A machine learning model of response to hypomethylating agents in myelodysplastic syndromes

Nathan Radakovich; David A Sallman; Rena Buckstein; Andrew Brunner; Amy Dezern; Sudipto Mukerjee; Rami Komrokji; Najla Al-Ali; Jacob Shreve; Yazan Rouphail; Anne Parmentier; Alexandre Mamedov; Mohammed Siddiqui; Yihong Guan; Teodora Kuzmanovic; Metis Hasipek; Babal Jha; Jaroslaw P Maciejewski; Mikkael A Sekeres; Aziz Nazha

doi:10.1016/j.isci.2022.104931

A machine learning model of response to hypomethylating agents in myelodysplastic syndromes

iScience. 2022 Aug 12;25(10):104931. doi: 10.1016/j.isci.2022.104931. eCollection 2022 Oct 21.

Authors

Nathan Radakovich^{1

2}, David A Sallman³, Rena Buckstein⁴, Andrew Brunner⁵, Amy Dezern⁶, Sudipto Mukerjee⁷, Rami Komrokji³, Najla Al-Ali³, Jacob Shreve⁸, Yazan Rouphail⁹, Anne Parmentier⁴, Alexandre Mamedov⁴, Mohammed Siddiqui⁴, Yihong Guan¹⁰, Teodora Kuzmanovic¹⁰, Metis Hasipek¹⁰, Babal Jha¹⁰, Jaroslaw P Maciejewski¹⁰, Mikkael A Sekeres¹¹, Aziz Nazha¹²

Affiliations

¹ Leukemia Program, Department of Hematology and Medical Oncology, Taussig Cancer Institute, Cleveland Clinic, Cleveland, OH, USA.
² Cleveland Clinic Lerner College of Medicine of Case Western Reserve University, Cleveland, OH, USA.
³ Department of Malignant Hematology, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL, USA.
⁴ Odette Cancer Centre, Sunnybrook Health Sciences Centre, Toronto, ON, Canada.
⁵ Massachusetts General Hospital, Boston, MA, USA.
⁶ Johns Hopkins Sidney Kimmel Comprehensive Cancer Center, Baltimore, MD, USA.
⁷ Department of Hematology and Medical Oncology, Taussig Cancer Institute, Cleveland Clinic, Cleveland, OH, USA.
⁸ Department of Internal Medicine, Cleveland Clinic, Cleveland, OH, USA.
⁹ Ohio State University, Columbus, OH, USA.
¹⁰ Department of Translational Hematology and Oncology Research, Taussig Cancer Institute, Cleveland Clinic, Cleveland, OH, USA.
¹¹ Division of Hematology, Sylvester Comprehensive Cancer Center, University of Miami, Miami, FL, USA.
¹² Department of Oncology, Sidney Kimmel Cancer Center, Thomas Jefferson University, Philadelphia, PA, USA.

Abstract

Hypomethylating agents (HMA) prolong survival and improve cytopenias in individuals with higher-risk myelodysplastic syndrome (MDS). Only 30-40% of patients, however, respond to HMAs, and responses may not occur for more than 6 months after HMA initiation. We developed a model to more rapidly assess HMA response by analyzing early changes in patients' blood counts. Three institutions' data were used to develop a model that assessed patients' response to therapy 90 days after the initiation using serial blood counts. The model was developed with a training cohort of 424 patients from 2 institutions and validated on an independent cohort of 90 patients. The final model achieved an area under the receiver operating characteristic curve (AUROC) of 0.79 in the train/test group and 0.84 in the validation group. The model provides cohort-wide and individual-level explanations for model predictions, and model certainty can be interrogated to gauge the reliability of a given prediction.

Keywords: Drugs; artificial intelligence; cancer.