Imagine a smart filter that looks at a patient's medical records, X-rays, and even the sound of their breathing to figure out exactly which type of lung disease they have. Instead of a one-size-fits-all approach, it compares a patient to thousands of similar cases across Europe to find the best treatment. It's like having a global panel of experts instantly analyzing every piece of a patient's data to avoid guesswork.
Respiratory disease diagnosis is often slow and fragmented, relying on separate exams over time. This leads to unnecessary testing, ineffective treatments, and inefficient resource allocation in health systems.
A guideline-based decision support system, interpretable AI computational models, a secure scalable data infrastructure, and a personalized interactive dashboard.
If you are a device maker dealing with basic audio recording tools — this project developed a way to integrate lung auscultation recordings into AI models that improve diagnosis. This turns a simple listening tool into a high-value diagnostic asset.
If you are a software provider dealing with fragmented patient data — this project developed a guideline-based decision support system and interactive dashboards. This allows your platform to offer precise patient positioning based on multi-modal data.
If you are a biotech firm dealing with patient recruitment for lung cancer or ILD trials — this project developed computational models using -omics biomarkers and data from 7000 patients. This enables more accurate patient stratification for targeted therapies.
Based on available project data, specific pricing or cost details are not provided.
Yes, the project aims to deploy a scalable infrastructure based on industry-accepted protocols to support patients from any hospital, regardless of size or location.
Based on available project data, specific licensing terms are not mentioned, though the project focuses on a sustainable exploitation strategy.
The system is designed to manage data according to GDPR, FAIR principles, and ethical guidelines, utilizing the Digital Ethical Risk Assessment (DERA®).
The project is developing a secure, easy-to-integrate infrastructure using existing systems from KPMG and Yonalink.
The consortium is well-balanced for commercialization, featuring a 39% industry ratio with 7 industrial partners, including 4 SMEs. The presence of 18 partners across 10 countries suggests a strong European market reach and a mix of academic research (10 partners) and practical implementation expertise.
Contact INESC TEC in Portugal
Contact us to explore licensing opportunities for the AI4LUNGS stratification models.
