Development and Evaluation of Machine Learning Models for Recovery Prediction after Treatment for Traumatic Brain Injury

Translational Outcomes Project in Neurotrauma (TOP-NT) Pre-Clinical Consortium Study: A Synopsis

Traumatic brain injury (TBI) has long been a leading cause of death and disability, yet research has failed to successfully translate findings from the pre-clinical, animal setting into the clinic. One factor that contributes significantly to this struggle is the heterogeneity observed in the clinical setting where patients present with injuries of varying types, severities, and comorbidities. Modeling this highly varied population in the laboratory remains challenging. Given feasibility constraints, individual laboratories often focus on single injury types and are limited to an abridged set of outcome measures. Furthermore, laboratories tend to use different injury or outcome methodologies from one another, making it difficult to compare studies and identify which pre-clinical findings may be best suited for clinical translation. The NINDS-funded Translational Outcomes Project in Neurotrauma (TOP-NT) is a multi-site consortium designed to address the reproducibility, rigor, and transparency of pre-clinical development and validation of clinically relevant biomarkers for TBI. The current overview article provides a detailed description of the infrastructure and strategic approach undertaken by the consortium. We outline the TOP-NT strategy to address three goals: (1) selection and cross-center validation of biomarker tools, (2) development and population of a data infrastructure to allow for the sharing and reuse of pre-clinical, animal research following findable, accessible, interoperable, and reusable data guidelines, and (3) demonstration of feasibility, reproducibility, and transparency in conducting a multi-center, pre-clinical research trial for TBI biomarker development. The synthesized scientific analysis and results of the TOP-NT efforts will be the topic of future articles.

Increasing Rigor of Preclinical Research to Maximize Opportunities for Translation

The use of animal models in pre-clinical research has significantly broadened our understanding of the pathologies that underlie traumatic brain injury (TBI)-induced damage and deficits. However, despite numerous pre-clinical studies reporting the identification of promising neurotherapeutics, translation of these therapies to clinical application has so far eluded the TBI research field. A concerted effort to address this lack of translatability is long overdue. Given the inherent heterogeneity of TBI and the replication crisis that continues to plague biomedical research, this is a complex task that will require a multifaceted approach centered around rigor and reproducibility. Here, we discuss the role of three primary focus areas for better aligning pre-clinical research with clinical TBI management. These focus areas are (1) reporting and standardization of protocols, (2) replication of prior knowledge including the confirmation of expected pharmacodynamics, and (3) the broad application of open science through inter-center collaboration and data sharing. We further discuss current efforts that are establishing the core framework needed for successfully addressing the translatability crisis of TBI.

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.

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

Objective

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

Methods

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

Results

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

Conclusion

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

Henry gas solubility optimization double machine learning classifier for neurosurgical patients

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

New Insight of Circular RNAs' Roles in Central Nervous System Post-Traumatic Injury

The central nervous system (CNS) post-traumatic injury can cause severe nerve damage with devastating consequences. However, its pathophysiological mechanisms remain vague. There is still an urgent need for more effective treatments. Circular RNAs (circRNAs) are non-coding RNAs that can form covalently closed RNA circles. Through second-generation sequencing technology, microarray analysis, bioinformatics, and other technologies, recent studies have shown that a number of circRNAs are differentially expressed after traumatic brain injury (TBI) or spinal cord injury (SCI). These circRNAs play important roles in the proliferation, inflammation, and apoptosis in CNS post-traumatic injury. In this review, we summarize the expression and functions of circRNAs in CNS in recent studies, as well as the circRNA–miRNA–mRNA interaction networks. The potential clinical value of circRNAs as a therapeutic target is also discussed.