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.

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

STUDY OBJECTIVE

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

METHODS

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

RESULTS

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

CONCLUSION

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

Artificial neural networks in neurorehabilitation: A scoping review

BACKGROUND

Advances in medical technology produce highly complex datasets in neurorehabilitation clinics and research laboratories. Artificial neural networks (ANNs) have been utilized to analyze big and complex datasets in various fields, but the use of ANNs in neurorehabilitation is limited.

OBJECTIVE

To explore the current use of ANNs in neurorehabilitation.

METHODS

PubMed, CINAHL, and Web of Science were used for the literature search. Studies in the scoping review (1) utilized ANNs, (2) examined populations with neurological conditions, and (3) focused on rehabilitation outcomes. The initial search identified 1,136 articles. A total of 19 articles were included.

RESULTS

ANNs were used for prediction of functional outcomes and mortality (n = 11) and classification of motor symptoms and cognitive status (n = 8). Most ANN-based models outperformed regression or other machine learning models (n = 11) and showed accurate performance (n = 6; no comparison with other models) in predicting clinical outcomes and accurately classifying different neurological impairments.

CONCLUSIONS

This scoping review provides encouraging evidence to use ANNs for clinical decision-making of complex datasets in neurorehabilitation. However, more research is needed to establish the clinical utility of ANNs in diagnosing, monitoring, and rehabilitation of individuals with neurological conditions.

Comparison of four variable selection methods to determine the important variables in predicting the prognosis of traumatic brain injury patients by support vector machine

Background:

Large amounts of information have called for increased computational complexity. Data dimension reduction is therefore critical to preliminary analysis. In this research, four variable selection (VS) methods are compared to obtain the important variables in predicting the prognosis of traumatic brain injury (TBI) patients.

Materials and Methods:

In a retrospective follow-up study, 741 TBI patients who were hospitalized for at least 2 days and had a Glasgow Coma Scale score of at least one were followed. Their clinical data recorded during intensive care unit (ICU) admission and eight-category extended GOS conditions 6 months after discharge were utilized here. Two filter- and two wrapper-based VS methods were applied for comparison. A support vector machine (SVM) classifier was then used, and the sensitivity, specificity, accuracy, and the area under the receiver characteristic curve (AUC) values were calculated.

Results:

Theoretically, the variables selected by sequential forward selection (SFS) method would better predict the prognosis (AUC = 0.737, 95% confidence interval [0.701, 0.772], specificity = 89.2%, sensitivity = 58.9% and accuracy = 79.1%) than the others. Genetic algorithm (GA), minimum redundancy maximum relevance (MRMR), and mutual information method were in the next orders, respectively.

Conclusion:

The use of an SVM classifier on optimal subsets given by GA and SFS reveals that wrapper-based methods perform better than filter-based methods in our data set, although all selected subsets, except for the MRMR, were clinically accepted. In addition, for prognosis prediction of TBI patients, a small subset of clinical records during ICU admission is enough to achieve an accepted accuracy.

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.

Comparison of artificial neural network and logistic regression models for prediction of outcomes in trauma patients: A systematic review and meta-analysis

BACKGROUND

Currently, two models of artificial neural network (ANN) and logistic regression (LR) are known as models that extensively used in medical sciences. The aim of this study was to compare the ANN and LR models in prediction of Health-related outcomes in traumatic patients using a systematic review.

METHODS

The study was planned and conducted based on the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) checklist. A literature search of published studies was conducted using PubMed, Embase, Web of knowledge, Scopus, and Google Scholar in May 2018. Joanna Briggs Institute (JBI) checklists was used for assessing the quality of the included articles.

RESULTS

The literature searches yielded 326 potentially relevant studies from the primary searches. Overall, the review included 10 unique studies. The results of this study showed that the area under curve (AUC) for the ANN was 0.91, (95% CI 0.89-0.83) and 0.89, (95% CI 0.87-90) for the LR in random effect model. The accuracy rate for ANN and LR in random effect models were 90.5, (95% CI, 87.6-94.2) and 83.2, (95% CI 75.1-91.2), respectively.

CONCLUSION

The results of our study showed that ANN has better performance than LR in predicting the terminal outcomes of traumatic patients in both the AUC and accuracy rate. Using an ANN to predict the final implications of trauma patients can provide more accurate clinical decisions.

Key Hospital Anxiety and Depression Scale (HADS) items associated with DSM-IV depressive and anxiety disorder 12-months post traumatic brain injury

BACKGROUND

Anxiety and depression are common problems following traumatic brain injury (TBI), warranting routine screening. Self-report rating scales including the Hospital Anxiety and Depression Scale (HADS) are associated with depression and anxiety diagnoses in individuals with TBI. The relationship between individual HADS symptoms and structured clinical interview methods (SCID) requires further investigation, particularly in regard to identifying a small number of key items that can potentially be recognised by clinicians and carers of individuals with TBI.

METHODS

138 individuals sustaining a complicated-mild to severe TBI completed the HADS, and the Structured Clinical Interview for DSM-IV, Research Version (SCID) at 12-months post-injury. The associations between individual HADS items, separately and in combination, as well as overall depression and anxiety subscale scores, and SCID-diagnosed depressive and anxiety disorders were analysed.

RESULTS

CART (Classification and Regression Tree) analysis found HADS depression item 2 "I still enjoy the things I used to enjoy" and a combination of two anxiety items, 3 "I get a sort of frightened feeling as if something awful is about to happen" and 5 "worrying thoughts go through my mind", performed similarly to total depression and anxiety subscales in terms of their association with depressive and anxiety disorders respectively, at 12-months post-injury.

LIMITATIONS

Patients were predominantly injured in motor vehicle accidents and received comprehensive care within a no-fault accident compensation system and so may not be representative of the wider TBI population.

CONCLUSIONS

Although validation is required, a small number of self-report items are highly associated with 12-month post-injury diagnoses.

The aggressiveness of neurotrauma practitioners and the influence of the IMPACT prognostic calculator

Published guidelines have helped to standardize the care of patients with traumatic brain injury; however, there remains substantial variation in the decision to pursue or withhold aggressive care. The International Mission for Prognosis and Analysis of Clinical Trials in TBI (IMPACT) prognostic calculator offers the opportunity to study and decrease variability in physician aggressiveness. The authors wish to understand how IMPACT’s prognostic calculations currently influence patient care and to better understand physician aggressiveness. The authors conducted an anonymous international, multidisciplinary survey of practitioners who provide care to patients with traumatic brain injury. Questions were designed to determine current use rates of the IMPACT prognostic calculator and thresholds of age and risk for death or poor outcome that might cause practitioners to consider withholding aggressive care. Correlations between physician aggressiveness, putative predictors of aggressiveness, and demographics were examined. One hundred fifty-four responses were received, half of which were from physicians who were familiar with the IMPACT calculator. The most frequent use of the calculator was to improve communication with patients and their families. On average, respondents indicated that in patients older than 76 years or those with a >85% chance of death or poor outcome it might be reasonable to pursue non-aggressive care. These thresholds were robust and were not influenced by provider or institutional characteristics. This study demonstrates the need to educate physicians about the IMPACT prognostic calculator. The consensus values for age and prognosis identified in our study may be explored in future studies aimed at reducing variability in physician aggressiveness and should not serve as a basis for withdrawing care.