scholarly journals Intelligent prediction of RBC demand in trauma patients using decision tree methods

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Yan-Nan Feng ◽  
Zhen-Hua Xu ◽  
Jun-Ting Liu ◽  
Xiao-Lin Sun ◽  
De-Qing Wang ◽  
...  
Keyword(s):  
Blood Transfusion ◽  
Decision Tree ◽  
Blood Cell ◽  
Prediction Model ◽  
Red Blood Cell ◽  
Vital Signs ◽  
Trauma Patients ◽  
Decision Tree Algorithm ◽  
Non Invasive ◽  
Prediction Parameters

Abstract Background The vital signs of trauma patients are complex and changeable, and the prediction of blood transfusion demand mainly depends on doctors’ experience and trauma scoring system; therefore, it cannot be accurately predicted. In this study, a machine learning decision tree algorithm [classification and regression tree (CRT) and eXtreme gradient boosting (XGBoost)] was proposed for the demand prediction of traumatic blood transfusion to provide technical support for doctors. Methods A total of 1371 trauma patients who were diverted to the Emergency Department of the First Medical Center of Chinese PLA General Hospital from January 2014 to January 2018 were collected from an emergency trauma database. The vital signs, laboratory examination parameters and blood transfusion volume were used as variables, and the non-invasive parameters and all (non-invasive + invasive) parameters were used to construct an intelligent prediction model for red blood cell (RBC) demand by logistic regression (LR), CRT and XGBoost. The prediction accuracy of the model was compared with the area under the curve (AUC). Results For non-invasive parameters, the LR method was the best, with an AUC of 0.72 [95% confidence interval (CI) 0.657–0.775], which was higher than the CRT (AUC 0.69, 95% CI 0.633–0.751) and the XGBoost (AUC 0.71, 95% CI 0.654–0.756, P < 0.05). The trauma location and shock index are important prediction parameters. For all the prediction parameters, XGBoost was the best, with an AUC of 0.94 (95% CI 0.893–0.981), which was higher than the LR (AUC 0.80, 95% CI 0.744–0.850) and the CRT (AUC 0.82, 95% CI 0.779–0.853, P < 0.05). Haematocrit (Hct) is an important prediction parameter. Conclusions The classification performance of the intelligent prediction model of red blood cell transfusion in trauma patients constructed by the decision tree algorithm is not inferior to that of the traditional LR method. It can be used as a technical support to assist doctors to make rapid and accurate blood transfusion decisions in emergency rescue environment, so as to improve the success rate of patient treatment.

scholarly journals Intelligent Prediction of RBC Demand in Trauma Patients

2020 ◽  
Author(s):  
Yannan Feng ◽  
Zhenhua Xu ◽  
Junting Liu ◽  
Xiaolin Sun ◽  
Deqing Wang ◽  
...  
Keyword(s):  
Blood Transfusion ◽  
Decision Tree ◽  
Prediction Model ◽  
Vital Signs ◽  
Technical Support ◽  
Trauma Patients ◽  
Decision Tree Algorithm ◽  
Tree Algorithm ◽  
Non Invasive ◽  
Prediction Parameters

Abstract Background: The vital signs of trauma patients are complex and changeable, and the prediction of blood transfusion demand mainly depends on doctors' experience and trauma scoring system, therefore it can’t be accurately predicted. In this study, the decision tree algorithm (Classification and Regression Tree, CRT and eXtreme Gradient Boosting, XGboost) of machine learning were proposed to the demand prediction of traumatic blood transfusion, hoping to provide technical support for doctors.Methods: Total 1371 trauma patients who were diverted to the emergency department from 2014.1 to 2018.1 were collected from the emergency trauma database. The vital signs, laboratory examination parameters and blood transfusion volume were used as variables, and the non-invasive parameters and all (non-invasive + invasive) parameters were used to construct the intelligent prediction model of RBC demand by logistic regression (LR), CRT and Xgboost. The prediction accuracy of the model was compared with the Area Under Curve (AUC). Results: The studies we have performed showed that non-invasive parameters were used to predict blood transfusion, LR method was the best, AUC 0.72 (95% confidence interval [CI] 0.657-0.775), highest than CRT AUC 0.69 (95%CI 0.633-0.751) and Xgboost AUC 0.71 (95%CI 0.654-0.756) (P<0.05). Trauma site and shock index are important prediction parameters. All the parameters to predict, Xgboost was the best with AUC 0.94 (95%CI 0.893-0.981), which was highest than LR AUC 0.80 (95%CI 0.744-0.850) and CRT AUC 0.82 (95%CI 0.779-0.853) (P<0.05). Hematocrit/Hemoglobin are important prediction parameters. Conclusions: The prediction model of red blood cell transfusion in trauma patients constructed by decision tree algorithm can be used as a technical support to assist doctors to make rapid and accurate blood transfusion decisions in emergency rescue environment, so as to improve the success rate of patient treatment.

scholarly journals Intelligent prediction of RBC demand in trauma patients using decision tree methods

2020 ◽  
Author(s):  
Yannan Feng ◽  
Zhenhua Xu ◽  
Junting Liu ◽  
Xiaolin Sun ◽  
Deqing Wang ◽  
...  
Keyword(s):  
Blood Transfusion ◽  
Decision Tree ◽  
Prediction Model ◽  
Vital Signs ◽  
Trauma Patients ◽  
Decision Tree Algorithm ◽  
Tree Algorithm ◽  
Non Invasive ◽  
Extreme Gradient Boosting ◽  
Prediction Parameters

Abstract Background: The vital signs of trauma patients are complex and changeable, and the prediction of blood transfusion demand mainly depends on doctors' experience and trauma scoring system; therefore, it cannot be accurately predicted. In this study, a machine learning decision tree algorithm (classification and regression tree, CRT and eXtreme gradient boosting, XGBoost) was proposed for the demand prediction of traumatic blood transfusion to provide technical support for doctors. Methods: A total of 1,371 trauma patients who were diverted to the emergency department from January 2014 to January 2018 were collected from an emergency trauma database. The vital signs, laboratory examination parameters and blood transfusion volume were used as variables, and the non-invasive parameters and all (non-invasive + invasive) parameters were used to construct an intelligent prediction model for RBC demand by logistic regression (LR), CRT and XGBoost. The prediction accuracy of the model was compared with the area under the curve (AUC).Results: The studies we performed showed that non-invasive parameters were used to predict blood transfusion. The LR method was the best, with an AUC of 0.72 (95% confidence interval [CI] 0.657-0.775), which was higher than the CRT AUC of 0.69 (95% CI 0.633-0.751) and the XGBoost AUC of 0.71 (95% CI 0.654-0.756) (P<0.05). The trauma site and shock index are important prediction parameters. For all the prediction parameters, XGBoost was the best, with an AUC of 0.94 (95% CI 0.893-0.981), which was higher than the LR AUC of 0.80 (95% CI 0.744-0.850) and the CRT AUC of 0.82 (95% CI 0.779-0.853) (P<0.05). Haematocrit/Haemoglobin is an important prediction parameter. Conclusions: The classification performance of the intelligent prediction model constructed by the decision tree algorithm is not inferior to that of the traditional LR method. With the increase in the data quantity, the accuracy of the model improved in the iteration process, and the prediction performance continuously improved, which is conducive to clinical application and wide promotion.

scholarly journals BLOOD TRANSFUSION IN CARDIAC SURGERY- NEED TO FOLLOW BASICS!

2020 ◽  
Vol 7 (3) ◽  
Keyword(s):  
Cardiac Surgery ◽  
Blood Transfusion ◽  
Blood Cell ◽  
Red Blood Cell ◽  
Red Blood Cell Transfusion ◽  
Transfusion Strategy ◽  
Transfusion Threshold ◽  
Restrictive Transfusion ◽  
Conflicting Evidence ◽  
American Society

More and more data is coming in recent times about hazards of blood transfusion. In a landmark TRICC1 trial Euvolemic patients in the intensive care unit (ICU) with Hb<9 g/dl were randomized to a restrictive transfusion strategy for transfusion of PRBCs (transfused if Hb<7 g/dl to maintain Hb between 7 and 9 g/dl) or a liberal strategy (transfused if Hb<10 g/dl to maintain Hb 10-12 g/dl). Mortality was similar in both groups, indicating that liberal transfusions were not beneficial. An Updated Report by the American Society of AnaesthesiologistsTask Force on Perioperative Blood Management tells us restrictive red blood cell transfusion strategy may be safely used to reduce transfusion administration. It further states that The determination of whether hemoglobin concentrations between 6 and 10 g/dl justify or require red blood cell transfusion should be based on potential or actual on going bleeding (rate and magnitude), intravascular volume status, signs of organ ischemia, and adequacy of cardiopulmonary reserve. Should we extrapolate these guidelines in Cardiac surgery? TRACS2 trial concluded that among patients undergoing cardiac surgery, the use of a restrictive perioperative transfusion strategy compared with a more liberal strategy resulted in noninferior rates of the combined outcome of 30-day all-cause mortality and severe morbidity.They advocated use of restrictive strategy, but 5 years later, the authors 3concluded that A restrictive transfusion threshold after cardiac surgery was not superior to a liberal threshold with respect to morbidity or health care costs. With this conflicting evidence, by which way anaesthesiologist to go?

scholarly journals A SARS-CoV-2-pandémia hatása a vérkészítmény-felhasználásra a Pécsi Tudományegyetemen

2021 ◽  
Vol 162 (43) ◽  
pp. 1717-1723
Author(s):  
Sándor Pál ◽  
Barbara Réger ◽  
Tamás Kiss ◽  
Hussain Alizadeh ◽  
András Vereczkei ◽  
...  
Keyword(s):  
Blood Transfusion ◽  
Blood Cell ◽  
Red Blood Cell ◽  
Blood Product ◽  
Patient Blood Management ◽  
Blood Products ◽  
Blood Management ◽  
Number Of Patients ◽  
Willingness To Donate ◽  
The Impact

Összefoglaló. Bevezetés: A COVID–19-világjárvány betegellátásra gyakorolt hatása hazánkban is jelentős. A vérellátást nehezítette a járványügyi intézkedések következményeként a véradási események elmaradása, a csökkent véradási hajlandóság, továbbá a nehezen megítélhető vérkészítményigény . A „Patient Blood Management” irányelveinek az orvosi gyakorlatban történő egyre szélesebb körű alkalmazása elősegíti az optimális vérkészítmény-felhasználást a transzfúziók lehetőség szerinti elkerülésével. Célkitűzés és módszer: Vizsgálatunk célja a Pécsi Tudományegyetem Klinikai Központjának Janus Pannonius Klinikai Tömbjében a vérkészítmény-felhasználás változásainak felmérése volt a 2020. év első öt hónapjában. Eredmények: A járványügyi intézkedéseket követő időszakban szignifikánsan csökkent a hospitalizált betegeknek (34,08%), a transzfúziót igénylő betegeknek (39,69%) és a felhasznált vörösvérsejt-készítményeknek (46,41%) a száma, valamint az egy betegre jutó felhasznált vörösvérsejt-koncentrátum átlaga (2,61-ről 1,97-re) is. Közel 30%-os arányban csökkent a felhasznált friss fagyasztott plazma egységeinek és a thrombocytakoncentrátumoknak a száma is. Következtetés: A szigorú korlátozások életbe léptetését követően a nehézségek ellenére sikerült elegendő mennyiségű vérkészítményt biztosítani a betegeknek. Az Országos Vérellátó Szolgálat Pécsi Regionális Vérellátó Központja munkatársainak és a klinikusok erőfeszítéseinek köszönhetően a vérkészítményigény és -kínálat között új egyensúly alakult ki, mely megfelelő ellátást biztosított a feltétlenül szükséges transzfúziók kivitelezéséhez. Orv Hetil. 2021; 162(43): 1717–1723. Summary. Introduction: The impact of COVID–19 pandemic on patient care is pronounced also in Hungary. Blood supply was hindered by the reduction of public blood donation events, the reduced willingness to donate, and the difficult predictability of blood product demand as a result of the epidemiological regulations. The wider application of Patient Blood Management guidelines in the medical practice will promote optimal blood product utilization by avoiding transfusions where possible. Objective and method: The aim of our study was to assess the changes in the usage of blood products in the first five months of 2020 at the Clinical Center of the University of Pécs, Janus Pannonius Clinical Building. Results: In the period following the epidemiological measures, we found reduction in the number of hospitalized patients (34.08%), in the number of patients requiring transfusion (39.69%) and in the number of red blood cell products used (46.41%). The number of transfused red blood cell concentrates per patient was also significantly reduced (from 2.61 to 1.97) in this period. The number of transfused fresh frozen plasma units and platelet concentrates also decreased by approximately 30%. Conclusion: After the implementation of the strict restrictions, despite the difficulties, it was possible to provide patients with sufficient blood products. Due to the efforts of both the Regional Blood Transfusion Center of Pécs of the Hungarian National Blood Transfusion Service and of the clinicians, a new balance was established between the demand and the supply of blood products, which provided adequate care for the necessary transfusions. Orv Hetil. 2021; 162(43): 1717–1723.

scholarly journals Changes in the red blood cell enzyme, carbonic anhydrase, following blood transfusion.

1981 ◽  
Vol 27 (6) ◽  
pp. 541-545
Author(s):  
Kenji Taki ◽  
Koji Murakami ◽  
Takae Kawamura ◽  
Mieko Takamura ◽  
Reiji Wakusawa
Keyword(s):  
Blood Transfusion ◽  
Carbonic Anhydrase ◽  
Blood Cell ◽  
Red Blood Cell ◽  
Cell Enzyme

Donor white blood cell survival and cytokine profiles following red blood cell transfusion in Australian major trauma patients

2018 ◽  
Vol 103 ◽  
pp. 229-234 ◽  
Author(s):  
Rena Hirani ◽  
Melinda M. Dean ◽  
Zsolt J. Balogh ◽  
Natalie J. Lott ◽  
Julie Seggie ◽  
...  
Keyword(s):  
Blood Cell ◽  
Cell Survival ◽  
White Blood Cell ◽  
Red Blood Cell ◽  
Major Trauma ◽  
Red Blood Cell Transfusion ◽  
Trauma Patients ◽  
Cytokine Profiles

scholarly journals Red blood cell age and potentiation of transfusion-related pathology in trauma patients

Transfusion ◽  
2011 ◽  
Vol 51 (4) ◽  
pp. 867-873 ◽  
Author(s):  
Jordan A. Weinberg ◽  
Scott R. Barnum ◽  
Rakesh P. Patel
Keyword(s):  
Blood Cell ◽  
Red Blood Cell ◽  
Trauma Patients ◽  
Cell Age

scholarly journals Infusion of Autologous Retrodifferentiated Stem Cells into Patients with Beta-Thalassemia

2006 ◽  
Vol 6 ◽  
pp. 1278-1297 ◽  
Author(s):  
Ilham Saleh Abuljadayel ◽  
Tasnim Ahsan ◽  
Huma Quereshi ◽  
Shakil Rizvi ◽  
Tamseela Ahmed ◽  
...  
Keyword(s):  
Blood Transfusion ◽  
Blood Cell ◽  
Red Blood Cell ◽  
White Blood Cells ◽  
Fetal Hemoglobin ◽  
Beta Thalassemia ◽  
Mean Corpuscular Hemoglobin ◽  
Beta Globin ◽  
Globin Chain ◽  
Adult Hemoglobin

Beta-thalassemia is a genetic, red blood cell disorder affecting the beta-globin chain of the adult hemoglobin gene. This results in excess accumulation of unpaired alpha-chain gene products leading to reduced red blood cell life span and the development of severe anemia. Current treatment of this disease involves regular blood transfusion and adjunct chelation therapy to lower blood transfusion–induced iron overload. Fetal hemoglobin switching agents have been proposed to treat genetic blood disorders, such as sickle cell anemia and beta-thalassemia, in an effort to compensate for the dysfunctional form of the beta-globin chain in adult hemoglobin. The rationale behind this approach is to pair the excess normal alpha-globin chain with the alternative fetal gamma-chain to promote red blood cell survival and ameliorate the anemia. Reprogramming of differentiation in intact, mature, adult white blood cells in response to inclusion of monoclonal antibody CR3/43 has been described. This form of retrograde development has been termed “retrodifferentiation”, with the ability to re-express a variety of stem cell markers in a heterogeneous population of white blood cells. This form of reprogramming, or reontogeny, to a more pluripotent stem cell state ought to recapitulate early hematopoiesis and facilitate expression of a fetal and/or adult program of hemoglobin synthesis or regeneration on infusion and subsequent redifferentiation. Herein, the outcome of infusion of autologous retrodifferentiated stem cells (RSC) into 21 patients with beta-thalassemia is described. Over 6 months, Infusion of 3-h autologous RSC subjected to hematopoietic-conducive conditions into patients with beta-thalassemia reduced mean blood transfusion requirement, increased mean fetal hemoglobin synthesis, and significantly lowered mean serum ferritin. This was always accompanied by an increase in mean corpuscular volume (MCV), mean corpuscular hemoglobin (MCH), and mean corpuscular hemoglobin concentration (MCHC) in such patients. No adverse side effects in response to the infusion of autologous RSC were noted.This novel clinical procedure may profoundly modify the devastating course of many genetic disorders in an autologous setting, thus paving the way to harnessing pluripotency from differentiated cells to regenerate transiently an otherwise genetically degenerate tissue such as thalassemic blood.

Sign in / Sign up

Export Citation Format

Share Document