Prediction of ineffectiveness of biological drugs
... using machine learning and explainable AI methods: data from the Austrian Biological Registry BioReg
Recent publication
The Division of Internal Medicine 2 at St. Pölten University Hospital took part in a study on the use of artificial intelligence to predict the efficacy of biological anti-rheumatic drugs. Various algorithms were trained and tested with data from the Austrian Biologics Register. Prediction models for five biologics were created and compared. The best was used for analysis and for identifiying factors that increase or decrease the risk of non-response. The use of artificial intelligence can support physicians in selecting the most effective medication. As the analysis also showed, the response or non-response to certain anti-rheumatic drugs is the result of a complex interplay of many factors. The work has been published open access in the journal "Arthritis Research and Therapy".
Ukalovic, D, Leeb, BF, Rintelen, B, Eichbauer-Sturm, G, Spellitz, P, Puchner, R, Herold, M, Stetter, M, Ferincz, V, Resch-Passini, J, Zwerina, J, Zimmermann-Rittereiser, M & Fritsch-Stork, R 2024, 'Prediction of ineffectiveness of biological drugs using machine learning and explainable AI methods: data from the Austrian Biological Registry BioReg', Arthritis Research and Therapy, vol. 26, no. 1, pp. 44. https://doi.org/10.1186/s13075-024-03277-x
Dr. Vera Ferincz BSc
Division of Internal Medicine 2 (University Hospital St. Pölten)