Machine Learning Model for Predicting Acute Respiratory Failure in Individuals With Moderate-to-Severe Traumatic Brain Injury.
Ontology highlight
ABSTRACT:
SUBMITTER: Ma RN
PROVIDER: S-EPMC8739486 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Acute respiratory failure (ARF) with a high incidence among moderate-to-severe traumatic brain injury (M-STBI) patients plays a pivotal role in worsening neurological outcomes. Traumatic subarachnoid hemorrhage (tSAH) is highly prevalent in M-STBI, which is associated with significant adverse outcomes. In this retrospective cohort study, we aimed to explore the association between the severity of the tSAH and ARF in the M-STBI population. A total of 771 subjects were reviewed. Clinical and neuroimaging data of M-STBI patients were retrospectively collected, and ARF was ascertained retrospectively based on their electronic medical record. The degree of tSAH was classified according to Fisher's criteria, and the grade of tSAH was dichotomized to a low Fisher grade (Fisher grade 1-2) and a high Fisher grade (Fisher grade 3-4). After exclusion procedures, the data of 695 M-STBI patients were analyzed. A total of 284 (30.8%) had a high Fisher grade on admission. The overall rate of ARF within 48 h upon admission was 34.4% (239/695); it was 29.5% (142/481) and 46.3% (99/214) for the low and high Fisher groups, respectively. In a full cohort, a high Fisher grade was associated with ARF after adjusting for age, gender, GCS, smoking history, comorbidities, multiple injuries, characteristics of TBI, and pulmonary factors (OR 1.78; 95% CI, 1.11-2.85, p = 0.016). This result remained robust in the comparisons after PSM (71/132, 42.8% vs. 53/132, 31.9%; OR, 1.59; 95% CI, 1.02-2.49, p = 0.042). A high Fisher SAH grade exposure on admission is associated with ARF in M-STBI patients.
| S-EPMC9318973 | biostudies-literature
Project description:BackgroundThe purpose of this study was to build a model of machine learning (ML) for the prediction of mortality in patients with isolated moderate and severe traumatic brain injury (TBI).MethodsHospitalized adult patients registered in the Trauma Registry System between January 2009 and December 2015 were enrolled in this study. Only patients with an Abbreviated Injury Scale (AIS) score ? 3 points related to head injuries were included in this study. A total of 1734 (1564 survival and 170 non-survival) and 325 (293 survival and 32 non-survival) patients were included in the training and test sets, respectively.ResultsUsing demographics and injury characteristics, as well as patient laboratory data, predictive tools (e.g., logistic regression [LR], support vector machine [SVM], decision tree [DT], naive Bayes [NB], and artificial neural networks [ANN]) were used to determine the mortality of individual patients. The predictive performance was evaluated by accuracy, sensitivity, and specificity, as well as by area under the curve (AUC) measures of receiver operator characteristic curves. In the training set, all five ML models had a specificity of more than 90% and all ML models (except the NB) achieved an accuracy of more than 90%. Among them, the ANN had the highest sensitivity (80.59%) in mortality prediction. Regarding performance, the ANN had the highest AUC (0.968), followed by the LR (0.942), SVM (0.935), NB (0.908), and DT (0.872). In the test set, the ANN had the highest sensitivity (84.38%) in mortality prediction, followed by the SVM (65.63%), LR (59.38%), NB (59.38%), and DT (43.75%).ConclusionsThe ANN model provided the best prediction of mortality for patients with isolated moderate and severe TBI.
| S-EPMC6226171 | biostudies-literature
Project description:Background Rapid referral of traumatic brain injury (TBI) patients requiring emergency neurosurgery to a specialized trauma center can significantly reduce morbidity and mortality. Currently, no model has been reported to predict the need for acute neurosurgery in severe to moderate TBI patients. This study aims to evaluate the performance of Machine Learning-based models to establish to predict the need for neurosurgery procedure within 24 h after moderate to severe TBI. Methods Retrospective multicenter cohort study using data from a national trauma registry (Traumabase®) from November 2011 to December 2020. Inclusion criteria correspond to patients over 18 years old with moderate or severe TBI (Glasgow coma score ≤ 12) during prehospital assessment. Patients who died within the first 24 h after hospital admission and secondary transfers were excluded. The population was divided into a train set (80% of patients) and a test set (20% of patients). Several approaches were used to define the best prognostic model (linear nearest neighbor or ensemble model). The Shapley Value was used to identify the most relevant pre-hospital variables for prediction. Results 2159 patients were included in the study. 914 patients (42%) required neurosurgical intervention within 24 h. The population was predominantly male (77%), young (median age 35 years [IQR 24–52]) with severe head injury (median GCS 6 [3–9]). Based on the evaluation of the predictive model on the test set, the logistic regression model had an AUC of 0.76. The best predictive model was obtained with the CatBoost technique (AUC 0.81). According to the Shapley values method, the most predictive variables in the CatBoost were a low initial Glasgow coma score, the regression of pupillary abnormality after osmotherapy, a high blood pressure and a low heart rate. Conclusion Machine learning-based models could predict the need for emergency neurosurgery within 24 h after moderate and severe head injury. Potential clinical benefits of such models as a decision-making tool deserve further assessment. The performance in real-life setting and the impact on clinical decision-making of the model requires workflow integration and prospective assessment. Supplementary Information The online version contains supplementary material available at 10.1186/s13017-022-00449-5.
| S-EPMC9351267 | biostudies-literature
Project description:Influenza virus is a major cause of acute hypoxemic respiratory failure. Early identification of patients who will suffer severe complications can help stratify patients for clinical trials and plan for resource use in case of pandemic. Objective:We aimed to identify which clinical variables best predict prolonged acute hypoxemic respiratory failure in influenza-infected critically ill children. Acute hypoxemic respiratory failure was defined using hypoxemia cutoffs from international consensus definitions of acute respiratory distress syndrome in patients with ventilatory support. Prolonged acute hypoxemic respiratory failure was defined by acute hypoxemic respiratory failure criteria still present at PICU day 7. Derivation Cohort:In this prospective multicenter study across 34 PICUs from November 2009 to April 2018, we included children (< 18 yr) without comorbid risk factors for severe disease. Validation Cohort:We used a Monte Carlo cross validation method with N 2 random train-test splits at a 70-30% proportion per model. Prediction Model:Using clinical data at admission (day 1) and closest to 8 am on PICU day 2, we calculated the area under the receiver operating characteristic curve using random forests machine learning algorithms and logistic regression. Results:We included 258 children (median age = 6.5 yr) and 11 (4.2%) died. By day 2, 65% (n = 165) had acute hypoxemic respiratory failure dropping to 26% (n = 67) with prolonged acute hypoxemic respiratory failure by day 7. Those with prolonged acute hypoxemic respiratory failure had a longer ICU stay (16.5 vs 4.0 d; p < 0.001) and higher mortality (13.4% vs 1.0%). A multivariable model using random forests with 10 admission and eight day 2 variables performed best (0.93 area under the receiver operating characteristic curve; 95 CI%: 0.90-0.95) where respiratory rate, Fio2, and pH on day 2 were the most important factors. Conclusions:In this prospective multicentric study, most children with influenza virus-related respiratory failure with prolonged acute hypoxemic respiratory failure can be identified early in their hospital course applying machine learning onto routine clinical data. Further validation is needed prior to bedside implementation.
| S-EPMC7417145 | biostudies-literature
Project description:ObjectivesAfter traumatic brain injury, continuous electroencephalography is widely used to detect electrographic seizures. With the development of standardized continuous electroencephalography terminology, we aimed to describe the prevalence and burden of ictal-interictal patterns, including electrographic seizures after moderate-to-severe traumatic brain injury and to correlate continuous electroencephalography features with functional outcome.DesignPost hoc analysis of the prospective, randomized controlled phase 2 multicenter INTREPID study (ClinicalTrials.gov: NCT00805818). Continuous electroencephalography was initiated upon admission to the ICU. The primary outcome was the 3-month Glasgow Outcome Scale-Extended. Consensus electroencephalography reviews were performed by raters certified in standardized continuous electroencephalography terminology blinded to clinical data. Rhythmic, periodic, or ictal patterns were referred to as "ictal-interictal continuum"; severe ictal-interictal continuum was defined as greater than or equal to 1.5 Hz lateralized rhythmic delta activity or generalized periodic discharges and any lateralized periodic discharges or electrographic seizures.SettingTwenty U.S. level I trauma centers.PatientsPatients with nonpenetrating traumatic brain injury and postresuscitation Glasgow Coma Scale score of 4-12 were included.InterventionsNone.Measurements and main resultsAmong 152 patients with continuous electroencephalography (age 34 ± 14 yr; 88% male), 22 (14%) had severe ictal-interictal continuum including electrographic seizures in four (2.6%). Severe ictal-interictal continuum burden correlated with initial prognostic scores, including the International Mission for Prognosis and Analysis of Clinical Trials in Traumatic Brain Injury (r = 0.51; p = 0.01) and Injury Severity Score (r = 0.49; p = 0.01), but not with functional outcome. After controlling clinical covariates, unfavorable outcome was independently associated with absence of posterior dominant rhythm (common odds ratio, 3.38; 95% CI, 1.30-9.09), absence of N2 sleep transients (3.69; 1.69-8.20), predominant delta activity (2.82; 1.32-6.10), and discontinuous background (5.33; 2.28-12.96) within the first 72 hours of monitoring.ConclusionsSevere ictal-interictal continuum patterns, including electrographic seizures, were associated with clinical markers of injury severity but not functional outcome in this prospective cohort of patients with moderate-to-severe traumatic brain injury. Importantly, continuous electroencephalography background features were independently associated with functional outcome and improved the area under the curve of existing, validated predictive models.
| S-EPMC6639805 | biostudies-literature
Project description:Background and aimsTraumatic brain injury (TBI) is a widespread global health issue with significant economic consequences. However, no existing model exists to predict the need for neurosurgical intervention in moderate TBI patients with positive initial computed tomography scans. This study determines the efficacy of machine learning (ML)-based models in predicting the need for neurosurgical intervention.MethodsThis is a retrospective study of patients admitted to the neuro-intensive care unit of Emtiaz Hospital, Shiraz, Iran, between January 2018 and December 2020. The most clinically important variables from patients that met our inclusion and exclusion criteria were collected and used as predictors. We developed models using multilayer perceptron, random forest, support vector machines (SVM), and logistic regression. To evaluate the models, their F1-score, sensitivity, specificity, and accuracy were assessed using a fourfold cross-validation method.ResultsBased on predictive models, SVM showed the highest performance in predicting the need for neurosurgical intervention, with an F1-score of 0.83, an area under curve of 0.93, sensitivity of 0.82, specificity of 0.84, a positive predictive value of 0.83, and a negative predictive value of 0.83.ConclusionThe use of ML-based models as decision-making tools can be effective in predicting with high accuracy whether neurosurgery will be necessary after moderate TBIs. These models may ultimately be used as decision-support tools to evaluate early intervention in TBI patients.
| S-EPMC10613807 | biostudies-literature
Project description:BackgroundLong-term physical, cognitive, and psychosocial problems resulting from moderate to severe traumatic brain injury (TBI) can prevent individuals from returning to preinjury lifestyles because of significant challenges with employment, leisure, and relationships. While physical activity (PA) is proposed as a cost-effective method to alleviate problems after moderate to severe TBI, there is no review to date that synthesizes the evidence for PA in the community-based context. Further, although sex- and gender-based considerations in research are considered requisite to good science, there is no review on PA and TBI that has included this explicit focus.ObjectiveThe purpose of this review is to map and synthesize the current evidence identified through a systematic search of community-based PA interventions for individuals of all ages with moderate to severe TBI and provide an overview of that evidence by asking the following research questions: (1) what are the characteristics of community-based PA programs for individuals with moderate to severe TBI, (2) what are the reported health-related outcomes and measurement tools used to evaluate them, and (3) what considerations have been given to sex and/or gender?MethodsSearches will be conducted of six academic databases for peer-reviewed articles. Two reviewers will independently screen the articles for inclusion and extract data for the analysis. The extracted data will be coded according to the Consensus on Exercise Reporting Template checklist and the Template for Intervention Description and Replication checklist to provide sufficient detail for replication.ResultsThe abstract screening was completed by two reviewers and the extracted data were analyzed. A qualitative synthesis and description of community-based PA interventions for individuals with moderate to severe TBI will be provided.ConclusionsThis scoping review will generate new knowledge from published and publicly available literature. Dissemination of the results will include activities related to knowledge transfer for community-based PA after moderate to severe TBI for future research and practice. Evidence-based recommendations, future directions, potential limitations, use of online/digital components, and the possible need for a systematic review will be discussed as well.International registered report identifier (irrid)DERR1-10.2196/24689.
| S-EPMC7840288 | biostudies-literature
Project description:OBJECTIVE:To examine the predictive ability of depression when considering long-term employment outcomes for individuals with moderate-to-severe traumatic brain injury (TBI) after controlling for key preinjury and injury-related variables. DESIGN:Secondary data analysis. SETTING:Community follow-up after discharge from an inpatient rehabilitation center. PARTICIPANTS:Individuals between 18 and 60 years old with moderate-to-severe TBI enrolled in the Traumatic Brain Injury Model Systems database. INTERVENTIONS:Not applicable. MAIN OUTCOME MEASURES:Employment status. RESULTS:The prevalence of employment at 2 and 5 years post injury was 40.3% and 44.5%, respectively. Individuals identified as depressed at 1 year were more likely to be unemployed at 2 years post injury (odds ratio [OR], 1.77; 95% CI, 1.38-2.27; P<.0001). Similar relations between current depression and future employment were observed from 1- and 2-year depression status predicting 5-year employment (1-year: OR, 1.88; 95% CI, 1.48-2.40; P<.0001: 2-year: OR, 1.72; 95% CI, 1.36-2.17; P<.0001). CONCLUSIONS:After controlling for baseline predictors variables, the experience of postinjury depression-a modifiable condition-contributes predictive ability to future employment outcomes. Incorporating assessments and/or interventions for depression into postacute rehabilitation programs could promote favorable employment outcomes after TBI.
| S-EPMC6765411 | biostudies-literature
Project description:PurposeIndividuals with moderate to severe traumatic brain injury (TBI) experience changes in their quality-of-life (QOL) post-injury. Given the vast literature that exists about QOL after TBI, a scoping review was performed to identify the different biopsychosocial factors that affect a person's QOL after a moderate to severe TBI.MethodsA scoping review was conducted using the following electronic databases: MEDLINE, CINAHL, Embase, and PsycINFO. Terms relating to TBI and QOL were used.ResultsThere were 7576 articles obtained from the databases, resulting in 535 full-text articles. Ultimately, 52 articles were extracted, which consisted of biopsychosocial QOL factors after TBI. The biopsychosocial factors of QOL after TBI included 19 biological factors (i.e., sex, TBI severity, cognition), 16 psychological factors (i.e., depression, self-efficacy, coping styles), and 19 social factors (i.e., employment, social participation, social support). Factors such as fatigue, self-awareness, transition, and discharge from hospitals are known issues in TBI literature but were minimally reported in studies in this review, identifying them as potential gaps in research.ConclusionIdentifying biopsychosocial factors relating to QOL after TBI can enable health services to develop targeted rehabilitation programs for individuals with TBI.
| S-EPMC10972932 | biostudies-literature
Project description:Background: Acute respiratory distress syndrome (ARDS) commonly develops in traumatic brain injury (TBI) patients and is a risk factor for poor prognosis. We designed this study to evaluate the performance of several machine learning algorithms for predicting ARDS in TBI patients. Methods: TBI patients from the Medical Information Mart for Intensive Care-III (MIMIC-III) database were eligible for this study. ARDS was identified according to the Berlin definition. Included TBI patients were divided into the training cohort and the validation cohort with a ratio of 7:3. Several machine learning algorithms were utilized to develop predictive models with five-fold cross validation for ARDS including extreme gradient boosting, light gradient boosting machine, Random Forest, adaptive boosting, complement naïve Bayes, and support vector machine. The performance of machine learning algorithms were evaluated by the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy and F score. Results: 649 TBI patients from the MIMIC-III database were included with an ARDS incidence of 49.5%. The random forest performed the best in predicting ARDS in the training cohort with an AUC of 1.000. The XGBoost and AdaBoost ranked the second and the third with an AUC of 0.989 and 0.815 in the training cohort. The random forest still performed the best in predicting ARDS in the validation cohort with an AUC of 0.652. AdaBoost and XGBoost ranked the second and the third with an AUC of 0.631 and 0.620 in the validation cohort. Several mutual top features in the random forest and AdaBoost were discovered including age, initial systolic blood pressure and heart rate, Abbreviated Injury Score chest, white blood cells, platelets, and international normalized ratio. Conclusions: The random forest and AdaBoost based models have stable and good performance for predicting ARDS in TBI patients. These models could help clinicians to evaluate the risk of ARDS in early stages after TBI and consequently adjust treatment decisions.
| S-EPMC9864532 | biostudies-literature