Clinical and Genomic-Based Decision Support System to Define the Optimal Timing of Allogeneic Hematopoietic Stem-Cell Transplantation in Patients With Myelodysplastic Syndromes

Abstract

Purpose: Allogeneic hematopoietic stem-cell transplantation (HSCT) is the only potentially curative treatment for patients with myelodysplastic syndromes (MDS). Several issues must be considered when evaluating the benefits and risks of HSCT for patients with MDS, with the timing of transplantation being a crucial question. Here, we aimed to develop and validate a decision support system to define the optimal timing of HSCT for patients with MDS on the basis of clinical and genomic information as provided by the Molecular International Prognostic Scoring System (IPSS-M).

Patients and methods: We studied a retrospective population of 7,118 patients, stratified into training and validation cohorts. A decision strategy was built to estimate the average survival over an 8-year time horizon (restricted mean survival time [RMST]) for each combination of clinical and genomic covariates and to determine the optimal transplantation policy by comparing different strategies.

Results: Under an IPSS-M based policy, patients with either low and moderate-low risk benefited from a delayed transplantation policy, whereas in those belonging to moderately high-, high- and very high-risk categories, immediate transplantation was associated with a prolonged life expectancy (RMST). Modeling decision analysis on IPSS-M versus conventional Revised IPSS (IPSS-R) changed the transplantation policy in a significant proportion of patients (15% of patient candidate to be immediately transplanted under an IPSS-R-based policy would benefit from a delayed strategy by IPSS-M, whereas 19% of candidates to delayed transplantation by IPSS-R would benefit from immediate HSCT by IPSS-M), resulting in a significant gain-in-life expectancy under an IPSS-M-based policy (P = .001).

Conclusion: These results provide evidence for the clinical relevance of including genomic features into the transplantation decision making process, allowing personalizing the hazards and effectiveness of HSCT in patients with MDS.

FIG 1.

DSS to define optimal timing of HSCT in patients with MDS stratified according to IPSS-M criteria. DSS, decision support system; HSCT, allogeneic hematopoietic stem-cell transplantation; IPSS-M, Molecular International Prognostic Scoring System; MDS, myelodysplastic syndromes; QALY, quality-adjusted life years.

FIG 2.

(A-D) Probability of overall survival and risk of leukemia evolution in the nontransplant study population stratified into training (A,B) and validation (C,D) cohorts. (E-H) Probability of post-transplantation survival and risk of disease relapse after transplant in the study population stratified into training (E,F) and validation (G,H) cohorts. OS, overall survival.

FIG 3.

IPSS-M–based transplantation policy in patients with MDS ((A) training cohort; (B) validation cohort). The decision model on the basis of microsimulation can be thought of as simulating a hypothetical randomized clinical trial where patients are randomly assigned to receive HSCT at different time points on diagnosis of MDS (in the x-axis). Results were used to estimate the average survival time (RMST, in the y-axis) over an 8-year time horizon. The primary emphasis in our decision analysis is on the shape of the curves, which captures the underlying relationship between HSCT timing and the corresponding RMST for different patient profiles. Hence, the width of the 95% CIs depicted as the colored area on the y-axis provides essential information about the overall probability of survival for a patient with a specific age and molecular profile but is of lesser significance for the final results and interpretation of the decision analysis. The interpretation of the figure is centered around the shape of the curves rather than the height or range of the curves themselves. It is therefore important to consider the 95% CI with respect to the optimal policies (on the x-axis), which, for each age group and IPSS-M category, defines the optimal transplantation policy (denoted with a solid line). QoL adjustments were made by incorporating utilities into the estimation of average survival time. The optimal timing for HSCT and the corresponding 95% CI from the model are presented in tabular format in the Data Supplement (File S4). HSCT, allogeneic hematopoietic stem-cell transplantation; IPSS-M, Molecular International Prognostic Scoring System; MDS, myelodysplastic syndromes; QoL, quality of life; RMST, restricted mean survival time.

FIG 4.

IPSS-R–based transplantation policy in patients with MDS ((A) training cohort; (B) validation cohort). The decision model on the basis of microsimulation can be thought of as simulating a hypothetical randomized clinical trial where patients are randomly assigned to receive HSCT at different time points on diagnosis of MDS (in the x-axis). Results were used to estimate the average survival time (RMST, in the y-axis) over an 8-year time horizon. The primary emphasis in our decision analysis is on the shape of the curves, which captures the underlying relationship between HSCT timing and the corresponding RMST for different patient profiles. Hence, the width of the 95% CIs depicted as the colored area on the y-axis provides essential information about the overall probability of survival for a patient with a specific age and molecular profile but is of lesser significance for the final results and interpretation of the decision analysis. The interpretation of the figure is centered around the shape of the curves rather than the height or range of the curves themselves. It is therefore important to consider the 95% CI with respect to the optimal policies (on the x-axis), which, for each age group and IPSS-R category, defines the optimal transplantation policy (denoted with a solid line). QoL adjustments were made by incorporating utilities into the estimation of average survival time. HSCT, allogeneic hematopoietic stem-cell transplantation; IPSS-R, Revised International Prognostic Scoring System; MDS, myelodysplastic syndromes; QoL, quality of life; RMST, restricted mean survival time.

FIG 5.

Comparison of IPSS-R versus IPSS-M transplantation policy. (A) Whole MDS population potentially eligible for HSCT (n = 3,172); (B) detailed description of change of transplantation policy at the individual patient level, according to the risk restratification by IPSS-M criteria. HSCT, allogeneic hematopoietic stem-cell transplantation; IPSS-M, Molecular International Prognostic Scoring System; IPSS-R, Revised IPSS; MDS, myelodysplastic syndromes.