Programa del congreso
Resúmenes y datos de las sesiones para este congreso. Seleccione una fecha o ubicación para mostrar solo las sesiones en ese día o ubicación. Seleccione una sola sesión para obtener una vista detallada (con resúmenes y descargas, si están disponibles).
|
Resumen diario |
| Sesión | |
|
Mi-S1.3-NeIn: Neuroingeniería y neurociencia computacional Lugar: Aula 0.02 Presidente de la sesión: Jesús Poza Crespo Presidente de la sesión: Alejandro Pascual Valdunciel | |
    | |
12:30 - 12:45
AI-powered clinical decision support system for monitoring patients with of age-related macular degeneration 1: Biomedical Image Technologies (BIT), ETSI Telecomunicación, Universidad Politécnica de Madrid, Madrid, Spain; 2: Instituto Provincial de Oftalmología, Hospital General Universitario Gregorio Marañon, Madrid, Spain; 3: Subdirección de Sistemas de Información , Hospital General Universitario Gregorio Marañón, Madrid, Spain; 4: Centro de Investigación Biomédica en Red de Bioingeniería, Biomateriales y Nanomedicina (CIBER-BBN), Madrid, Spain Age-related macular degeneration (AMD) is the main cause of legal blindness in elderly populations of developed countries. Its neovascular form, the most aggressive, requires frequent OCT monitoring and repeated anti-VEGF injections, creating high workload and variability in clinical decisions. We present STEP-AMD, an AI-powered clinical decision support system (CDSS) designed to assist in the follow-up of neovascular AMD patients. The system integrates OCT analysis with clinical data stored in a relational database and automatically generates structured PDF reports. These longitudinal reports summarize fluid biomarkers, visual acuity, treatment dates, and predicted therapy response, providing specialists with a comprehensive overview for personalized treatment planning. The system was developed and deployed at Hospital General Universitario Gregorio Marañón using a dataset of 503 OCT studies from 190 patients to train segmentation and prediction models. In a proof-of-concept study with two retina specialists evaluating 17 patients (21 eyes), STEP-AMD reduced average decision-making time by 39\%, improved inter-rater agreement (Cohen’s kappa from 0.42 to 0.71), and increased diagnostic accuracy on average from 0.42 to 0.56. Clinicians rated the AI-generated reports highly in usability and usefulness. These results highlight the potential of STEP-AMD to standardize follow-up, reduce workload, and improve efficiency in AMD management.
| |