Identifying the most effective therapy tailored to the individual patient is a long-sought goal in breast cancer treatment. Prof. MD. Michel Aguet, a molecular biologist at EPFL in Lausanne, wanted to find out if the Exploris AI-X engine could be used to optimize therapy for breast cancer patients. For some of these patients, surgery with radiation may be sufficient, but others may need additional treatments such as chemotherapy, additional hormone therapy or more. Many patients receive more treatments than necessary, often causing severe physical and psychological distress. Reliable prediction of breast cancer progression and patient survival is the key to individualized therapy.
Prof. Aguet and his team provided data from 1249 gene expression profiles of primary tumor samples with the goal of helping physicians make more informed decisions about which treatment is most appropriate for their patients and which therapy may not be necessary. Using our advanced AI-X engine, we were able to develop a model that provided accurate predictions of disease progression to optimize treatment plans. The accuracy of the model, as measured by the Kaplan-Meier curve, exceeded the results of the well-known Dutch Van de Vijver study (2002) data by 30%. This is a significant improvement, demonstrating the potential of AI-assisted treatment decisions in terms of safety and simplification.
 van de Vijver MJ, He YD, van't Veer LJ, Dai H, HartAA, Voskuil DW, Schreiber GJ, Peterse JL, Roberts C, Marton MJ, Parrish M,Atsma D, Witteveen A, Glas A, Delahaye L, van der Velde T, Bartelink H,Rodenhuis S, Rutgers ET, Friend SH, Bernards R. A gene-expression signature asa predictor of survival in breast cancer. N Engl J Med. 2002 Dec19;347(25):1999-2009. doi: 10.1056/NEJMoa021967. PMID: 12490681.