Application of machine learning to predict the outcome of pediatric traumatic brain injury

Binary classification model of machine learning detected altered gut integrity in controlled-cortical impact model of traumatic brain injury

Aim of the study: To examine the effect of controlled-cortical impact (CCI), a preclinical model of traumatic brain injury (TBI), on intestinal integrity using a binary classification model of machine learning (ML).Materials and methods: Adult, male C57BL/6 mice were subjected to CCI surgery using a stereotaxic impactor (Impact One™). The rotarod and hot-plate tests were performed to assess the neurological deficits.Results: Mice underwent CCI displayed a remarkable neurological deficit as noticed by decreased latency to fall and lesser paw withdrawal latency in rotarod and hot plate test, respectively. Animals were sacrificed 3 days post-injury (dpi). The colon sections were stained with hematoxylin and eosin (H&E) to integrate with machinery tool-based algorithms. Several stained colon images were captured to build a dataset for ML model to predict the impact of CCI vs sham procedure. The best results were obtained with VGG16 features with SVM RBF kernel and VGG16 features with stacked fully connected layers on top. We achieved a test accuracy of 84% and predicted the disrupted gut permeability and epithelium wall of colon in CCI group as compared to sham-operated mice.Conclusion: We suggest that ML may become an important tool in the development of preclinical TBI model and discovery of newer therapeutics.

Artificial Intelligence in Pediatric Emergency Medicine: Applications, Challenges, and Future Perspectives

The dawn of Artificial intelligence (AI) in healthcare stands as a milestone in medical innovation. Different medical fields are heavily involved, and pediatric emergency medicine is no exception. We conducted a narrative review structured in two parts. The first part explores the theoretical principles of AI, providing all the necessary background to feel confident with these new state-of-the-art tools. The second part presents an informative analysis of AI models in pediatric emergencies. We examined PubMed and Cochrane Library from inception up to April 2024. Key applications include triage optimization, predictive models for traumatic brain injury assessment, and computerized sepsis prediction systems. In each of these domains, AI models outperformed standard methods. The main barriers to a widespread adoption include technological challenges, but also ethical issues, age-related differences in data interpretation, and the paucity of comprehensive datasets in the pediatric context. Future feasible research directions should address the validation of models through prospective datasets with more numerous sample sizes of patients. Furthermore, our analysis shows that it is essential to tailor AI algorithms to specific medical needs. This requires a close partnership between clinicians and developers. Building a shared knowledge platform is therefore a key step.

Unveiling the Influence of AI Predictive Analytics on Patient Outcomes: A Comprehensive Narrative Review

This comprehensive literature review explores the transformative impact of artificial intelligence (AI) predictive analytics on healthcare, particularly in improving patient outcomes regarding disease progression, treatment response, and recovery rates. AI, encompassing capabilities such as learning, problem-solving, and decision-making, is leveraged to predict disease progression, optimize treatment plans, and enhance recovery rates through the analysis of vast datasets, including electronic health records (EHRs), imaging, and genetic data. The utilization of machine learning (ML) and deep learning (DL) techniques in predictive analytics enables personalized medicine by facilitating the early detection of conditions, precision in drug discovery, and the tailoring of treatment to individual patient profiles. Ethical considerations, including data privacy, bias, and accountability, emerge as vital in the responsible implementation of AI in healthcare. The findings underscore the potential of AI predictive analytics in revolutionizing clinical decision-making and healthcare delivery, emphasizing the necessity of ethical guidelines and continuous model validation to ensure its safe and effective use in augmenting human judgment in medical practice.

Machine learning-based classification of pineal germinoma from magnetic resonance imaging

Introduction

Surgical approaches for tissue diagnosis of pineal tumors have been associated with morbidity and mortality. The classification of images by machine learning (ML) may assist physicians in determining the extent of resection and treatment plans for a specific patient. Therefore, the present study aimed to evaluate the diagnostic performances of the ML-based models for distinguishing between pure and non-germinoma of the pineal area. In addition, the secondary objective was to compare diagnostic performances among feature extraction methods.

Methods

This is a retrospective cohort study of patients diagnosed with pineal tumors. We used the RGB feature extraction, histogram of oriented gradients (HOG), and local binary pattern methods from magnetic resonance imaging (MRI) scans; therefore, we trained an ML model from various algorithms to classify pineal germinoma. Diagnostic performances were calculated from a test dataset with several diagnostic indices.

Results

MRI scans from 38 patients with pineal tumors were collected and extracted features. As a result, the k-nearest neighbors (KNN) algorithm with HOG had the highest sensitivity of 0.81 (95% CI 0.78-0.84), while the random forest (RF) algorithm with HOG had the highest sensitivity of 0.82 (95% CI 0.79-0.85). Moreover, the KNN model with HOG had the highest AUC, at 0.845. Additionally, the AUCs of the artificial neural network and RF algorithms with HOG were 0.770 and 0.713, respectively.

Conclusions

The classification of images using ML is a viable way for developing a diagnostic tool to differentiate between germinoma and non-germinoma that will aid neurosurgeons in treatment planning in the future.

Predicting return to work after traumatic brain injury using machine learning and administrative data

BACKGROUND

Accurate patient-specific predictions on return-to-work after traumatic brain injury (TBI) can support both clinical practice and policymaking. The use of machine learning on large administrative data provides interesting opportunities to create such prognostic models.

AIM

The current study assesses whether return-to-work one year after TBI can be predicted accurately from administrative data. Additionally, this study explores how model performance and feature importance change depending on whether a distinction is made between mild and moderate-to-severe TBI.

METHODS

This study used a population-based dataset that combined discharge, claims and social security data of patients hospitalized with a TBI in Belgium during the year 2016. The prediction of TBI was attempted with three algorithms, elastic net logistic regression, random forest and gradient boosting and compared in their performance by their accuracy, sensitivity, specificity and area under the receiver operator curve (ROC AUC).

RESULTS

The distinct modelling algorithms resulted in similar results, with 83% accuracy (ROC AUC 85%) for a binary classification of employed vs. not employed and up to 76% (ROC AUC 82%) for a multiclass operationalization of employment outcome. Modelling mild and moderate-to-severe TBI separately did not result in considerable differences in model performance and feature importance. The features of main importance for return-to-work prediction were related to pre-injury employment.

DISCUSSION

While clearly offering some information beneficial for predicting return-to-work, administrative data needs to be supplemented with additional information to allow further improvement of patient-specific prognose.

A sensor-enabled cloud-based computing platform for computational brain biomechanics

BACKGROUND AND OBJECTIVES

Driven by the risk of repetitive head trauma, sensors have been integrated into mouthguards to measure head impacts in contact sports and military activities. These wearable devices, referred to as "instrumented" or "smart" mouthguards are being actively developed by various research groups and organizations. These instrumented mouthguards provide an opportunity to further study and understand the brain biomechanics due to impact. In this study, we present a brain modeling service that can use information from these sensors to predict brain injury metrics in an automated fashion.

METHODS

We have built a brain modeling platform using several of Amazon's Web Services (AWS) to enable cloud computing and scalability. We use a custom-built cloud-based finite element modeling code to compute the physics-based nonlinear response of the intracranial brain tissue and provide a frontend web application and an application programming interface for groups working on head impact sensor technology to include simulated injury predictions into their research pipeline.

RESULTS

The platform results have been validated against experimental data available in literature for brain-skull relative displacements, brain strains and intracranial pressure. The parallel processing capability of the platform has also been tested and verified. We also studied the accuracy of the custom head surfaces generated by Avatar 3D.

CONCLUSION

We present a validated cloud-based computational brain modeling platform that uses sensor data as input for numerical brain models and outputs a quantitative description of brain tissue strains and injury metrics. The platform is expected to generate transparent, reproducible, and traceable brain computing results.

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.

The use of machine learning and artificial intelligence within pediatric critical care

The field of pediatric critical care has been hampered in the era of precision medicine by our inability to accurately define and subclassify disease phenotypes. This has been caused by heterogeneity across age groups that further challenges the ability to perform randomized controlled trials in pediatrics. One approach to overcome these inherent challenges include the use of machine learning algorithms that can assist in generating more meaningful interpretations from clinical data. This review summarizes machine learning and artificial intelligence techniques that are currently in use for clinical data modeling with relevance to pediatric critical care. Focus has been placed on the differences between techniques and the role of each in the clinical arena. The various forms of clinical decision support that utilize machine learning are also described. We review the applications and limitations of machine learning techniques to empower clinicians to make informed decisions at the bedside. IMPACT: Critical care units generate large amounts of under-utilized data that can be processed through artificial intelligence. This review summarizes the machine learning and artificial intelligence techniques currently being used to process clinical data. The review highlights the applications and limitations of these techniques within a clinical context to aid providers in making more informed decisions at the bedside.

A hierarchical machine learning model based on Glioblastoma patients' clinical, biomedical, and image data to analyze their treatment plans

AIM OF STUDY

Glioblastoma Multiforme (GBM) is an aggressive brain cancer in adults that kills most patients in the first year due to ineffective treatment. Different clinical, biomedical, and image data features are needed to analyze GBM, increasing complexities. Besides, they lead to weak performances for machine learning models due to ignoring physicians' knowledge. Therefore, this paper proposes a hierarchical model based on Fuzzy C-mean (FCM) clustering, Wrapper feature selection, and twelve classifiers to analyze treatment plans.

METHODOLOGY/APPROACH

The proposed method finds the effectiveness of previous and current treatment plans, hierarchically determining the best decision for future treatment plans for GBM patients using clinical data, biomedical data, and different image data. A case study is presented based on the Cancer Genome Atlas Glioblastoma Multiforme dataset to prove the effectiveness of the proposed model. This dataset is analyzed using data preprocessing, experts' knowledge, and a feature reduction method based on the Principal Component Analysis. Then, the FCM clustering method is utilized to reinforce classifier learning.

OUTCOMES OF STUDY

The proposed model finds the best combination of Wrapper feature selection and classifier for each cluster based on different measures, including accuracy, sensitivity, specificity, precision, F-score, and G-mean according to a hierarchical structure. It has the best performance among other reinforced classifiers. Besides, this model is compatible with real-world medical processes for GBM patients based on clinical, biomedical, and image data.

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.

Comparing Prediction of Early TBI Mortality with Multilayer Perceptron Neural Network and Convolutional Neural Network

In this work, we compare the performance of a multilayer perceptron neural network and convolutional networks for the prediction of 14-day mortality in patients with TBI, using a database obtained in a low-and middle-income country, with 529 records and 16 predictor variables. The missing values of several variables were filled in with techniques such as decision tree, random forest, k-nearest-neighbor and linear regression. In the simulation of neural networks, several optimization methods were used, such as RMSProp, Adam, Adamax and SGDM. The best results obtained for the prediction rate were an accuracy of 0.845 and an area under the ROC curve of 0.911. Clinical Relevance- This proposes the prediction of early mortality in patients with TBI with an area under ROC curve of 0.911.

Economic impact of a machine learning-based strategy for preparation of blood products in brain tumor surgery

Background

Globally, blood donation has been disturbed due to the pandemic. Consequently, the optimization of preoperative blood preparation should be a point of concern. Machine learning (ML) is one of the modern approaches that have been applied by physicians to help decision-making. The main objective of this study was to identify the cost differences of the ML-based strategy compared with other strategies in preoperative blood products preparation. A secondary objective was to compare the effectiveness indexes of blood products preparation among strategies.

Methods

The study utilized a retrospective cohort design conducted on brain tumor patients who had undergone surgery between January 2014 and December 2021. Overall data were divided into two cohorts. The first cohort was used for the development and deployment of the ML-based web application, while validation, comparison of the effectiveness indexes, and economic evaluation were performed using the second cohort. Therefore, the effectiveness indexes of blood preparation and cost difference were compared among the ML-based strategy, clinical trial-based strategy, and routine-based strategy.

Results

Over a 2-year period, the crossmatch to transfusion (C/T) ratio, transfusion probability (Tp), and transfusion index (Ti) of the ML-based strategy were 1.10, 57.0%, and 1.62, respectively, while the routine-based strategy had a C/T ratio of 4.67%, Tp of 27.9%%, and Ti of 0.79. The overall costs of blood products preparation among the ML-based strategy, clinical trial-based strategy, and routine-based strategy were 30, 061.56$, 57,313.92$, and 136,292.94$, respectively. From the cost difference between the ML-based strategy and routine-based strategy, we observed cost savings of 92,519.97$ (67.88%) for the 2-year period.

Conclusion

The ML-based strategy is one of the most effective strategies to balance the unnecessary workloads at blood banks and reduce the cost of unnecessary blood products preparation from low C/T ratio as well as high Tp and Ti. Further studies should be performed to confirm the generalizability and applicability of the ML-based strategy.

Towards PErsonalised PRognosis for children with traumatic brain injury: the PEPR study protocol

INTRODUCTION

Traumatic brain injury (TBI) in children can be associated with poor outcome in crucial functional domains, including motor, neurocognitive and behavioural functioning. However, outcome varies between patients and is mediated by complex interplay between demographic factors, premorbid functioning and (sub)acute clinical characteristics. At present, methods to understand let alone predict outcome on the basis of these variables are lacking, which contributes to unnecessary follow-up as well as undetected impairments in children. Therefore, this study aims to develop prognostic models for the individual outcome of children with TBI in a range of important developmental domains. In addition, the potential added value of advanced neuroimaging data and the use of machine learning algorithms in the development of prognostic models will be assessed.

METHODS AND ANALYSIS

210 children aged 4-18 years diagnosed with mild-to-severe TBI will be prospectively recruited from a research network of Dutch hospitals. They will be matched 2:1 to a control group of neurologically healthy children (n=105). Predictors in the model will include demographic, premorbid and clinical measures prospectively registered from the TBI hospital admission onwards as well as MRI metrics assessed at 1 month post-injury. Outcome measures of the prognostic models are (1) motor functioning, (2) intelligence, (3) behavioural functioning and (4) school performance, all assessed at 6 months post-injury.

ETHICS AND DISSEMINATION

Ethics has been obtained from the Medical Ethical Board of the Amsterdam UMC (location AMC). Findings of our multicentre prospective study will enable clinicians to identify TBI children at risk and aim towards a personalised prognosis. Lastly, findings will be submitted for publication in open access, international and peer-reviewed journals.

TRIAL REGISTRATION NUMBER

NL71283.018.19 and NL9051.

Integrated Features for Optimizing Machine Learning Classifiers of Pediatric and Young Adults With a Post-Traumatic Headache From Healthy Controls

Post-traumatic headache (PTH) is a challenging clinical condition to identify and treat as it integrates multiple subjectively defined symptoms with underlying physiological processes. The precise mechanisms underlying PTH are unclear, and it remains to be understood how to integrate the patient experience with underlying biology when attempting to classify persons with PTH, particularly in the pediatric setting where patient self-report may be highly variable. The objective of this investigation was to evaluate the use of different machine learning (ML) classifiers to differentiate pediatric and young adult subjects with PTH from healthy controls using behavioral data from self-report questionnaires that reflect concussion symptoms, mental health, pain experience of the participants, and structural brain imaging from cortical and sub-cortical locations. Behavioral data, alongside brain imaging, survived data reduction methods and both contributed toward final models. Behavioral data that contributed towards the final model included both the child and parent perspective of the pain-experience. Brain imaging features produced two unique clusters that reflect regions that were previously found in mild traumatic brain injury (mTBI) and PTH. Affinity-based propagation analysis demonstrated that behavioral data remained independent relative to neuroimaging data that suggest there is a role for both behavioral and brain imaging data when attempting to classify children with PTH.

Predicting Outcome of Traumatic Brain Injury: Is Machine Learning the Best Way?

One of the main challenges in traumatic brain injury (TBI) patients is to achieve an early and definite prognosis. Despite the recent development of algorithms based on artificial intelligence for the identification of these prognostic factors relevant for clinical practice, the literature lacks a rigorous comparison among classical regression and machine learning (ML) models. This study aims at providing this comparison on a sample of TBI patients evaluated at baseline (T0), after 3 months from the event (T1), and at discharge (T2). A Classical Linear Regression Model (LM) was compared with independent performances of Support Vector Machine (SVM), k-Nearest Neighbors (k-NN), Naïve Bayes (NB) and Decision Tree (DT) algorithms, together with an ensemble ML approach. The accuracy was similar among LM and ML algorithms on the analyzed sample when two classes of outcome (Positive vs. Negative) approach was used, whereas the NB algorithm showed the worst performance. This study highlights the utility of comparing traditional regression modeling to ML, particularly when using a small number of reliable predictor variables after TBI. The dataset of clinical data used to train ML algorithms will be publicly available to other researchers for future comparisons.

Intracranial Densitometry-Augmented Machine Learning Enhances the Prognostic Value of Brain CT in Pediatric Patients With Traumatic Brain Injury: A Retrospective Pilot Study

Background: The inter- and intrarater variability of conventional computed tomography (CT) classification systems for evaluating the extent of ischemic-edematous insult following traumatic brain injury (TBI) may hinder the robustness of TBI prognostic models. Objective: This study aimed to employ fully automated quantitative densitometric CT parameters and a cutting-edge machine learning algorithm to construct a robust prognostic model for pediatric TBI. Methods: Fifty-eight pediatric patients with TBI who underwent brain CT were retrospectively analyzed. Intracranial densitometric information was derived from the supratentorial region as a distribution representing the proportion of Hounsfield units. Furthermore, a machine learning-based prognostic model based on gradient boosting (i.e., CatBoost) was constructed with leave-one-out cross-validation. At discharge, the outcome was assessed dichotomously with the Glasgow Outcome Scale (favorability: 1-3 vs. 4-5). In-hospital mortality, length of stay (>1 week), and need for surgery were further evaluated as alternative TBI outcome measures. Results: Densitometric parameters indicating reduced brain density due to subtle global ischemic changes were significantly different among the TBI outcome groups, except for need for surgery. The skewed intracranial densitometry of the unfavorable outcome became more distinguishable in the follow-up CT within 48 h. The prognostic model augmented by intracranial densitometric information achieved adequate AUCs for various outcome measures [favorability = 0.83 (95% CI: 0.72-0.94), in-hospital mortality = 0.91 (95% CI: 0.82-1.00), length of stay = 0.83 (95% CI: 0.72-0.94), and need for surgery = 0.71 (95% CI: 0.56-0.86)], and this model showed enhanced performance compared to the conventional CRASH-CT model. Conclusion: Densitometric parameters indicative of global ischemic changes during the acute phase of TBI are predictive of a worse outcome in pediatric patients. The robustness and predictive capacity of conventional TBI prognostic models might be significantly enhanced by incorporating densitometric parameters and machine learning techniques.