Ultrasound Radiomics for Forecasting Adverse Cardiovascular Events
Objective
Assessing the effectiveness of ultrasound-based radiomics in predicting major adverse cardiovascular events (MACE) within 1 year after percutaneous coronary intervention (PCI) for acute coronary syndrome (ACS) patients.
Methods
161 ACS patients who underwent PCI were included, with 114 in the training set and 47 in the validation set. Echocardiography was conducted 3-7 days after PCI, and patients were followed up for 1 year. Radiomics features related to MACE were extracted to create the RAD score. An ultrasound personalized model was developed, incorporating RAD score, LVEF, LVGLS, and NT-ProBNP. The model’s predictive capacity was evaluated using ROC curves.
Results
Analysis showed RAD score and LVGLS as independent risk factors for MACE. The RAD score predicted MACE with AUC values of 0.85 and 0.86 in the training and validation sets. The ultrasound personalized model outperformed the clinical model, with AUC values of 0.88 and 0.92, compared to 0.72 and 0.80 respectively. DCA indicated a more favorable net clinical benefit with the ultrasound personalized model.
Conclusions
Ultrasound radiomics is a reliable tool for predicting MACE after PCI in ACS patients, providing quantifiable data for personalized clinical treatment.
PMID:39158954 | DOI:10.1111/echo.15907
Integrating Clinical Trials into Everyday Medical Practice
Clinical trials play a crucial role in developing safe and effective treatments. Our AI-driven platform, DocSym, consolidates ICD-11 standards, clinical protocols, and research into an easily accessible knowledge base for clinicians, extending the benefits of clinical trials into everyday medical practice.
Streamlining Healthcare Operations
In today’s healthcare environment, streamlining operations is vital. Our mobile apps support scheduling, monitoring treatments, and telemedicine, making it easier to manage patient care and expand services digitally. By utilizing AI, clinics can enhance their workflows, improve patient outcomes, and reduce paper routines.
Learn more about our solutions at aidevmd.com.
