Background The study aimed to introduce a machine learning model that predicts in-hospital mortality in patients on mechanical ventilation (MV) following moderate to severe traumatic brain injury (TBI). Methods A retrospective analysis was conducted for all adult patients who sustained TBI and were hospitalized at the trauma center from January 2014 to February 2019 with an abbreviated injury severity score for head region (HAIS) ≥ 3. We used the demographic characteristics, injuries and CT findings as predictors. Logistic regression (LR) and Artificial neural networks (ANN) were used to predict the in-hospital mortality. Accuracy, area under the receiver operating characteristics curve (AUROC), precision, negative predictive value (NPV), sensitivity, specificity and F-score were used to compare the models` performance. Results Across the study duration; 785 patients met the inclusion criteria (581 survived and 204 deceased). The two models (LR and ANN) achieved good performance with an accuracy over 80% and AUROC over 87%. However, when taking the other performance measures into account, LR achieved higher overall performance than the ANN with an accuracy and AUROC of 87% and 90.5%, respectively compared to 80.9% and 87.5%, respectively. Venous thromboembolism prophylaxis, severity of TBI as measured by abbreviated injury score, TBI diagnosis, the need for blood transfusion, heart rate upon admission to the emergency room and patient age were found to be the significant predictors of in-hospital mortality for TBI patients on MV. Conclusions Machine learning based LR achieved good predictive performance for the prognosis in mechanically ventilated TBI patients. This study presents an opportunity to integrate machine learning methods in the trauma registry to provide instant clinical decision-making support.
Background: The use of machine learning techniques to predict diseases outcomes has grown significantly in the last decade. Several studies prove that the machine learning predictive techniques outperform the classical multivariate techniques. We aimed to build a machine learning predictive model to predict the in-hospital mortality for patients who sustained Traumatic Brain Injury (TBI). Methods: Adult patients with TBI who were hospitalized in the level 1 trauma center in the period from January 2014 to February 2019 were included in this study. Patients' demographics, injury characteristics and CT findings were used as predictors. The predictive performance of Artificial Neural Networks (ANN) and Support Vector Machines (SVM) was evaluated in terms of accuracy, Area Under the Curve (AUC), sensitivity, precision, Negative Predictive Value (NPV), specificity and F-score. Results: A total of 1620 eligible patients were included in the study (1417 survival and 203 non-survivals). Both models achieved accuracy over 91% and AUC over 93%. SVM achieved the optimal performance with accuracy 95.6% and AUC 96%. Conclusions: for prediction of mortality in patients with TBI, SVM outperformed the well-known classical models that utilized the conventional multivariate analytical techniques.
Blunt bowel and mesenteric injury (BBMI) is frequently a difficult diagnosis at initial presentation. We aimed to study the predictors for early diagnosis and outcomes in patients with BBMI. Data were collected retrospectively from the database registry between January 2008 and December 2011 in the only Level I trauma unit in Qatar. Patients with BBMI were divided into Group A (surgically treated within 8 hours) and Group B (treated after 8 hours). Data were analyzed and χ2, Student's t test, and multivariate regression analysis were performed appropriately. Among 984 patients admitted with blunt abdominal trauma (BAT), 11 per cent had BBMI with mean age of 35 ± 9.5 years. Polytrauma and isolated bowel injury were identified in 53 and 42 per cent, respectively. Mean Injury Severity Score (ISS) was higher in Group A in comparison to Group B (18 ± 11 vs 13 ± 8; P = 0.02). Presence of pain and seatbelt sign ( P = 0.02) were evident in Group B. Hypotension ( P = 0.004) and hypothermia ( P = 0.01) were prominent in Group A. The rate of positive Focused Assessment Sonography for Trauma was greater in Group A ( P = 0.001). Among operative findings, bowel perforation was more frequent in Group B ( P = 0.04), whereas mesenteric full-thickness hematoma was significantly higher in Group A. Pelvic fracture was more frequent finding in Group A ( P = 0.005). The overall mortality rate was 15.6 per cent. In patients with BAT, the presence of abdominal pain, hypotension, ISS greater than 16, hypothermia, pelvic fracture, and mesenteric hematoma might help in early diagnosis of BBMI. Moreover, base deficit and mean ISS were independent predictors of mortality. Delayed operative interventions greater than 8 hours increased morbidity rate but had no significant impact on mortality.
Background As trauma systems mature, they are expected to improve patient care, reduce in-hospital complications and optimize outcomes. Qatar has a single trauma center, at the Hamad General Hospital, which serves as the hub for the trauma system that was verified as a level 1 trauma system by the Accreditation Canada International Distinction program in 2014. We hypothesized that this international accreditation was a major step, in the maturation process of the Qatar trauma system, that has positively impacted patient care, reduced complications and improved outcomes of trauma patients in such a rapidly developing country. Methods A retrospective analysis of data was conducted for all trauma patients who were admitted between 2010 and 2018. Data were obtained from the level 1 trauma center registry at Hamad Medical Corporation. Patients were divided into Group 1- pre-accreditation (admitted from January 2010 to October 2014) and Group 2- post-accreditation (admitted from November 2014 to December 2018). Patients’ characteristics and in-hospital outcomes were analyzed and compared. Data included patients’ demographics; injury types, mechanism and injury severity scores, interventions, hospital stay, complications and mortality (pre-hospital and in-hospital). Time series analysis for mortality was performed using expert modeler. Results Data from a total of 15,864 patients was collected and analyzed. Group 2 patients had more severe injuries in comparison to Group 1 (p<0.05). However, Group 2, had a lower complication rate (ventilator associated pneumonia (VAP)) and a shorter mean hospital length of stay (p<0.05). The overall mortality was 8%. In Group 2; the pre-hospital mortality was higher (52% vs. 41%, p = 0.001), while in-hospital mortality was lower (48% vs. 59%) compared to Group 1 (p = 0.001). Conclusions The international recognition and accreditation of the trauma center in 2014 was the key factor in the maturation of the trauma system that improved the in-hospital outcomes. Accreditation also brought other benefits including a reduction in VAP and hospital length of stay. However, further studies are required to explore the maturation process of all individual components of the trauma system including the prehospital setting.
We aimed to build a machine learning predictive model to predict the risk of prolonged mechanical ventilation (PMV) for patients with Traumatic Brain Injury (TBI). Methods This study included TBI patients who were hospitalized in a level 1 trauma center between January 2014 and February 2019. Data were analyzed for all adult patients who received mechanical ventilation following TBI with abbreviated injury severity (AIS) score for the head region of � 3. This study designed three sets of machine learning models: set A defined PMV to be greater than 7 days, set B (PMV > 10 days) and set C (PMV >14 days) to determine the optimal model for deployment. Patients' demographics, injury characteristics and CT findings were used as predictors. Logistic regression (LR), Artificial neural networks (ANN) Support vector machines (SVM), Random Forest (RF) and C.5 Decision Tree (C.5 DT) were used to predict the PMV. Results The number of eligible patients that were included in the study were 674, 643 and 622 patients in sets A, B and C respectively. In set A, LR achieved the optimal performance with accuracy 0.75 and Area under the curve (AUC) 0.83. SVM achieved the optimal performance among other models in sets B with accuracy/AUC of 0.79/0.84 respectively. ANNs achieved the optimal performance in set C with accuracy/AUC of 0.76/0.72 respectively. Machine learning models in set B demonstrated more stable performance with higher prediction success and discrimination power.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.