PURPOSE Patients with myelodysplastic syndromes (MDS) have a survival that can range from months to decades. Prognostic systems that incorporate advanced analytics of clinical, pathologic, and molecular data have the potential to more accurately and dynamically predict survival in patients receiving various therapies. METHODS A total of 1,471 MDS patients with comprehensively annotated clinical and molecular data were included in a training cohort and analyzed using machine learning techniques. A random survival algorithm was used to build a prognostic model, which was then validated in external cohorts. The accuracy of the proposed model, compared with other established models, was assessed using a concordance (c)index. RESULTS The median age for the training cohort was 71 years. Commonly mutated genes included SF3B1, TET2, and ASXL1. The algorithm identified chromosomal karyotype, platelet, hemoglobin levels, bone marrow blast percentage, age, other clinical variables, seven discrete gene mutations, and mutation number as having prognostic impact on overall and leukemia-free survivals. The model was validated in an independent external cohort of 465 patients, a cohort of patients with MDS treated in a prospective clinical trial, a cohort of patients with paired samples at different time points during the disease course, and a cohort of patients who underwent hematopoietic stem-cell transplantation. CONCLUSION A personalized prediction model on the basis of clinical and genomic data outperformed established prognostic models in MDS. The new model was dynamic, predicting survival and leukemia transformation probabilities at different time points that are unique for a given patient, and can upstage and downstage patients into more appropriate risk categories.
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.
Hospital systems, payers, and regulators have focused on reducing length of stay (LOS) and early readmission, with uncertain benefit. Interpretable machine learning (ML) may assist in transparently identifying the risk of important outcomes. We conducted a retrospective cohort study of hospitalizations at a tertiary academic medical center and its branches from January 2011 to May 2018. A consecutive sample of all hospitalizations in the study period were included. Algorithms were trained on medical, sociodemographic, and institutional variables to predict readmission, length of stay (LOS), and death within 48-72 h. Prediction performance was measured by area under the receiver operator characteristic curve (AUC), Brier score loss (BSL), which measures how well predicted probability matches observed probability, and other metrics. Interpretations were generated using multiple feature extraction algorithms. The study cohort included 1,485,880 hospitalizations for 708,089 unique patients (median age of 59 years, first and third quartiles (QI) [39, 73]; 55.6% female; 71% white). There were 211,022 30-day readmissions for an overall readmission rate of 14% (for patients ≥65 years: 16%). Median LOS, including observation and labor and delivery patients, was 2.94 days (QI [1.67, 5.34]), or, if these patients are excluded, 3.71 days (QI [2.15, 6.51]). Predictive performance was as follows: 30-day readmission (AUC 0.76/BSL 0.11); LOS > 5 days (AUC 0.84/BSL 0.15); death within 48-72 h (AUC 0.91/BSL 0.001). Explanatory diagrams showed factors that impacted each prediction.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.