Search

Summary: Background: Transthoracic echocardiography (TTE) is the primary modality for diagnosing aortic stenosis (AS), yet it requires skilled operators and can be resource-intensive. We developed and validated an artificial intelligence (AI)-based system for evaluating AS that is effective in both resource-limited and advanced settings. Methods: We created a dual-pathway AI system for AS evaluation using a nationwide echocardiographic dataset (developmental dataset, n = 8427): 1) a deep learning (DL)-based AS continuum assessment algorithm using limited 2D TTE videos, and 2) automating conventional AS evaluation. We performed internal (internal test dataset [ITDS], n = 841) and external validation (distinct hospital dataset [DHDS], n = 1696; temporally distinct dataset [TDDS], n = 772) for diagnostic value across various stages of AS and prognostic value for composite endpoints (cardiovascular death, heart failure, and aortic valve replacement). Findings: The DL index for the AS continuum (DLi-ASc, range 0–100) increased with worsening AS severity and demonstrated excellent discrimination for any AS (AUC 0.91–0.99), significant AS (0.95–0.98), and severe AS (0.97–0.99). DLi-ASc was independent predictor for composite endpoint (adjusted hazard ratios 2.19, 1.64, and 1.61 per 10-point increase in ITDS, DHDS, and TDDS, respectively). Automatic measurement of conventional AS parameters demonstrated excellent correlation with manual measurement, resulting in high accuracy for AS staging (98.2% for ITDS, 82.1% for DHDS, and 96.8% for TDDS) and comparable prognostic value to manually-derived parameters. Interpretation: The AI-based system provides accurate and prognostically valuable AS assessment, suitable for various clinical settings. Further validation studies are planned to confirm its effectiveness across diverse environments. Funding: This work was supported by a grant from the Institute of Information & Communications Technology Planning & Evaluation (IITP) funded by the Korea government (Ministry of Science and ICT; MSIT, Republic of Korea) (No. 2022000972, Development of a Flexible Mobile Healthcare Software Platform Using 5G MEC); and the Medical AI Clinic Program through the National IT Industry Promotion Agency (NIPA) funded by the MSIT, Republic of Korea (Grant No.: H0904-24-1002).

BackgroundEfficient emergency patient transport systems, which are crucial for delivering timely medical care to individuals in critical situations, face certain challenges. To address this, CONNECT-AI (CONnected Network for EMS Comprehensive Technical-Support using Artificial Intelligence), a novel digital platform, was introduced. This artificial intelligence (AI)–based network provides comprehensive technical support for the real-time sharing of medical information at the prehospital stage. ObjectiveThis study aimed to evaluate the effectiveness of this system in reducing patient transport delays. MethodsThe CONNECT-AI system provided 3 key AI services to prehospital care providers by collecting real-time patient data from the scene and hospital resource information, such as bed occupancy and the availability of emergency surgeries or procedures, using 5G communication technology and internet of things devices. These services included guidance on first aid, prediction of critically ill patients, and recommendation of the optimal transfer hospital. In addition, the platform offered emergency department medical staff real-time clinical information, including live video of patients during transport to the hospital. This community-based, nonrandomized controlled intervention study was designed to evaluate the effectiveness of the CONNECT-AI system in 2 regions of South Korea, each of which operated an intervention and a control period, each lasting 16 weeks. The impact of the system was assessed based on the proportion of patients experiencing transfer delays. ResultsA total of 14,853 patients transported by public ambulance were finally selected for analysis. Overall, the median transport time was 10 (IQR 7-14) minutes in the intervention group and 9 (IQR 6-13) minutes in the control group. When comparing the incidence of transport time outliers (>75%), which was the primary outcome of this study, the rate was higher in the intervention group in region 1, but significantly reduced in region 2, with the overall outlier rate being higher in the intervention group (27.5%-29.7%, P=.04). However, for patients with fever or respiratory symptoms, the group using the system showed a statistically significant reduction in outlier cases (36.5%-30.1%, P=.01). For patients who received real-time acceptance signals from the hospital, the reduction in the percentage of 75% outliers was statistically significant compared with those without the system (27.5%-19.6%, P=.02). As a result of emergency department treatment, 1.5% of patients in the control group and 1.1% in the intervention group died (P=.14). In the system-guided optimal hospital transfer group, the mortality rate was significantly lower than in the control group (1.54%-0.64%, P=.01). ConclusionsThe present digital emergency medical system platform offers a novel approach to enhancing emergency patient transport by leveraging AI, real-time information sharing, and decision support. While the system demonstrated improvements for certain patient groups facing transfer challenges, further research and modifications are necessary to fully realize its benefits in diverse health care contexts. Trial RegistrationClinicalTrials.gov NCT04829279; https://clinicaltrials.gov/study/NCT04829279