%0 Conference Paper %F Oral %T Online Verification through Model Checking of Medical Critical Intelligent Systems %+ Departamento de Engenharia Informática / Department of Informatics Engineering (DEI) %+ Centre de Recherche en Informatique de Paris 1 (CRI) %+ Ecole Supérieure d'Informatique Electronique Automatique [Paris] (ESIEA) %A Martins, Joao %A Barbosa, Raul %A Lourenco, Nuno %A Robin, Jacques %A Madeira, Henrique %< avec comité de lecture %B 2020 50th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W) %C Valencia, Spain %I IEEE %P 32-37 %8 2020-06-29 %D 2020 %R 10.1109/DSN-W50199.2020.00015 %K critical systems intelligent systems verification model checking medical risk scores %K critical systems %K intelligent systems %K verification %K model checking %K medical risk scores %Z Computer Science [cs]Conference papers %X Software systems based on Artificial Intelligence (AI) and Machine Learning (ML) are being widely adopted in various scenarios, from online shopping to medical applications. When developing these systems, one needs to take into account that they should be verifiable to make sure that they are in accordance with their requirements. In this work we propose a framework to perform online verification of ML models, through the use of model checking. In order to validate the proposal, we apply it to the medical domain to help qualify medical risk. The results reveal that we can efficiently use the framework to determine if a patient is close to the decision boundary. This is particularly relevant since these patients are the ones that might be misclassified. As such, our framework can be used to help medical teams make better informed decisions. %G English %2 https://paris1.hal.science/hal-03967999/document %2 https://paris1.hal.science/hal-03967999/file/_DSML_2020__Verification_through_model_checking.pdf %L hal-03967999 %U https://paris1.hal.science/hal-03967999 %~ UNIV-PARIS1 %~ CRI %~ TEST3-HALCNRS