An Explainable Artificial Intelligence Model to Predict Malignant Cerebral Edema after Acute Anterior Circulating Large-Hemisphere Infarction.

INTRODUCTION: Malignant cerebral edema (MCE) is a serious complication and the main cause of poor prognosis in patients with large-hemisphere infarction (LHI). Therefore, the rapid and accurate identification of potential patients with MCE is essential for timely therapy. This study utilized an artificial intelligence-based machine learning approach to establish an interpretable model for predicting MCE in patients with LHI. METHODS: This study included 314 patients with LHI not undergoing recanalization therapy. The patients were divided into MCE and non-MCE groups, and the eXtreme Gradient Boosting (XGBoost) model was developed. A confusion matrix was used to measure the prediction performance of the XGBoost model. We also utilized the SHapley Additive exPlanations (SHAP) method to explain the XGBoost model. Decision curve and receiver operating characteristic curve analyses were performed to evaluate the net benefits of the model. RESULTS: MCE was observed in 121 (38.5%) of the 314 patients with LHI. The model showed excellent predictive performance, with an area under the curve of 0.916. The SHAP method revealed the top 10 predictive variables of the MCE such as ASPECTS score, NIHSS score, CS score, APACHE II score, HbA1c, AF, NLR, PLT, GCS, and age based on their importance ranking. CONCLUSION: An interpretable predictive model can increase transparency and help doctors accurately predict the occurrence of MCE in LHI patients not undergoing recanalization therapy within 48 h of onset, providing patients with better treatment strategies and enabling optimal resource allocation.

External validation and comparison of MBE, EDEMA, and modified EDEMA scores for predicting malignant cerebral EDEMA in Chinese patients with large hemispheric infarction patients without revascularization.

BACKGROUND: Malignant cerebral edema (MCE) is a severe condition characterized by rapid neurological deterioration and a potentially poor prognosis. Scoring systems including the malignant brain edema (MBE) score, Enhanced Detection of Edema in Malignant Anterior Circulation Stroke score (EDEMA), and modified EDEMA score, have been developed to predict MCE in patients with large hemispheric infarction (LHI). We aimed to externally validate and comparethe predictive efficacy of these scores in LHI patients within 48 h of onset and not undergoing reperfusion therapy. METHODS: Demographic, clinical and radiological data were retrospectively collected from LHI patients within 48 h of onset and not receiving reperfusion therapy. Patients were divided into MCE and non-MCE group. The calibration, discrimination, and clinical practicability of the three scores were verified using Hosmer-Lemeshow goodness-of-fit test, receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA), respectively. Finally, continuous net reclassification improvement (NRI) and integrated discrimination improvement (IDI) were applied to determine the discrimination performance of the three scores. RESULTS: A total of 314 patients were included in the study, with 122 cases being MCE patients. The Hosmer-Lemeshow goodness-of-fit test showed excellent fitting ability across the MBE (p = 0.36), EDEMA (p = 0.61), and modified EDEMA scores (p = 0.62) in our patients. The MBE, EDEMA, and modified EDEMA scores had the AUCs of 0.855 (95 % CI 0.818-0.898), 0.782 (95 % CI 0.727-0.837) and 0.878 (95 % CI 0.844-0.919) respectively. The MBE (NRI, 0.33; 95 % CI, 0.11-0.56, p = 0.003 and IDI, 0.11; 95 % CI, 0.03-0.18; p = 0.004) and modified EDEMA scores (NRI, 1.10; 95 % CI, 0.94-1.26; p < 0.001 and IDI, 0.17; 95 % CI, 0.13-0.20, p < 0.001) showed better performance than the EDEMA score. DCA demonstrated that the modified EDEMA score outperformed the other two scores, possessing heightened clinical usefulness. CONCLUSIONS: The MBE, EDEMA, and modified EDEMA scores for predicting MCE are also applicable in non-revascularization LHI patients within 48 h of onset. Both the MBE and modified EDEMA scores demonstrated higher predictive validity as predictive tools for MCE in LHI patients than the EDEMA score. Furthermore, the modified EDEMA score could be a suitable prediction tool in Chinese patients for its excellent clinical utility.

3D slicer-based calculation of hematoma irregularity index for predicting hematoma expansion in intracerebral hemorrhage.

BACKGROUND: Irregular hematoma is considered as a risk sign of hematoma expansion. The aim of this study was to quantify hematoma irregularity with computed tomography based on 3D Slicer. METHODS: Patients with spontaneous intracerebral hemorrhage who underwent an initial and subsequent non-contrast computed tomography (CT) at a single medical center between January 2019 to January 2020 were retrospectively identified. The Digital Imaging and Communication in Medicine (DICOM) standard images were loaded into the 3D Slicer, and the surface area (S) and volume (V) of hematoma were calculated. The hematoma irregularity index (HII) was defined as [Formula: see text]. Logistic regression analyses and receiver operating characteristic (ROC) curve analysis were performed to assess predictive performance of HII. RESULTS: The enrolled patients were divided into those with hematoma enlargement (n = 36) and those without the enlargement (n = 57). HII in hematoma expansion group was 130.4 (125.1-140.0), and the index in non-enlarged hematoma group was 118.6 (113.5-122.3). There was significant difference in HII between the two groups (P < 0.01). Multivariate logistic regression analysis revealed that the HII was significantly associated with hematoma expansion before (odds ratio = 1.203, 95% confidence interval [CI], 1.115-1.298; P < 0.001) and after adjustment for age, hematoma volume, Glasgow Coma Scale score (odds ratio = 1.196, 95% CI, 1.102-1.298, P < 0.001). The area under the ROC curve was 0.86 (CI, 0.78-0.93, P < 0.01), and the best cutoff of HII for predicting hematoma growth was 123.8. CONCLUSION: As a quantitative indicator of irregular hematoma, HII can be calculated using the 3D Slicer. And the HII was independently correlated with hematoma expansion.

Defect of branched-chain amino acid metabolism promotes the development of Alzheimer's disease by targeting the mTOR signaling.

Diabetes is a risk factor for Alzheimer's disease (AD) in humans. Branched-chain amino acids (BCAAs, namely valine, leucine, and isoleucine) metabolic defect is observed in human diabetes, which is associated with insulin resistance. But whether BCAAs connect diabetes and AD remains unknown. Here, we show that BCAA metabolic defect may be one of the drivers of AD. BCAA levels were increased in the blood in human patients and mice with diabetes or AD. BCAA-enriched diet promoted the development of AD in mice as evidenced by the behavior and pathological analysis. Branched-chain amino acid transaminase 1 and 2 (BCAT1 and BCAT2) are the two enzymes for the first step metabolism of BCAAs by catalyzing BCAAs to generate branched-chain ketoacids. The expression of Bcat1 but not Bcat2 was significantly down-regulated in the brain tissues of diabetic, aged, and AD mice. Leucine up-regulated the phosphorylation of Tau but not affected the accumulation of amyloid ß in the brain tissues or isolated neurons. In addition, knockdown of the expression of Bcat1, which would result in the accumulation of BCAAs, led to the same phenotype as BCAAs supplement in neurons. Interestingly, leucine supplement or Bcat1 knockdown promoted the activation of the mTOR signaling in the brains of AD mice or neurons. Subsequently, mTOR was critically involved in leucine and Bcat1 knockdown-mediated phosphorylation of Tau. Taken together, our findings demonstrated that diabetes-related BCAA accumulation in the brain tissues led to the phosphorylation of Tau and, subsequently, the development of diabetes-related AD.

FTO is involved in Alzheimer's disease by targeting TSC1-mTOR-Tau signaling.

Diabetes and obesity are commonly associated with Alzheimer's disease (AD). Accumulating evidence show that insulin signaling defects are protentional upstream driver of AD. However, the mechanism by which diabetes and insulin signaling defects contribute to AD remains unknown. Here we show that Fat mass and obesity-associated protein (FTO) is involved the insulin defects-associated AD. Defective insulin signaling in diabetes and obesity in human and mice activated Fto in the brain tissues. Lentivirus-mediated knockdown of Fto reduced the phosphorylation of Tau protein whereas overexpression of FTO promoted the level of phosphorylated Tau in neurons. Mechanism study demonstrated that FTO activated the phosphorylation of Tau in a mTOR-dependent manner because FTO activated mTOR and its downstream signaling and rapamycin blocked FTO-mediated phosphorylation of Tau. FTO promoted the activation of mTOR by increasing the mRNA level of TSC1 but not TSC2, the upstream inhibitor of mTOR. Finally, we found that conditional knockout of Fto in the neurons reduced the cognitive deficits in 3xTg AD mice. Collectively, our evidence demonstrated that FTO is critically involved in insulin defects-related AD.

cAMP/PKA signaling pathway contributes to neuronal apoptosis via regulating IDE expression in a mixed model of type 2 diabetes and Alzheimer's disease.

Type 2 diabetes (T2D) may play a relevant role in the development of Alzheimer's disease (AD), however, the underlying mechanism was not clear yet. We developed an animal model presenting both AD and T2D, morris water maze (MWM) test and recognition task were performed to trace the cognitive function. Fasting plasma glucose (FPG) and oral glucose tolerance test (OGTT) were determined to trace the metabolism evolution. TUNEL assay and apoptosis-related protein levels were analyzed for the detection of neuronal apoptosis. Cyclic adenosine monophosphate (cAMP) agonist bucladesine or protein kinase (PKA) inhibitor H-89 were used to determine the effects of cAMP/PKA signaling pathway on IDE expression and neuronal apoptosis. The results showed that T2D contributes to the AD progress by accelerating and worsening spatial memory and recognition dysfunctions. Metabolic parameters and glucose tolerance were significantly changed in the presence of the AD and T2D. The significantly induced neuronal apoptosis and increased pro-apoptotic proteins in mice with AD and T2D were also observed. We showed the decreased expression level of IDE and the activating of cAMP/PKA signaling pathway in AD and T2D mice. Further studies indicated that cAMP agonist decreased the expression level of IDE and induced the neuronal apoptosis in mice with AD and T2D; whereas PKA inhibitor H-89 treatment showed the completely opposite results. Our study indicated that, in the T2D and AD mice, cAMP/PKA signaling pathway and IDE may participate in the contribute role of T2D in accelerating the pathological process of AD via causing the accumulation of Aß and neuronal apoptosis.

Insulin degrading enzyme contributes to the pathology in a mixed model of Type 2 diabetes and Alzheimer's disease: possible mechanisms of IDE in T2D and AD.

Insulin degrading enzyme (IDE) is believed to act as a junction point of Type 2 diabetes (T2D) and Alzheimer's disease (AD); however, the underlying mechanism was not completely clear yet. Transgenic APPSwe/PS1 mice were used as the AD model and were treated with streptozocin/streptozotocin (STZ) to develop a mixed mice model presenting both AD and T2D. Morris Water Maze (MWM) and recognition task were performed to trace the cognitive function. The detection of fasting plasma glucose (FPG) and plasma insulin concentration, and oral glucose tolerance test (OGTT) were used to trace the metabolism evolution. Aß40 and Aß42 were quantified by colorimetric ELISA kits. The mRNA or protein expression levels were determined by quantitative real-time RT-PCR and Western blotting analysis respectively. T2D contributes to the AD progress by accelerating and worsening spatial learning and recognition impairments. Metabolic parameters and glucose tolerance were significantly changed in the presence of the AD and T2D. The expression levels of IDE, PPARγ, and AMPK were down-regulated in mice with AD and T2D. PPARγ activator rosiglitazone (RSZ) or AMPK activator AICAR increased the expression level of IDE and decreased Aß levels in mice with AD and T2D. RSZ or AICAR treatment also alleviated the spatial learning and recognition impairments in AD and T2D mice. Our results found that, in the mice with T2D and AD, the activators of PPARγ/AMPK signaling pathway significantly increased the expression level of IDE, and decreased the accumulation of Aß40 and Aß42, as well as alleviated the spatial learning and recognition impairments.