Background: Functional outcomes after acute ischemic stroke are of great concern to patients and their families, as well as physicians and surgeons who make the clinical decisions. We developed machine learning (ML)-based functional outcome prediction models in acute ischemic stroke. Methods: This retrospective study used a prospective cohort database. A total of 1066 patients with acute ischemic stroke between January 2019 and March 2021 were included. Variables such as demographic factors, stroke-related factors, laboratory findings, and comorbidities were utilized at the time of admission. Five ML algorithms were applied to predict a favorable functional outcome (modified Rankin Scale 0 or 1) at 3 months after stroke onset. Results: Regularized logistic regression showed the best performance with an area under the receiver operating characteristic curve (AUC) of 0.86. Support vector machines represented the second-highest AUC of 0.85 with the highest F1-score of 0.86, and finally, all ML models applied achieved an AUC > 0.8. The National Institute of Health Stroke Scale at admission and age were consistently the top two important variables for generalized logistic regression, random forest, and extreme gradient boosting models. Conclusions: ML-based functional outcome prediction models for acute ischemic stroke were validated and proven to be readily applicable and useful.

Background: Spinal cord infarction (SCI) is a rare disease and its early diagnosis is challenging. Here, we described the clinical features and imaging findings of SCI, and assessed the results of evoked potential (EP) studies to elucidate their diagnostic role in the early stage of SCI. Methods: We retrospectively analyzed 14 patients who had spontaneous SCI. The demographic, neurological, and temporal profiles of the SCI patients were identified. We reviewed the imaging findings and assessed the changes in them over time. To review EP, central motor conduction time (CMCT) and somatosensory evoked potential (SEP) values were obtained. We also enrolled 15 patients with transverse myelitis (TM), and compared the clinical, radiological and electrophysiological features between SCI and TM patients. Results: The ages of the SCI patients ranged from 54 to 73 years. Nine patients (64.3%) showed nadir deficits within 6 h. The most common type of clinical visit was via the emergency center. Nine patients (64.3%) presented with peri-onset focal pain. The median initial modified Rankin scale score was 3. For 9 patients (64.3%), initial T2 imaging findings were negative, but subsequent diffusion weighed imaging (DWI) showed diffusion restriction. Vertebral body infarction was observed in 5 patients (35.7%). EP data were available for 10 SCI patients. All 8 patients who had their CMCT measured showed abnormalities. Among them, motor evoked potentials were not evoked in 6 patients at all. SEP was measured in 10 patients, and 9 of them showed abnormalities; one of them showed no SEP response. For 5 patients, the EP studies were done prior to DWI, and all the patients showed definite abnormalities. The abnormalities in the EP findings of the SCI patients were more profound than those of the TM patients, even though the duration from the onset to the start of the study was much shorter for SCI patients. Conclusion: SCI can be diagnosed based on typical clinical manifestations and appropriate imaging studies. Our study also indicates that immediate sensory and motor EP study can have an adjuvant diagnostic role in the hyperacute stage of SCI, and can improve the accuracy of diagnosis.

This study aimed to evaluate the behavioral and disease-related characteristics of patients with acute stroke during the Coronavirus disease (COVID-19) pandemic. This retrospective study was conducted using the Korean Stroke Registry database from a single cerebrovascular specialty hospital. We categorized the COVID-19 pandemic (February 2020 to June 2021) into three waves according to the number of COVID-19 cases recorded and the subjective fear index of the general population and matched them with the corresponding pre-COVID-19 (January 2019 to January 2020) periods. The total number of acute stroke hospitalizations during the pre-COVID-19 and COVID-19 periods was 402 and 379, respectively. The number of acute stroke hospitalizations recorded during the regional outbreak of COVID-19 was higher than that recorded during the corresponding pre-COVID-19 period (97 vs. 80). Length of hospital stay was significantly longer during the COVID-19 pandemic than during the pre-COVID-19 period (11.1 and 8.5 days, respectively; p = 0.003). There were no significant differences in the time from onset to hospital arrival, rate of acute intravenous/intra-arterial (IV/IA) treatments, and door-to-IV/IA times between the pre-COVID-19 and COVID-19 periods. This study suggests that specialty hospitals can effectively maintain the quality of healthcare through the management of acute time-dependent diseases, even during pandemics.

Background: Efficient and accurate clinical data management is crucial for stroke care and research; however, for complex stroke cohorts, manual data entry is often complicated by high human error rates and significant inefficiency. This study addressed this gap by developing and evaluating an automated system for constructing high-quality stroke cohorts from electronic health records (EHRs). Methods: This retrospective cohort study was conducted at a single specialty hospital, comparing manual data entry (January–June 2022) with an automated system (January–June 2024). The system uses C# and secure SQL protocols for direct EHR integration. We developed an automated system using the C# programming language to extract 133 items covering the full hospitalization period (from admission to discharge) from EHRs, aligning with the Korean Stroke Registry, the Registry of Stroke Care Quality, and national quality assessment programs. The system’s effectiveness was evaluated by assessing the data entry time, data error rate, and medical record completion rate and comparing the automated method’s performance against conventional data entry. Results: The automated system significantly reduced the data entry time from 35 min to 19 s per patient. Furthermore, the data error rate decreased from 2.32% to 0.15% (p < 0.001), and the rate of missing medical records decreased from 28.9% to 16.2% (p < 0.001). Conclusions: The proposed clinical data collection and cohort construction system effectively improved data quality and efficiency compared to the manual method. This system provides a reliable and scalable data infrastructure that could facilitate research on stroke and quality improvement initiatives.