Prediction model for drug response of acute myeloid leukemia patients

Quang Thinh Trac; Yudi Pawitan; Tian Mou; Tom Erkers; Päivi Östling; Anna Bohlin; Albin Österroos; Mattias Vesterlund; Rozbeh Jafari; Ioannis Siavelis; Helena Bäckvall; Santeri Kiviluoto; Lukas M Orre; Mattias Rantalainen; Janne Lehtiö; Sören Lehmann; Olli Kallioniemi; Trung Nghia Vu

doi:10.1038/s41698-023-00374-z

Prediction model for drug response of acute myeloid leukemia patients

NPJ Precis Oncol. 2023 Mar 24;7(1):32. doi: 10.1038/s41698-023-00374-z.

Authors

Quang Thinh Trac¹, Yudi Pawitan¹, Tian Mou², Tom Erkers³, Päivi Östling^{3

4}, Anna Bohlin⁵, Albin Österroos⁶, Mattias Vesterlund³, Rozbeh Jafari³, Ioannis Siavelis³, Helena Bäckvall³, Santeri Kiviluoto³, Lukas M Orre³, Mattias Rantalainen¹, Janne Lehtiö³, Sören Lehmann^{5

6}, Olli Kallioniemi^{3

4}, Trung Nghia Vu⁷

Affiliations

¹ Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden.
² School of Biomedical Engineering, Shenzhen University, Shenzhen, China.
³ Department of Oncology Pathology, Karolinska Institutet, Science for Life Laboratory, Stockholm, Sweden.
⁴ Institute for Molecular Medicine Finland, University of Helsinki, Helsinki, Finland.
⁵ Department of Medicine Huddinge, Karolinska Institutet, Unit for Hematology, Karolinska University Hospital Huddinge, Stockholm, Sweden.
⁶ Department of Medical Sciences, Hematology, Uppsala University Hospital, Uppsala, Sweden.
⁷ Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden. trungnghia.vu@ki.se.

Abstract

Despite some encouraging successes, predicting the therapy response of acute myeloid leukemia (AML) patients remains highly challenging due to tumor heterogeneity. Here we aim to develop and validate MDREAM, a robust ensemble-based prediction model for drug response in AML based on an integration of omics data, including mutations and gene expression, and large-scale drug testing. Briefly, MDREAM is first trained in the BeatAML cohort (n = 278), and then validated in the BeatAML (n = 183) and two external cohorts, including a Swedish AML cohort (n = 45) and a relapsed/refractory acute leukemia cohort (n = 12). The final prediction is based on 122 ensemble models, each corresponding to a drug. A confidence score metric is used to convey the uncertainty of predictions; among predictions with a confidence score >0.75, the validated proportion of good responders is 77%. The Spearman correlations between the predicted and the observed drug response are 0.68 (95% CI: [0.64, 0.68]) in the BeatAML validation set, -0.49 (95% CI: [-0.53, -0.44]) in the Swedish cohort and 0.59 (95% CI: [0.51, 0.67]) in the relapsed/refractory cohort. A web-based implementation of MDREAM is publicly available at https://www.meb.ki.se/shiny/truvu/MDREAM/ .