Electroencephalography (EEG)-based imagined speech decoding technology offers a communication solution for patients with language impairments. However, existing research on English-language systems cannot be directly applied to Chinese due to significant linguistic differences. Multi-channel EEG systems face hardware complexity and computational delays. This study aimed to develop a single-channel EEG decoding system for Chinese imagined speech, explore neural mechanisms to promote low-cost rehabilitation devices.

EEG signals were recorded from four Chinese participants imagining five distinct Chinese characters. The SGLCNN model was proposed and compared with VGG16, EEGNet, and machine learning methods. Experiments evaluated the performance of 20 single-channel time–frequency graphs and compared their accuracy with traditional methods.

The CP5 and C3 channels achieved the highest classification accuracies of 74.33% and 73%. The SGLCNN model outperformed EEGNet and VGG16 in decoding binary classification tasks for Chinese characters. Single-channel signals improved classification accuracy by 0.67% (SGLCNN) and 2.75% (EEGNet) compared to full-brain signals under the same models.

This is the first study to decode imagined Chinese speech using single-channel EEG and tests the performance of 20 channels for this task. The SGLCNN system maintains performance while reducing hardware needs. Identifying dominant channels (CP5/C3) informs clinical electrode placement, accelerating brain-computer interfaces (BCIs) translation.

Acute spontaneous intracerebral hemorrhage (ICH) is a life-threatening condition, and certain serological indicators may be associated with the prognosis after ICH. This study investigated the relationship between N-terminal pro-B-type natriuretic peptide (NT-pro-BNP) and other serological indicators with prognosis 90 days after the onset of acute ICH.

The general information, clinical, and follow-up data of patients with ICH who were admitted to the Department of Neurology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology from January 2019 to September 2022 were retrospectively collected. Based on the modified Rankin Scale (mRS) at 90 days of onset, the patients were divided into poor prognosis group (mRS > 3) and good prognosis group (mRS ≤ 3), and the differences in various indicators between these two groups were compared. Serological indicators related to prognosis were determined by univariate and multivariate logistic regression analysis, and the predictive value was evaluated by receiver operating characteristic (ROC) analysis and decision curve analysis (DCA).

A total of 121 patients with ICH were included in the study with 49 patients having a good prognosis and 72 patients having a poor prognosis. Multivariate logistic regression analysis showed that NT-pro-BNP at admission was associated with prognosis at 90 days after ICH onset (P < 0.05). ROC and DCA analyses demonstrated that NT-pro-BNP had a certain predictive ability for ICH prognosis.

The level of NT-pro-BNP at admission may be an independent risk factor for predicting prognosis at 90 days after the onset of ICH. The higher the level, the worse the prognosis may be.

Hematoma growth rarely occurs after 24 h in patients with intracerebral hemorrhage (ICH). Here we report a case with delayed hematoma growth caused by thrombocytopenia.

A 68-year-old leukemia patient presented with sudden left-sided weakness. Initial computed tomography scans revealed a small basal ganglia hemorrhage without early expansion. However, three days later, there was a significant hematoma expansion coupled with thrombocytopenia. The patient’s condition remained stable after treatment. Our case suggests that hematoma expansion may occur even 3 days after symptom onset in patients with ICH.

This underscores the significance of promptly recognizing and closely monitoring delayed hematoma growth in cases of ICH associated with leukemia to facilitate timely intervention.

To observe the effect of intra-hematoma Rosiglitazone (RSG) infusion therapy in treating intracerebral hemorrhage (ICH). Specifically, to explore the effects of RSG on tight junction associated proteins Occludin and ZO-1 expression within perihematomal brain tissues as well as the blood–brain barrier (BBB) permeability after ICH in rabbits.

A total of 30 rabbits were randomly assigned to three groups including sham control group (NC group, n = 10), hemorrhage model group (HM group, n = 10), and hemorrhage model with RSG treatment group (RSG group, n = 10). ICH was induced in rabbits of HM group and RSG group, involving an injection of autologous non-anticoagulant artery blood (0.3 mL, similar to basal ganglia hematoma 30 mL in humans) into the left basal ganglia of the rabbits' brains. The NC group was injected with the same amount of saline into the same area. Six hours later after ICH induction or sham surgery, the RSG group received the intra-hematoma RSG (0.5 mg/0.1 mL) infusion, meanwhile the NC group and the HM group were injected with saline (0.1 mL) into the hematoma area. On day seven, the perihematomal brain tissues were obtained to determine the Occludin and ZO-1 expressions by Western Blot and RT-PCR, and the BBB permeability by the Evan' s Blue (EB) content.

Occludin and ZO-1 expressions and mRNA levels were all significantly decreased in the HM group and RSG group compared with the NC group (P < 0.01). Occludin and ZO-1 expressions and mRNA levels were all significantly increased in the RSG group compared with the HM group (P < 0.01). The EB contents were all significantly increased in the HM group and RSG group compared with the NC group (P < 0.01). The EB content was significantly decreased in the RSG group compared with the HM group (P < 0.01).

Intra-hematoma RSG infusion therapy could increase the expressions of tight junction associated proteins Occludin and ZO-1 in the perihematomal brain tissues and decrease the BBB permeability in rabbits after ICH.