A geno-clinical decision model for the diagnosis of myelodysplastic syndromes
Nathan Radakovich, Manja Meggendorfer, Luca Malcovati, C. Beau Hilton, Mikkael A. Sekeres, Jacob Shreve, Yazan Rouphail, Wencke Walter, Stephan Hütter, Anna Gallì, Sara Pozzi, Chiara Elena, Eric Padron, Michael R. Savona, Aaron T. Gerds, Sudipto Mukherjee, Yasunobu Nagata, Rami S. Komrokji, Babal K. Jha, Claudia Haferlach, Jaroslaw P. Maciejewski, Torsten Haferlach, Aziz Nazha
Abstract
The differential diagnosis of myeloid malignancies is challenging and subject to interobserver variability. We used clinical and next-generation sequencing (NGS) data to develop a machine learning model for the diagnosis of myeloid malignancies independent of bone marrow biopsy data based on a 3-institution, international cohort of patients. The model achieves high performance, with model interpretations indicating that it relies on factors similar to those used by clinicians. In addition, we describe associations between NGS findings and clinically important phenotypes and introduce the use of machine learning algorithms to elucidate clinicogenomic relationships.