Development and validation of a machine learning-based predictive model for assessing the 90-day prognostic outcome of patients with spontaneous intracerebral hemorrhage.

BACKGROUND: Spontaneous intracerebral hemorrhage (sICH) is associated with significant mortality and morbidity. Predicting the prognosis of patients with sICH remains an important issue, which significantly affects treatment decisions. Utilizing readily available clinical parameters to anticipate the unfavorable prognosis of sICH patients holds notable clinical significance. This study employs five machine learning algorithms to establish a practical platform for the prediction of short-term prognostic outcomes in individuals afflicted with sICH. METHODS: Within the framework of this retrospective analysis, the model underwent training utilizing data gleaned from 413 cases from the training center, with subsequent validation employing data from external validation center. Comprehensive clinical information, laboratory analysis results, and imaging features pertaining to sICH patients were harnessed as training features for machine learning. We developed and validated the model efficacy using all the selected features of the patients using five models: Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), XGboost and LightGBM, respectively. The process of Recursive Feature Elimination (RFE) was executed for optimal feature screening. An internal five-fold cross-validation was employed to pinpoint the most suitable hyperparameters for the model, while an external five-fold cross-validation was implemented to discern the machine learning model demonstrating the superior average performance. Finally, the machine learning model with the best average performance is selected as our final model while using it for external validation. Evaluation of the machine learning model's performance was comprehensively conducted through the utilization of the ROC curve, accuracy, and other relevant indicators. The SHAP diagram was utilized to elucidate the variable importance within the model, culminating in the amalgamation of the above metrics to discern the most succinct features and establish a practical prognostic prediction platform. RESULTS: A total of 413 patients with sICH patients were collected in the training center, of which 180 were patients with poor prognosis. A total of 74 patients with sICH were collected in the external validation center, of which 26 were patients with poor prognosis. Within the training set, the test set AUC values for SVM, LR, RF, XGBoost, and LightGBM models were recorded as 0.87, 0.896, 0.916, 0.885, and 0.912, respectively. The best average performance of the machine learning models in the training set was the RF model (average AUC: 0.906 ± 0.029, P < 0.01). The model still maintains a good performance in the external validation center, with an AUC of 0.817 (95% CI 0.705-0.928). Pertaining to feature importance for short-term prognostic attributes of sICH patients, the NIHSS score reigned supreme, succeeded by AST, Age, white blood cell, and hematoma volume, among others. In culmination, guided by the RF model's variable importance weight and the model's ROC curve insights, the NIHSS score, AST, Age, white blood cell, and hematoma volume were integrated to forge a short-term prognostic prediction platform tailored for sICH patients. CONCLUSION: We constructed a prediction model based on the results of the RF model incorporating five clinically accessible predictors with reliable predictive efficacy for the short-term prognosis of sICH patients. Meanwhile, the performance of the external validation set was also more stable, which can be used for accurate prediction of short-term prognosis of sICH patients.

Prognostic Significance of Uric Acid Levels in Intracerebral Hemorrhage Patients.

Background and Purpose: The role of serum uric acid (UA) level in patients suffering from stroke remains controversial. Our aim was to investigate the effect of UA level on clinical outcomes in patients with intracerebral hemorrhage (ICH). Methods: In the retrospective cohort study, we analyzed data from 250 patients with intracerebral hemorrhage (85 women and 165 men) to investigate the difference in UA levels between patients with a good prognosis and those with a poor prognosis. Additionally, we analyzed the impact of UA levels on the risk of short-time prognosis of ICH patients. Results: Patients with a good prognosis presented with significantly lower levels of UA (348.71 ± 84.97 µmol/L) than those with poor prognosis (393.06 ± 148.46 µmol/L). Furthermore, multivariate logistic regression model demonstrated that a high UA level was a likely risk factor for worse prognosis among patients suffering in ICH (odds ratio [95% confidence interval], 1.006 [1.0012, 1.0108]; P = 0.015). Additionally, UA has a threshold effect value of 363.9 µmol/L and was presented in levels that were in a nonlinear relationship with incidence rate of short-time prognosis outcome of ICH patients. Conclusion: Our findings indicate that higher UA levels can increase the risk of poor clinical prognosis in patients with ICH and high UA levels are not conductive to the clinical prognosis of patients with ICH. These findings provide a new perspective on the treatment and prevention of ICH.

Development and validation of a novel clinical prediction model to predict the 90-day functional outcome of spontaneous intracerebral hemorrhage.

Background: Spontaneous intracerebral hemorrhage (SICH) is associated with high mortality and disability. Accurately predicting adverse prognostic risks of SICH is helpful in developing risk stratification and precision medicine strategies for this phenomenon. Methods: We analyzed 413 patients with SICH admitted to Hefei Second People's Hospital as a training cohort, considering 74 patients from the First Affiliated Hospital of Anhui Medical University for external validation. Univariate and multivariate logistic regression analyses were used to select risk factors for 90-day functional outcomes, and a nomogram was developed to predict their incidence in patients. Discrimination, fitting performance, and clinical utility of the resulting nomogram were evaluated through receiver operating characteristic (ROC) curves, accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), calibration plots, and decision curves analysis (DCA), respectively. Results: Of the 413 patients, 180 had a poor prognosis. Univariate analysis showed significant variance of age, systolic pressure, intraventricular hemorrhage (IVH), Glasgow Coma Scale (GCS) scores, National Institute of Health Stroke Scale (NIHSS) scores, and hematoma volume between the groups (p < 0.05). Logistic multivariate regression analysis showed that age, IVH, NIHSS, and hematoma volume were associated with unfavorable outcomes. Based on the results, a nomogram model was developed with an area under the ROC curve of 0.91 (95% CI; 0.88-0.94) and 0.89 (95% CI; 0.80-0.95) in the training and validation sets, respectively. In the validation set, the accuracy, sensitivity, specificity, PPV, and NPV of the model were 0.851, 0.923, 0.812, 0.727, and 0.951, respectively. The calibration plot demonstrates the goodness of fit between the nomogram predictions and actual observations. Finally, DCA indicated significant clinical adaptability. Conclusion: We developed and validated a short-term prognostic nomogram model for patients with SICH including NIHSS scores, age, hematoma volume, and IVH. This model has valuable potential in predicting the prognosis of patients with SICH.

Serum ß2-microglobulin is closely associated with 3-month outcome of acute intracerebral hemorrhage: a retrospective cohort study.

BACKGROUND: Intracerebral hemorrhage (ICH) is a frequent type of hemorrhagic stroke. Numerous studies have suggested that inflammation plays an important role in the injury and recovery of ICH. ß2-microglobulin (ß2M) is an inflammatory indicator with an unclear association with ICH development. This study aimed to explore the role of ß2M in the outcome of patients with ICH after 3 months of ICH onset. METHODS: The ß2M and other baseline information of 231 patients with ICH were assessed (83 females and 148 males). We followed up with all patients 3 months after ICH onset, and severe disability or a worse outcome was our main focus. We collected the serum ß2M levels, National Institutes of Health Stroke Scale (NIHSS) and modified Rankin scale (mRS) scores, and other relevant baseline information of each patient. We used multiple regression analysis to explore the association between ß2M levels and follow-up outcomes. RESULTS: Our results indicated that the ß2M level of the good outcome (2.35 ± 0.84 mg/l) group was significantly lower than that of the poor outcome group (3.06 ± 1.71 mg/l) (P < 0.001). Further multiple regression analysis showed that ß2M was regarded as a risk factor that was closely associated with the poor outcome 3 months after ICH onset (odds ratio = 2.26, 95% confidence interval = 1.22-4.19, P = 0.009). Further correlation analysis revealed that ß2M was significantly correlated with NIHSS scores (r = 0.187, P = 0.004) and follow-up mRS scores (r = 0.25, P < 0.001). CONCLUSION: ß2M was a risk factor for early outcome after ICH onset, and high ß2M level was associated with short-time poor prognosis of ICH patients.

Triphlorethol-A attenuates U251 human glioma cancer cell proliferation and ameliorates apoptosis through JAK2/STAT3 and p38 MAPK/ERK signaling pathways.

Glioma is the foremost recurrent type of brain tumor in humans; in particular, glioblastoma (GBM) is the main form of brain tumor (GBM) that is highly proliferative and impervious to apoptosis. Triphlorethol-A (TA), a phlorotannin isolated from Ecklonia cava, exhibited cytoprotective, antioxidant, and anticancer properties. However, the exact molecular action of TA in the U251 human GBM cells remains unknown. This may be the first report on the antiproliferative and apoptotic mechanisms of TA on GBM. The cytotoxicity, intracellular reactive oxygen species (ROS), matrix metalloproteinase (MMP), and cell apoptosis activity of TA have been evaluated by the MTT assay and by DCFH-DA, Rh-123, AO/EB, and western blot analysis. The results obtained showed that TA abridged the viability of U251 cells, while MMP increased apoptosis by increasing the ROS levels in a time-dependent manner. The results showed that a reduction in U251 cell proliferation was associated with the regulation of JAK2/STAT3 and p38 MAPK/ERK signaling pathways. TA was found to suppress pJAK, pSTAT3, p38 MAPK, and pERK phosphorylation, thereby causing Bax/Bcl-2 imbalance, activating the caspase cascade and cytochrome c, and inducing apoptosis. Our findings showed that the suppression of JAK2/STAT3 and p38 MAPK/ERK signaling by TA results in cell growth arrest and stimulation of apoptosis in GBM cells. These studies justify the protective remedy of TA against GBM.

Gold nanourchin enhances detection of Alzheimer's disease biomarker "miRNA-137" on dual electrode sensing surface.

Diagnosis of Alzheimer's disease (AD) is a complex task, and at present, neuroimaging such as magnetic resonance imaging and positron emission tomography is commonly used for the diagnosis of AD. This research work developed a new biosensing method with gold nanomaterial to identify AD biomarker of miRNA-137. Gold nanourchin (GNU) was attached on the interdigitated electrode through the silane linker and COOH-ended capture oligonucleotide was immobilized on the GNU surface. This surface helps to quantify the target sequence of miRNA-137 and the detection limit reached to 0.01 pM on the linear range of 0.01-100 pM. With 3δ calculation on the linearity, the determination coefficient was noticed as y = 1.2867x - 2.2697; R2  = 0.9059. The control performances did not show a significant response, indicating the specific identification of target.

Skullcapflavone II protects neuronal damage in cerebral ischemic rats via inhibiting NF-ĸB and promoting angiogenesis.

BACKGROUND: Cerebral ischemia (CI) is considered as a main cause of cerebral stroke (CS) and poses significant risk to the mankind across the world. In the present study, we intended to investigate the protective effect of Skullcapflavone II (SCP) a flavonoid isolated from S. baicalensis on cerebral ischemia/reperfusion (I/R) injury. METHODS: The middle cerebral artery occlusion (MCAO) and reperfusion was used to create ischemic stroke rat model. The rats were treated with (5, 10, and 15 mg/kg) SCP and after the end of the experiment the rats were sacrificed and various biochemical parameters were assed to determine the pharmacological action of SCP. RESULTS: SCP dramatically decreases cerebral edema, infarct volume, and improves neurological manifestation as confirmed by reduced neurological deficit. SCP also improves the survivability of neurons as evidenced by H and E and Nissl staining. The level of oxidative stress in the cerebral cortex of the rats was found reduced after treatment with SCP, as confirmed by increase in GSH and SOD activity with reduction in MDA content. In addition, SCP attenuated inflammation via reducing the level of TNF-α, IL-1ß and IL-6 in brain tissues of rats. SCP increases the expression of Bcl2, cleaved caspase-3 and -9, while decreasing Bax, and NF-ĸB/TLR4. It causes induction of angiogenesis as suggested by increased expression of VEGF, Ang-1 and Tie-2 in cerebral cortex of rat. CONCLUSIONS: Our data determined that SCP may provide protective effect on the I/R-induced cerebral ischemia.

Exosome-Mediated Transfer of Long Noncoding RNA HOTAIR Regulates Temozolomide Resistance by miR-519a-3p/RRM1 Axis in Glioblastoma.

Background: Chemoresistance obstructs the treatment of glioblastoma (GB). Exosome-mediated transfer of long noncoding RNAs (lncRNAs) was reported to regulate chemoresistance in diverse cancers. The authors aimed to investigate the underlying mechanism of lncRNA HOX transcript antisense intergenic RNA (HOTAIR) in regulating temozolomide (TMZ) resistance in GB. Materials and Methods: 3-(4,5-Dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide (MTT) assay was utilized to check TMZ resistance and cell proliferation. The abilities of cell migration and invasion were evaluated by transwell assay. The protein levels of E-cadherin, N-cadherin, Vimentin, CD63, CD81, and ribonucleoside-diphosphate reductase subunit M1 (RRM1) were measured by western blot. Quantitative real-time polymerase chain reaction was conducted to detect the levels of HOTAIR, microRNA (miR)-519a-3p, and RRM1. The starBase was hired to predict the target sites between miR-519a-3p and HOTAIR or RRM1 and the dual-luciferase reporter assay was performed to verify the interaction. Xenograft tumor model was established to investigate the biological role of HOTAIR in vivo. Results: The high abilities of cell viability and metastasis were observed in TMZ-resistant GB cells. LncRNA HOTAIR was significantly upregulated in TMZ-resistant GB cells and its downregulation inhibited proliferation, migration, invasion, and epithelial/mesenchymal transition in TMZ-resistant GB cells. Further analysis indicated that exosomal lncRNA HOTAIR induced TMZ resistance and modulated TMZ resistance through miR-519a-3p/RRM1 axis. Besides, serum exosomal lncRNA HOTAIR was stable and had diagnostic value. Moreover, knockdown of lncRNA HOTAIR reduced TMZ resistance in vivo. Conclusions: Exosomal lncRNA HOTAIR mediated TMZ resistance through miR-519a-3p/RRM1 axis in GB.

Genetically Confirmed CARASIL: Case Report with Novel HTRA1 Mutation and Literature Review.

BACKGROUND: Cerebral autosomal recessive arteriopathy with subcortical infarcts and leukoencephalopathy (CARASIL) is an extremely rare monogenic autosomal disease associated with the HtrA serine protease 1 (HTRA 1) gene mutation. Recently, a few genetically confirmed CARASIL cases with novel HTRA1 mutations have been reported in countries other than Japan. CASE DESCRIPTION: Here, we report a case of a patient presenting with worsening right hemiplegia and hemiparesthesia. Physical examination revealed that the patient had typical clinical features of CARASIL including thinning hair, cognitive impairment, emotional changes, lumbago, and gait disorder. Brain magnetic resonance imaging showed abnormal diffuse symmetric changes in white matter and hypertensive diffusion-weighted imaging signals in the left centrum ovale and right splenium of the corpus callosum, and susceptibility-weighted imaging showed multiple cerebral microbleeds. Lumbar magnetic resonance imaging showed herniated disks with degenerative changes. A genetic test showed a novel homozygous nucleotide variation of c.847G>T in the HTRA1 gene, thereby resulting in p.Gly283Ter. Thus the patient met the diagnostic criteria for CARASIL. We provide a literature review of genetically confirmed CARASIL cases reported to date. CONCLUSIONS: CARASIL is a rare autosomal recessive disease with an HTRA1 mutation. Familiarity with the early clinical and imaging features of CARASIL combined with a genetic test is key for its early diagnosis.

MiR-92a antagonized the facilitation effect of extracellular matrix protein 1 in GC metastasis through targeting its 3'UTR region.

MicroRNAs were known to play very important roles in human diseases, and have attracted great interests of research scientists in medicine, toxicology and functional foods. Gastric carcinoma (GC) remains one of the most common and lethal types of malignancy worldwide. However, the molecular mechanism of GC and the role of microRNAs in GC development remain unclear. The expression of extracellular matrix protein 1 (ECM1) is up-regulated in many cancer types, but its functional role is inconstant. In the present study, we aimed to investigate the correlation between GC development and ECM1 expression, along with its regulation by microRNAs. Immunohistochemical results showed that ECM1 was up-regulated in GC tissues and ECM1 expression level was negatively correlated with the prognosis of GC. ECM1 was found to promote gastric cancer cell metastasis in cell migration assays by facilitating the expression of proteins involved in epithelial-mesenchymal transition (EMT). MiR-92a was recognized for the first time to suppress the migration of human GC cells by directly targeting to the 3'UTR of ECM1 gene in a dual-luciferase reporter assay. These results highlighted the antagonistic roles of ECM1 and miR-92a in GC development, which may serve as a new target for gastric cancer.

Targeted nanoparticles for drug delivery through the blood-brain barrier for Alzheimer's disease.

Alzheimer's disease (AD) is the most common cause of dementia among the elderly, affecting 5% of Americans over age 65, and 20% over age 80. An excess of senile plaques (beta-amyloid protein) and neurofibrillary tangles (tau protein), ventricular enlargement, and cortical atrophy characterizes it. Unfortunately, targeted drug delivery to the central nervous system (CNS), for the therapeutic advancement of neurodegenerative disorders such as Alzheimer's, is complicated by restrictive mechanisms imposed at the blood-brain barrier (BBB). Opsonization by plasma proteins in the systemic circulation is an additional impediment to cerebral drug delivery. This review gives an account of the BBB and discusses the literature on biodegradable polymeric nanoparticles (NPs) with appropriate surface modifications that can deliver drugs of interest beyond the BBB for diagnostic and therapeutic applications in neurological disorders, such as AD. The physicochemical properties of the NPs at different surfactant concentrations, stabilizers, and amyloid-affinity agents could influence the transport mechanism.