Building healthcare AI that’s faster, smarter, and more trustworthy
Source: https://www.tue.nl/en/news-and-events/news-overview/23-03-2026-building-healthcare-ai-thats-faster-smarter-and-more-trustworthy Parent: https://www.tue.nl/en/research
Share
Turning advanced AI into usable solutions for healthcare
Building healthcare AI that’s faster, smarter, and more trustworthy
March 23, 2026
PhD researcher Israel Campero Jurado investigated how artificial intelligence can be developed in a way that is practical, efficient, and suitable for real healthcare environments.
Artificial Intelligence (AI) is increasingly used to support medical decision-making. From analyzing medical images to monitoring heart signals, AI systems are being used to help doctors detect patterns that might otherwise go unnoticed. However, building reliable medical AI often requires large amounts of computing power, expert knowledge, and development time. This makes many advanced AI techniques difficult to use in everyday clinical practice.
PhD researcher Israel Campero Jurado set out to address this challenge by improving automated machine learning (AutoML) An AutoML system automatically designs and optimizes AI models, potentially making the development of AI systems faster and more accessible. Yet in high-stakes domains such as healthcare, these systems are often too computationally expensive, difficult to adapt to real-world medical data, and insufficiently transparent.\ \ Campero Jurado defended his PhD thesis at the Department of Mathematics and Computer Science on Thursday, March 19.
Smarter ways to build AI systems
A central goal of Campero Jurado’s research was to make AutoML systems more efficient. He developed new search methods that allow computers to explore many possible AI models while respecting strict limits on time and computing resources. These strategies make it possible to discover effective models without performing unnecessary calculations.
The research also shows that AI systems can learn faster by reusing knowledge from previous experiments. By incorporating existing metadata and information generated by large language models, AutoML systems can search for solutions with better initial guesses, thus reducing the time needed to reach useful results.
Testing AI under realistic conditions
Another key contribution of the research concerns how AI systems are evaluated. Traditional benchmarking often requires long and computationally expensive experiments. Campero Jurado demonstrates that shorter evaluation runs—ranging from just 5 to 30 minutes—can still provide reliable comparisons between AI methods. This makes the development and testing of AI systems more sustainable and accessible, while still maintaining meaningful performance evaluation.
Applications in long-term heart monitoring
To demonstrate the practical value of the methods, his system was tested on real biomedical data from long-term electrocardiogram (ECG) monitoring. In this study, cardiac patients with chronic coronary syndrome (CCS) wore a thin, self-adhesive sensor patch on their chest (specifically the 5th intercostal space) which continuously recorded heart activity over the course of five days.\ \ Analyzing these recordings presented challenges, particularly as the signal quality varied depending on daily activities, movement, or sensor placement. Campero Jurado studied how the quality of these ECG signals changed over time and identified clear daily patterns in the recordings, such as higher signal quality during the night when movement is minimal.
By developing signal quality indicators based on heart rhythm and ECG waveform characteristics, Campero Jurado’s research can help in determining when data from wearable heart monitors is reliable enough for clinical analysis. This is important for long-term monitoring devices to provide information to doctors that can be trusted.\ \ His work also resulted in an interpretable AI system that automatically detects subtle abnormalities in ECG signals, including small deviations in the ST segment. These deviations are critical indicators of serious heart problems such as myocardial ischemia (reduced blood flow to the heart) or an acute myocardial infarction (heart attack).
Towards practical medical AI
Overall, Campero Jurado’s research shows that automated machine learning does not need excessive computational resources to produce effective outcomes. By combining efficient optimization methods, knowledge reuse, and realistic evaluation, AI systems can be both powerful and practical.\ \ As vital part of the INNO4HEALTH project, this research moves AI from a theoretical promise to a tool that is ready for use in the real world. The study provides proven digital tools that can now be integrated into the daily routines of hospitals and clinical workflows.
By making AI more efficient and easier to understand, this work helps bridge the gap between complex technology and the practical needs of patients and medical professionals. These systems are designed to support doctors in making faster, more accurate decisions, ultimately leading to better care for people with heart conditions.
\ PhD Israel Campero Jurado. Photo: Angeline Swinkels
- [### Promovendus
Israel Campero Jurado, department of Mathematics and Computer Science
Read more](https://www.linkedin.com/in/israel-campero-jurado-51619056/) - [### Thesis title
Innovations in Optimization and Applications in Healthcare
Read more](https://pure.tue.nl/ws/files/380686324/20260319_Campero_Jurado_hf.pdf) - ### Supervisors
Joaquin Vanschoren, Aarnout Brombacher
Written by
Bouri, Danai
(Communications Advisor M&CS)
More on Health
[March 13, 2026
Making homes more sustainable leads to better health for children
Research by TU/e and VU shows that better insulation and ventilation lead to important health benefits for children.
Read more](https://www.tue.nl/en/news-and-events/news-overview/13-03-2026-making-homes-more-sustainable-leads-to-better-health-for-children) [March 4, 2026
Giving Healthcare Professionals Creative Control in Digital Health
AI supported tools help healthcare professionals create personalized, gamified content that supports patient engagement and improves digital health experiences.
Read more](https://www.tue.nl/en/news-and-events/news-overview/04-03-2026-giving-healthcare-professionals-creative-control-in-digital-health) [February 27, 2026
When Online Experiences Shape Care
PhD researcher Jhon Cerón Guzmán examined how patients can better find relevant experiential knowledge in online health communities, supporting users and...
Read more](https://www.tue.nl/en/news-and-events/news-overview/27-02-2026-when-online-experiences-shape-care)
Latest news
[March 18, 2026
TU/e awards an honorary doctorate to Christian Borgs
Borgs is a world-leading researcher at the interface of mathematics, statistical physics, theoretical computer science, and AI for science.
Read more](https://www.tue.nl/en/news-and-events/news-overview/18-03-2026-tue-awards-an-honorary-doctorate-to-christian-borgs) [March 13, 2026
Municipality of Roermond and TU/e investigate collaboration
First potential project: housing for students and starters next to Roermond station
Read more](https://www.tue.nl/en/news-and-events/news-overview/13-03-2026-municipality-of-roermond-and-tue-investigate-collaboration) [March 13, 2026
Making homes more sustainable leads to better health for children
Research by TU/e and VU shows that better insulation and ventilation lead to important health benefits for children.
Read more](https://www.tue.nl/en/news-and-events/news-overview/13-03-2026-making-homes-more-sustainable-leads-to-better-health-for-children)
keep following us
[Socials
Experience life at our university on Instagram. With every week a different person taking over.](https://www.instagram.com/tue_campuslife/)[Video
YouTube
On our YouTube channel you find the latest videos and animations about research, education and working at TU/e.](https://www.youtube.com/user/tueindhoven)
- 1
- 2
- 3
Previous
Next
Previous
Next