Machine learning demonstrates that somatic mutations imprint invariant morphologic features in myelodysplastic syndromes

Morphological interpretation is the standard in diagnosing myelodysplastic syndrome (MDS), but it has limitations, such as varying reliability in pathologic evaluation and lack of integration with genetic data. Somatic events shape morphologic features, but the complexity of morphologic and genetic changes make clear associations challenging. This article interrogates novel clinical subtypes of MDS using a machine learning technique devised to identify patterns of co-occurrence among morphologic features and genomic events. We sequenced 1,079 MDS patients and analyzed bone marrow bone marrow: The soft, spongy tissue inside most bones. Blood cells are formed in the bone marrow. morphological alterations and other clinical features. A total of 1,929 somatic mutations were identified. Five distinct morphologic profiles with unique clinical characteristics were defined. 77% of higher-risk patients clustered in profile-1. All lower-risk patients clustered into the remaining 4 profiles: profile-2 was characterized by pancytopenia pancytopenia: A shortage of all types of blood cells - red blood cells, white blood cells, and platelets. , profile-3 by monocytosis, profile-4 by elevated megakaryocytes, and profile-5 by erythroid dysplasia. These profiles could also separate patients with different prognosis. Lower-risk MDS patients were classified into eight genetic signatures (e.g. signature-A had TET2 mutations, signature-B had both TET2 and SRSF2 mutations and signature-G had SF3B1 mutations) demonstrating association with specific morphologic profiles. Six morphologic profiles/genetic signatures' associations were confirmed in a separate analysis of an independent cohort. Our study demonstrates that non-random or even pathognomonic relationships between morphology morphology: The study of the structure and form of an organism or one of its parts. and genotype to define clinical features can be identified. This is the first comprehensive implementation of machine learning algorithms to elucidate potential intrinsic interdependencies among genetic lesions, morphologies, and clinical prognostic in attributes of MDS.