Which therapy is best for which patient?
Personalized antineoplastic treatment is a crucial advancement in cancer management tailoring therapies according to individual patient biology. However, most commonly patients are still treated with a ‚one-size-fits-all‘ chemotherapy regimen since deciphering tumor biology and identifying potential markers of adverse risk is a challenging task and targetable molecular lesions are rare.
In our lab, we use supervised machine learning to predict response to therapy given individual patient biology. Our models are trained on large multi-center data sets of hematologic malignancies such as acute myeloid leukemia, where we currently cooperate with the German Study Alliance Leukemia, the German-Austrian AML Cooperative Group, and partners from the USA.
Our models automatically identify important patient features for outcome prediction, such as molecular and cytogenetic alterations, to provide a data-driven basis for patient management.
Apart from being highly accurate, our models have identified a novel marker of adverse risk in AML that has previously been unacknowledged: Mutations of IKZF1 – a tumor suppressor gene well known in acute lymphoblastic leukemia but insufficiently studied in AML. We went back to the lab and found a hotspot variant conferring adverse risk in AML that was confirmed as an independent predictor of poor outcomes in the clinical setting,
We now aim to expand our models to other hematologic and oncologic neoplasms such as acute lymphoblastic leukemia, multiple myeloma, and diffuse large b-cell lymphoma(among others). Stay tuned for more exciting advancements in machine-learning-guided response prediction!
References
Eckardt JN et al. Prediction of complete remission and survival in acute myeloid leukemia using supervised machine learning. Haematologica. 2023
https://www.haematologica.org/article/view/haematol.2021.280027
Eckardt JN et al. Age-stratified machine learning identifies divergent prognostic significance of molecular alterations in AML. Hemasphere. 2025
Eckardt JN et al. Mutated IKZF1 is an independent marker of adverse risk in acute myeloid leukemia. Leukemia. 2023
https://www.nature.com/articles/s41375-023-02061-1
Stasik S, Eckardt JN, et al. The IKZF1 N159S mutation is associated with poor outcome and a distinct molecular profile in adult patients with AML. British Journal of Haematology. 2025
https://onlinelibrary.wiley.com/doi/10.1111/bjh.20027
