A Machine Learning-Based Approach to Predict Prognosis and Length of Hospital Stay in Adults and Children With Traumatic Brain Injury: Retrospective Cohort Study

Random forest-based prediction of intracranial hypertension in patients with traumatic brain injury

BACKGROUND

Treatment and prevention of intracranial hypertension (IH) to minimize secondary brain injury are central to the neurocritical care management of traumatic brain injury (TBI). Predicting the onset of IH in advance allows for a more aggressive prophylactic treatment. This study aimed to develop random forest (RF) models for predicting IH events in TBI patients.

METHODS

We analyzed prospectively collected data from patients admitted to the intensive care unit with invasive intracranial pressure (ICP) monitoring. Patients with persistent ICP > 22 mmHg in the early postoperative period (first 6 h) were excluded to focus on IH events that had not yet occurred. ICP-related data from the initial 6 h were used to extract linear (ICP, cerebral perfusion pressure, pressure reactivity index, and cerebrospinal fluid compensatory reserve index) and nonlinear features (complexity of ICP and cerebral perfusion pressure). IH was defined as ICP > 22 mmHg for > 5 min, and severe IH (SIH) as ICP > 22 mmHg for > 1 h during the subsequent ICP monitoring period. RF models were then developed using baseline characteristics (age, sex, and initial Glasgow Coma Scale score) along with linear and nonlinear features. Fivefold cross-validation was performed to avoid overfitting.

RESULTS

The study included 69 patients. Forty-three patients (62.3%) experienced an IH event, of whom 30 (43%) progressed to SIH. The median time to IH events was 9.83 h, and to SIH events, it was 11.22 h. The RF model showed acceptable performance in predicting IH with an area under the curve (AUC) of 0.76 and excellent performance in predicting SIH (AUC = 0.84). Cross-validation analysis confirmed the stability of the results.

CONCLUSIONS

The presented RF model can forecast subsequent IH events, particularly severe ones, in TBI patients using ICP data from the early postoperative period. It provides researchers and clinicians with a potentially predictive pathway and framework that could help triage patients requiring more intensive neurological treatment at an early stage.

Predicting the Severity and Discharge Prognosis of Traumatic Brain Injury Based on Intracranial Pressure Data Using Machine Learning Algorithms

OBJECTIVE

This study aimed to explore the potential of employing machine learning algorithms based on intracranial pressure (ICP), ICP-derived parameters, and their complexity to predict the severity and short-term prognosis of traumatic brain injury (TBI).

METHODS

A single-center prospectively collected cohort of neurosurgical intensive care unit admissions was analyzed. We extracted ICP-related data within the first 6 hours and processed them using complex algorithms. To indicate TBI severity and short-term prognosis, Glasgow Coma Scale score on the first postoperative day and Glasgow Outcome Scale-Extended score at discharge were used as binary outcome variables. A univariate logistic regression model was developed to predict TBI severity using only mean ICP values. Subsequently, 3 multivariate Random Forest (RF) models were constructed using different combinations of mean and complexity metrics of ICP-related data. To avoid overfitting, five-fold cross-validations were performed. Finally, the best-performing multivariate RF model was used to predict patients' discharge Glasgow Outcome Scale-Extended score.

RESULTS

The logistic regression model exhibited limited predictive ability with an area under the curve (AUC) of 0.558. Among multivariate models, the RF model, combining the mean and complexity metrics of ICP-related data, achieved the most robust ability with an AUC of 0.815. Finally, in terms of predicting discharge Glasgow Outcome Scale-Extended score, this model had a consistent performance with an AUC of 0.822. Cross-validation analysis confirmed the performance.

CONCLUSIONS

This study demonstrates the clinical utility of the RF model, which integrates the mean and complexity metrics of ICP data, in accurately predicting the TBI severity and short-term prognosis.

Enhancing hospital course and outcome prediction in patients with traumatic brain injury: A machine learning study

PURPOSE

We aimed to use machine learning (ML) algorithms with clinical, lab, and imaging data as input to predict various outcomes in traumatic brain injury (TBI) patients.

METHODS

In this retrospective study, blood samples were analyzed for glial fibrillary acidic protein (GFAP) and ubiquitin C-terminal hydrolase L1 (UCH-L1). The non-contrast head CTs were reviewed by two neuroradiologists for TBI common data elements (CDE). Three outcomes were designed to predict: discharged or admitted for further management (prediction 1), deceased or not deceased (prediction 2), and admission only, prolonged stay, or neurosurgery performed (prediction 3). Five ML models were trained. SHapley Additive exPlanations (SHAP) analyses were used to assess the relative significance of variables.

RESULTS

Four hundred forty patients were used to predict predictions 1 and 2, while 271 patients were used in prediction 3. Due to Prediction 3's hospitalization requirement, deceased and discharged patients could not be utilized. The Random Forest model achieved an average accuracy of 1.00 for prediction 1 and an accuracy of 0.99 for prediction 2. The Random Forest model achieved a mean accuracy of 0.93 for prediction 3. Key features were extracranial injury, hemorrhage, UCH-L1 for prediction 1; The Glasgow Coma Scale, age, GFAP for prediction 2; and GFAP, subdural hemorrhage volume, and pneumocephalus for prediction 3, per SHAP analysis.

CONCLUSION

Combining clinical and laboratory parameters with non-contrast CT CDEs allowed our ML models to accurately predict the designed outcomes of TBI patients. GFAP and UCH-L1 were among the significant predictor variables, demonstrating the importance of these biomarkers.

Machine Learning in Neurosurgery: Toward Complex Inputs, Actionable Predictions, and Generalizable Translations

Machine learning can predict neurosurgical diagnosis and outcomes, power imaging analysis, and perform robotic navigation and tumor labeling. State-of-the-art models can reconstruct and generate images, predict surgical events from video, and assist in intraoperative decision-making. In this review, we will detail the neurosurgical applications of machine learning, ranging from simple to advanced models, and their potential to transform patient care. As machine learning techniques, outputs, and methods become increasingly complex, their performance is often more impactful yet increasingly difficult to evaluate. We aim to introduce these advancements to the neurosurgical audience while suggesting major potential roadblocks to their safe and effective translation. Unlike the previous generation of machine learning in neurosurgery, the safe translation of recent advancements will be contingent on neurosurgeons' involvement in model development and validation.

Identifying miRNA biomarkers for breast cancer and ovarian cancer: a text mining perspective

BACKGROUND

microRNA (miRNAs) are small, non-coding RNAs that mediate post-transcriptional gene silencing. Numerous studies have demonstrated the critical role of miRNAs in the development of breast cancer and ovarian cancer. To reduce potential bias from individual studies, a more comprehensive approach of exploring miRNAs in cancer research is essential. This study aims to explore the role of miRNAs in the development of breast cancer and ovarian cancer.

METHODS

Abstracts of the publications were tokenized and the biomedical terms (miRNA, gene, disease, species) were identified and extracted for vectorization. Predictive analyses were conducted with four machine learning models: K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Random Forest (RF), and Naïve Bayes. Both holdout validation and cross-validation were utilized. Feature importance will be identified for miRNA-cancer networks construction.

RESULTS

We found that miR-182 is highly specific to female cancers. miR-182 targets different genes in regulating breast cancer and ovarian cancer. Naïve Bayes provided a promising prediction model for breast cancer and ovarian cancer with miRNAs and genes combination, with an accuracy score greater than 60%. Feature importance identified miR-155 and miR-199 are critical for breast cancer and ovarian cancer prediction, with miR-155 being highly related to breast cancer, whereas miR-199 being more associated with ovarian cancer.

CONCLUSION

Our approach effectively identified potential miRNA biomarkers associated with breast cancer and ovarian cancer, providing a solid foundation for generating novel research hypotheses and guiding future experimental studies.

Estimability study on the age of toddlers' gait development based on gait parameters

In the first few years of toddlers' locomotion, various gait parameters improve gradually and dynamically with gait development. Therefore, in this study, we hypothesized that the age of gait development, or the level of gait development with age as its indicator, can be estimated from several gait parameters related to gait development, and investigated its estimability. In total, 97 healthy toddlers aged about 1-3 years participated in the study. All five selected gait parameters showed a moderate or higher correlation with age, but the duration with a large change and the strength of the association with gait development varied for each gait parameter. Multiple regression analysis was performed using age as the objective variable and five selected gait parameters as explanatory variables, and an estimation model (R² = 0.683, adjusted R² = 0.665) was created. The estimation model was verified using a test dataset separate from the training dataset (R² = 0.82, p < 0.001). It was suggested that the age of gait development could be estimated from gait alone. Gait analysis based on empirical observations may reduce the need for skilled observers and their potential variability.

Predicting length of stay ranges by using novel deep neural networks

Background and aims

Accurately predicting length of stay (LOS) is considered a challenging task for health care systems globally. In previous studies on LOS range prediction, researchers commonly pre-classified the LOS ranges, which were the same for all patients in the same classification, and then utilized a classifier for prediction. In this study, we innovatively aimed to predict the specific LOS range for each patient (the LOS range was different for each patient).

Methods

In the modified deep neural network (DNN), the overall sample error (root mean square error (RMSE) method), the estimated sample error (ERR_pred method), the probability distribution with different loss functions (Dis_pred_Loss1, Dis_pred_Loss2, and Dis_pred_Loss3 method), and the generative adversarial networks (WGAN-GP for LOS method) are used for LOS range prediction. The Medical Information Mart for Intensive Care III (MIMIC-III) database is used to validate these methods.

Results

The RMSE method is convenient for LOS range prediction, but the predicted ranges are all consistent in the same batch of samples. The ERR_pred method can achieve better prediction results in samples with low errors. However, the prediction effect is worse in samples with larger errors. The Dis_pred_Loss1 method encounters a training instability problem. The Dis_pred_Loss2 and Dis_pred_Loss3 methods perform well in making predictions. Although WGAN-GP for LOS method does not show a substantial advantage over other methods, this method might have the potential to improve the predictive performance.

Conclusion

The results show that it is possible to achieve an acceptable accurate LOS range prediction through a reasonable model design, which may help physicians in the clinic.

Construction of a predictive model based on MIV-SVR for prognosis and length of stay in patients with traumatic brain injury: Retrospective cohort study

Objective

To investigate the mean impact value (MIV) method for discerning the most efficacious input variables for the machine learning (ML) model. Subsequently, various ML algorithms are harnessed to formulate a more accurate predictive model that can forecast both the prognosis and the length of hospital stay for patients suffering from traumatic brain injury (TBI).

Design

Retrospective cohort study.

Participants

The study retrospectively accrued data from 1128 cases of patients who sought medical intervention at the Neurosurgery Center of the Second Affiliated Hospital of Anhui Medical University, within the timeframe spanning from May 2017 to May 2022.

Methods

We performed a retrospective analysis of patient data obtained from the Neurosurgery Center of the Second Hospital of Anhui Medical University, covering the period from May 2017 to May 2022. Following meticulous data filtration and partitioning, 70% of the data were allocated for model training, while the remaining 30% served for model evaluation. During the construction phase of the ML models, a gamut of 11 independent variables-including, but not limited to, in-hospital complications and patient age-were utilized as input variables. Conversely, the length of stay (LOS) and the Glasgow Outcome Scale (GOS) scores were designated as output variables. The model architecture was initially refined through the MIV methodology to identify optimal input variables, whereupon five distinct predictive models were constructed, encompassing support vector regression (SVR), convolutional neural networks (CNN), backpropagation (BP) neural networks, artificial neural networks (ANN) and logistic regression (LR). Ultimately, SVR emerged as the most proficient predictive model and was further authenticated through an external dataset obtained from the First Hospital of Anhui Medical University.

Results

Upon incorporating the optimal input variables as ascertained through MIV, it was observed that the SVR model exhibited remarkable predictive prowess. Specifically, the Mean Absolute Percentage Error (MAPE) of the SVR model in predicting the GOS score in the test dataset is only 6.30%, and the MAPE in the external validation set is only 7.61%. In terms of predicting hospitalization time, the accuracy of the test and external validation sets were 9.28% and 7.91%, respectively. This error indicator is significantly lower than the error of other prediction models, thus proving the excellent efficacy and clinical reliability of the MIV-optimized SVR model.

Conclusion

This study unequivocally substantiates that the incorporation of MIV for selecting optimal input variables can substantially augment the predictive accuracy of machine learning models. Among the models examined, the MIV-SVR model emerged as the most accurate and clinically applicable, thereby rendering it highly conducive for future clinical decision-making processes.

Differential Diagnostic Value of Machine Learning-Based Models for Embolic Stroke

Cancer-associated thrombosis (CAT) and atrial fibrillation (AF)-related stroke are two subtypes of acute embolic stroke with distinct lesion patterns on diffusion weighted imaging (DWI). This pilot study aimed to evaluate the feasibility and performance of DWI-based machine learning models for differentiating between CAT and AF-related stroke. Patients with CAT and AF-related stroke were enrolled. In this pilot study with a small sample size, DWI images were augmented by flipping and/or contrast shifting to build convolutional neural network (CNN) predicative models. DWI images from 29 patients, including 9 patients with CAT and 20 with AF-related stroke, were analyzed. Training and testing accuracies of the DWI-based CNN model were 87.1% and 78.6%, respectively. Training and testing accuracies were 95.2% and 85.7%, respectively, for the second CNN model that combined DWI images with demographic/clinical characteristics. There were no significant differences in sensitivity, specificity, accuracy, and AUC between two CNN models (all P = n.s.).The DWI-based CNN model using data augmentation may be useful for differentiating CAT from AF-related stroke.