Dataset Information

Self-Reported Complaints as Prognostic Markers for Outcome After Mild Traumatic Brain Injury in Elderly: A Machine Learning Approach.

ABSTRACT: Self-reported complaints are common after mild traumatic brain injury (mTBI). Particularly in the elderly with mTBI, the pre-injury status might play a relevant role in the recovery process. In most mTBI studies, however, pre-injury complaints are neither analyzed nor are the elderly included. Here, we aimed to identify which individual pre- and post-injury complaints are potential prognostic markers for incomplete recovery (IR) in elderly patients who sustained an mTBI. Since patients report many complaints across several domains that are strongly related, we used an interpretable machine learning (ML) approach to robustly deal with correlated predictors and boost classification performance. Pre- and post-injury levels of 20 individual complaints, as self-reported in the acute phase, were analyzed. We used data from two independent studies separately: UPFRONT study was used for training and validation and ReCONNECT study for independent testing. Functional outcome was assessed with the Glasgow Outcome Scale Extended (GOSE). We dichotomized functional outcome into complete recovery (CR; GOSE = 8) and IR (GOSE ≤ 7). In total 148 elderly with mTBI (median age: 67 years, interquartile range [IQR]: 9 years; UPFRONT: N = 115; ReCONNECT: N = 33) were included in this study. IR was observed in 74 (50%) patients. The classification model (IR vs. CR) achieved a good performance (the area under the receiver operating characteristic curve [ROC-AUC] = 0.80; 95% CI: 0.74-0.86) based on a subset of only 8 out of 40 pre- and post-injury complaints. We identified increased neck pain (p = 0.001) from pre- to post-injury as the strongest predictor of IR, followed by increased irritability (p = 0.011) and increased forgetfulness (p = 0.035) from pre- to post-injury. Our findings indicate that a subset of pre- and post-injury physical, emotional, and cognitive complaints has predictive value for determining long-term functional outcomes in elderly patients with mTBI. Particularly, post-injury neck pain, irritability, and forgetfulness scores were associated with IR and should be assessed early. The application of an ML approach holds promise for application in self-reported questionnaires to predict outcomes after mTBI.

SUBMITTER: Bittencourt M

PROVIDER: S-EPMC8674199 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Background: Mild traumatic brain injuries (mTBIs) are a significant social, sport, and military health issue. In spite of advances in the clinical management of these injuries, the underlying pathophysiology is not well-understood. There is a critical need to advance objective biomarkers, allowing the identification and tracking of the long-term evolution of changes resulting from mTBI. Diffusion-weighted imaging (DWI) allows for the assessment of white-matter properties in the brain and shows promise as a suitable biomarker of mTBI pathophysiology. Methods: 34 individuals within a year of an mTBI (age: 24.4 ± 7.4) and 18 individuals with no history of mTBI (age: 23.2 ± 3.4) participated in this study. Participants completed self-report measures related to functional outcomes, psychological health, post-injury symptoms, and sleep, and underwent a neuroimaging session that included DWI. Whole-brain white matter was skeletonized using tract-based spatial statistics (TBSS) and compared between groups as well as correlated within-group with the self-report measures. Results: There were no statistically significant anatomical differences between the two groups. After controlling for time since injury, fractional anisotropy (FA) demonstrated a negative correlation with sleep quality scores (higher FA was associated with better sleep quality) and increasing depressive symptoms in the mTBI participants. Conversely, mean (MD) and radial diffusivity (RD) demonstrated positive correlations with sleep quality scores (higher RD was associated with worse sleep quality) and increasing depressive symptoms. These correlations were observed bilaterally in the internal capsule (anterior and posterior limbs), corona radiata (anterior and superior), fornix, and superior fronto-occipital fasciculi. Conclusion: The results of this study indicate that the clinical presentation of mTBI, particularly with respect to depression and sleep, is associated with reduced white-matter integrity in multiple areas of the brain, even after controlling for time since injury. These areas are generally associated not only with sleep and emotion regulation but also cognition. Consequently, the onset of depression and sleep dysfunction as well as cognitive impairments following mTBI may be closely related to each other and to white-matter integrity throughout the brain.

Dataset Information

Self-Reported Complaints as Prognostic Markers for Outcome After Mild Traumatic Brain Injury in Elderly: A Machine Learning Approach.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets