The group has developed new ways to objectively measure pain using Artificial Intelligence
A team of seven researchers from the BSICoS group at the I3A-Unizar (University of Zaragoza) has won the "Second Multimodal Sensing Grand Challenge for Next-Gen Pain Assessment" (AI4PAIN 2025). This international challenge was held in Australia as part of the ACM International Conference on Multimodal Interaction.
The Aragonese team prevailed over competitors from various countries, including the United States, Japan, India, Germany, and Australia. Their project demonstrated new ways to measure pain more objectively using artificial intelligence (AI). Their model combines AI with different biomarkers developed in previous years. "This biomarker," they explain, "offers a clinically objective value for pain assessment, which is especially important for people with communication difficulties."
Through a hybrid method combining deep learning and traditional machine learning with physiologically guided signal processing, the research team trained a neural network to detect patterns and applied explanatory machine learning techniques to select the optimal combination of biomarkers for pain detection. “Our model not only achieved high accuracy (F1 = 0.84 in validation), but also demonstrated the possibility of identifying objective pain markers through modulations in the cardiovascular system and micro-sweating triggered by the autonomic nervous system,” they explain.
The purpose of this research is to advance the development of objective pain biomarkers, a challenge that remains open in the scientific and medical fields.
More information is available on the University of Zaragoza website
