Predictive modeling in pediatric traumatic brain injury using machine learning

Development and external validation of a machine learning model for brain injury in pediatric patients on extracorporeal membrane oxygenation

BACKGROUND

Patients supported by extracorporeal membrane oxygenation (ECMO) are at a high risk of brain injury, contributing to significant morbidity and mortality. This study aimed to employ machine learning (ML) techniques to predict brain injury in pediatric patients ECMO and identify key variables for future research.

METHODS

Data from pediatric patients undergoing ECMO were collected from the Chinese Society of Extracorporeal Life Support (CSECLS) registry database and local hospitals. Ten ML methods, including random forest, support vector machine, decision tree classifier, gradient boosting machine, extreme gradient boosting, light gradient boosting machine, Naive Bayes, neural networks, a generalized linear model, and AdaBoost, were employed to develop and validate the optimal predictive model based on accuracy and area under the curve (AUC). Patients were divided into retrospective cohort for model development and internal validation, and one cohort for external validation.

RESULTS

A total of 1,633 patients supported by ECMO were included in the model development, of whom 181 experienced brain injury. In the external validation cohort, 30 of the 154 patients experienced brain injury. Fifteen features were selected for the model construction. Among the ML models tested, the random forest model achieved the best performance, with an AUC of 0.912 for internal validation and 0.807 for external validation.

CONCLUSION

The Random Forest model based on machine learning demonstrates high accuracy and robustness in predicting brain injury in pediatric patients supported by ECMO, with strong generalization capabilities and promising clinical applicability.

Prediction of white matter hyperintensities evolution one-year post-stroke from a single-point brain MRI and stroke lesions information

Predicting the evolution of white matter hyperintensities (WMH), a common feature in brain magnetic resonance imaging (MRI) scans of older adults (i.e., whether WMH will grow, remain stable, or shrink with time) is important for personalised therapeutic interventions. However, this task is difficult mainly due to the myriad of vascular risk factors and comorbidities that influence it, and the low specificity and sensitivity of the image intensities and textures alone for predicting WMH evolution. Given the predominantly vascular nature of WMH, in this study, we evaluate the impact of incorporating stroke lesion information to a probabilistic deep learning model to predict the evolution of WMH 1-year after the baseline image acquisition, taken soon after a mild stroke event, using T2-FLAIR brain MRI. The Probabilistic U-Net was chosen for this study due to its capability of simulating and quantifying the uncertainties involved in the prediction of WMH evolution. We propose to use an additional loss called volume loss to train our model, and incorporate stroke lesions information, an influential factor in WMH evolution. Our experiments showed that jointly segmenting the disease evolution map (DEM) of WMH and stroke lesions, improved the accuracy of the DEM representing WMH evolution. The combination of introducing the volume loss and joint segmentation of DEM of WMH and stroke lesions outperformed other model configurations with mean volumetric absolute error of 0.0092 ml (down from 1.7739 ml) and 0.47% improvement on average Dice similarity coefficient in shrinking, growing and stable WMH.

Comparison of Machine Learning Models in Predicting Mental Health Sequelae Following Concussion in Youth

Youth who experience concussions may be at greater risk for subsequent mental health challenges, making early detection crucial for timely intervention. This study utilized Bidirectional Long Short-Term Memory (BiLSTM) networks to predict mental health outcomes following concussion in youth and compared its performance to traditional models. We also examined whether incorporating social determinants of health (SDoH) improved predictive power, given the disproportionate impact of concussions and mental health issues on disadvantaged populations. We evaluated the models using accuracy, area under the curve (AUC) of the receiver operating characteristic (ROC), and other performance metrics. Our BiLSTM model with SDoH data achieved the highest accuracy (0.883) and AUC-ROC score (0.892). Unlike traditional models, our approach provided real-time predictions at each visit within 12 months of the index concussion, aiding clinicians in making timely, visit-specific referrals for further treatment and interventions.

Random Forest Prognostication of Survival and 6-Month Outcome in Pediatric Patients Following Decompressive Craniectomy for Traumatic Brain Injury

BACKGROUND

There is a dearth of literature regarding prognostic and predictive factors for outcome following pediatric decompressive craniectomy (DC) performed after traumatic brain injury (TBI). The aim of this study was to develop a random forest machine learning algorithm to predict outcomes following DC in pediatric patients.

METHODS

This multi-institutional retrospective study assessed the 6-month postoperative outcome in pediatric patients who underwent DC. We developed a machine learning model using classification random forest (CRF) and survival random forest (SRF) algorithms for prediction of outcomes. Data on clinical signs, radiographic studies, and laboratory studies were collected. Outcome measures for the CRF model were mortality and good or bad outcome based on Glasgow Outcome Scale at 6 months. A Glasgow Outcome Scale score of ≥4 indicated a good outcome. Outcome for the SRF model was mortality during the follow-up period.

RESULTS

The study included 40 pediatric patients. Hospital mortality rate was 27.5%, and 75.8% of survivors had a good outcome at 6-month follow up. The CRF model for 6-month mortality had a receiver operating characteristic area under the curve of 0.984, whereas, 6-month good and bad outcomes had a receiver operating characteristic area under the curve of 0.873. The SRF model was trained at the 6-month time point with a receiver operating characteristic area under the curve of 0.921.

CONCLUSIONS

CRF and SRF models successfully predicted 6-month outcomes and mortality following DC in pediatric patients with TBI. These results suggest that random forest models may be efficacious for predicting outcome in this patient population.

Applications of machine learning in pediatric traumatic brain injury (pTBI): a systematic review of the literature

OBJECTIVE

Pediatric traumatic brain injury (pTBI) is a heterogeneous condition requiring the development of clinical decision rules (CDRs) for the optimal management of these patients. Machine learning (ML) is a novel artificial intelligence (AI) predictive tool with various applications in modern neurosurgery, including the creation of CDRs for patients with pTBI. In the present study, we summarized the current literature on the applications of ML in pTBI.

METHODS

A systematic review was conducted following the PRISMA guidelines. The literature search included PubMed/MEDLINE, SCOPUS, and ScienceDirect databases. We included observational or experimental studies focusing on the applications of ML in patients with pTBI under 18 years of age.

RESULTS

A total of 18 articles were included in our systematic review. Of these articles, 16 were retrospective cohorts, 1 was a prospective cohort, and 1 was a case-control study. Of these articles, ten concerned ML applications in predicting the outcome of pTBI patients, while 8 reported applications of ML in predicting the need for CT scans. Artificial Neuronal Network (ANN) and Random Forest (RF) were the most commonly utilized models for the creation of predictive algorithms. The accuracy of the ML algorithms to predict the need for CT scan in pTBI cases ranged from 0.790 to 0.999, and the Area Under Curve (AUC) ranged from 0.411 (95%CI: 0.354-0.468) to 0.980 (95%CI: 0.950-1.00). The model with the maximum accuracy to predict the need for CT scan was a Deep ANN model, while the model with the maximum AUC was Ensemble Learning. The model with the maximum accuracy to predict the outcome (favorable vs. unfavorable) of patients with TBI was a support vector machine (SVM) model with 94.0% accuracy, whereas the model with the highest AUC was an ANN model with an AUC of 0.991.

CONCLUSION

In the present systematic review, conventional and novel ML models were utilized to either predict the presence of intracranial trauma or the prognosis of children with pTBI. However, most of the reported ML algorithms have not been externally validated and are pending further research.

Usefulness of Artificial Intelligence in Traumatic Brain Injury: A Bibliometric Analysis and Mini-review

BACKGROUND

Traumatic brain injury (TBI) has become a major source of disability worldwide, increasing the interest in algorithms that use artificial intelligence (AI) to optimize the interpretation of imaging studies, prognosis estimation, and critical care issues. In this study we present a bibliometric analysis and mini-review on the main uses that have been developed for TBI in AI.

METHODS

The results informing this review come from a Scopus database search as of April 15, 2023. The bibliometric analysis was carried out via the mapping bibliographic metrics method. Knowledge mapping was made in the VOSviewer software (V1.6.18), analyzing the "link strength" of networks based on co-occurrence of key words, countries co-authorship, and co-cited authors. In the mini-review section, we highlight the main findings and contributions of the studies.

RESULTS

A total of 495 scientific publications were identified from 2000 to 2023, with 9262 citations published since 2013. Among the 160 journals identified, The Journal of Neurotrauma, Frontiers in Neurology, and PLOS ONE were those with the greatest number of publications. The most frequently co-occurring key words were: "machine learning", "deep learning", "magnetic resonance imaging", and "intracranial pressure". The United States accounted for more collaborations than any other country, followed by United Kingdom and China. Four co-citation author clusters were found, and the top 20 papers were divided into reviews and original articles.

CONCLUSIONS

AI has become a relevant research field in TBI during the last 20 years, demonstrating great potential in imaging, but a more modest performance for prognostic estimation and neuromonitoring.

Friedman's Gradient-Boosting Algorithm Predicts Lactate-Pyruvate Ratio Trends in Cases of Intracerebral Hemorrhages

OBJECTIVE

The local effects of an intracerebral hemorrhage (ICH) on surrounding brain tissue can be detected bedside using multimodal brain monitoring techniques. The aim of this study is to design a gradient boosting regression model using the R package boostmtree with the ability to predict lactate-pyruvate ratio measurements in ICH.

METHODS

We performed a retrospective analysis of 6 spontaneous ICH and 6 traumatic ICH patients who underwent surgical removal of the clot with microdialysis catheters placed in the perihematomal zone. Predictors of glucose, lactate, pyruvate, age, sex, diagnosis, and operation status were used to design our model.

RESULTS

In a holdout analysis, the model forecasted lactate-pyruvate ratio trends in a representative in-sample testing set. We anticipate that boostmtree could be applied to designs of similar regression models to analyze trends in other multimodal monitoring features across other types of acute brain injury.

CONCLUSIONS

The model successfully predicted hourly lactate-pyruvate ratios in spontaneous ICH and traumatic ICH cases after the hemorrhage evacuation and displayed significantly better performance than linear models. Our results suggest that boostmtree may be a powerful tool in developing more advanced mathematical models to assess other multimodal monitoring parameters for cases in which the perihematomal environment is monitored.

The recent two decades of traumatic brain injury: a bibliometric analysis and systematic review

BACKGROUND

Traumatic brain injury (TBI) is a serious public health burden worldwide, with a mortality rate of 20-30%; however, reducing the incidence and mortality rates of TBI remains a major challenge. This study provides a multidimensional analysis to explore the potential breakthroughs in TBI over the past two decades.

MATERIALS AND METHODS

The authors used bibliometric and Latent Dirichlet Allocation (LDA) analyses to analyze publications focusing on TBI published between 2003 and 2022 from the Web of Science Core Collection (WOSCC) database to identify core journals and collaborations among countries/regions, institutions, authors, and research trends.

RESULTS

Over the past 20 years, 41 545 articles on TBI from 3043 journals were included, with 12 916 authors from 20 449 institutions across 145 countries/regions. The annual number of publications has increased 10-fold compared to previous publications. This study revealed that high-income countries, especially the United States, have a significant influence. Collaboration was limited to several countries/regions. The LDA results indicated that the hotspots included four main areas: 'Clinical finding', 'Molecular mechanism', 'Epidemiology', and 'Prognosis'. Epidemiological research has consistently increased in recent years. Through epidemiological topic analysis, the main etiology of TBI has shifted from traffic accidents to falls in a demographically aging society.

CONCLUSION

Over the past two decades, TBI research has developed rapidly, and its epidemiology has received increasing attention. Reducing the incidence of TBI from a preventive perspective is emerging as a trend to alleviate the future social burden; therefore, epidemiological research might bring breakthroughs in TBI.

Prediction of Postnatal Growth Failure in Very Low Birth Weight Infants Using a Machine Learning Model

Accurate prediction of postnatal growth failure (PGF) can be beneficial for early intervention and prevention. We aimed to develop a machine learning model to predict PGF at discharge among very low birth weight (VLBW) infants using extreme gradient boosting. A total of 729 VLBW infants, born between 2013 and 2017 in four hospitals, were included. PGF was defined as a decrease in z-score between birth and discharge that was greater than 1.28. Feature selection and addition were performed to improve the accuracy of prediction at four different time points, including 0, 7, 14, and 28 days after birth. A total of 12 features with high contribution at all time points by feature importance were decided upon, and good performance was shown as an area under the receiver operating characteristic curve (AUROC) of 0.78 at 7 days. After adding weight change to the 12 features-which included sex, gestational age, birth weight, small for gestational age, maternal hypertension, respiratory distress syndrome, duration of invasive ventilation, duration of non-invasive ventilation, patent ductus arteriosus, sepsis, use of parenteral nutrition, and reach at full enteral nutrition-the AUROC at 7 days after birth was shown as 0.84. Our prediction model for PGF performed well at early detection. Its potential clinical application as a supplemental tool could be helpful for reducing PGF and improving child health.

Advances in neuroproteomics for neurotrauma: unraveling insights for personalized medicine and future prospects

Neuroproteomics, an emerging field at the intersection of neuroscience and proteomics, has garnered significant attention in the context of neurotrauma research. Neuroproteomics involves the quantitative and qualitative analysis of nervous system components, essential for understanding the dynamic events involved in the vast areas of neuroscience, including, but not limited to, neuropsychiatric disorders, neurodegenerative disorders, mental illness, traumatic brain injury, chronic traumatic encephalopathy, and other neurodegenerative diseases. With advancements in mass spectrometry coupled with bioinformatics and systems biology, neuroproteomics has led to the development of innovative techniques such as microproteomics, single-cell proteomics, and imaging mass spectrometry, which have significantly impacted neuronal biomarker research. By analyzing the complex protein interactions and alterations that occur in the injured brain, neuroproteomics provides valuable insights into the pathophysiological mechanisms underlying neurotrauma. This review explores how such insights can be harnessed to advance personalized medicine (PM) approaches, tailoring treatments based on individual patient profiles. Additionally, we highlight the potential future prospects of neuroproteomics, such as identifying novel biomarkers and developing targeted therapies by employing artificial intelligence (AI) and machine learning (ML). By shedding light on neurotrauma's current state and future directions, this review aims to stimulate further research and collaboration in this promising and transformative field.

Integrating unsupervised and supervised learning techniques to predict traumatic brain injury: A population-based study

This work aimed to identify pre-existing health conditions of patients with traumatic brain injury (TBI) and develop predictive models for the first TBI event and its external causes by employing a combination of unsupervised and supervised learning algorithms. We acquired up to five years of pre-injury diagnoses for 488,107 patients with TBI and 488,107 matched control patients who entered the emergency department or acute care hospitals between April 1st, 2002, and March 31st, 2020. Diagnoses were obtained from the Ontario Health Insurance Plan (OHIP) database which contains province-wide claims data by physicians in Ontario, Canada for inpatient and outpatient services. A screening process was conducted on the OHIP diagnostic codes to limit the subsequent analysis to codes that were predictive of TBI, which concluded that 314 codes were significantly associated with TBI. The Latent Dirichlet Allocation (LDA) model was applied to the diagnostic codes and generated an optimal number of 19 topics that concur with published literature but also suggest other unexplored areas. Estimated word-topic probabilities from the LDA model helped us detect pre-morbid conditions among patients with TBI by uncovering the underlying patterns of diagnoses, meanwhile estimated document-topic probabilities were utilized in variable creation as form of a dimension reduction. We created 19 topic scores for each patient in the cohort which were utilized along with socio-demographic factors for Random Forest binary classifier models. Test set performances evaluated using area under the receiver operating characteristic curve (AUC) were: TBI event (AUC = 0.85), external cause of injury: falls (AUC = 0.85), struck by/against (AUC = 0.83), cyclist collision (AUC = 0.76), motor vehicle collision (AUC = 0.83). Our analysis successfully demonstrated the feasibility of using machine learning to predict TBI due to various external causes and identified the most important factors that contribute to this prediction.

Machine learning-based models to predict the need for neurosurgical intervention after moderate traumatic brain injury

Background and Aims

Traumatic 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.

Methods

This 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.

Results

Based 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.

Conclusion

The 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.

Machine learning-based classification of chronic traumatic brain injury using hybrid diffusion imaging

Background and purpose

Traumatic brain injury (TBI) can cause progressive neuropathology that leads to chronic impairments, creating a need for biomarkers to detect and monitor this condition to improve outcomes. This study aimed to analyze the ability of data-driven analysis of diffusion tensor imaging (DTI) and neurite orientation dispersion imaging (NODDI) to develop biomarkers to infer symptom severity and determine whether they outperform conventional T1-weighted imaging.

Materials and methods

A machine learning-based model was developed using a dataset of hybrid diffusion imaging of patients with chronic traumatic brain injury. We first extracted the useful features from the hybrid diffusion imaging (HYDI) data and then used supervised learning algorithms to classify the outcome of TBI. We developed three models based on DTI, NODDI, and T1-weighted imaging, and we compared the accuracy results across different models.

Results

Compared with the conventional T1-weighted imaging-based classification with an accuracy of 51.7-56.8%, our machine learning-based models achieved significantly better results with DTI-based models at 58.7-73.0% accuracy and NODDI with an accuracy of 64.0-72.3%.

Conclusion

The machine learning-based feature selection and classification algorithm based on hybrid diffusion features significantly outperform conventional T1-weighted imaging. The results suggest that advanced algorithms can be developed for inferring symptoms of chronic brain injury using feature selection and diffusion-weighted imaging.

Modelling 30-day hospital readmission after discharge for COPD patients based on electronic health records

Chronic Obstructive Pulmonary Disease (COPD) is the third most common chronic disease in China with frequent exacerbations, resulting in increased hospitalization and readmission rate. COPD readmission within 30 days after discharge is an important indicator of care transitions, patient's quality of life and disease management. Identifying risk factors and improving 30-day readmission prediction help inform appropriate interventions, reducing readmissions and financial burden. This study aimed to develop a 30-day readmission prediction model using decision tree by learning from the data extracted from the electronic health record of COPD patients in Macao. Health records data of COPD inpatients from Kiang Wu Hospital, Macao, from January 1, 2018, to December 31, 2019 were reviewed and analyzed. A total of 782 hospitalizations for AECOPD were enrolled, where the 30-day readmission rate was 26.5% (207). A balanced dataset was randomly generated, where male accounted for 69.1% and mean age was 80.73 years old. Age, length of stay, history of tobacco smoking, hemoglobin, systemic steroids use, antibiotics use and number of hospital admission due to COPD in last 12 months were found to be significant risk factors for 30-day readmission of CODP patients (P < 0.01). A data-driven decision tree-based modelling approach with Bayesian hyperparameter optimization was developed. The mean precision-recall and AUC value for the classifier were 73.85, 73.7 and 0.7506, showing a satisfying prediction performance. The number of hospital admission due to AECOPD in last 12 months, smoke status and patients' age were the top factors for 30-day readmission in Macao population.

Prognosis prediction in traumatic brain injury patients using machine learning algorithms

Predicting treatment outcomes in traumatic brain injury (TBI) patients is challenging worldwide. The present study aimed to achieve the most accurate machine learning (ML) algorithms to predict the outcomes of TBI treatment by evaluating demographic features, laboratory data, imaging indices, and clinical features. We used data from 3347 patients admitted to a tertiary trauma centre in Iran from 2016 to 2021. After the exclusion of incomplete data, 1653 patients remained. We used ML algorithms such as random forest (RF) and decision tree (DT) with ten-fold cross-validation to develop the best prediction model. Our findings reveal that among different variables included in this study, the motor component of the Glasgow coma scale, the condition of pupils, and the condition of cisterns were the most reliable features for predicting in-hospital mortality, while the patients' age takes the place of cisterns condition when considering the long-term survival of TBI patients. Also, we found that the RF algorithm is the best model to predict the short-term mortality of TBI patients. However, the generalized linear model (GLM) algorithm showed the best performance (with an accuracy rate of 82.03 ± 2.34) in predicting the long-term survival of patients. Our results showed that using appropriate markers and with further development, ML has the potential to predict TBI patients' survival in the short- and long-term.

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.

Individualized prediction of chronic kidney disease for the elderly in longevity areas in China: Machine learning approaches

Background

Chronic kidney disease (CKD) has become a major public health problem worldwide and has caused a huge social and economic burden, especially in developing countries. No previous study has used machine learning (ML) methods combined with longitudinal data to predict the risk of CKD development in 2 years amongst the elderly in China.

Methods

This study was based on the panel data of 925 elderly individuals in the 2012 baseline survey and 2014 follow-up survey of the Healthy Aging and Biomarkers Cohort Study (HABCS) database. Six ML models, logistic regression (LR), lasso regression, random forests (RF), gradient-boosted decision tree (GBDT), support vector machine (SVM), and deep neural network (DNN), were developed to predict the probability of CKD amongst the elderly in 2 years (the year of 2014). The decision curve analysis (DCA) provided a range of threshold probability of the outcome and the net benefit of each ML model.

Results

Amongst the 925 elderly in the HABCS 2014 survey, 289 (18.8%) had CKD. Compared with the other models, LR, lasso regression, RF, GBDT, and DNN had no statistical significance of the area under the receiver operating curve (AUC) value (>0.7), and SVM exhibited the lowest predictive performance (AUC = 0.633, p-value = 0.057). DNN had the highest positive predictive value (PPV) (0.328), whereas LR had the lowest (0.287). DCA results indicated that within the threshold ranges of ~0-0.03 and 0.37-0.40, the net benefit of GBDT was the largest. Within the threshold ranges of ~0.03-0.10 and 0.26-0.30, the net benefit of RF was the largest. Age was the most important predictor variable in the RF and GBDT models. Blood urea nitrogen, serum albumin, uric acid, body mass index (BMI), marital status, activities of daily living (ADL)/instrumental activities of daily living (IADL) and gender were crucial in predicting CKD in the elderly.

Conclusion

The ML model could successfully capture the linear and nonlinear relationships of risk factors for CKD in the elderly. The decision support system based on the predictive model in this research can help medical staff detect and intervene in the health of the elderly early.

Predicting Outcome in Patients with Brain Injury: Differences between Machine Learning versus Conventional Statistics

Defining reliable tools for early prediction of outcome is the main target for physicians to guide care decisions in patients with brain injury. The application of machine learning (ML) is rapidly increasing in this field of study, but with a poor translation to clinical practice. This is basically dependent on the uncertainty about the advantages of this novel technique with respect to traditional approaches. In this review we address the main differences between ML techniques and traditional statistics (such as logistic regression, LR) applied for predicting outcome in patients with stroke and traumatic brain injury (TBI). Thirteen papers directly addressing the different performance among ML and LR methods were included in this review. Basically, ML algorithms do not outperform traditional regression approaches for outcome prediction in brain injury. Better performance of specific ML algorithms (such as Artificial neural networks) was mainly described in the stroke domain, but the high heterogeneity in features extracted from low-dimensional clinical data reduces the enthusiasm for applying this powerful method in clinical practice. To better capture and predict the dynamic changes in patients with brain injury during intensive care courses ML algorithms should be extended to high-dimensional data extracted from neuroimaging (structural and fMRI), EEG and genetics.

Computational Approaches for Acute Traumatic Brain Injury Image Recognition

In recent years, there have been major advances in deep learning algorithms for image recognition in traumatic brain injury (TBI). Interest in this area has increased due to the potential for greater objectivity, reduced interpretation times and, ultimately, higher accuracy. Triage algorithms that can re-order radiological reading queues have been developed, using classification to prioritize exams with suspected critical findings. Localization models move a step further to capture more granular information such as the location and, in some cases, size and subtype, of intracranial hematomas that could aid in neurosurgical management decisions. In addition to the potential to improve the clinical management of TBI patients, the use of algorithms for the interpretation of medical images may play a transformative role in enabling the integration of medical images into precision medicine. Acute TBI is one practical example that can illustrate the application of deep learning to medical imaging. This review provides an overview of computational approaches that have been proposed for the detection and characterization of acute TBI imaging abnormalities, including intracranial hemorrhage, skull fractures, intracranial mass effect, and stroke.

Pediatric severe traumatic brain injury mortality prediction determined with machine learning-based modeling

INTRODUCTION

Severe traumatic brain injury (sTBI) is a leading cause of mortality in children. As clinical prognostication is important in guiding optimal care and decision making, our goal was to create a highly discriminative sTBI outcome prediction model for mortality.

METHODS

Machine learning and advanced analytics were applied to the patient admission variables obtained from a comprehensive pediatric sTBI database. Demographic and clinical data, head CT imaging abnormalities and blood biochemical data from 196 children and adolescents admitted to a tertiary pediatric intensive care unit (PICU) with sTBI were integrated using feature ranking by way of a forest of randomized decision trees, and a model was generated from a reduced number of admission variables with maximal ability to discriminate outcome.

RESULTS

In total, 36 admission variables were analyzed using feature ranking with variable weighting to determine their predictive importance for mortality following sTBI. Reduction analysis utilizing Borata feature selection resulted in a parsimonious six-variable model with a mortality classification accuracy of 82%. The final admission variables that predicted mortality were: partial thromboplastin time (22%); motor Glasgow Coma Scale (21%); serum glucose (16%); fixed pupil(s) (16%); platelet count (13%) and creatinine (12%). Using only these six admission variables, a t-distributed stochastic nearest neighbor embedding algorithm plot demonstrated visual separation of sTBI patients that lived or died, with high mortality predictive ability of this model on the validation dataset (AUC = 0.90) which was confirmed with a conventional area-under-the-curve statistical approach on the total dataset (AUC = 0.91; P < 0.001).

CONCLUSIONS

Machine learning-based modeling identified the most clinically important prognostic factors resulting in a pragmatic, high performing prognostic tool for pediatric sTBI with excellent discriminative ability to predict mortality risk with 82% classification accuracy (AUC = 0.90). After external multicenter validation, our prognostic model might help to guide treatment decisions, aggressiveness of therapy and prepare family members and caregivers for timely end-of-life discussions and decision making.

LEVEL OF EVIDENCE

III; Prognostic.

Near Infrared Spectroscopy for High-Temporal Resolution Cerebral Physiome Characterization in TBI: A Narrative Review of Techniques, Applications, and Future Directions

Multimodal monitoring has been gaining traction in the critical care of patients following traumatic brain injury (TBI). Through providing a deeper understanding of the individual patient's comprehensive physiologic state, or "physiome," following injury, these methods hold the promise of improving personalized care and advancing precision medicine. One of the modalities being explored in TBI care is near-infrared spectroscopy (NIRS), given it's non-invasive nature and ability to interrogate microvascular and tissue oxygen metabolism. In this narrative review, we begin by discussing the principles of NIRS technology, including spatially, frequency, and time-resolved variants. Subsequently, the applications of NIRS in various phases of clinical care following TBI are explored. These applications include the pre-hospital, intraoperative, neurocritical care, and outpatient/rehabilitation setting. The utility of NIRS to predict functional outcomes and evaluate dysfunctional cerebrovascular reactivity is also discussed. Finally, future applications and potential advancements in NIRS-based physiologic monitoring of TBI patients are presented, with a description of the potential integration with other omics biomarkers.

The Impact of Weather and Air Pollution on Viral Infection and Disease Outcome Among Pediatric Pneumonia Patients in Chongqing, China, from 2009 to 2018: A Prospective Observational Study

BACKGROUND

For pediatric pneumonia, the meteorological and air pollution indicators have been frequently investigated for their association with viral circulation but not for their impact on disease severity.

METHODS

We performed a 10-year prospective, observational study in 1 hospital in Chongqing, China, to recruit children with pneumonia. Eight commonly seen respiratory viruses were tested. Autoregressive distributed lag (ADL) and random forest (RF) models were used to fit monthly detection rates of each virus at the population level and to predict the possibility of severe pneumonia at the individual level, respectively.

RESULTS

Between 2009 and 2018, 6611 pediatric pneumonia patients were included, and 4846 (73.3%) tested positive for at least 1 respiratory virus. The patient median age was 9 months (interquartile range, 4‒20). ADL models demonstrated a decent fitting of detection rates of R2 > 0.7 for respiratory syncytial virus, human rhinovirus, parainfluenza virus, and human metapneumovirus. Based on the RF models, the area under the curve for host-related factors alone was 0.88 (95% confidence interval [CI], .87‒.89) and 0.86 (95% CI, .85‒.88) for meteorological and air pollution indicators alone and 0.62 (95% CI, .60‒.63) for viral infections alone. The final model indicated that 9 weather and air pollution indicators were important determinants of severe pneumonia, with a relative contribution of 62.53%, which is significantly higher than respiratory viral infections (7.36%).

CONCLUSIONS

Meteorological and air pollution predictors contributed more to severe pneumonia in children than did respiratory viruses. These meteorological data could help predict times when children would be at increased risk for severe pneumonia and when interventions, such as reducing outdoor activities, may be warranted.

The detection of mild traumatic brain injury in paediatrics using artificial neural networks

Head computed tomography (CT) is the gold standard in emergency departments (EDs) to evaluate mild traumatic brain injury (mTBI) patients, especially for paediatrics. Data-driven models for successfully classifying head CT scans that have mTBI will be valuable in terms of timeliness and cost-effectiveness for TBI diagnosis. This study applied two different machine learning (ML) models to diagnose mTBI in a paediatric population collected as part of the paediatric emergency care applied research network (PECARN) study between 2004 and 2006. The models were conducted using 15,271 patients under the age of 18 years with mTBI and had a head CT report. In the conventional model, random forest (RF) ranked the features to reduce data dimensionality and the top ranked features were used to train a shallow artificial neural network (ANN) model. In the second model, a deep ANN applied to classify positive and negative mTBI patients using the entirety of the features available. The dataset was divided into two subsets: 80% for training and 20% for testing using five-fold cross-validation. Accuracy, sensitivity, precision, and specificity were calculated by comparing the model's prediction outcome to the actual diagnosis for each patient. RF ranked ten clinical demographic features and twelve CT-findings; the hybrid RF-ANN model achieved an average specificity of 99.96%, sensitivity of 95.98%, precision of 99.25%, and accuracy of 99.74% in identifying positive mTBI from negative mTBI subjects. The deep ANN proved its ability to carry out the task efficiently with an average specificity of 99.9%, sensitivity of 99.2%, precision of 99.9%, and accuracy of 99.9%. The performance of the two proposed models demonstrated the feasibility of using ANN to diagnose mTBI in a paediatric population. This is the first study to investigate deep ANN in a paediatric cohort with mTBI using clinical and non-imaging data and diagnose mTBI with balanced sensitivity and specificity using shallow and deep ML models. This method, if validated, would have the potential to reduce the burden of TBI evaluation in EDs and aide clinicians in the decision-making process.

Epidemiology and risk stratification of minor head injuries in school-going children

INTRODUCTION

Head injuries occur commonly in children and can lead to concussion injuries. We aim to describe the epidemiology of head injuries among school-going children and identify predictors of brain concussions in Singapore.

METHODS

This is a retrospective study of children 7-16 years old who presented to the Emergency Department (ED) of KK Women's and Children's Hospital in Singapore with minor head injury between June 2017 and August 2018. Data including demographics, clinical presentation, ED and hospital management were collected using a standardised electronic template. Multivariable logistic regression analysis was performed to identify early predictors for brain concussion. Concussion symptoms were defined as persistent symptoms after admission, need for inpatient intervention, or physician concerns necessitating neuroimaging.

RESULTS

Among 1,233 children (mean age, 6.6 years; 72.6% boys) analysed, the commonest mechanism was falls (64.6%). Headache and vomiting were the most common presenting symptoms. A total of 395 (32.0%) patients required admission, and 277 (22.5%) had symptoms of concussion. Older age (13-16 years old) (adjusted odds ratio [aOR] 1.53, 95% confidence interval [CI] 1.12-2.08), children involved in road traffic accidents (aOR 2.12, CI 1.17-3.85) and a presenting complaint of headache (aOR 2.64, CI 1.99-3.50) were significantly associated with symptoms of concussion.

CONCLUSION

This study provides a detailed description of the pattern of head injuries among school-going children in Singapore. High risk patients may require closer monitoring to detect post-concussion syndrome early.

GUESS: projecting machine learning scores to well-calibrated probability estimates for clinical decision-making

MOTIVATION

Clinical decision support systems have been applied in numerous fields, ranging from cancer survival toward drug resistance prediction. Nevertheless, clinical decision support systems typically have a caveat: many of them are perceived as black-boxes by non-experts and, unfortunately, the obtained scores cannot usually be interpreted as class probability estimates. In probability-focused medical applications, it is not sufficient to perform well with regards to discrimination and, consequently, various calibration methods have been developed to enable probabilistic interpretation. The aims of this study were (i) to develop a tool for fast and comparative analysis of different calibration methods, (ii) to demonstrate their limitations for the use on clinical data and (iii) to introduce our novel method GUESS.

RESULTS

We compared the performances of two different state-of-the-art calibration methods, namely histogram binning and Bayesian Binning in Quantiles, as well as our novel method GUESS on both, simulated and real-world datasets. GUESS demonstrated calibration performance comparable to the state-of-the-art methods and always retained accurate class discrimination. GUESS showed superior calibration performance in small datasets and therefore may be an optimal calibration method for typical clinical datasets. Moreover, we provide a framework (CalibratR) for R, which can be used to identify the most suitable calibration method for novel datasets in a timely and efficient manner. Using calibrated probability estimates instead of original classifier scores will contribute to the acceptance and dissemination of machine learning based classification models in cost-sensitive applications, such as clinical research.

AVAILABILITY AND IMPLEMENTATION

GUESS as part of CalibratR can be downloaded at CRAN.

Machine Learning-Based Prediction Models for 30-Day Readmission after Hospitalization for Chronic Obstructive Pulmonary Disease

While machine learning approaches can enhance prediction ability, little is known about their ability to predict 30-day readmission after hospitalization for Chronic Obstructive Pulmonary Disease (COPD). We identified patients aged ≥40 years with unplanned hospitalization due to COPD in the Diagnosis Procedure Combination database, an administrative claims database in Japan, from 2011 through 2016 (index hospitalizations). COPD was defined by ICD-10-CM diagnostic codes, according to Centers for Medicare and Medicaid Services (CMS) readmission measures. The primary outcome was any readmission within 30 days after index hospitalization. In the training set (randomly-selected 70% of sample), patient characteristics and inpatient care data were used as predictors to derive a conventional logistic regression model and two machine learning models (lasso regression and deep neural network). In the test set (remaining 30% of sample), the prediction performances of the machine learning models were examined by comparison with the reference model based on CMS readmission measures. Among 44,929 index hospitalizations for COPD, 3413 (7%) were readmitted within 30 days after discharge. The reference model had the lowest discrimination ability (C-statistic: 0.57 [95% confidence interval (CI) 0.56-0.59]). The two machine learning models had moderate, significantly higher discrimination ability (C-statistic: lasso regression, 0.61 [95% CI 0.59-0.61], p = 0.004; deep neural network, 0.61 [95% CI 0.59-0.63], p = 0.007). Tube feeding duration, blood transfusion, thoracentesis use, and male sex were important predictors. In this study using nationwide administrative data in Japan, machine learning models improved the prediction of 30-day readmission after COPD hospitalization compared with a conventional model.

Using artificial neural networks to identify patients with concussion and postconcussion syndrome based on antisaccades

OBJECTIVE

Artificial neural networks (ANNs) have shown considerable promise as decision support tools in medicine, including neurosurgery. However, their use in concussion and postconcussion syndrome (PCS) has been limited. The authors explore the value of using an ANN to identify patients with concussion/PCS based on their antisaccade performance.

METHODS

Study participants were prospectively recruited from the emergency department and head injury clinic of a large teaching hospital in Toronto. Acquaintances of study participants were used as controls. Saccades were measured using an automated, portable, head-mounted device preprogrammed with an antisaccade task. Each participant underwent 100 trials of the task and 11 saccade parameters were recorded for each trial. ANN analysis was performed using the MATLAB Neural Network Toolbox, and individual saccade parameters were further explored with receiver operating characteristic (ROC) curves and a logistic regression analysis.

RESULTS

Control (n = 15), concussion (n = 32), and PCS (n = 25) groups were matched by age and level of education. The authors examined 11 saccade parameters and found that the prosaccade error rate (p = 0.04) and median antisaccade latency (p = 0.02) were significantly different between control and concussion/PCS groups. When used to distinguish concussion and PCS participants from controls, the neural networks achieved accuracies of 67% and 72%, respectively. This method was unable to distinguish study patients with concussion from those with PCS, suggesting persistence of eye movement abnormalities in patients with PCS. The authors' observations also suggest the potential for improved results with a larger training sample.

CONCLUSIONS

This study explored the utility of ANNs in the diagnosis of concussion/PCS based on antisaccades. With the use of an ANN, modest accuracy was achieved in a small cohort. In addition, the authors explored the pearls and pitfalls of this novel approach and identified important future directions for this research.

Using machine-learning methods to support health-care professionals in making admission decisions

BACKGROUND

Large tertiary hospitals usually face long waiting lines; patients who want to receive hospitalization need to be screened in advance. The patient admission screening process involves a health-care professional ranking patients by analyzing registration information.

OBJECTIVE

The purpose of this study was to develop a machine-learning approach to screening, using historical data and the experience of health-care professionals to develop a set of screening rules to help health-care professionals prioritize patient needs automatically.

METHODS

We used five machine-learning methods to sequence and predict elective patients: logistic regression (LR), random forest (RF), gradient-boosting decision tree (GBDT), extreme gradient boosting (XGBoost), and an ensemble model of the four models.

RESULTS

The results indicate that all of the five models showed a good prioritization performance with high predictive values. In particular, XGBoost had the best predictive performance compared with others in terms of the area under the receiver operating characteristic curve (AUC), with the AUC values of LR, RF, GBDT, XGBoost, and the ensemble model being 0.881, 0.816, 0.820, 0.901, and 0.897, respectively.

CONCLUSION

The results reported here indicate that machine-learning techniques can be valuable for automating the screening process. Our model can assist health-care professionals in automatically evaluating less complex cases by identifying important factors affecting patient admission.

Current trends in biomarker discovery and analysis tools for traumatic brain injury

Traumatic brain injury (TBI) affects 1.7 million people in the United States each year, causing lifelong functional deficits in cognition and behavior. The complex pathophysiology of neural injury is a primary barrier to developing sensitive and specific diagnostic tools, which consequentially has a detrimental effect on treatment regimens. Biomarkers of other diseases (e.g. cancer) have provided critical insight into disease emergence and progression that lend to developing powerful clinical tools for intervention. Therefore, the biomarker discovery field has recently focused on TBI and made substantial advancements to characterize markers with promise of transforming TBI patient diagnostics and care. This review focuses on these key advances in neural injury biomarkers discovery, including novel approaches spanning from omics-based approaches to imaging and machine learning as well as the evolution of established techniques.

Using an artificial neural network to predict traumatic brain injury

In BriefPediatric traumatic brain injury (TBI) is common, but not all injuries require hospitalization. A computational tool for ruling-in patients who will have clinically relevant TBI (CRTBI) would be valuable, providing an evidence-based mechanism for safe discharge. Here, using data from 12,902 patients from the Pediatric Emergency Care Applied Research Network (PECARN) TBI data set, the authors utilize artificial intelligence to predict CRTBI using radiologist-interpreted CT information with > 99% sensitivity and an AUC of 0.99.

Machine Learning-Based Prediction of Clinical Outcomes for Children During Emergency Department Triage

IMPORTANCE

While machine learning approaches may enhance prediction ability, little is known about their utility in emergency department (ED) triage.

OBJECTIVES

To examine the performance of machine learning approaches to predict clinical outcomes and disposition in children in the ED and to compare their performance with conventional triage approaches.

DESIGN, SETTING, AND PARTICIPANTS

Prognostic study of ED data from the National Hospital Ambulatory Medical Care Survey from January 1, 2007, through December 31, 2015. A nationally representative sample of 52 037 children aged 18 years or younger who presented to the ED were included. Data analysis was performed in August 2018.

MAIN OUTCOMES AND MEASURES

The outcomes were critical care (admission to an intensive care unit and/or in-hospital death) and hospitalization (direct hospital admission or transfer). In the training set (70% random sample), using routinely available triage data as predictors (eg, demographic characteristics and vital signs), we derived 4 machine learning-based models: lasso regression, random forest, gradient-boosted decision tree, and deep neural network. In the test set (the remaining 30% of the sample), we measured the models' prediction performance by computing C statistics, prospective prediction results, and decision curves. These machine learning models were built for each outcome and compared with the reference model using the conventional triage classification information.

RESULTS

Of 52 037 eligible ED visits by children (median [interquartile range] age, 6 [2-14] years; 24 929 [48.0%] female), 163 (0.3%) had the critical care outcome and 2352 (4.5%) had the hospitalization outcome. For the critical care prediction, all machine learning approaches had higher discriminative ability compared with the reference model, although the difference was not statistically significant (eg, C statistics of 0.85 [95% CI, 0.78-0.92] for the deep neural network vs 0.78 [95% CI, 0.71-0.85] for the reference; P = .16), and lower number of undertriaged critically ill children in the conventional triage levels 3 to 5 (urgent to nonurgent). For the hospitalization prediction, all machine learning approaches had significantly higher discrimination ability (eg, C statistic, 0.80 [95% CI, 0.78-0.81] for the deep neural network vs 0.73 [95% CI, 0.71-0.75] for the reference; P < .001) and fewer overtriaged children who did not require inpatient management in the conventional triage levels 1 to 3 (immediate to urgent). The decision curve analysis demonstrated a greater net benefit of machine learning models over ranges of clinical thresholds.

CONCLUSIONS AND RELEVANCE

Machine learning-based triage had better discrimination ability to predict clinical outcomes and disposition, with reduction in undertriaging critically ill children and overtriaging children who are less ill.

Machine Learning for Predicting Outcomes in Trauma

To date, there are no reviews on machine learning (ML) for predicting outcomes in trauma. Consequently, it remains unclear as to how ML-based prediction models compare in the triage and assessment of trauma patients. The objective of this review was to survey and identify studies involving ML for predicting outcomes in trauma, with the hypothesis that models predicting similar outcomes may share common features but the performance of ML in these studies will differ greatly. MEDLINE and other databases were searched for studies involving trauma and ML. Sixty-five observational studies involving ML for the prediction of trauma outcomes met inclusion criteria. In total 2,433,180 patients were included in the studies. The studies focused on prediction of the following outcome measures: survival/mortality (n = 34), morbidity/shock/hemorrhage (n = 12), hospital length of stay (n = 7), hospital admission/triage (n = 6), traumatic brain injury (n = 4), life-saving interventions (n = 5), post-traumatic stress disorder (n = 4), and transfusion (n = 1). Six studies were prospective observational studies. Of the 65 studies, 33 used artificial neural networks for prediction. Importantly, most studies demonstrated the benefits of ML models. However, algorithm performance was assessed differently by different authors. Sensitivity-specificity gap values varied greatly from 0.035 to 0.927. Notably, studies shared many features for model development. A common ML feature base may be determined for predicting outcomes in trauma. However, the impact of ML will require further validation in prospective observational studies and randomized clinical trials, establishment of common performance criteria, and high-quality evidence about clinical and economic impacts before ML can be widely accepted in practice.

Paediatric traumatic brain injury: prognostic insights and outlooks

PURPOSE OF REVIEW

Traumatic brain injury (TBI) is a leading cause of death and disability in children. Prognostication of outcome following TBI is challenging in this population and likely requires complex, multimodal models to achieve clinically relevant accuracy. This review highlights injury characteristics, physiological indicators, biomarkers and neuromonitoring modalities predictive of outcome that may be integrated for future development of sensitive and specific prognostic models.

RECENT FINDINGS

Paediatric TBI is responsible for physical, psychosocial and neurocognitive deficits that may significantly impact quality of life. Outcome prognostication can be difficult in the immature brain, but is aided by the identification of novel biomarkers (neuronal, astroglial, myelin, inflammatory, apoptotic and autophagic) and neuromonitoring techniques (electroencephalogram and MRI). Investigation in the future may focus on assessing the prognostic ability of combinations of biochemical, protein, neuroimaging and functional biomarkers and the use of mathematical models to develop multivariable predication tools to improve the prognostic ability following childhood TBI.

SUMMARY

Prognostication of outcome following paediatric TBI is multidimensional, influenced by injury severity, age, physiological factors, biomarkers, electroencephalogram and neuroimaging. Further development, integration and validation of combinatorial prognostic algorithms are necessary to improve the accuracy and timeliness of prognosis in a meaningful fashion.

Epidemiology of Mild Traumatic Brain Injury with Intracranial Hemorrhage: Focusing Predictive Models for Neurosurgical Intervention

OBJECTIVE

To outline differences in neurosurgical intervention (NI) rates between intracranial hemorrhage (ICH) types in mild traumatic brain injuries and help identify which ICH types are most likely to benefit from creation of predictive models for NI.

METHODS

A multicenter retrospective study of adult patients spanning 3 years at 4 U.S. trauma centers was performed. Patients were included if they presented with mild traumatic brain injury (Glasgow Coma Scale score 13-15) with head CT scan positive for ICH. Patients were excluded for skull fractures, "unspecified hemorrhage," or coagulopathy. Primary outcome was NI. Stepwise multivariable logistic regression models were built to analyze the independent association between ICH variables and outcome measures.

RESULTS

The study comprised 1876 patients. NI rate was 6.7%. There was a significant difference in rate of NI by ICH type. Subdural hematomas had the highest rate of NI (15.5%) and accounted for 78% of all NIs. Isolated subarachnoid hemorrhages had the lowest, nonzero, NI rate (0.19%). Logistic regression models identified ICH type as the most influential independent variable when examining NI. A model predicting NI for isolated subarachnoid hemorrhages would require 26,928 patients, but a model predicting NI for isolated subdural hematomas would require only 328 patients.

CONCLUSIONS

This study highlighted disparate NI rates among ICH types in patients with mild traumatic brain injury and identified mild, isolated subdural hematomas as most appropriate for construction of predictive NI models. Increased health care efficiency will be driven by accurate understanding of risk, which can come only from accurate predictive models.

Accurate and dynamic predictive model for better prediction in medicine and healthcare

INTRODUCTION

Information and communication technologies (ICTs) have changed the trend into new integrated operations and methods in all fields of life. The health sector has also adopted new technologies to improve the systems and provide better services to customers. Predictive models in health care are also influenced from new technologies to predict the different disease outcomes. However, still, existing predictive models have suffered from some limitations in terms of predictive outcomes performance.

AIMS AND OBJECTIVES

In order to improve predictive model performance, this paper proposed a predictive model by classifying the disease predictions into different categories. To achieve this model performance, this paper uses traumatic brain injury (TBI) datasets. TBI is one of the serious diseases worldwide and needs more attention due to its seriousness and serious impacts on human life.

CONCLUSION

The proposed predictive model improves the predictive performance of TBI. The TBI data set is developed and approved by neurologists to set its features. The experiment results show that the proposed model has achieved significant results including accuracy, sensitivity, and specificity.

Machine learning methods to predict child posttraumatic stress: a proof of concept study

BACKGROUND

The care of traumatized children would benefit significantly from accurate predictive models for Posttraumatic Stress Disorder (PTSD), using information available around the time of trauma. Machine Learning (ML) computational methods have yielded strong results in recent applications across many diseases and data types, yet they have not been previously applied to childhood PTSD. Since these methods have not been applied to this complex and debilitating disorder, there is a great deal that remains to be learned about their application. The first step is to prove the concept: Can ML methods - as applied in other fields - produce predictive classification models for childhood PTSD? Additionally, we seek to determine if specific variables can be identified - from the aforementioned predictive classification models - with putative causal relations to PTSD.

METHODS

ML predictive classification methods - with causal discovery feature selection - were applied to a data set of 163 children hospitalized with an injury and PTSD was determined three months after hospital discharge. At the time of hospitalization, 105 risk factor variables were collected spanning a range of biopsychosocial domains.

RESULTS

Seven percent of subjects had a high level of PTSD symptoms. A predictive classification model was discovered with significant predictive accuracy. A predictive model constructed based on subsets of potentially causally relevant features achieves similar predictivity compared to the best predictive model constructed with all variables. Causal Discovery feature selection methods identified 58 variables of which 10 were identified as most stable.

CONCLUSIONS

In this first proof-of-concept application of ML methods to predict childhood Posttraumatic Stress we were able to determine both predictive classification models for childhood PTSD and identify several causal variables. This set of techniques has great potential for enhancing the methodological toolkit in the field and future studies should seek to replicate, refine, and extend the results produced in this study.

Computerized Decision Support System for Traumatic Brain Injury Management

Mortality and morbidity related to traumatic brain injury (TBI) present a major health care burden. Patients with severe TBI must be managed rapidly and efficiently to minimize secondary brain injury potentially leading to permanent sequelae. This is especially important in young patients, whose brain is still in development, making them particularly susceptible to secondary insults. The complexity of both brain injury pathophysiology and the intensive care unit environment makes the management of these patients challenging, with a risk of delayed response and/or patient instability contributing to worsened outcome. Computerized assistance in TBI appears likely to improve patient management, by helping clinicians quickly analyze and respond to ongoing clinical changes and optimizing patient status by guiding management. Currently, computerized decision support systems (CDSSs) do not feature continuous medical assistance with individualized treatment plans. This review presents new developments in CDSSs specialized in TBI. We also present the framework for future CDSSs needed to improve TBI management in real time, taking into account individual patient characteristics.

A prospective surveillance of paediatric head injuries in Singapore: a dual-centre study

OBJECTIVE

To study the causes of head injuries among the paediatric population in Singapore, and the association between causes and mortality, as well as the need for airway or neurosurgical intervention.

DESIGN

This is a prospective observational study utilising data from the trauma surveillance system from January 2011 to March 2015.

SETTING

Paediatric emergency departments (EDs) of KK Women's and Children's Hospital and the National University Health System.

PARTICIPANTS

We included children aged <16 years presenting to the paediatric EDs with head injuries who required a CT scan, admission for monitoring of persistent symptoms, or who died from the head injury. We excluded children who presented with minor mechanisms and those whose symptoms had spontaneously resolved.

PRIMARY AND SECONDARY OUTCOME MEASURES

Primary composite outcome was defined as death or the need for intubation or neurosurgical intervention. Secondary outcomes included length of hospital stay and type of neurosurgical intervention.

RESULTS

We analysed 1049 children who met the inclusion criteria. The mean age was 6.7 (SD 5.2) years. 260 (24.8%) had a positive finding on CT. 17 (1.6%) children died, 52 (5.0%) required emergency intubation in the ED and 58 (5.5%) underwent neurosurgery. The main causes associated with severe outcomes were motor vehicle crashes (OR 7.2, 95% CI 4.3 to 12.0) and non-accidental trauma (OR 5.8, 95% CI 1.8 to 18.6). This remained statistically significant when we stratified to children aged <2 years and performed a multivariable analysis adjusting for age and location of injury. For motor vehicle crashes, less than half of the children were using restraints.

CONCLUSIONS

Motor vehicle crashes and non-accidental trauma causes are particularly associated with poor outcomes among children with paediatric head injury. Continued vigilance and compliance with injury prevention initiatives and legislature are vital.