INPI grants software registration for Euploidy Prediction with Machine Learning
The software for non-invasive prediction of euploidy in human embryos received a computer program registration certificate granted by INPI, under process BR512026003650-0.
Brasilia, May 26, 2026
The Machine Learning Application for Non-Invasive Prediction of Euploidy in Human Embryos Based on Morphokinetic Data software received a computer program registration certificate granted by the Brazilian National Institute of Industrial Property (INPI) under process BR512026003650-0, published in the Industrial Property Gazette (RPI) No. 2890, dated May 26, 2026.
The product was developed by Maria Eduarda dos Santos Abritta Ferreira and Sabrina Caldas Berno, under the supervision of Prof. George Marsicano Corrêa , within the Artificial intelligence and data analysis for digital transformation project. The registration was granted with Fundação Universidade de Brasília (UnB) as the rights holder.
The software uses Artificial Intelligence and Machine Learning techniques to predict embryonic euploidy in in vitro fertilization treatments, based on the automated analysis of morphokinetic and morphological data obtained from continuous embryonic monitoring systems (Time-Lapse). The model, based on an Artificial Neural Network of the Multilayer Perceptron (MLP) type, achieved 88.2% accuracy and AUC of 0.944, and uses the LIME method to make predictions interpretable — an essential requirement in the biomedical context.
Intended for assisted reproduction clinics, embryologists, researchers, and fertility centers, the system serves as a clinical decision-support tool for embryo selection. Unlike existing market solutions — which rely mostly on proprietary scores or subjective morphological analysis — the program employs statistically trained and validated models combined with explainability methods. More information is available on the product page at CEDIS .
The INPI registration secures legal protection of the computer program for 50 years, as established by Law No. 9.609/1998.
Registration Information
- Program title: Machine Learning Application for Non-Invasive Prediction of Euploidy in Human Embryos Based on Morphokinetic Data
- Process: BR512026003650-0
- Publication: RPI No. 2890, dated May 26, 2026
- Publisher: Brazilian National Institute of Industrial Property (INPI)