Search

Introduction: Post-stroke depression (PSD) has complex pathophysiology determined by various biological and psychological factors. Although it is a long-term complication of stroke, PSD is often underdiagnosed. Given the diagnostic role of quantitative electroencephalography (qEEG) in depression, it was investigated whether a possible marker of PSD could be identified by observing the evolution of the (Delta + Theta)/(Alpha + Beta) Ratio (DTABR), respectively the Delta/Alpha Ratio (DAR) values in post-stroke depressed patients (evaluated through the HADS-D subscale). Methods: The current paper analyzed the data of 57 patients initially selected from a randomized control trial (RCT) that assessed the role of N-Pep 12 in stroke rehabilitation. EEG recordings from the original trial database were analyzed using signal processing techniques, respecting the conditions (eyes open, eyes closed), and several cognitive tasks. Results: We observed two significant associations between the DTABR values and the HADS-D scores of post-stroke depressed patients for each of the two visits (V1 and V2) of the N-Pep 12 trial. We recorded the relationships in the Global (V1 = 30 to 120 days after stroke) and Frontal Extended (V2 = 90 days after stroke) regions during cognitive tasks that trained attention and working memory. For the second visit, the association between the analyzed variables was negative. Conclusions: As both our relationships were described during the cognitive condition, we can state that the neural networks involved in processing attention and working memory might go through a reorganization process one to four months after the stroke onset. After a period longer than six months, the process could localize itself at the level of frontal regions, highlighting a possible divergence between the local frontal dynamics and the subjective well-being of stroke survivors. QEEG parameters linked to stroke progression evolution (like DAR or DTABR) can facilitate the identification of the most common neuropsychiatric complication in stroke survivors.

Stroke is a leading cause of disability and mortality, resulting in substantial socio-economic burden for healthcare systems. With advances in artificial intelligence, visual image information can be processed into numerous quantitative features in an objective, repeatable and high-throughput fashion, in a process known as radiomics analysis (RA). Recently, investigators have attempted to apply RA to stroke neuroimaging in the hope of promoting personalized precision medicine. This review aimed to evaluate the role of RA as an adjuvant tool in the prognosis of disability after stroke. We conducted a systematic review following the PRISMA guidelines, searching PubMed and Embase using the keywords: ‘magnetic resonance imaging (MRI)’, ‘radiomics’, and ‘stroke’. The PROBAST tool was used to assess the risk of bias. Radiomics quality score (RQS) was also applied to evaluate the methodological quality of radiomics studies. Of the 150 abstracts returned by electronic literature research, 6 studies fulfilled the inclusion criteria. Five studies evaluated predictive value for different predictive models (PMs). In all studies, the combined PMs consisting of clinical and radiomics features have achieved the best predictive performance compared to PMs based only on clinical or radiomics features, the results varying from an area under the ROC curve (AUC) of 0.80 (95% CI, 0.75–0.86) to an AUC of 0.92 (95% CI, 0.87–0.97). The median RQS of the included studies was 15, reflecting a moderate methodological quality. Assessing the risk of bias using PROBAST, potential high risk of bias in participants selection was identified. Our findings suggest that combined models integrating both clinical and advanced imaging variables seem to better predict the patients’ disability outcome group (favorable outcome: modified Rankin scale (mRS) ≤ 2 and unfavorable outcome: mRS > 2) at three and six months after stroke. Although radiomics studies’ findings are significant in research field, these results should be validated in multiple clinical settings in order to help clinicians to provide individual patients with optimal tailor-made treatment.