Artificial intelligence(AI),a branch of machine learning(ML)has been increasingly employed in the research of trauma in various aspects.Hemorrhage is the most common cause of trauma-related death.To better elucidate t...Artificial intelligence(AI),a branch of machine learning(ML)has been increasingly employed in the research of trauma in various aspects.Hemorrhage is the most common cause of trauma-related death.To better elucidate the current role of AI and contribute to future development of ML in trauma care,we conducted a review focused on the use of ML in the diagnosis or treatment strategy of traumatic hemorrhage.A literature search was carried out on PubMed and Google scholar.Titles and abstracts were screened and,if deemed appropriate,the full articles were reviewed.We included 89 studies in the review.These studies could be grouped into five areas:(1)prediction of outcomes;(2)risk assessment and injury severity for triage;(3)prediction of transfusions;(4)detection of hemorrhage;and(5)prediction of coagulopathy.Performance analysis of ML in comparison with current standards for trauma care showed that most studies demonstrated the benefits of ML models.However,most studies were retrospective,focused on prediction of mortality,and development of patient outcome scoring systems.Few studies performed model assessment via test datasets obtained from different sources.Prediction models for transfusions and coagulopathy have been developed,but none is in widespread use.AI-enabled ML-driven technology is becoming integral part of the whole course of trauma care.Comparison and application of ML algorithms using different datasets from initial training,testing and validation in prospective and randomized controlled trials are warranted for provision of decision support for individualized patient care as far forward as possible.展开更多
Background: Musculoskeletal injuries(MSkIs) are a leading cause of health care utilization, as well as limited duty and disability in the US military and other armed forces. MSkIs affect members of the military during...Background: Musculoskeletal injuries(MSkIs) are a leading cause of health care utilization, as well as limited duty and disability in the US military and other armed forces. MSkIs affect members of the military during initial training,operational training, and deployment and have a direct negative impact on overall troop readiness. Currently, a systematic overview of all risk factors for MSkIs in the military is not available.Methods: A systematic literature search was carried out using the PubMed, Ovid/Medline, and Web of Science databases from January 1, 2000 to September 10, 2019. Additionally, a reference list scan was performed(using the “snowball method”). Thereafter, an international, multidisciplinary expert panel scored the level of evidence per risk factor, and a classification of modifiable/non-modifiable was made.Results: In total, 176 original papers and 3 meta-analyses were included in the review. A list of 57 reported potential risk factors was formed. For 21 risk factors, the level of evidence was considered moderate or strong. Based on this literature review and an in-depth analysis, the expert panel developed a model to display the most relevant risk factors identified, introducing the idea of the “order of importance” and including concepts that are modifiable/nonmodifiable, as well as extrinsic/intrinsic risk factors.Conclusions: This is the qualitative systematic review of studies on risk factors for MSkIs in the military that has attempted to be all-inclusive. A total of 57 different potential risk factors were identified, and a new, prioritizing injury model was developed. This model may help us to understand risk factors that can be addressed, and in which order they should be prioritized when planning intervention strategies within military groups.展开更多
The bootstrap resampling method is applied to an ensemble artificial neural network (ANN) approach (which combines machine learning with physical data obtained from a numerical weather prediction model) to provide a m...The bootstrap resampling method is applied to an ensemble artificial neural network (ANN) approach (which combines machine learning with physical data obtained from a numerical weather prediction model) to provide a multi-ANN model super-ensemble for application to multi-step-ahead forecasting of wind speed and of the associated power generated from a wind turbine. A statistical combination of the individual forecasts from the various ANNs of the super-ensemble is used to construct the best deterministic forecast, as well as the prediction uncertainty interval associated with this forecast. The bootstrapped neural-network methodology is validated using measured wind speed and power data acquired from a wind turbine in an operational wind farm located in northern China.展开更多
Hemorrhage is the leading cause of preventable death in combat trauma and the secondary cause of death in civilian trauma.A significant number of deaths due to hemorrhage occur before and in the first hour after hospi...Hemorrhage is the leading cause of preventable death in combat trauma and the secondary cause of death in civilian trauma.A significant number of deaths due to hemorrhage occur before and in the first hour after hospital arrival.A literature search was performed through PubMed,Scopus,and Institute of Scientific Information databases for English language articles using terms relating to hemostatic agents,prehospital,battlefield or combat dressings,and prehospital hemostatic resuscitation,followed by cross-reference searching.Abstracts were screened to determine relevance and whether appropriate further review of the original articles was warranted.Based on these findings,this paper provides a review of a variety of hemostatic agents ranging from clinically approved products for human use to newly developed concepts with great potential for use in prehospital settings.These hemostatic agents can be administered either systemically or locally to stop bleeding through different mechanisms of action.Comparisons of current hemostatic products and further directions for prehospital hemorrhage control are also discussed.展开更多
This paper presents a flight control design for an unmanned aerial vehicle （UAV） using a nonlinear autoregressive moving average （NARMA-L2） neural network based feedback linearization and output redefinition techn...This paper presents a flight control design for an unmanned aerial vehicle （UAV） using a nonlinear autoregressive moving average （NARMA-L2） neural network based feedback linearization and output redefinition technique. The UAV investigated is non- minimum phase. The output redefinition technique is used in such a way that the resulting system to be inverted is a minimum phase system. The NARMA-L2 neural network is trained off-line for forward dynamics of the UAV model with redefined output and is then inverted to force the real output to approximately track a command input. Simulation results show that the proposed approaches have good performance.展开更多
基金Defence Research and Development Canada,Program Activity PEOPLE_014.
文摘Artificial intelligence(AI),a branch of machine learning(ML)has been increasingly employed in the research of trauma in various aspects.Hemorrhage is the most common cause of trauma-related death.To better elucidate the current role of AI and contribute to future development of ML in trauma care,we conducted a review focused on the use of ML in the diagnosis or treatment strategy of traumatic hemorrhage.A literature search was carried out on PubMed and Google scholar.Titles and abstracts were screened and,if deemed appropriate,the full articles were reviewed.We included 89 studies in the review.These studies could be grouped into five areas:(1)prediction of outcomes;(2)risk assessment and injury severity for triage;(3)prediction of transfusions;(4)detection of hemorrhage;and(5)prediction of coagulopathy.Performance analysis of ML in comparison with current standards for trauma care showed that most studies demonstrated the benefits of ML models.However,most studies were retrospective,focused on prediction of mortality,and development of patient outcome scoring systems.Few studies performed model assessment via test datasets obtained from different sources.Prediction models for transfusions and coagulopathy have been developed,but none is in widespread use.AI-enabled ML-driven technology is becoming integral part of the whole course of trauma care.Comparison and application of ML algorithms using different datasets from initial training,testing and validation in prospective and randomized controlled trials are warranted for provision of decision support for individualized patient care as far forward as possible.
文摘Background: Musculoskeletal injuries(MSkIs) are a leading cause of health care utilization, as well as limited duty and disability in the US military and other armed forces. MSkIs affect members of the military during initial training,operational training, and deployment and have a direct negative impact on overall troop readiness. Currently, a systematic overview of all risk factors for MSkIs in the military is not available.Methods: A systematic literature search was carried out using the PubMed, Ovid/Medline, and Web of Science databases from January 1, 2000 to September 10, 2019. Additionally, a reference list scan was performed(using the “snowball method”). Thereafter, an international, multidisciplinary expert panel scored the level of evidence per risk factor, and a classification of modifiable/non-modifiable was made.Results: In total, 176 original papers and 3 meta-analyses were included in the review. A list of 57 reported potential risk factors was formed. For 21 risk factors, the level of evidence was considered moderate or strong. Based on this literature review and an in-depth analysis, the expert panel developed a model to display the most relevant risk factors identified, introducing the idea of the “order of importance” and including concepts that are modifiable/nonmodifiable, as well as extrinsic/intrinsic risk factors.Conclusions: This is the qualitative systematic review of studies on risk factors for MSkIs in the military that has attempted to be all-inclusive. A total of 57 different potential risk factors were identified, and a new, prioritizing injury model was developed. This model may help us to understand risk factors that can be addressed, and in which order they should be prioritized when planning intervention strategies within military groups.
文摘The bootstrap resampling method is applied to an ensemble artificial neural network (ANN) approach (which combines machine learning with physical data obtained from a numerical weather prediction model) to provide a multi-ANN model super-ensemble for application to multi-step-ahead forecasting of wind speed and of the associated power generated from a wind turbine. A statistical combination of the individual forecasts from the various ANNs of the super-ensemble is used to construct the best deterministic forecast, as well as the prediction uncertainty interval associated with this forecast. The bootstrapped neural-network methodology is validated using measured wind speed and power data acquired from a wind turbine in an operational wind farm located in northern China.
基金Canadian Forces Health Services and Defence Research and Development Canada for their support
文摘Hemorrhage is the leading cause of preventable death in combat trauma and the secondary cause of death in civilian trauma.A significant number of deaths due to hemorrhage occur before and in the first hour after hospital arrival.A literature search was performed through PubMed,Scopus,and Institute of Scientific Information databases for English language articles using terms relating to hemostatic agents,prehospital,battlefield or combat dressings,and prehospital hemostatic resuscitation,followed by cross-reference searching.Abstracts were screened to determine relevance and whether appropriate further review of the original articles was warranted.Based on these findings,this paper provides a review of a variety of hemostatic agents ranging from clinically approved products for human use to newly developed concepts with great potential for use in prehospital settings.These hemostatic agents can be administered either systemically or locally to stop bleeding through different mechanisms of action.Comparisons of current hemostatic products and further directions for prehospital hemorrhage control are also discussed.
文摘This paper presents a flight control design for an unmanned aerial vehicle （UAV） using a nonlinear autoregressive moving average （NARMA-L2） neural network based feedback linearization and output redefinition technique. The UAV investigated is non- minimum phase. The output redefinition technique is used in such a way that the resulting system to be inverted is a minimum phase system. The NARMA-L2 neural network is trained off-line for forward dynamics of the UAV model with redefined output and is then inverted to force the real output to approximately track a command input. Simulation results show that the proposed approaches have good performance.
