For nearly 20 years, the prevalent view has been that women who carry copies of the ε4 allele of the apolipoprotein E (APOE) gene have a greater risk of developing Alzheimer disease (AD) than men with the same number of copies.¹ The ε4 allele is the main genetic risk factor for late-onset Alzheimer disease (AD),² and sex-based differences in AD risk have important implications for treatment trials, diagnostics, and therapeutics.³ Additionally, the sex-dependent relationship between APOE and mild cognitive impairment (MCI), which is often a transitional phase from cognitively normal (NL) aging to dementia,⁴ is unclear. Studies are in general agreement that the APOE ε4 allele is a risk factor for developing MCI,^5-11 but there is controversy as to whether it increases^10,12-14 or does not increase^9,11,15,16 the risks of transitioning from MCI to AD or dementia. The 3 most common alleles of the APOE gene are ε2, ε3, and ε4; whereas carrying the ε4 allele increases one’s risk of developing AD, the ε2 allele conversely has a putative protective effect that is associated with longevity and a lower AD risk.¹⁷

Brain computed tomography (CT) is commonly used for evaluating the cerebral condition, but immediately and accurately interpreting emergent brain CT images is tedious, even for skilled neuroradiologists. Deep learning networks are commonly employed for medical image analysis because they enable efficient computer-aided diagnosis. This study proposed the use of convolutional neural network (CNN)-based deep learning models for efficient classification of strokes based on unenhanced brain CT image findings into normal, hemorrhage, infarction, and other categories. The included CNN models were CNN-2, VGG-16, and ResNet-50, all of which were pretrained through transfer learning with various data sizes, mini-batch sizes, and optimizers. Their performance in classifying unenhanced brain CT images was tested thereafter. This performance was then compared with the outcomes in other studies on deep learning–based hemorrhagic or ischemic stroke diagnoses. The results revealed that among our CNN-2, VGG-16, and ResNet-50 analyzed by considering several hyperparameters and environments, the CNN-2 and ResNet-50 outperformed the VGG-16, with an accuracy of 0.9872; however, ResNet-50 required a longer time to present the outcome than did the other networks. Moreover, our models performed much better than those reported previously. In conclusion, after appropriate hyperparameter optimization, our deep learning–based models can be applied to clinical scenarios where neurologist or radiologist may need to verify whether their patients have a hemorrhage stroke, an infarction, and any other symptom.

A midline shift (MLS) is an important clinical indicator for intracranial hemorrhage. In this study, we proposed a robust, fully automatic neural network-based model for the detection of MLS and compared it with MLSs drawn by clinicians; we also evaluated the clinical applications of the fully automatic model. We recruited 300 consecutive non-contrast CT scans consisting of 7269 slices in this study. Six different types of hemorrhage were included. The automatic detection of MLS was based on modified Keypoint R-CNN with keypoint detection followed by training on the ResNet-FPN-50 backbone. The results were further compared with manually drawn outcomes and manually defined keypoint calculations. Clinical parameters, including Glasgow coma scale (GCS), Glasgow outcome scale (GOS), and 30-day mortality, were also analyzed. The mean absolute error for the automatic detection of an MLS was 0.936 mm compared with the ground truth. The interclass correlation was 0.9899 between the automatic method and MLS drawn by different clinicians. There was high sensitivity and specificity in the detection of MLS at 2 mm (91.7%, 80%) and 5 mm (87.5%, 96.7%) and MLSs greater than 10 mm (85.7%, 97.7%). MLS showed a significant association with initial poor GCS and GCS on day 7 and was inversely correlated with poor 30-day GOS (p < 0.001). In conclusion, automatic detection and calculation of MLS can provide an accurate, robust method for MLS measurement that is clinically comparable to the manually drawn method.

Background: Differences of treatment outcome between full or reduced dose of tissue plasminogen activator (tPA) for bridge mechanical thrombectomy (MT) in the extended time window have not been clearly established. We aimed to present real-world results of bridge MT with different tPA dosages in the standard and extended windows. Materials and methods: Patients with anterior circulation stroke treated with MT between 2017 and 2021 at two stroke referral centers were retrospectively reviewed. Bridge MT with tPA were categorized as full (0.9 mg/kg) or reduced (<0.9 mg/kg) dose. Standard window (SW) cohort was defined as MT performed within 6 h of acute ischemic stroke onset, while those beyond 6 h as the extended window (EW) cohort. 90 days Modified Rankin Scale (mRS) score, technical treatment success, in-hospital mortality, and post-treatment hemorrhage were analyzed. Results: A total of 423 patients met the inclusion criteria, 218 of which treated in the SW, while 205 treated in the EW. Within the SW cohort, the full-dose tPA group demonstrated a higher proportion of good functional outcome (GFO) at 90 days (mRS0-3) versus reduced (49% vs 21%, p = 0.0358). The overall GFO of SW was higher than that of the EW cohort (33% vs 20%, p = 0.0480). Within the EW cohort, GFO was similar between full and reduced dose groups. Successful reperfusion rate was lower in SW versus EW cohorts (39% vs 58%, p = 0.0199). Conclusion: In real-world practice, the GFO of bridge MT is better than MT alone. The tPA dosage is not a determining factor of GFO in EW MT.