A weakly supervised deep learning model integrating noncontrasted computed tomography images and clinical factors facilitates haemorrhagic transformation prediction after intravenous thrombolysis in acute ischaemic stroke patients.

BACKGROUND: Haemorrhage transformation (HT) is a serious complication of intravenous thrombolysis (IVT) in acute ischaemic stroke (AIS). Accurate and timely prediction of the risk of HT before IVT may change the treatment decision and improve clinical prognosis. We aimed to develop a deep learning method for predicting HT after IVT for AIS using noncontrast computed tomography (NCCT) images. METHODS: We retrospectively collected data from 828 AIS patients undergoing recombinant tissue plasminogen activator (rt-PA) treatment within a 4.5-h time window (n = 665) or of undergoing urokinase treatment within a 6-h time window (n = 163) and divided them into the HT group (n = 69) and non-HT group (n = 759). HT was defined based on the criteria of the European Cooperative Acute Stroke Study-II trial. To address the problems of indiscernible features and imbalanced data, a weakly supervised deep learning (WSDL) model for HT prediction was constructed based on multiple instance learning and active learning using admission NCCT images and clinical information in addition to conventional deep learning models. Threefold cross-validation and transfer learning were performed to confirm the robustness of the network. Of note, the predictive value of the commonly used scales in clinics associated with NCCT images (i.e., the HAT and SEDAN score) was also analysed and compared to measure the feasibility of our proposed DL algorithms. RESULTS: Compared to the conventional DL and ML models, the WSDL model had the highest AUC of 0.799 (95% CI 0.712-0.883). Significant differences were observed between the WSDL model and five ML models (P < 0.05). The prediction performance of the WSDL model outperforms the HAT and SEDAN scores at the optimal operating point (threshold = 1.5). Further subgroup analysis showed that the WSDL model performed better for symptomatic intracranial haemorrhage (AUC = 0.833, F1 score = 0.909). CONCLUSIONS: Our WSDL model based on NCCT images had relatively good performance for predicting HT in AIS and may be suitable for assisting in clinical treatment decision-making.

Cell-therapy for Parkinson's disease: a systematic review and meta-analysis.

BACKGROUND: Cell-based strategies focusing on replacement or protection of dopaminergic neurons have been considered as a potential approach to treat Parkinson's disease (PD) for decades. However, despite promising preclinical results, clinical trials on cell-therapy for PD reported mixed outcomes and a thorough synthesis of these findings is lacking. We performed a systematic review and meta-analysis to evaluate cell-therapy for PD patients. METHODS: We systematically identified all clinical trials investigating cell- or tissue-based therapies for PD published before July 2023. Out of those, studies reporting transplantation of homogenous cells (containing one cell type) were included in meta-analysis. The mean difference or standardized mean difference in quantitative neurological scale scores before and after cell-therapy was analyzed to evaluate treatment effects. RESULTS: The systematic literature search revealed 106 articles. Eleven studies reporting data from 11 independent trials (210 patients) were eligible for meta-analysis. Disease severity and motor function evaluation indicated beneficial effects of homogenous cell-therapy in the 'off' state at 3-, 6-, 12-, or 24-month follow-ups, and for motor function even after 36 months. Most of the patients were levodopa responders (61.6-100% in different follow-ups). Cell-therapy was also effective in improving the daily living activities in the 'off' state of PD patients. Cells from diverse sources were used and multiple transplantation modes were applied. Autografts did not improve functional outcomes, while allografts exhibited beneficial effects. Encouragingly, both transplantation into basal ganglia and to areas outside the basal ganglia were effective to reduce disease severity. Some trials reported adverse events potentially related to the surgical procedure. One confirmed and four possible cases of graft-induced dyskinesia were reported in two trials included in this meta-analysis. CONCLUSIONS: This meta-analysis provides preliminary evidence for the beneficial effects of homogenous cell-therapy for PD, potentially to the levodopa responders. Allogeneic cells were superior to autologous cells, and the effective transplantation sites are not limited to the basal ganglia. PROSPERO registration number: CRD42022369760.

Prediction of Joint Angles Based on Human Lower Limb Surface Electromyography.

Wearable exoskeletons can help people with mobility impairments by improving their rehabilitation. As electromyography (EMG) signals occur before movement, they can be used as input signals for the exoskeletons to predict the body's movement intention. In this paper, the OpenSim software is used to determine the muscle sites to be measured, i.e., rectus femoris, vastus lateralis, semitendinosus, biceps femoris, lateral gastrocnemius, and tibial anterior. The surface electromyography (sEMG) signals and inertial data are collected from the lower limbs while the human body is walking, going upstairs, and going uphill. The sEMG noise is reduced by a wavelet-threshold-based complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) reduction algorithm, and the time-domain features are extracted from the noise-reduced sEMG signals. Knee and hip angles during motion are calculated using quaternions through coordinate transformations. The random forest (RF) regression algorithm optimized by cuckoo search (CS), shortened as CS-RF, is used to establish the prediction model of lower limb joint angles by sEMG signals. Finally, root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2) are used as evaluation metrics to compare the prediction performance of the RF, support vector machine (SVM), back propagation (BP) neural network, and CS-RF. The evaluation results of CS-RF are superior to other algorithms under the three motion scenarios, with optimal metric values of 1.9167, 1.3893, and 0.9815, respectively.

Therapeutic effect of mesenchymal stem cells in rats with intracerebral hemorrhage: reduced apoptosis and enhanced neuroprotection.

Stem cell transplantation has been used to improve neural function in intracerebral hemorrhage (ICH). However, reports on bone marrow-derived mesenchymal stem cell (MSC) transplantation in ICH are limited. We aimed to explore the therapeutic effect and related mechanisms by transplantation of MSCs in rats with ICH. An experimental rat ICH model was established by intrastriatal administration of collagenase. The rats were randomly divided to receive either rat MSCs or PBS solution intravenously. In addition, behavioral tests using the modified neurological severity score (mNSS) were performed following ICH. Immunohistochemistry was performed to detect the Brdu-labeled MSCs and the protein expression of caspase 2, NF200 and GFAP in neural tissues. Western blotting and ELISA were performed to measure the protein expression of Akt and bcl-2 or the protein content of G-CSF and BDNF. The MSC-transplanted group demonstrated better neural function on the mNSS test following ICH compared with the control group (P<0.05). The MSC-transplanted group also showed reduced hemorrhage volume at 24 and 72 h following ICH. In the perihematomal regions of rat brain with ICH, a substantial number of Brdu-labeled MSCs were observed, and a high protein expression of caspase 3, NF200 and GFAP was found in the MSC-transplanted group. The protein content of Akt, Bcl-2, G-CSF and BDNF were all elevated by MSC transplantation. Intravenously transplanted MSCs are capable of improving functional recovery and restoring neurological deficits in experimental ICH. The mechanisms are associated with enhanced survival and differentiation of neural cells, and increased expression of anti-apoptotic proteins and trophic factors.