The overall healthcare system has been prioritized within development top lists worldwide.Since many national populations are aging,combined with the availability of sophisticated medical treatments,healthcare expendi...The overall healthcare system has been prioritized within development top lists worldwide.Since many national populations are aging,combined with the availability of sophisticated medical treatments,healthcare expenditures are rapidly growing.Blood banks are a major component of any healthcare system,which store and provide the blood products needed for organ transplants,emergency medical treatments,and routine surgeries.Timely delivery of blood products is vital,especially in emergency settings.Hence,blood delivery process parameters such as safety and speed have received attention in the literature,as well as other parameters such as delivery cost.In this paper,delivery time and cost are modeled mathematically and marked as objective functions requiring simultaneous optimization.A solution is proposed based on Deep Reinforcement Learning(DRL)to address the formulated delivery functions as Multi-objective Optimization Problems(MOPs).The basic concept of the solution is to decompose the MOP into a scalar optimization sub-problems set,where each one of these sub-problems is modeled as a separate Neural Network(NN).The overall model parameters for each sub-problem are optimized based on a neighborhood parameter transfer and DRL training algorithm.The optimization step for the subproblems is undertaken collaboratively to optimize the overall model.Paretooptimal solutions can be directly obtained using the trained NN.Specifically,the multi-objective blood bank delivery problem is addressed in this research.Onemajor technical advantage of this approach is that once the trainedmodel is available,it can be scaled without the need formodel retraining.The scoring can be obtained directly using a straightforward computation of the NN layers in a limited time.The proposed technique provides a set of technical strength points such as the ability to generalize and solve rapidly compared to othermulti-objective optimizationmethods.The model was trained and tested on 5 major hospitals in Saudi Arabia’s Riyadh region,and the simulation results indicated that time and cost decreased by 35%and 30%,respectively.In particular,the proposed model outperformed other state-of-the-art MOP solutions such as Genetic Algorithms and Simulated Annealing.展开更多
AIM: Hyperglycemia commonly seen in liver transplantation (LT) has often been attributed to the dextrose in the storage solution of blood transfusion products. The purpose of the study is to compare the changes of the...AIM: Hyperglycemia commonly seen in liver transplantation (LT) has often been attributed to the dextrose in the storage solution of blood transfusion products. The purpose of the study is to compare the changes of the blood glucose levels in transfused and non-transfused patients during LT. METHODS: A retrospective study on 60 biliary pediatric patients and 16 adult patients undergoing LT was carried out. Transfused pediatric patients were included in Group Ⅰ (GⅠ), those not transfused in Group Ⅱ (GⅡ). Twelve adult patients were not given transfusion and assigned to Group Ⅲ(GⅢ); whereas, four adult patients who received massive transfusion were assigned to Group Ⅳ (GⅣ). The blood glucose levels, volume of blood transfused, and the volume of crystalloid infused were recorded, compared and analyzed. RESULTS: Results showed that the changes in blood glucose levels during LT for both non-transfused and minimally transfused pediatric groups and non-transfused and massively-transfused adult groups were almost the same. CONCLUSION: We conclude that blood transfusion does not cause significant changes in the blood glucose levels in this study.展开更多
Objective:To screen the blood group system genes of Duffy,Lutheran,Kidd,Diego,Dombrock blood group systems of Li ethnic group in Hainan Province and provide laboratory data for the rare blood group database in this ar...Objective:To screen the blood group system genes of Duffy,Lutheran,Kidd,Diego,Dombrock blood group systems of Li ethnic group in Hainan Province and provide laboratory data for the rare blood group database in this area.Methods:The alleles of Duffy,Lutheran,Kidd,Diego,Dombrock blood group systems of 300 voluntary participants of Li ethnic group in Hainan were detected by sequence-specific primer polymerase chain reaction,and the polymorphism was analyzed.Results:The allele frequencies of Duffy,Lutheran,Kidd,Diego,Dombrock blood group systems of Li ethnic groups in Hainan Province are 0.9583 for Fy^(a),0.0417 for Fy^(b),0.8350 for Au^(a),0.1650 for Au^(b),0.4500 for Jk^(a),0.5500 for Jk^(b),0.0667 for Di^(a),0.9333 for Di^(b),0.1017 for Doa and 0.8983 for Dob,respectively.The antigen incompatibility rates of Fy^(a)/Fy^(b),Au^(a)/Au^(b),Jk^(a)/Jk^(b),Di^(a)/Di^(b),Doa/Dob of Duffy,Lutheran,Kidd,Diego,Dombrock blood group systems were 7.67%,23.76%,37.25%,11.67%and 16.60%,respectively.Conclusion:The gene frequencies of Duffy,Lutheran,Kidd,Diego,Dombrock blood group systems of Li ethnic group in Hainan Province are polymorphic,and the antigen incompatibility rates of alleles are higher,which is quite different from that of other nationalities in China and with unique ethnic distribution characteristics.It is of great significance to establish the rare blood group database in this region.展开更多
This article presents an optimized approach of mathematical techniques in themedical domain by manoeuvring the phenomenon of ant colony optimization algorithm(also known as ACO).A complete graph of blood banks and a p...This article presents an optimized approach of mathematical techniques in themedical domain by manoeuvring the phenomenon of ant colony optimization algorithm(also known as ACO).A complete graph of blood banks and a path that covers all the blood banks without repeating any link is required by applying the Travelling Salesman Problem(often TSP).The wide use promises to accelerate and offers the opportunity to cultivate health care,particularly in remote or unmerited environments by shrinking lab testing reversal times,empowering just-in-time lifesaving medical supply.展开更多
文摘The overall healthcare system has been prioritized within development top lists worldwide.Since many national populations are aging,combined with the availability of sophisticated medical treatments,healthcare expenditures are rapidly growing.Blood banks are a major component of any healthcare system,which store and provide the blood products needed for organ transplants,emergency medical treatments,and routine surgeries.Timely delivery of blood products is vital,especially in emergency settings.Hence,blood delivery process parameters such as safety and speed have received attention in the literature,as well as other parameters such as delivery cost.In this paper,delivery time and cost are modeled mathematically and marked as objective functions requiring simultaneous optimization.A solution is proposed based on Deep Reinforcement Learning(DRL)to address the formulated delivery functions as Multi-objective Optimization Problems(MOPs).The basic concept of the solution is to decompose the MOP into a scalar optimization sub-problems set,where each one of these sub-problems is modeled as a separate Neural Network(NN).The overall model parameters for each sub-problem are optimized based on a neighborhood parameter transfer and DRL training algorithm.The optimization step for the subproblems is undertaken collaboratively to optimize the overall model.Paretooptimal solutions can be directly obtained using the trained NN.Specifically,the multi-objective blood bank delivery problem is addressed in this research.Onemajor technical advantage of this approach is that once the trainedmodel is available,it can be scaled without the need formodel retraining.The scoring can be obtained directly using a straightforward computation of the NN layers in a limited time.The proposed technique provides a set of technical strength points such as the ability to generalize and solve rapidly compared to othermulti-objective optimizationmethods.The model was trained and tested on 5 major hospitals in Saudi Arabia’s Riyadh region,and the simulation results indicated that time and cost decreased by 35%and 30%,respectively.In particular,the proposed model outperformed other state-of-the-art MOP solutions such as Genetic Algorithms and Simulated Annealing.
文摘AIM: Hyperglycemia commonly seen in liver transplantation (LT) has often been attributed to the dextrose in the storage solution of blood transfusion products. The purpose of the study is to compare the changes of the blood glucose levels in transfused and non-transfused patients during LT. METHODS: A retrospective study on 60 biliary pediatric patients and 16 adult patients undergoing LT was carried out. Transfused pediatric patients were included in Group Ⅰ (GⅠ), those not transfused in Group Ⅱ (GⅡ). Twelve adult patients were not given transfusion and assigned to Group Ⅲ(GⅢ); whereas, four adult patients who received massive transfusion were assigned to Group Ⅳ (GⅣ). The blood glucose levels, volume of blood transfused, and the volume of crystalloid infused were recorded, compared and analyzed. RESULTS: Results showed that the changes in blood glucose levels during LT for both non-transfused and minimally transfused pediatric groups and non-transfused and massively-transfused adult groups were almost the same. CONCLUSION: We conclude that blood transfusion does not cause significant changes in the blood glucose levels in this study.
基金Hainan Provincial Natural Science Foundation of China(No.820QN410)Hainan Province Clinical Medical Center(No.QWYH202175)。
文摘Objective:To screen the blood group system genes of Duffy,Lutheran,Kidd,Diego,Dombrock blood group systems of Li ethnic group in Hainan Province and provide laboratory data for the rare blood group database in this area.Methods:The alleles of Duffy,Lutheran,Kidd,Diego,Dombrock blood group systems of 300 voluntary participants of Li ethnic group in Hainan were detected by sequence-specific primer polymerase chain reaction,and the polymorphism was analyzed.Results:The allele frequencies of Duffy,Lutheran,Kidd,Diego,Dombrock blood group systems of Li ethnic groups in Hainan Province are 0.9583 for Fy^(a),0.0417 for Fy^(b),0.8350 for Au^(a),0.1650 for Au^(b),0.4500 for Jk^(a),0.5500 for Jk^(b),0.0667 for Di^(a),0.9333 for Di^(b),0.1017 for Doa and 0.8983 for Dob,respectively.The antigen incompatibility rates of Fy^(a)/Fy^(b),Au^(a)/Au^(b),Jk^(a)/Jk^(b),Di^(a)/Di^(b),Doa/Dob of Duffy,Lutheran,Kidd,Diego,Dombrock blood group systems were 7.67%,23.76%,37.25%,11.67%and 16.60%,respectively.Conclusion:The gene frequencies of Duffy,Lutheran,Kidd,Diego,Dombrock blood group systems of Li ethnic group in Hainan Province are polymorphic,and the antigen incompatibility rates of alleles are higher,which is quite different from that of other nationalities in China and with unique ethnic distribution characteristics.It is of great significance to establish the rare blood group database in this region.
文摘This article presents an optimized approach of mathematical techniques in themedical domain by manoeuvring the phenomenon of ant colony optimization algorithm(also known as ACO).A complete graph of blood banks and a path that covers all the blood banks without repeating any link is required by applying the Travelling Salesman Problem(often TSP).The wide use promises to accelerate and offers the opportunity to cultivate health care,particularly in remote or unmerited environments by shrinking lab testing reversal times,empowering just-in-time lifesaving medical supply.
