Background: Prioritizing patients in need of intensive care is necessary to reduce the mortality rate during the COVID-19 pandemic. Although several scoring methods have been introduced, many require laboratory or radiographic findings that are not always easily available. Objective: The purpose of this study was to develop a machine learning model that predicts the need for intensive care for patients with COVID-19 using easily obtainable characteristics—baseline demographics, comorbidities, and symptoms. Methods: A retrospective study was performed using a nationwide cohort in South Korea. Patients admitted to 100 hospitals from January 25, 2020, to June 3, 2020, were included. Patient information was collected retrospectively by the attending physicians in each hospital and uploaded to an online case report form. Variables that could be easily provided were extracted. The variables were age, sex, smoking history, body temperature, comorbidities, activities of daily living, and symptoms. The primary outcome was the need for intensive care, defined as admission to the intensive care unit, use of extracorporeal life support, mechanical ventilation, vasopressors, or death within 30 days of hospitalization. Patients admitted until March 20, 2020, were included in the derivation group to develop prediction models using an automated machine learning technique. The models were externally validated in patients admitted after March 21, 2020. The machine learning model with the best discrimination performance was selected and compared against the CURB-65 (confusion, urea, respiratory rate, blood pressure, and 65 years of age or older) score using the area under the receiver operating characteristic curve (AUC). Results: A total of 4787 patients were included in the analysis, of which 3294 were assigned to the derivation group and 1493 to the validation group. Among the 4787 patients, 460 (9.6%) patients needed intensive care. Of the 55 machine learning models developed, the XGBoost model revealed the highest discrimination performance. The AUC of the XGBoost model was 0.897 (95% CI 0.877-0.917) for the derivation group and 0.885 (95% CI 0.855-0.915) for the validation group. Both the AUCs were superior to those of CURB-65, which were 0.836 (95% CI 0.825-0.847) and 0.843 (95% CI 0.829-0.857), respectively. Conclusions: We developed a machine learning model comprising simple patient-provided characteristics, which can efficiently predict the need for intensive care among patients with COVID-19.

Kim HC, et al. Clin Hypertens. 2025 Mar;31(1):e11. https://doi.org/10.5646/ch.2025.31.e11

Background and Purpose: Patients with acute stroke are often accompanied by comorbidities, such as active cancer. However, adequate treatment guidelines are not available for these patients. The purpose of this study was to evaluate the association between cancer and the outcomes of reperfusion therapy in patients with stroke. Methods: We compared treatment outcomes in patients who underwent reperfusion therapy, using a nationwide reperfusion therapy registry. We divided the patients into 3 groups according to cancer activity: active cancer, nonactive cancer, and without a history of cancer. We investigated reperfusion processes, 24-hour neurological improvement, adverse events, 3-month functional outcome, and 6-month survival and related factors after reperfusion therapy. Results: Among 1338 patients who underwent reperfusion therapy, 62 patients (4.6%) had active cancer, 78 patients (5.8%) had nonactive cancer, and 1198 patients (89.5%) had no history of cancer. Of the enrolled patients, 969 patients received intravenous thrombolysis and 685 patients underwent endovascular treatment (316 patients received combined therapy). Patients with active cancer had more comorbidities and experienced more severe strokes; however, they showed similar 24-hour neurological improvement and adverse events, including cerebral hemorrhage, compared with the other groups. Although the functional outcome at 3 months was poorer than the other groups, 36.4% of patients with active cancer showed functional independence. Additionally, 52.9% of the patients with determined stroke etiology showed functional independence despite active cancer. During the 6-month follow-up, 46.6% of patients with active cancer died, and active cancer was independently associated with poor survival (hazard ratio, 3.973 [95% CI, 2.528–6.245]). Conclusions: In patients with active cancer, reperfusion therapy showed similar adverse events and short-term outcomes to that of other groups. While long-term prognosis was worse in the active cancer group than the nonactive cancer groups, not negligible number of patients had good functional outcomes, especially those with determined stroke mechanisms.

Background: The purpose of the RAFAS (Risk and Benefits of Urgent Rhythm Control of Atrial Fibrillation in Patients With Acute Stroke) trial was to explore the risks and benefits of early rhythm control in patients with newly documented atrial fibrillation (AF) during an acute ischemic stroke (IS). Method and Results: An open‐label, randomized, multicenter trial design was used. If AF was diagnosed, the patients in the early rhythm control group started rhythm control within 2 months after the occurrence of an IS, unlikely the usual care. The primary end points were recurrent IS within 3 and 12 months. The secondary end points were a composite of all deaths, unplanned hospitalizations from any cause, and adverse arrhythmia events. Patients (n=300) with AF and an acute IS (63.0% men, aged 69.6±8.5 years; 51.2% with paroxysmal AF) were randomized 2:1 to early rhythm control (n=194) or usual care (n=106). A total of 273 patients excluding those lost to follow‐up (n=27) were analyzed. The IS recurrences did not differ between the groups within 3 months of the index stroke (2 [1.1%] versus 4 [4.2%]; hazard ratio [HR], 0.257 [log‐rank P =0.091]) but were significantly lower in the early rhythm control group at 12 months (3 [1.7%] versus 6 [6.3%]; HR, 0.251 [log‐rank P =0.034]). Although the rates of overall mortality, any cause of hospitalizations (25 [14.0%] versus 16 [16.8%]; HR, 0.808 [log‐rank P =0.504]), and arrhythmia‐related adverse events (5 [2.8%] versus 1 [1.1%]; HR, 2.565 [log‐rank P =0.372]) did not differ, the proportion of sustained AF was lower in the early rhythm control group than the usual care group (60 [34.1%] versus 59 [62.8%], P <0.001) in 12 months. Conclusions: The early rhythm control strategy of an acute IS decreased the sustained AF and recurrent IS within 12 months without an increase in the composite adverse outcomes. Registration: URL: https://www.clinicaltrials.gov ; Unique identifier: NCT 02285387.

Background and Objectives: A machine learning technique for identifying hidden coronary artery disease (CAD) might be useful. We developed and validated machine learning models to predict patients with hidden CAD and assess long-term outcomes in patients with acute ischemic stroke. Methods: Multidetector coronary computed tomography was performed for patients without known history of CAD. Primary outcomes were defined as having any degree of CAD and having obstructive CAD (≥50% stenosis). Demographic variables, risk factors, laboratory results, Trial of ORG 10172 in Acute Stroke Treatment (TOAST) classification, NIH Stroke Scale score, blood pressure, and carotid artery stenosis were used to develop and validate machine learning models to predict CAD. Area under the receiver operating characteristic curves (AUC) was calculated for performance analysis, and Kaplan–Meier and Cox survival analyses of long-term outcomes were performed. Major adverse cardiovascular events (MACE) were defined as ischemic stroke, myocardial infarction, unstable angina, urgent coronary revascularization, and cardiovascular mortality. Results: Overall, 1,710 patients were included for the training dataset and 348 patients for the validation dataset. An Extreme Gradient Boosting model was developed to predict any degree of CAD, which showed an AUC of 0.763 (95% CI 0.711–0.814) on validation. A logistic regression model was used to predict obstructive CAD and had an AUC of 0.714 (95% CI 0.692–0.799). During the first 5 years of follow-up, MACE occurred more frequently when predicted of any CAD (P = 0.022) or obstructive CAD (P < 0.001). Cox proportional analysis showed that the hazard ratio of MACE was 1.5 (95% CI 1.1–2.2; P = 0.016) when predicted of any CAD, whereas it was 1.9 (95% CI 1.3–2.6; P < 0.001) for obstructive CAD. Discussion: We demonstrated that machine learning may help identify hidden CAD in patients with acute ischemic stroke. Long-term outcomes were also associated with prediction results. Classification of Evidence: This study provides Class II evidence that in patients with acute ischemic stroke with CAD risk factors but no known history of CAD, a machine learning model predicts CAD on multidetector coronary computed tomography with an AUC of 0.763 (95% CI 0.711-0.814).

Artificial intelligence (AI) is revolutionizing stroke care by enhancing diagnosis, treatment, and outcome prediction. This review examines 505 original studies on AI applications in ischemic stroke, categorized into outcome prediction, stroke risk prediction, diagnosis, etiology prediction, and complication and comorbidity prediction. Outcome prediction, the most explored category, includes studies predicting functional outcomes, mortality, and recurrence, often achieving high accuracy and outperforming traditional methods. Stroke risk prediction models effectively integrate clinical and imaging data, improving assessments of both first-time and recurrent stroke risks. Diagnostic tools, such as automated imaging analysis and lesion segmentation, streamline acute stroke workflows, while AI models for large vessel occlusion detection demonstrate clinical utility. Etiology prediction focuses on identifying causes such as atrial fibrillation or cancer-associated thrombi, using imaging and thrombus analysis. Complication and comorbidity prediction models address stroke-associated pneumonia and acute kidney injury, aiding in risk stratification and resource allocation. While significant advancements have been made, challenges such as limited validation, ethical considerations, and the need for better data collection persist. This review highlights the advancements in AI applications for addressing key challenges in stroke care, demonstrating its potential to enhance precision medicine and improve patient outcomes.