Prediction of in-hospital mortality in patients on mechanical ventilation post traumatic brain injury: machine learning approach

Classification and Regression Tree Predictive Model for Acute Kidney Injury in Traumatic Brain Injury Patients

Background

Acute kidney injury (AKI) is prevalent in hospitalized patients with traumatic brain injury (TBI), and increases the risk of poor outcomes. We designed this study to develop a visual and convenient decision-tree-based model for predicting AKI in TBI patients.

Methods

A total of 376 patients admitted to the emergency department of the West China Hospital for TBI between January 2015 and June 2019 were included. Demographic information, vital signs on admission, laboratory test results, radiological signs, surgical options, and medications were recorded as variables. AKI was confirmed since the second day after admission, based on the Kidney Disease Improving Global Outcomes criteria. We constructed two predictive models for AKI using least absolute shrinkage and selection operator (LASSO) regression and classification and regression tree (CART), respectively. Receiver operating characteristic (ROC) curves of these two predictive models were drawn, and the area under the ROC curve (AUC) was calculated to compare their predictive accuracy.

Results

The incidence of AKI on the second day after admission was 10.4% among patients with TBI. Lasso regression identified five potent predictive factors for AKI: glucose, serum creatinine, cystatin C, serum uric acid, and fresh frozen plasma transfusions. The CART analysis showed that glucose, serum uric acid, and cystatin C ranked among the top three in terms of the feature importance of the decision tree model. The AUC value of the decision-tree predictive model was 0.892, which was higher than the 0.854 of the LASSO regression model, although the difference was not statistically significant.

Conclusion

The decision tree model is valuable for predicting AKI among patients with TBI. This tree-based flowchart is convenient for physicians to identify patients with TBI who are at high risk of AKI and prompts them to develop suitable therapeutic strategies.

[The use of transcranial micropolarization in the acute period of severe traumatic brain injury in children]

Traumatic brain injury, which is often considered as a silent epidemic, is a public health problem. The duration of acute recovery period remains a commonly used criterion for injury severity and clinical management. In this connection, the first stage of medical rehabilitation is carried out in the conditions of resuscitation and neurosurgery department in the hospital providing specialized care. Rehabilitation techniques such as postural training, phase verticalization, individual kinesiotherapy, transcranial micropolarization and etc. are used.

OBJECTIVE

To assess the effectiveness of using transcranial micropolarization in acute period of severe traumatic brain injury in children.

MATERIAL AND METHODS

The study on the effectiveness of using transcranial micropolarization in acute period of severe traumatic brain injury in 85 children, divided into 2 groups, was carried out. The study group (42 patients) received the transcranial micropolarization on the 2nd day after severe traumatic brain injury. The control group (43 patients) received only rehabilitation in neurosurgery department. The neurological status in the patients of both groups was assessed on the 2nd day after severe traumatic brain injury in resuscitation department, and after 1, 3 and 6 months.

RESULTS AND CONCLUSION

The inclusion of transcranial micropolarization in the early medical rehabilitation of children with severe traumatic brain injury increases consciousness level in a shorter period of time, that predicts early patient's socialization.

Machine learning-based model for predicting inpatient mortality in adults with traumatic brain injury: a systematic review and meta-analysis

Background and objective

Predicting mortality from traumatic brain injury facilitates early data-driven treatment decisions. Machine learning has predicted mortality from traumatic brain injury in a growing number of studies, and the aim of this study was to conduct a meta-analysis of machine learning models in predicting mortality from traumatic brain injury.

Methods

This systematic review and meta-analysis included searches of PubMed, Web of Science and Embase from inception to June 2023, supplemented by manual searches of study references and review articles. Data were analyzed using Stata 16.0 software. This study is registered with PROSPERO (CRD2023440875).

Results

A total of 14 studies were included. The studies showed significant differences in the overall sample, model type and model validation. Predictive models performed well with a pooled AUC of 0.90 (95% CI: 0.87 to 0.92).

Conclusion

Overall, this study highlights the excellent predictive capabilities of machine learning models in determining mortality following traumatic brain injury. However, it is important to note that the optimal machine learning modeling approach has not yet been identified.

Systematic review registration

https://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=440875, identifier CRD2023440875.

Development and Validation of an XGBoost-Algorithm-Powered Survival Model for Predicting In-Hospital Mortality Based on 545,388 Isolated Severe Traumatic Brain Injury Patients from the TQIP Database

BACKGROUND

Traumatic brain injury (TBI) represents a significant global health issue; the traditional tools such as the Glasgow Coma Scale (GCS) and Abbreviated Injury Scale (AIS) which have been used for injury severity grading, struggle to capture outcomes after TBI.

AIM AND METHODS

This paper aims to implement extreme gradient boosting (XGBoost), a powerful machine learning algorithm that combines the predictions of multiple weak models to create a strong predictive model with high accuracy and efficiency, in order to develop and validate a predictive model for in-hospital mortality in patients with isolated severe traumatic brain injury and to identify the most influential predictors. In total, 545,388 patients from the 2013-2021 American College of Surgeons Trauma Quality Improvement Program (TQIP) database were included in the current study, with 80% of the patients used for model training and 20% of the patients for the final model test. The primary outcome of the study was in-hospital mortality. Predictors were patients' demographics, admission status, as well as comorbidities, and clinical characteristics. Penalized Cox regression models were used to investigate the associations between the survival outcomes and the predictors and select the best predictors. An extreme gradient boosting (XGBoost)-powered Cox regression model was then used to predict the survival outcome. The performance of the models was evaluated using the Harrell's concordance index (C-index). The time-dependent area under the receiver operating characteristic curve (AUC) was used to evaluate the dynamic cumulative performance of the models. The importance of the predictors in the final prediction model was evaluated using the Shapley additive explanations (SHAP) value.

RESULTS

On average, the final XGBoost-powered Cox regression model performed at an acceptable level for patients with a length of stay up to 250 days (mean time-dependent AUC = 0.713) in the test dataset. However, for patients with a length of stay between 20 and 213 days, the performance of the model was relatively poor (time-dependent AUC < 0.7). When limited to patients with a length of stay ≤20 days, which accounts for 95.4% of all the patients, the model achieved an excellent performance (mean time-dependent AUC = 0.813). When further limited to patients with a length of stay ≤5 days, which accounts for two-thirds of all the patients, the model achieved an outstanding performance (mean time-dependent AUC = 0.917).

CONCLUSION

The XGBoost-powered Cox regression model can achieve an outstanding predictive ability for in-hospital mortality during the first 5 days, primarily based on the severity of the injury, the GCS on admission, and the patient's age. These variables continue to demonstrate an excellent predictive ability up to 20 days after admission, a period of care that accounts for over 95% of severe TBI patients. Past 20 days of care, other factors appear to be the primary drivers of in-hospital mortality, indicating a potential window of opportunity for improving outcomes.

Machine learning based prediction of prolonged duration of mechanical ventilation incorporating medication data

Rationale

Duration of mechanical ventilation is associated with adverse outcomes in critically ill patients and increased use of resources. The increasing complexity of medication regimens has been associated with increased mortality, length of stay, and fluid overload but has never been studied specifically in the setting of mechanical ventilation.

Objective

The purpose of this analysis was to develop prediction models for mechanical ventilation duration to test the hypothesis that incorporating medication data may improve model performance.

Methods

This was a retrospective cohort study of adults admitted to the ICU and undergoing mechanical ventilation for longer than 24 hours from October 2015 to October 2020. Patients were excluded if it was not their index ICU admission or if the patient was placed on comfort care in the first 24 hours of admission. Relevant patient characteristics including age, sex, body mass index, admission diagnosis, morbidities, vital signs measurements, severity of illness, medication regimen complexity as measured by the MRC-ICU, and medical treatments before intubation were collected. The primary outcome was area under the receiver operating characteristic (AUROC) of prediction models for prolonged mechanical ventilation (defined as greater than 5 days). Both logistic regression and supervised learning techniques including XGBoost, Random Forest, and Support Vector Machine were used to develop prediction models.

Results

The 318 patients [age 59.9 (SD 16.9), female 39.3%, medical 28.6%] had mean 24-hour MRC-ICU score of 21.3 (10.5), mean APACHE II score of 21.0 (5.4), mean SOFA score of 9.9 (3.3), and ICU mortality rate of 22.6% (n=72). The strongest performing logistic model was the base model with MRC-ICU added, with AUROC of 0.72, positive predictive value (PPV) of 0.83, and negative prediction value (NPV) of 0.92. The strongest overall model was Random Forest with an AUROC of 0.78, a PPV of 0.53, and NPV of 0.90. Feature importance analysis using support vector machine and Random Forest revealed severity of illness scores and medication related data were the most important predictors.

Conclusions

Medication regimen complexity is significantly associated with prolonged duration of mechanical ventilation in critically ill patients, and prediction models incorporating medication information showed modest improvement in this prediction.

Prediction performance of the machine learning model in predicting mortality risk in patients with traumatic brain injuries: a systematic review and meta-analysis

PURPOSE

With the in-depth application of machine learning(ML) in clinical practice, it has been used to predict the mortality risk in patients with traumatic brain injuries(TBI). However, there are disputes over its predictive accuracy. Therefore, we implemented this systematic review and meta-analysis, to explore the predictive value of ML for TBI.

METHODOLOGY

We systematically retrieved literature published in PubMed, Embase.com, Cochrane, and Web of Science as of November 27, 2022. The prediction model risk of bias(ROB) assessment tool (PROBAST) was used to assess the ROB of models and the applicability of reviewed questions. The random-effects model was adopted for the meta-analysis of the C-index and accuracy of ML models, and a bivariate mixed-effects model for the meta-analysis of the sensitivity and specificity.

RESULT

A total of 47 papers were eligible, including 156 model, with 122 newly developed ML models and 34 clinically recommended mature tools. There were 98 ML models predicting the in-hospital mortality in patients with TBI; the pooled C-index, sensitivity, and specificity were 0.86 (95% CI: 0.84, 0.87), 0.79 (95% CI: 0.75, 0.82), and 0.89 (95% CI: 0.86, 0.92), respectively. There were 24 ML models predicting the out-of-hospital mortality; the pooled C-index, sensitivity, and specificity were 0.83 (95% CI: 0.81, 0.85), 0.74 (95% CI: 0.67, 0.81), and 0.75 (95% CI: 0.66, 0.82), respectively. According to multivariate analysis, GCS score, age, CT classification, pupil size/light reflex, glucose, and systolic blood pressure (SBP) exerted the greatest impact on the model performance.

CONCLUSION

According to the systematic review and meta-analysis, ML models are relatively accurate in predicting the mortality of TBI. A single model often outperforms traditional scoring tools, but the pooled accuracy of models is close to that of traditional scoring tools. The key factors related to model performance include the accepted clinical variables of TBI and the use of CT imaging.

Machine learning algorithms for predicting outcomes of traumatic brain injury: A systematic review and meta-analysis

BACKGROUND

Traumatic brain injury (TBI) is a leading cause of death and disability worldwide. The use of machine learning (ML) has emerged as a key advancement in TBI management. This study aimed to identify ML models with demonstrated effectiveness in predicting TBI outcomes.

METHODS

We conducted a systematic review in accordance with the Preferred Reporting Items for Systematic Review and Meta-Analysis statement. In total, 15 articles were identified using the search strategy. Patient demographics, clinical status, ML outcome variables, and predictive characteristics were extracted. A small meta-analysis of mortality prediction was performed, and a meta-analysis of diagnostic accuracy was conducted for ML algorithms used across multiple studies.

RESULTS

ML algorithms including support vector machine (SVM), artificial neural networks (ANN), random forest, and Naïve Bayes were compared to logistic regression (LR). Thirteen studies found significant improvement in prognostic capability using ML versus LR. The accuracy of the above algorithms was consistently over 80% when predicting mortality and unfavorable outcome measured by Glasgow Outcome Scale. Receiver operating characteristic curves analyzing the sensitivity of ANN, SVM, decision tree, and LR demonstrated consistent findings across studies. Lower admission Glasgow Coma Scale (GCS), older age, elevated serum acid, and abnormal glucose were associated with increased adverse outcomes and had the most significant impact on ML algorithms.

CONCLUSION

ML algorithms were stronger than traditional regression models in predicting adverse outcomes. Admission GCS, age, and serum metabolites all have strong predictive power when used with ML and should be considered important components of TBI risk stratification.

Red Blood Cell Omics and Machine Learning in Transfusion Medicine: Singularity Is Near

Background

Blood transfusion is a life-saving intervention for millions of recipients worldwide. Over the last 15 years, the advent of high-throughput, affordable omics technologies - including genomics, proteomics, lipidomics, and metabolomics - has allowed transfusion medicine to revisit the biology of blood donors, stored blood products, and transfusion recipients.

Summary

Omics approaches have shed light on the genetic and non-genetic factors (environmental or other exposures) impacting the quality of stored blood products and efficacy of transfusion events, based on the current Food and Drug Administration guidelines (e.g., hemolysis and post-transfusion recovery for stored red blood cells). As a treasure trove of data accumulates, the implementation of machine learning approaches promises to revolutionize the field of transfusion medicine, not only by advancing basic science. Indeed, computational strategies have already been used to perform high-content screenings of red blood cell morphology in microfluidic devices, generate in silico models of erythrocyte membrane to predict deformability and bending rigidity, or design systems biology maps of the red blood cell metabolome to drive the development of novel storage additives.

Key Message

In the near future, high-throughput testing of donor genomes via precision transfusion medicine arrays and metabolomics of all donated products will be able to inform the development and implementation of machine learning strategies that match, from vein to vein, donors, optimal processing strategies (additives, shelf life), and recipients, realizing the promise of personalized transfusion medicine.

AI-Based Decision Support System for Traumatic Brain Injury: A Survey

Traumatic brain injury (TBI) is one of the major causes of disability and mortality worldwide. Rapid and precise clinical assessment and decision-making are essential to improve the outcome and the resulting complications. Due to the size and complexity of the data analyzed in TBI cases, computer-aided data processing, analysis, and decision support systems could play an important role. However, developing such systems is challenging due to the heterogeneity of symptoms, varying data quality caused by different spatio-temporal resolutions, and the inherent noise associated with image and signal acquisition. The purpose of this article is to review current advances in developing artificial intelligence-based decision support systems for the diagnosis, severity assessment, and long-term prognosis of TBI complications.

Hospital mortality prediction in traumatic injuries patients: comparing different SMOTE-based machine learning algorithms

BACKGROUND

Trauma is one of the most critical public health issues worldwide, leading to death and disability and influencing all age groups. Therefore, there is great interest in models for predicting mortality in trauma patients admitted to the ICU. The main objective of the present study is to develop and evaluate SMOTE-based machine-learning tools for predicting hospital mortality in trauma patients with imbalanced data.

METHODS

This retrospective cohort study was conducted on 126 trauma patients admitted to an intensive care unit at Besat hospital in Hamadan Province, western Iran, from March 2020 to March 2021. Data were extracted from the medical information records of patients. According to the imbalanced property of the data, SMOTE techniques, namely SMOTE, Borderline-SMOTE1, Borderline-SMOTE2, SMOTE-NC, and SVM-SMOTE, were used for primary preprocessing. Then, the Decision Tree (DT), Random Forest (RF), Naive Bayes (NB), Artificial Neural Network (ANN), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost) methods were used to predict patients' hospital mortality with traumatic injuries. The performance of the methods used was evaluated by sensitivity, specificity, Positive Predictive Value (PPV), Negative Predictive Value (NPV), accuracy, Area Under the Curve (AUC), Geometric Mean (G-means), F1 score, and P-value of McNemar's test.

RESULTS

Of the 126 patients admitted to an ICU, 117 (92.9%) survived and 9 (7.1%) died. The mean follow-up time from the date of trauma to the date of outcome was 3.98 ± 4.65 days. The performance of ML algorithms is not good with imbalanced data, whereas the performance of SMOTE-based ML algorithms is significantly improved. The mean area under the ROC curve (AUC) of all SMOTE-based models was more than 91%. F1-score and G-means before balancing the dataset were below 70% for all ML models except ANN. In contrast, F1-score and G-means for the balanced datasets reached more than 90% for all SMOTE-based models. Among all SMOTE-based ML methods, RF and ANN based on SMOTE and XGBoost based on SMOTE-NC achieved the highest value for all evaluation criteria.

CONCLUSIONS

This study has shown that SMOTE-based ML algorithms better predict outcomes in traumatic injuries than ML algorithms. They have the potential to assist ICU physicians in making clinical decisions.

Computational Intelligence-Based Disease Severity Identification: A Review of Multidisciplinary Domains

Disease severity identification using computational intelligence-based approaches is gaining popularity nowadays. Artificial intelligence and deep-learning-assisted approaches are proving to be significant in the rapid and accurate diagnosis of several diseases. In addition to disease identification, these approaches have the potential to identify the severity of a disease. The problem of disease severity identification can be considered multi-class classification, where the class labels are the severity levels of the disease. Plenty of computational intelligence-based solutions have been presented by researchers for severity identification. This paper presents a comprehensive review of recent approaches for identifying disease severity levels using computational intelligence-based approaches. We followed the PRISMA guidelines and compiled several works related to the severity identification of multidisciplinary diseases of the last decade from well-known publishers, such as MDPI, Springer, IEEE, Elsevier, etc. This article is devoted toward the severity identification of two main diseases, viz. Parkinson's Disease and Diabetic Retinopathy. However, severity identification of a few other diseases, such as COVID-19, autonomic nervous system dysfunction, tuberculosis, sepsis, sleep apnea, psychosis, traumatic brain injury, breast cancer, knee osteoarthritis, and Alzheimer's disease, was also briefly covered. Each work has been carefully examined against its methodology, dataset used, and the type of disease on several performance metrics, accuracy, specificity, etc. In addition to this, we also presented a few public repositories that can be utilized to conduct research on disease severity identification. We hope that this review not only acts as a compendium but also provides insights to the researchers working on disease severity identification using computational intelligence-based approaches.

Machine learning and network analysis for diagnosis and prediction in disorders of consciousness

BACKGROUND

Prolonged Disorders of Consciousness (PDOC) resulting from severe acquired brain injury can lead to complex disabilities that make diagnosis challenging. The role of machine learning (ML) in diagnosing PDOC states and identifying intervention strategies is relatively under-explored, having focused on predicting mortality and poor outcome. This study aims to: (a) apply ML techniques to predict PDOC diagnostic states from variables obtained from two non-invasive neurobehavior assessment tools; and (b) apply network analysis for guiding possible intervention strategies.

METHODS

The Coma Recovery Scale-Revised (CRS-R) is a well-established tool for assessing patients with PDOC. More recently, music has been found to be a useful medium for assessment of coma patients, leading to the standardization of a music-based assessment of awareness: Music Therapy Assessment Tool for Awareness in Disorders of Consciousness (MATADOC). CRS-R and MATADOC data were collected from 74 PDOC patients aged 16-70 years at three specialist centers in the USA, UK and Ireland. The data were analyzed by three ML techniques (neural networks, decision trees and cluster analysis) as well as modelled through system-level network analysis.

RESULTS

PDOC diagnostic state can be predicted to a relatively high level of accuracy that sets a benchmark for future ML analysis using neurobehavioral data only. The outcomes of this study may also have implications for understanding the role of music therapy in interdisciplinary rehabilitation to help patients move from one coma state to another.

CONCLUSIONS

This study has shown how ML can derive rules for diagnosis of PDOC with data from two neurobehavioral tools without the need to harvest large clinical and imaging datasets. Network analysis using the measures obtained from these two non-invasive tools provides novel, system-level ways of interpreting possible transitions between PDOC states, leading to possible use in novel, next-generation decision-support systems for PDOC.

Association between ondansetron use and mortality of patients on mechanical ventilation in the intensive care unit: a retrospective cohort study

Background

Basic studies show that selective 5-hydroxytryptamine type 3 (5-HT₃) serotonin-receptor antagonists can protect organs from inflammatory injury and have shown lung protection. Whether 5-HT₃ receptor antagonists ondansetron benefits patients with mechanical ventilation is unclear in the intensive care unit (ICU).

Methods

The Medical Information Mart for Intensive Care-IV (MIMIC-IV) database was reviewed to identify patients on mechanical ventilation (aged >16 years) in the ICU, which was divided into two groups according to whether ondansetron is used. Demographic characteristics, medical history data, clinical parameters, diagnosis and treatment measures were included as covariates. Ondansetron use was defined as any kind of ondansetron administration regardless of the dose before the induction of mechanical ventilation. The primary outcome was in-hospital death. Hazard ratios (HRs) with 95% confidence intervals (CIs) were calculated by multivariable Cox regression. Propensity score matching (PSM) and inverse probability of treatment weighting (IPTW) were performed to further adjust for confounding factors. Kaplan-Meier (KM) curves with log-rank test were also performed.

Results

A total of 18,566 patients on mechanical ventilation were included (5,735 with ondansetron use). The overall in-hospital mortality rate of patients on mechanical ventilation was 18.9% (3,512/18,566). Approximately 13.0% (746/5,735) and 21.6% (2,766/12,831) in-hospital mortality rates occurred in the ondansetron and non-ondansetron use groups, respectively. Multivariable regression indicated that ondansetron usage was associated with a 33% and 32% lower risk of in-hospital and 60-day death (HR =0.77, 95% CI: 0.70-0.85, P<0.001; HR =0.68, 95% CI: 0.62-0.75, P<0.001) in the whole sample. Multivariable regression post-PSM indicated that ondansetron usage was associated with a 38% and 31% lower risk of in-hospital and 60-day death (HR =0.62, 95% CI: 0.56-0.68, P<0.001; HR =0.69, 95% CI: 0.62-0.77, P<0.001). Log-rank test for the KM curve of ondansetron and 60-day death was statistically significant (P<0.001). The duration of ventilator use pre- and post-PSM was statistically different (P<0.001 and P=0.007) in the two groups.

Conclusions

Ondansetron usage was significantly associated with a lower mortality risk of ventilated patients in the ICU. The 5-HT3 receptor antagonist use is may be new potential adjunctive therapeutic strategy for patients on mechanical ventilation in the ICU.

Prediction of motor function in patients with traumatic brain injury using genetic algorithms modified back propagation neural network: A data-based study

Objective

Traumatic brain injury (TBI) is one of the leading causes of death and disability worldwide. In this study, the characteristics of the patients, who were admitted to the China Rehabilitation Research Center, were elucidated in the TBI database, and a prediction model based on the Fugl-Meyer assessment scale (FMA) was established using this database.

Methods

A retrospective analysis of 463 TBI patients, who were hospitalized from June 2016 to June 2020, was performed. The data of the patients used for this study included the age and gender of the patients, course of TBI, complications, and concurrent dysfunctions, which were assessed using FMA and other measures. The information was collected at the time of admission to the hospital and 1 month after hospitalization. After 1 month, a prediction model, based on the correlation analyses and a 1-layer genetic algorithms modified back propagation (GA-BP) neural network with 175 patients, was established to predict the FMA. The correlations between the predicted and actual values of 58 patients (prediction set) were described.

Results

Most of the TBI patients, included in this study, had severe conditions (70%). The main causes of the TBI were car accidents (56.59%), while the most common complication and dysfunctions were hydrocephalus (46.44%) and cognitive and motor dysfunction (65.23 and 63.50%), respectively. A total of 233 patients were used in the prediction model, studying the 11 prognostic factors, such as gender, course of the disease, epilepsy, and hydrocephalus. The correlation between the predicted and the actual value of 58 patients was R ² = 0.95.

Conclusion

The genetic algorithms modified back propagation neural network can predict motor function in patients with traumatic brain injury, which can be used as a reference for risk and prognosis assessment and guide clinical decision-making.

Henry gas solubility optimization double machine learning classifier for neurosurgical patients

This study aims to predict head trauma outcome for Neurosurgical patients in children, adults, and elderly people. As Machine Learning (ML) algorithms are helpful in healthcare field, a comparative study of various ML techniques is developed. Several algorithms are utilized such as k-nearest neighbor, Random Forest (RF), C4.5, Artificial Neural Network, and Support Vector Machine (SVM). Their performance is assessed using anonymous patients' data. Then, a proposed double classifier based on Henry Gas Solubility Optimization (HGSO) is developed with Aquila optimizer (AQO). It is implemented for feature selection to classify patients' outcome status into four states. Those are mortality, morbidity, improved, or the same. The double classifiers are evaluated via various performance metrics including recall, precision, F-measure, accuracy, and sensitivity. Another contribution of this research is the original use of hybrid technique based on RF-SVM and HGSO to predict patient outcome status with high accuracy. It determines outcome status relationship with age and mode of trauma. The algorithm is tested on more than 1000 anonymous patients' data taken from a Neurosurgical unit of Mansoura International Hospital, Egypt. Experimental results show that the proposed method has the highest accuracy of 99.2% (with population size = 30) compared with other classifiers.

Statistical and machine learning approaches to predict the necessity for computed tomography in children with mild traumatic brain injury

BACKGROUND

Minor head trauma in children is a common reason for emergency department visits, but the risk of traumatic brain injury (TBI) in those children is very low. Therefore, physicians should consider the indication for computed tomography (CT) to avoid unnecessary radiation exposure to children. The purpose of this study was to statistically assess the differences between control and mild TBI (mTBI). In addition, we also investigate the feasibility of machine learning (ML) to predict the necessity of CT scans in children with mTBI.

METHODS AND FINDINGS

The study enrolled 1100 children under the age of 2 years to assess pre-verbal children. Other inclusion and exclusion criteria were per the PECARN study. Data such as demographics, injury details, medical history, and neurological assessment were used for statistical evaluation and creation of the ML algorithm. The number of children with clinically important TBI (ciTBI), mTBI on CT, and controls was 28, 30, and 1042, respectively. Statistical significance between the control group and clinically significant TBI requiring hospitalization (csTBI: ciTBI+mTBI on CT) was demonstrated for all nonparametric predictors except severity of the injury mechanism. The comparison between the three groups also showed significance for all predictors (p<0.05). This study showed that supervised ML for predicting the need for CT scan can be generated with 95% accuracy. It also revealed the significance of each predictor in the decision tree, especially the "days of life."

CONCLUSIONS

These results confirm the role and importance of each of the predictors mentioned in the PECARN study and show that ML could discriminate between children with csTBI and the control group.

Mechanical power of ventilation is associated with mortality in neurocritical patients: a cohort study

This study aimed to determine the predictive relevance of mechanical power in the clinical outcomes (such as ICU mortality, hospital mortality, 90-day mortality, length of ICU stay, and number of ventilator-free days at day 28) of neurocritical patients. This is a retrospective cohort analysis of an open-access clinical database known as MIMIC-III. The study included patients who had sustained an acute brain injury and required invasive ventilation for at least 24 h. Demographic parameters, disease severity scores (Glasgow coma scale), comorbidities, vital signs, laboratory parameters and ventilator parameters were collected within the first 24 h of ICU admission. The main outcome was the relationship between MP and ICU mortality. A total of 529 patients were selected for the study. The critical value of MP was 12.16 J/min, with the area under the curve (AUC) of the MP was 0.678 (95% CI 0.637-0.718), and compared to the GCS scores, the MP performed significantly better in discrimination (DeLong's test: p < 0.001). Among these patients elevated MP was associated to higher ICU mortality (OR 1.11; 95% CI 1.06-1.17; p < 0.001), enhanced the risk of hospital mortality, prolonged ICU stay, and decreased the number of ventilator-free days. In the subgroup analysis, high MP was associated with ICU mortality regardless of ARDS (OR 1.01, 95% CI 1.00-1.02, p = 0.009; OR 1.01, 95% CI 1.00-1.02, p = 0.018, respectively) or obesity (OR 1.01, 95% CI 1.00-1.02, p = 0.012; OR 1.01, 95% CI 1.01-1.02, p < 0.001, respectively). In neurocritical care patients undergoing invasive ventilation, elevated MP is linked to higher ICU mortality and a variety of other clinical outcomes.

A Machine Learning-Based Prognostic Model for the Prediction of Early Death After Traumatic Brain Injury: Comparison with the Corticosteroid Randomization After Significant Head Injury (CRASH) Model

BACKGROUND

Machine learning (ML) has been used to predict the outcomes of traumatic brain injury. However, few studies have reported the use of ML models to predict early death. This study aimed to develop ML models for early death prediction and to compare performance with the corticosteroid randomization after significant head injury (CRASH) model.

METHODS

We retrospectively reviewed traumatic brain injury patients between February 2017 and August 2021. The patients were randomly assigned to a training set and a test set. Predictive variables included clinical findings, laboratory values, and computed tomography findings. The ML models (random forest, support vector machine [SVM], logistic regression) were developed with the training set. The CRASH model is a prognostic model that was developed based on 10,008 patients included in the CRASH trial. The ML and CRASH models were applied to the test set to evaluate the performance.

RESULTS

A total of 423 patients were included; 317 and 106 patients were randomly assigned to the training and test sets, respectively. The area under the curve was highest in the SVM (0.952, 95% confidence interval = 0.906-0.990) and lowest in the CRASH model (0.942, 95% confidence interval = 0.886-0.999). There were no significant differences between the area under the curves of the ML and CRASH models (P = 0.899 for random forest vs. the CRASH model, P = 0.760 for SVM vs. the CRASH model, P = 0.806 for logistic regression vs. the CRASH model).

CONCLUSIONS

The ML models may have comparable performances compared to the CRASH model despite being developed with a smaller sample size.

Machine Learning in the Prediction of Trauma Outcomes: A Systematic Review

STUDY OBJECTIVE

Machine learning models carry unique potential as decision-making aids and prediction tools for improving patient care. Traumatically injured patients provide a uniquely heterogeneous population with severe injuries that can be difficult to predict. Given the relative infancy of machine learning applications in medicine, this systematic review aimed to better understand the current state of machine learning development and implementation to help create a basis for future research.

METHODS

We conducted a systematic review from inception to May 2021, using Embase, MEDLINE through Ovid, Web of Science, Google Scholar, and relevant gray literature, for uses of machine learning in predicting the outcomes of trauma patients. The screening and data extraction were performed by 2 independent reviewers.

RESULTS

Of the 14,694 identified articles screened, 67 were included for data extraction. Artificial neural networks comprised the most commonly used model, and mortality was the most prevalent outcome of interest. In terms of machine learning model development, there was a lack of studies that employed external validation, feature selection methods, and performed formal calibration testing. Significant heterogeneity in reporting was also observed between the machine learning models employed, patient populations, performance metrics, and features employed.

CONCLUSION

This review highlights the heterogeneity in the development and reporting of machine learning models for the prediction of trauma outcomes. While these models present an area of opportunity as an ancillary to clinical decision-making, we recommend more standardization and rigorous guidelines for the development of future models.

XGBoost machine learning algorism performed better than regression models in predicting mortality of moderate to severe traumatic brain injury

BACKGROUND

Traumatic brain injury (TBI) brings severe mortality and morbidity risk to patients. Predicting outcome of these patients is necessary for physicians to make suitable treatments to improve prognosis. The aim of this study is to develop a mortality prediction approach using the XGBoost (extreme gradient boosting) in moderate to severe TBI.

METHODS

368 patients hospitalized in West China hospital for TBI with GCS below 13 were identified. To construct XGBoost prediction approach, patients were divided into training set and test set with ratio of 7:3. Logistic regression prediction model was also constructed and compared with XGBoost model. Area under the receiver operating characteristic curve (AUC), accuracy, sensitivity and specificity were calculated to compare the prognostic value between XGBoost and logistic regression.

RESULTS

205 patients suffered poor outcome with mortality of 55.7%. Non-survivors had lower Glasgow Coma Scale (GCS) (5 vs 7, p<0.001) and higher Injury Severit Score (ISS) than survivors (25 vs 16, p<0.001). Platelet (p<0.001), albumin (p<0.001), hemoglobin (p<0.001) were significantly lower in non-survivors while glucose (p<0.001) and prothrombin time (PT) (p<0.001)was significantly higher in non-survivors. Among the XGBoost approach, GCS, PT and glucose had the most significant feature importance. The AUC (0.955 vs 0.805) and accuracy (0.955 vs 0.70) of XGBoost were both higher than logistic regression.

CONCLUSION

Predicting mortality of moderate to severe TBI patients using XGBoost algorism is more effective and precise than logistic regression. The XGBoost prediction approach is beneficial for physicians to evaluate TBI patients at high risk of poor outcome.

Data Science Trends Relevant to Nursing Practice: A Rapid Review of the 2020 Literature

BACKGROUND

The term "data science" encompasses several methods, many of which are considered cutting edge and are being used to influence care processes across the world. Nursing is an applied science and a key discipline in health care systems in both clinical and administrative areas, making the profession increasingly influenced by the latest advances in data science. The greater informatics community should be aware of current trends regarding the intersection of nursing and data science, as developments in nursing practice have cross-professional implications.

OBJECTIVES

This study aimed to summarize the latest (calendar year 2020) research and applications of nursing-relevant patient outcomes and clinical processes in the data science literature.

METHODS

We conducted a rapid review of the literature to identify relevant research published during the year 2020. We explored the following 16 topics: (1) artificial intelligence/machine learning credibility and acceptance, (2) burnout, (3) complex care (outpatient), (4) emergency department visits, (5) falls, (6) health care-acquired infections, (7) health care utilization and costs, (8) hospitalization, (9) in-hospital mortality, (10) length of stay, (11) pain, (12) patient safety, (13) pressure injuries, (14) readmissions, (15) staffing, and (16) unit culture.

RESULTS

Of 16,589 articles, 244 were included in the review. All topics were represented by literature published in 2020, ranging from 1 article to 59 articles. Numerous contemporary data science methods were represented in the literature including the use of machine learning, neural networks, and natural language processing.

CONCLUSION

This review provides an overview of the data science trends that were relevant to nursing practice in 2020. Examinations of such literature are important to monitor the status of data science's influence in nursing practice.

Mediators of neutrophil lymphocyte ratio in the relationship between ondansetron pre-treatment and the mortality of ICU patients on mechanical ventilation: causal mediation analysis from the MIMIC-IV database

AIMS

The mortality of critically ill patients undergoing mechanical ventilation (MV) is high and few strategies are available. We explored the relationship between ondansetron pre-treatment, the neutrophil:lymphocyte ratio (NLR), and platelet:lymphocyte ratio (PLR), and mortality of ventilated patients in the intensive care unit.

METHODS

We developed a retrospective cohort study that involved patients undergoing MV in the Multiparameter Intelligent Monitoring in Intensive Care IV (MIMIC-IV) database. Causal mediation analysis was conducted to assess the relationship of ondansetron use and mortality and explore the potential causal pathway mediated by the NLR or PLR. The primary outcome was 28-day mortality.

RESULTS

A total of 17,927 eligible patients was obtained (5665 had taken ondansetron before MV initiation and 12,262 patients had not). The OR for 28-day mortality for ondansetron use uncorrelated with the mediator (NLR, PLR) was 0.72 (95%CI=0.64-0.81, P <0.001). Ondansetron was also associated with a reduction in 28-day mortality after controlling for the mediator of NLR (OR = 0.98, 95%CI = 0.97-0.99, P < 0.01). For the indirect effect, the NLR could explain 13.47% (95%CI = 8.59-20.54%, P < 0.01) of the impact of ondansetron use on 28-day mortality. The proportion mediated increased to 21.50% (95%CI = 12.36-47.44%, P < 0.01) for 90-day mortality. Adjusted mediation analysis revealed no suggestion of a causal mediation pathway for this effect by the PLR (P = 0.12).

CONCLUSIONS

NLR may play substantial roles in the relationship between ondansetron pre-treatment before initiation of mechanical ventilation and the reduction of death risk in ventilated patients.

Artificial intelligence to predict in-hospital mortality using novel anatomical injury score

The aim of the study is to develop artificial intelligence (AI) algorithm based on a deep learning model to predict mortality using abbreviate injury score (AIS). The performance of the conventional anatomic injury severity score (ISS) system in predicting in-hospital mortality is still limited. AIS data of 42,933 patients registered in the Korean trauma data bank from four Korean regional trauma centers were enrolled. After excluding patients who were younger than 19 years old and those who died within six hours from arrival, we included 37,762 patients, of which 36,493 (96.6%) survived and 1269 (3.4%) deceased. To enhance the AI model performance, we reduced the AIS codes to 46 input values by organizing them according to the organ location (Region-46). The total AIS and six categories of the anatomic region in the ISS system (Region-6) were used to compare the input features. The AI models were compared with the conventional ISS and new ISS (NISS) systems. We evaluated the performance pertaining to the 12 combinations of the features and models. The highest accuracy (85.05%) corresponded to Region-46 with DNN, followed by that of Region-6 with DNN (83.62%), AIS with DNN (81.27%), ISS-16 (80.50%), NISS-16 (79.18%), NISS-25 (77.09%), and ISS-25 (70.82%). The highest AUROC (0.9084) corresponded to Region-46 with DNN, followed by that of Region-6 with DNN (0.9013), AIS with DNN (0.8819), ISS (0.8709), and NISS (0.8681). The proposed deep learning scheme with feature combination exhibited high accuracy metrics such as the balanced accuracy and AUROC than the conventional ISS and NISS systems. We expect that our trial would be a cornerstone of more complex combination model.

Machine Learning Models to Predict 30-Day Mortality in Mechanically Ventilated Patients

Previous scoring models, such as the Acute Physiologic Assessment and Chronic Health Evaluation II (APACHE II) score, do not adequately predict the mortality of patients receiving mechanical ventilation in the intensive care unit. Therefore, this study aimed to apply machine learning algorithms to improve the prediction accuracy for 30-day mortality of mechanically ventilated patients. The data of 16,940 mechanically ventilated patients were divided into the training-validation (83%, n = 13,988) and test (17%, n = 2952) sets. Machine learning algorithms including balanced random forest, light gradient boosting machine, extreme gradient boost, multilayer perceptron, and logistic regression were used. We compared the area under the receiver operating characteristic curves (AUCs) of machine learning algorithms with those of the APACHE II and ProVent score results. The extreme gradient boost model showed the highest AUC (0.79 (0.77–0.80)) for the 30-day mortality prediction, followed by the balanced random forest model (0.78 (0.76–0.80)). The AUCs of these machine learning models as achieved by APACHE II and ProVent scores were higher than 0.67 (0.65–0.69), and 0.69 (0.67–0.71)), respectively. The most important variables in developing each machine learning model were APACHE II score, Charlson comorbidity index, and norepinephrine. The machine learning models have a higher AUC than conventional scoring systems, and can thus better predict the 30-day mortality of mechanically ventilated patients.