancreatitis(AP)is a potentially life-threatening inflammatory disease of the pancreas,with clinical management determined by the severity of the disease.Diagnosis,severity prediction,and prognosis assessment of AP typically involve the use of imaging technologies,such as computed tomography,magnetic resonance imaging,and ultrasound,and scoring systems,including Ranson,Acute Physiology and Chronic Health Evaluation II,and Bedside Index for Severity in AP scores.Computed tomography is considered the gold standard imaging modality for AP due to its high sensitivity and specificity,while magnetic resonance imaging and ultrasound can provide additional information on biliary obstruction and vascular complications.Scoring systems utilize clinical and laboratory parameters to classify AP patients into mild,moderate,or severe categories,guiding treatment decisions,such as intensive care unit admission,early enteral feeding,and antibiotic use.Despite the central role of imaging technologies and scoring systems in AP management,these methods have limitations in terms of accuracy,reproducibility,practicality and economics.Recent advancements of artificial intelligence(AI)provide new opportunities to enhance their performance by analyzing vast amounts of clinical and imaging data.AI algorithms can analyze large amounts of clinical and imaging data,identify scoring system patterns,and predict the clinical course of disease.AI-based models have shown promising results in predicting the severity and mortality of AP,but further validation and standardization are required before widespread clinical application.In addition,understanding the correlation between these three technologies will aid in developing new methods that can accurately,sensitively,and specifically be used in the diagnosis,severity prediction,and prognosis assessment of AP through complementary advantages.
基金The National Natural Science Foundation of China under contract No.41930538the Scientific Research Foundation of the Third Institute of Oceanography,Ministry of Natural Resources under contract No.2019029.
文摘Extreme storm events in coastal zones play significant roles in shaping the morphology of boulder beaches.However,boulder displacement and the geomorphological evolution of boulder beaches driven by different extreme storm events,especially typhoon events,remain poorly understood.Thus,boulder displacement and the geomorphic response on a boulder beach in Fujian,southeastern China,were explored before,during and after a cold wave event(Dec.1–7,2020)and before and after Typhoon In-Fa(Jul.19–27,2021),a large tropical storm.This was achieved by tracking 42 tagged boulders distributed in the intertidal and supratidal zones using Radio Frequency Identification(RFID)and topographic surveys using real-time kinematic techniques,respectively.The results showed obvious disparities in boulder displacement in different geomorphic zones due to cold wave and typhoon events that were mainly characterized by migration magnitude,range,direction,and mode of transport.The typhoon event led to rapid and substantial changes in the overall morphology of the boulder beach,while the cold wave event impacted the intertidal morphology of the boulder beach to only a small extent.The surrounding structure of boulders,beach slope and beach elevation had a combined dominant effect on boulder displacement under the same extreme event.Hydrodynamic factors(effective wave energy fluxes,incident wave direction,storm surge and water level)had dominant effects on boulder displacement during different extreme events.In terms of a single event,the magnitude of the boulder displacement driven by the typhoon was much greater than that driven by the cold wave.However,considering the frequency and duration of cold waves in winter,the impact of multiple consecutive cold waves on the geomorphology of the boulder beach cannot be ignored in this study area.Alternating and repeated interactions between these two processes constitute the complete geomorphic evolution of the boulder beach.This study contributes to improved predictions of the morphodynamic response of boulder beaches to future storms,especially large tropical storms,and facilitates better coastal management.
文摘The aim of the study is to comparatively assess the concentrations of lead, zinc and iron in Rivers Ase, Warri and Ethiope, in Nigeria. Monthly water samples were collected from six randomly selected sites along the rivers course. 72 water samples were collected from each river at 0 - 15 cm depths. Samples were analysed based on the standard methods recommended by the WHO for testing lead, zinc and iron. The assessment of the water quality was done using the Water Quality Index (WQI) of the Canadian Council of Ministers of the Environment (CCME-WQI). While hypotheses were tested using ANOVA. Findings indicated that CCME-WQI values were 47.3, 66.52 and 78.7. This meant that the water quality of River Ase is impaired and departed from desirable levels, while that of Warri and Ethiope were considered to occasionally be impaired and depart from desirable levels. The ANOVA model showed that there is a significant variation in heavy metal load in the selected rivers at P < 0.05. River water was put to domestic uses such as drinking (20.5%) preparing food (17.8%), bathing (19.8%), washing clothes and dishes (21.3%), brushing teeth (13.3%), and catering for domestic animals (7.5%). Poverty (49.5%) was the major reason for the use of river water for domestic purposes. The locals highlighted that they usually suffer from cholera (26.8%), diarrhoea (25.8%), dysentery (24%) and typhoid (23.5%) as a result of using the river water. The study recommended routine monitoring of anthropogenic and geologic activities, testing of the water regularly amongst others.
基金the National Key R&D Program of China(Grant No.2022YFF0503702)the National Natural Science Foundation of China(Grant Nos.42074186,41831071,42004136,and 42274195)+1 种基金the Natural Science Foundation of Jiangsu Province(Grant No.BK20211036)the Specialized Research Fund for State Key Laboratories,and the University of Science and Technology of China Research Funds of the Double First-Class Initiative(Grant No.YD2080002013).
文摘The global ionosphere maps(GIM)provided by the International GNSS Service(IGS)are extensively utilized for ionospheric morphology monitoring,scientific research,and practical application.Assessing the credibility of GIM products in data-sparse regions is of paramount importance.In this study,measurements from the Crustal Movement Observation Network of China(CMONOC)are leveraged to evaluate the suitability of IGS-GIM products over China region in 2013-2014.The indices of mean error(ME),root mean square error(RMSE),and normalized RMSE(NRMSE)are then utilized to quantify the accuracy of IGS-GIM products.Results revealed distinct local time and latitudinal dependencies in IGS-GIM errors,with substantially high errors at nighttime(NRMSE:39%)and above 40°latitude(NRMSE:49%).Seasonal differences also emerged,with larger equinoctial deviations(NRMSE:33.5%)compared with summer(20%).A preliminary analysis implied that the irregular assimilation of sparse IGS observations,compounded by China’s distinct geomagnetic topology,may manifest as error variations.These results suggest that modeling based solely on IGS-GIM observations engenders inadequate representations across China and that a thorough examination would proffer the necessary foundation for advancing regional total electron content(TEC)constructions.
基金financially supported by the Guangxi Medical University 2023 Innovation and Entrepreneurship Training Program Project(No.202310598015).
文摘Cancer patients are at high risk of malnutrition,which can lead to adverse health outcomes such as prolonged hospitalization,increased complications,and increased mortality.Accurate and timely nutritional assessment plays a critical role in effectively managing malnutrition in these patients.However,while many tools exist to assess malnutrition,there is no universally accepted standard.Although different tools have their own strengths and limitations,there is a lack of narrative reviews on nutritional assessment tools for cancer patients.To address this knowledge gap,we conducted a non-systematic literature search using PubMed,Embase,Web of Science,and the Cochrane Library from their inception until May 2023.A total of 90 studies met our selection criteria and were included in our narrative review.We evaluated the applications,strengths,and limitations of 4 commonly used nutritional assessment tools for cancer patients:the Subjective Global Assessment(SGA),Patient-Generated Subjective Global Assessment(PG-SGA),Mini Nutritional Assessment(MNA),and Global Leadership Initiative on Malnutrition(GLIM).Our findings revealed that malnutrition was associated with adverse health outcomes.Each of these 4 tools has its applications,strengths,and limitations.Our findings provide medical staff with a foundation for choosing the optimal tool to rapidly and accurately assess malnutrition in cancer patients.It is essential for medical staff to be familiar with these common tools to ensure effective nutritional management of cancer patients.
基金supported by the projects of the China Geological Survey(DD20221729,DD20190291)Zhuhai Urban Geological Survey(including informatization)(MZCD–2201–008).
文摘Machine learning is currently one of the research hotspots in the field of landslide prediction.To clarify and evaluate the differences in characteristics and prediction effects of different machine learning models,Conghua District,which is the most prone to landslide disasters in Guangzhou,was selected for landslide susceptibility evaluation.The evaluation factors were selected by using correlation analysis and variance expansion factor method.Applying four machine learning methods namely Logistic Regression(LR),Random Forest(RF),Support Vector Machines(SVM),and Extreme Gradient Boosting(XGB),landslide models were constructed.Comparative analysis and evaluation of the model were conducted through statistical indices and receiver operating characteristic(ROC)curves.The results showed that LR,RF,SVM,and XGB models have good predictive performance for landslide susceptibility,with the area under curve(AUC)values of 0.752,0.965,0.996,and 0.998,respectively.XGB model had the highest predictive ability,followed by RF model,SVM model,and LR model.The frequency ratio(FR)accuracy of LR,RF,SVM,and XGB models was 0.775,0.842,0.759,and 0.822,respectively.RF and XGB models were superior to LR and SVM models,indicating that the integrated algorithm has better predictive ability than a single classification algorithm in regional landslide classification problems.
文摘As a basic technology at physical layer of mobile communications,non-orthogonal multiple access has been attracting wide attention across the academia and the industry.During the standardization of the fifth-generation(5G)of mobile communications,3GPP conducted preliminary study on non-orthogonal multiple access without reaching the consensus to standardize the technology.
文摘The Nigerian oil sands represent the largest oil sand deposit in Africa, yet there is little published information on the distribution and potential health and ecological risks of trace elements in the oil resource. In the present study, we investigated the distribution pattern of 18trace elements(including biophile and chalcophile elements) as well as the estimated risks associated with exposure to these elements. The results of the study indicated that Fe was the most abundant element, with a mean concentration of 22,131 mg/kg while Br had the lowest mean concentration of 48 mg/kg. The high occurrence of Fe and Ti suggested a possible occurrence of ilmenite(Fe TiO_(3)) in the oil sands. Source apportionment using positive matrix factorization showed that the possible sources of detected elements in the oil sands were geogenic, metal production, and crustal. The contamination factor, geo-accumulation index, modified degree of contamination, pollution load index, and Nemerow pollution index indicated that the oil sands are heavily polluted by the elements. Health risk assessment showed that children were relatively more susceptible to the potentially toxic elements in the oil sands principally via ingestion exposure route(HQ > 1E-04). Cancer risks from inhalation are unlikely due to CR < 1E-06 but ingestion and dermal contact pose severe risks(CR > 1E-04). The high concentrations of the elements pose serious threats due to the potential for atmospheric transport, bioaccessibility, and bioavailability.
基金supported by the National Natural Science Foundation of China(52009140).
文摘Quantitative assessment of the impact of climate variability and human activities on runoff plays a pivotal role in water resource management and maintaining ecosystem integrity.This study considered six sub-basins in the upper reaches of the Yangtze River basin,China,to reveal the trend of the runoff evolution and clarify the driving factors of the changes during 1956–2020.Linear regression,Mann-Kendall test,and sliding t-test were used to study the trend of the hydrometeorological elements,while cumulative distance level and ordered clustering methods were applied to identify mutation points.The contributions of climate change and human disturbance to runoff changes were quantitatively assessed using three methods,i.e.,the rainfall-runoff relationship method,slope variation method,and variable infiltration capacity(Budyko)hypothesis method.Then,the availability and stability of the three methods were compared.The results showed that the runoff in the upper reaches of the Yangtze River basin exhibited a decreasing trend from 1956 to 2020,with an abrupt change in 1985.For attribution analysis,the runoff series could be divided into two phases,i.e.,1961–1985(baseline period)and 1986–2020(changing period);and it was found that the rainfall-runoff relationship method with precipitation as the representative of climate factors had limited usability compared with the other two methods,while the slope variation and Budyko hypothesis methods had highly consistent results.Different factors showed different effects in the sub-basins of the upper reaches of the Yangtze River basin.Moreover,human disturbance was the main factor that contributed to the runoff changes,accounting for 53.0%–82.0%;and the contribution of climate factors to the runoff change was 17.0%–47.0%,making it the secondary factor,in which precipitation was the most representative climate factor.These results provide insights into how climate and anthropogenic changes synergistically influence the runoff of the upper reaches of the Yangtze River basin.
文摘Cancer is a leading cause of death worldwide, with breast cancer being the most common (2.26 million new cases and 685,000 deaths). In Saudi Arabia, breast cancer ranked the first among females in 2014, accounting for 15.9% of all cancers reported among Saudi nationals and 28.7% of all cancers reported among females of all ages. Early detection of breast cancer could decrease the risks, have a better prognosis, and have better outcomes/more successful treatments. Prevalence of breast cancer reached more than 25% of all diagnosed cancer in the kingdom among women. Aim: This study aims to assess the knowledge and performance of women attending primary care centers about breast self-examination and mammogram screening for prevention and early detection of breast cancer in Abha city primary healthcare centers, Kingdom of Saudi Arabia. Research Method: cross sectional design was conducted by using questionnaire, which was distributed to primary care center nurses. The collected data was statistically analyzed using the Statistical Package for Social Sciences, version 25. Results: The study found that participants had poor awareness and knowledge about breast self-examination, risk factors for breast cancer, and trends and practices in early diagnosis of breast cancer. Conclusion and Recommendations: It recommends increasing awareness campaigns and providing educational programs to improve knowledge and practices.
基金This work is supported by the National Natural Science Foundation of China(Nos.72071150,71871174).
文摘Cardiovascular disease(CVD)has gradually become one of the main causes of harm to the life and health of residents.Exploring the influencing factors and risk assessment methods of CVD has become a general trend.In this paper,a machine learning-based decision-making mechanism for risk assessment of CVD is designed.In this mechanism,the logistics regression analysismethod and factor analysismodel are used to select age,obesity degree,blood pressure,blood fat,blood sugar,smoking status,drinking status,and exercise status as the main pathogenic factors of CVD,and an index systemof risk assessment for CVD is established.Then,a two-stage model combining K-means cluster analysis and random forest(RF)is proposed to evaluate and predict the risk of CVD,and the predicted results are compared with the methods of Bayesian discrimination,K-means cluster analysis and RF.The results show that thepredictioneffect of theproposedtwo-stagemodel is better than that of the comparedmethods.Moreover,several suggestions for the government,the medical industry and the public are provided based on the research results.
基金the National Natural Science Foundation of China(U2033213)the Fundamental Research Funds for the Central Universities(FZ2021ZZ01,FZ2022ZX50).
文摘With the development of the integration of aviation safety and artificial intelligence,research on the combination of risk assessment and artificial intelligence is particularly important in the field of risk management,but searching for an efficient and accurate risk assessment algorithm has become a challenge for the civil aviation industry.Therefore,an improved risk assessment algorithm(PS-AE-LSTM)based on long short-term memory network(LSTM)with autoencoder(AE)is proposed for the various supervised deep learning algorithms in flight safety that cannot adequately address the problem of the quality on risk level labels.Firstly,based on the normal distribution characteristics of flight data,a probability severity(PS)model is established to enhance the quality of risk assessment labels.Secondly,autoencoder is introduced to reconstruct the flight parameter data to improve the data quality.Finally,utilizing the time-series nature of flight data,a long and short-termmemory network is used to classify the risk level and improve the accuracy of risk assessment.Thus,a risk assessment experimentwas conducted to analyze a fleet landing phase dataset using the PS-AE-LSTMalgorithm to assess the risk level associated with aircraft hard landing events.The results show that the proposed algorithm achieves an accuracy of 86.45%compared with seven baseline models and has excellent risk assessment capability.
基金supported by the National Natural Science Foundation of China (No.72071150).
文摘Stroke is a chronic cerebrovascular disease that carries a high risk.Stroke risk assessment is of great significance in preventing,reversing and reducing the spread and the health hazards caused by stroke.Aiming to objectively predict and identify strokes,this paper proposes a new stroke risk assessment decision-making model named Logistic-AdaBoost(Logistic-AB)based on machine learning.First,the categorical boosting(CatBoost)method is used to perform feature selection for all features of stroke,and 8 main features are selected to form a new index evaluation system to predict the risk of stroke.Second,the borderline synthetic minority oversampling technique(SMOTE)algorithm is applied to transform the unbalanced stroke dataset into a balanced dataset.Finally,the stroke risk assessment decision-makingmodel Logistic-AB is constructed,and the overall prediction performance of this new model is evaluated by comparing it with ten other similar models.The comparison results show that the new model proposed in this paper performs better than the two single algorithms(logistic regression and AdaBoost)on the four indicators of recall,precision,F1 score,and accuracy,and the overall performance of the proposed model is better than that of common machine learning algorithms.The Logistic-AB model presented in this paper can more accurately predict patients’stroke risk.
