Publications

(Version 1.00 – March 30 th , 2026) Ms. Yumi HEO The problem with imbalanced data Imagine training a model to detect a rare disease from medical scans. Your dataset has 950 healthy scans and only 50 diseased ones. If you train naively, the model quickly learns to simply predict "healthy" every single time. It could achieve 95% accuracy but this is completely useless. This is the class imbalance problem. It is everywhere in the real world and it's also common in image datasets

We are thrilled to announce that AITIS’ Skin Cancer App and Wound Care App have officially received EUDAMED approval, marking a significant milestone in our mission to deliver safe and effective digital health solutions. What is EUDAMED? EUDAMED (European Database on Medical Devices) is the European Union’s centralized database designed to enhance transparency and traceability of medical devices and software. Managed under the EU Medical Device Regulation (MDR), EUDAMED store

This year, AITIS attended the Health Valley Event 2026 in Nijmegen, one of the leading innovation events in the Netherlands focused on the future of healthcare. The event brought together professionals from across healthcare, technology, research, government and the social domain to explore new ideas and collaborations that can help shape tomorrow’s healthcare system. Throughout the day, the focus was on innovation, collaboration and the transformation of healthcare, with man

Last week, AITIS participated in the Woodlands Health Research Day 2026 in Singapore, an event dedicated to fostering curiosity and empowering emerging researchers to enhance clinical practice through collaborative research and innovation. Showcasing digital health and preventive care During the event, AITIS hosted a booth where we presented several of our digital healthcare solutions. Visitors had the opportunity to learn more about our Skin Cancer App and Wound Care App, bo

(Version 1.00 – February 19 th , 2026) Mr. Guy THANAPONPAIBOON Ever wonder how your phone understands your voice in a noisy room, or how music streaming services instantly recognize a song from just a few seconds of audio? The magic often lies in something called signal and sound preprocessing. It's the unsung hero that takes raw, messy audio and transforms it into something intelligent systems can actually understand and use. It's the essential preparation that transforms ra

Ms. Femke MELENHORST I started the programme with two clear goals: to move more and eat healthier. Two things I had been thinking about for a while, but never really approached in a structured way. What I ultimately gained from the Greenhabit programme went far beyond just moving more and eating healthier. Along the way, I realised that the programme was also about becoming more aware of all the different choices I make in my life. I hadn’t expected that beforehand.   Among

(Version 1.00 – January 15 th , 2026) Mr. Jorge RODRIGUEZ When data scientists build a model, the first stop is usually the evaluation metric mean squared error, log-loss, F1 score, and the like. We track performance across training, validation, and test sets to check that the model isn’t just memorizing patterns but can actually generalize. On paper, that’s what makes a model look “ready” for the real world. But the world outside of datasets is messy and that’s where the gap

(Version 1.18 – January 07, 2026) Ms. Yumi HEO What is multilabel classification? Imagine classifying the colour of a single skin mole not just as light brown or dark brown but as both light brown and dark brown simultaneously. This is the core task of multilabel classification: training a machine learning model to assign multiple relevant labels to a single input. However, accurately evaluating this model often encounters a greater challenge than evaluating a standard classi