Search

Foot drop can have a variety of causes, including the common peroneal nerve (CPN) injuries, and is often difficult to diagnose. We aimed to develop a deep learning-based algorithm that can classify foot drop with CPN injury in patients with knee MRI axial images only. In this retrospective study, we included 945 MR image data from foot drop patients confirmed with CPN injury in electrophysiologic tests (n = 42), and 1341 MR image data with non-traumatic knee pain (n = 107). Data were split into training, validation, and test datasets using a 8:1:1 ratio. We used a convolution neural network-based algorithm (EfficientNet-B5, ResNet152, VGG19) for the classification between the CPN injury group and the others. Performance of each classification algorithm used the area under the receiver operating characteristic curve (AUC). In classifying CPN MR images and non-CPN MR images, EfficientNet-B5 had the highest performance (AUC = 0.946), followed by the ResNet152 and the VGG19 algorithms. On comparison of other performance metrics including precision, recall, accuracy, and F1 score, EfficientNet-B5 had the best performance of the three algorithms. In a saliency map, the EfficientNet-B5 algorithm focused on the nerve area to detect CPN injury. In conclusion, deep learning-based analysis of knee MR images can successfully differentiate CPN injury from other etiologies in patients with foot drop. [ABSTRACT FROM AUTHOR]

Glycemic variability has been shown to be correlated more with oxidative stress than chronic hyperglycemia. We evaluated the impact of pre-stroke glycemic variability measured using glycated albumin (GA) on hematoma expansion and clinical outcomes following spontaneous intracerebral hemorrhage (ICH). We consecutively enrolled 343 patients with ICH for 72 months using a single-center registry database. The primary outcome measure was hematoma expansion. The secondary outcome measures were early neurological deterioration (END), 1-month mortality, and 3-month poor functional outcomes (modified Rankin scale score of 4–6). The patients were divided into two groups based on pre-stroke glycemic variability: a higher GA group (GA ≥ 16.0%) and a lower GA group (GA < 16.0%). During the study period, there were 63 (18.4%) events of hematoma expansion, 61 (17.8%) of END, 45 (13.1%) of 1-month mortality, and 45 (13.1%) of 3-month poor functional outcomes after ICH. The higher GA group (36.4%) had higher rates of hematoma expansion, END, 1-month mortality, and 3-month poor functional outcomes than the lower GA group. Multivariate analysis showed that a higher GA level was significantly associated with increased hematoma expansion (adjusted odds ratio 5.83; 95% confidence interval [CI] 2.58–13.19, p < 0.001). The area under the receiver operating characteristic curve of GA (0.83; 95% CI 0.48–0.65) for predicting hematoma expansion was higher than that of glycated hemoglobin (0.57; 95% CI 0.48–0.65, p for DeLong's pairwise comparison < 0.001). Higher GA levels could be a reliable marker for predicting hematoma expansion and poor outcomes following ICH. [ABSTRACT FROM AUTHOR]

There is little knowledge of the effect of inflammatory markers on the prognoses of hematoma expansion (HE) in patients with intracranial hemorrhage (ICH). We evaluated the impact of neutrophil–lymphocyte ratio (NLR) and platelet–lymphocyte ratio (PLR) on HE and worse outcomes after acute ICH. This study included 520 consecutive patients with ICH from the registry database enrolled over 80 months. Patients' whole blood samples were collected upon arrival in the emergency department. Brain computed tomography scans were performed during hospitalization and repeated at 24 h and 72 h. The primary outcome measure was HE, defined as relative growth >33% or absolute growth <6 mL. A total of 520 patients were enrolled in this study. Multivariate analysis showed that NLR and PLR were associated with HE (NLR: odds ratio [OR], [95% CI] = 1.19 [1.12–1.27], p < 0.001; PLR: OR, [95% CI] = 1.01 [1.00–1.02], p = 0.04). Receiver operating characteristic curve analysis revealed that NLR and PLR could predict HE (AUC of NLR: 0.84, 95% CI [0.80–0.88], p < 0.001; AUC of PLR: 0.75 95% CI [0.70–0.80], p < 0.001). The cut-off value of NLR for predicting HE was 5.63, and that of PLR was 23.4. Higher NLR and PLR values increase HE risk in patients with ICH. NLR and PLR were reliable for predicting HE after ICH. [ABSTRACT FROM AUTHOR]

Objectives: We evaluated the impact of malnutrition as estimated by the controlling nutritional status (CONUT) score and prognostic nutritional index (PNI) on hemorrhagic transformation (HT) and stroke outcomes after intravenous thrombolysis (IVT). Materials and methods: Using a multicenter registry database, we enrolled 808 patients with acute ischemic stroke who received IVT between August 2013 and May 2021. We defined malnutrition as a CONUT score ≥ 2 and low PNI. The primary outcome measure was the occurrence of symptomatic HT contributing to early neurologic deterioration (END-SHT) after IVT. Multivariable analysis was performed to analyze the association between CONUT score, PNI, and END-SHT after IVT. Results: The rate of END-SHT was higher with increasing CONUT scores and PNI values. In the multivariable analysis, CONUT score ≥ 5 and low PNI were significantly associated with END-SHT (odds ratio [95% confidence interval], CONUT score ≥ 5: 12.23 [2.41–62.07], p = 0.003; low PNI: 4.98 [1.76–14.09], p = 0.003). The receiver operating characteristic curve showed that both the CONUT score and PNI had good predictive ability. The cutoff values for CONUT and PNI were 5 and 42.3, respectively, for END-SHT. Conclusion: Malnutrition, as denoted by a higher CONUT score and lower PNI, was associated with END-SHT. The joint application of both nutritional markers could be useful in predicting END-SHT after IVT. [ABSTRACT FROM AUTHOR]

Although the potential relationship between headaches, particularly migraine, and peripheral inflammatory markers (PIMs) has been investigated, it is unclear whether PIMs are involved in the pathogenesis of migraine or can differentiate it from non-migraine headaches (nMHs). Using 10 years of data from the Smart Clinical Data Warehouse, patients who visited the neurology outpatient department (OPD) within 30 days after visiting the emergency room (ER) for headaches were divided into migraine and nMH groups, the PIMs were compared including the neutrophil-to-lymphocyte (NLR), monocyte-to-lymphocyte (MLR), platelet-to-lymphocyte (PLR) ratios, and neutrophil-to-monocyte ratio (NMR). Of the 32,761 patients who visited the ER for headaches, 4005 patients visited the neurology OPD within 30 days. There were significant increases in the NLR, MLR, and NMR, but a lower PLR in the migraine and nMH groups than the controls. The NMR was significantly higher in the migraine than the nMH group. A receiver operating characteristic curve analysis showed that the ability of the NLR and NMR to differentiate between migraine and nMHs was poor, whereas it was fair between the migraine groups and controls. The elevated PIMs, particularly the NLR and NMR, during headache attacks in migraineurs suggest that inflammation plays a role in migraine and PIMs may be useful for supporting a migraine diagnosis. [ABSTRACT FROM AUTHOR]

We evaluated the impact of prestroke glycemic variability estimated by glycated albumin (GA) on symptomatic hemorrhagic transformation (SHT) in patients with intravenous thrombolysis (IVT). Using a multicenter database, we consecutively enrolled acute ischemic stroke patients receiving IVT. A total of 378 patients were included in this study. Higher GA was defined as GA ≥ 16.0%. The primary outcome measure was SHT. Multivariate regression analysis and a receiver operating characteristic curve were used to assess risks and predictive ability for SHT. Among the 378 patients who were enrolled in this study, 27 patients (7.1%) had SHT as defined by the Safe Implementation of Thrombolysis in Stroke-Monitoring Study (SHTSITS). The rate of SHTSITS was higher in the higher GA group than in the lower GA group (18.0% vs. 1.6%, p < 0.001). A higher GA level (GA ≥ 16.0%) significantly increased the risk of SHTSITS (adjusted odds ratio [OR], [95% confidence interval, CI], 12.57 [3.08–41.54]) in the logistic regression analysis. The predictive ability of the GA level for SHTSITS was good (AUC [95% CI]: 0.83 [0.77–0.90], p < 0.001), and the cutoff value of GA in SHT was 16.3%. GA was a reliable predictor of SHT after IVT in acute ischemic stroke in this study. [ABSTRACT FROM AUTHOR]

Hemorrhagic transformation (HT) is one of the leading causes of a poor prognostic marker after acute ischemic stroke (AIS). We compared the performances of the several machine learning (ML) algorithms to predict HT after AIS using only structured data. A total of 2028 patients with AIS, who were admitted within seven days of symptoms onset, were included in this analysis. HT was defined based on the criteria of the European Co-operative Acute Stroke Study-II trial. The whole dataset was randomly divided into a training and a test dataset with a 7:3 ratio. Binary logistic regression, support vector machine, extreme gradient boosting, and artificial neural network (ANN) algorithms were used to assess the performance of predicting the HT occurrence after AIS. Five-fold cross validation and a grid search technique were used to optimize the hyperparameters of each ML model, which had its performance measured by the area under the receiver operating characteristic (AUROC) curve. Among the included AIS patients, the mean age and number of male subjects were 69.6 years and 1183 (58.3%), respectively. HT was observed in 318 subjects (15.7%). There were no significant differences in corresponding variables between the training and test dataset. Among all the ML algorithms, the ANN algorithm showed the best performance in terms of predicting the occurrence of HT in our dataset (0.844). Feature scaling including standardization and normalization, and the resampling strategy showed no additional improvement of the ANN's performance. The ANN-based prediction of HT after AIS showed better performance than the conventional ML algorithms. Deep learning may be used to predict important outcomes for structured data-based prediction. [ABSTRACT FROM AUTHOR]

Background: Studies assessing the prognostic effect of inflammatory markers of blood cells on the outcomes of patients with acute ischemic stroke treated with endovascular treatment (EVT) are sparse. We evaluated whether the neutrophil-to-lymphocyte ratio (NLR) and platelet-to-lymphocyte ratio (PLR) affect reperfusion status in patients receiving EVT. Methods: Using a multicenter registry database, 282 patients treated with EVT were enrolled in this study. The primary outcome measure was unsuccessful reperfusion rate after EVT defined by thrombolysis in cerebral infarction grades 0–2a. Logistic regression analysis was performed to analyze the association between NLR/PLR and unsuccessful reperfusion rate after EVT. Results: Both NLR and PLR were higher in the unsuccessful reperfusion group than in the successful reperfusion group (p < 0.001). Multivariate analysis showed that both NLR and PLR were significantly associated with unsuccessful reperfusion (adjusted odds ratio (95% confidence interval): 1.11 (1.04–1.19), PLR: 1.004 (1.001–1.01)). The receiver operating characteristic curve showed that the predictive ability of both NLR and PLR was close to good (area under the curve (AUC) of NLR: 0.63, 95% CI (0.54–0.72), p < 0.001; AUC of PLR: 0.65, 95% CI (0.57–0.73), p < 0.001). The cutoff values of NLR and PLR were 6.2 and 103.6 for unsuccessful reperfusion, respectively. Conclusion: Higher NLR and PLR were associated with unsuccessful reperfusion after EVT. The combined application of both biomarkers could be useful for predicting outcomes after EVT. [ABSTRACT FROM AUTHOR]

Objectives: This study aimed to investigate whether transfusions and hemoglobin variability affects the outcome of stroke after an acute ischemic stroke (AIS). Methods: We studied consecutive patients with AIS admitted in three tertiary hospitals who received red blood cell (RBC) transfusion (RBCT) during admission. Hemoglobin variability was assessed by minimum, maximum, range, median absolute deviation, and mean absolute change in hemoglobin level. Timing of RBCT was grouped into two categories: admission to 48 h (early) or more than 48 h (late) after hospitalization. Late RBCT was entered into multivariable logistic regression model. Poor outcome at three months was defined as a modified Rankin Scale score ≥3. Results: Of 2698 patients, 132 patients (4.9%) received a median of 400 mL (interquartile range: 400–840 mL) of packed RBCs. One-hundred-and-two patients (77.3%) had poor outcomes. The most common cause of RBCT was gastrointestinal bleeding (27.3%). The type of anemia was not associated with the timing of RBCT. Late RBCT was associated with poor outcome (odd ratio (OR), 3.55; 95% confidence interval (CI), 1.43–8.79; p-value = 0.006) in the univariable model. After adjusting for age, sex, Charlson comorbidity index, and stroke severity, late RBCT was a significant predictor (OR, 3.37; 95% CI, 1.14–9.99; p-value = 0.028) of poor outcome at three months. In the area under the receiver operating characteristics curve comparison, addition of hemoglobin variability indices did not improve the performance of the multivariable logistic model. Conclusion: Late RBCT, rather than hemoglobin variability indices, is a predictor for poor outcome in patients with AIS. [ABSTRACT FROM AUTHOR]