Browsing by Author "Sekeres, Mikkael A"

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    Genomic Biomarkers to Predict Resistance to Hypomethylating Agents in Patients With Myelodysplastic Syndromes Using Artificial Intelligence.
    (JCO precision oncology, 2019-01) Nazha, Aziz; Sekeres, Mikkael A; Bejar, Rafael; Rauh, Michael J; Othus, Megan; Komrokji, Rami S; Barnard, John; Hilton, Cameron B; Kerr, Cassandra M; Steensma, David P; DeZern, Amy; Roboz, Gail; Garcia-Manero, Guillermo; Erba, Harry; Ebert, Benjamin L; Maciejewski, Jaroslaw P
    PURPOSE:We developed an unbiased framework to study the association of several mutations in predicting resistance to hypomethylating agents (HMAs) in patients with myelodysplastic syndromes (MDS), analogous to consumer and commercial recommender systems in which customers who bought products A and B are likely to buy C: patients who have a mutation in gene A and gene B are likely to respond or not respond to HMAs. METHODS:We screened a cohort of 433 patients with MDS who received HMAs for the presence of common myeloid mutations in 29 genes that were obtained before the patients started therapy. The association between mutations and response was evaluated by the Apriori market basket analysis algorithm. Rules with the highest confidence (confidence that the association exists) and the highest lift (strength of the association) were chosen. We validated our biomarkers in samples from patients enrolled in the S1117 trial. RESULTS:Among 433 patients, 193 (45%) received azacitidine, 176 (40%) received decitabine, and 64 (15%) received HMA alone or in combination. The median age was 70 years (range, 31 to 100 years), and 28% were female. The median number of mutations per sample was three (range, zero to nine), and 176 patients (41%) had three or more mutations per sample. Association rules identified several genomic combinations as being highly associated with no response. These molecular signatures were present in 30% of patients with three or more mutations/sample with an accuracy rate of 87% in the training cohort and 93% in the validation cohort. CONCLUSION:Genomic biomarkers can identify, with high accuracy, approximately one third of patients with MDS who will not respond to HMAs. This study highlights the importance of machine learning technologies such as the recommender system algorithm in translating genomic data into useful clinical tools.
  • Thumbnail Image
    ItemOpen Access
    Relative survival following response to 7 + 3 versus azacytidine is similar in acute myeloid leukemia and high-risk myelodysplastic syndromes: an analysis of four SWOG studies.
    (Leukemia, 2019-02) Othus, Megan; Sekeres, Mikkael A; Nand, Sucha; Garcia-Manero, Guillermo; Appelbaum, Frederick R; Erba, Harry P; Estey, Eli
    Here we quantify and compare the absolute and relative overall survival (OS) benefits conveyed by complete remission (CR) in AML and high-risk MDS, and by CR with incomplete count recovery (CRi) in AML and by hematologic improvement (HI) in MDS, following treatment with 7 + 3 versus azacytidine. We compared patients receiving 7 + 3 in SWOG studies S0106 (n = 301) and S1203 (n = 261) enrolling adults ≤ 60 years, with patients receiving azacytidine therapies in S0703 (n = 133 AML patients ≥ 60) and S1117 (n = 277 MDS patients ≥ 18). Absolute survival benefit was evaluated with 1-year, 3-year, and median OS; relative benefit was evaluated with univariate and covariate-adjusted hazard ratios. CR conveyed a relative survival advantage in multivariable analysis, with a similar relative effect of CR across studies. CR also conferred an absolute survival benefit, but with a smaller magnitude of absolute benefit in the azacytidine trials. In AML, OS was similar for CRi and failure to achieve CR/CRi. In MDS, CR conferred a survival advantage versus HI and HI versus failure. The relative survival benefit of CR was similar regardless of initial therapy for AML or high-risk MDS. With both therapies, CR has a beneficial effect on survival compared with CRi or HI.