Roni Shouval

Prediction of Allogeneic Hematopoietic Stem-Cell Transplantation Mortality 100 Days After Transplantation Using a Machine Learning Algorithm: A European Group for Blood and Marrow Transplantation Acute Leukemia Working Party Retrospective Data Mining Study

PURPOSE Allogeneic hematopoietic stem-cell transplantation (HSCT) is potentially curative for acute leukemia (AL), but carries considerable risk. Machine learning algorithms, which are part of the data mining (DM) approach, may serve for transplantation-related mortality risk prediction. PATIENTS AND METHODS This work is a retrospective DM study on a cohort of 28,236 adult HSCT recipients from the AL registry of the European Group for Blood and Marrow Transplantation. The primary objective was prediction of overall mortality (OM) at 100 days after HSCT. Secondary objectives were estimation of nonrelapse mortality, leukemia-free survival, and overall survival at 2 years. Donor, recipient, and procedural characteristics were analyzed. The alternating decision tree machine learning algorithm was applied for model development on 70% of the data set and validated on the remaining data. RESULTS OM prevalence at day 100 was 13.9% (n=3,936). Of the 20 variables considered, 10 were selected by the model for OM prediction, and several interactions were discovered. By using a logistic transformation function, the crude score was transformed into individual probabilities for 100-day OM (range, 3% to 68%). The models discrimination for the primary objective performed better than the European Group for Blood and Marrow Transplantation score (area under the receiver operating characteristics curve, 0.701 v 0.646; P<.001). Calibration was excellent. Scores assigned were also predictive of secondary objectives. CONCLUSION The alternating decision tree model provides a robust tool for risk evaluation of patients with AL before HSCT, and is available online (http://bioinfo.lnx.biu.ac.il/∼bondi/web1.html). It is presented as a continuous probabilistic score for the prediction of day 100 OM, extending prediction to 2 years. The DM method has proved useful for clinical prediction in HSCT.

Isolated Extramedullary Relapse of Acute Leukemia after Allogeneic Stem Cell Transplantation: Different Kinetics and Better Prognosis than Systemic Relapse

Allogeneic stem cell transplantation (SCT) is curative treatment in patients with acute leukemia and myelodysplastic syndrome. However, recurrent disease is the major cause of treatment failure. Isolated extramedullary relapse (iEMR) after SCT is relatively rare and not well characterized. We performed a retrospective analysis of 566 consecutive patients with acute myeloid leukemia (n = 446) and acute lymphoblastic leukemia (ALL; n = 120) after SCT to study the incidence, risk factors, treatment options, and outcome of iEMR. The 5-year cumulative incidence of bone marrow relapse (BMR) and iEMR was 41.0% and 5.8%, respectively. iEMR occurred significantly later than BMR at 10 and 4 months, respectively (P < .001). Diagnosis of ALL (HR, 2.6; P = .05), poor cytogenetics (HR, 2.1; P = .06), and prior extramedullary disease (HR, 3.8; P = .002) were independent factors predicting iEMR. Acute and chronic graft-versus-host disease (GVHD) reduced the risk of BMR but did not protect against iEMR. Most patients with iEMR received systemic treatment combined with local radiation and donor lymphocyte infusions when feasible. The 3-year survival after relapse was 8.5% and 30.1% after BMR and iEMR, respectively (P = .002). Patients with a first iEMR continued to have recurrent EMRs, and only a minority progressed to BMR. Second iEMR was also common after first BMR and associated with longer survival than second BMR. iEMR is more frequent in patients with ALL and prior extramedullary disease. It occurs later than BMR and more commonly in patients with chronic GVHD, suggesting less effective graft-versus-leukemia effect in extramedullary sites. Second iEMR is common after a first iEMR but also after a first BMR. Long-term survival is feasible with aggressive treatment.

Prediction of Hematopoietic Stem Cell Transplantation Related Mortality- Lessons Learned from the In-Silico Approach: A European Society for Blood and Marrow Transplantation Acute Leukemia Working Party Data Mining Study

Models for prediction of allogeneic hematopoietic stem transplantation (HSCT) related mortality partially account for transplant risk. Improving predictive accuracy requires understating of prediction limiting factors, such as the statistical methodology used, number and quality of features collected, or simply the population size. Using an in-silico approach (i.e., iterative computerized simulations), based on machine learning (ML) algorithms, we set out to analyze these factors. A cohort of 25,923 adult acute leukemia patients from the European Society for Blood and Marrow Transplantation (EBMT) registry was analyzed. Predictive objective was non-relapse mortality (NRM) 100 days following HSCT. Thousands of prediction models were developed under varying conditions: increasing sample size, specific subpopulations and an increasing number of variables, which were selected and ranked by separate feature selection algorithms. Depending on the algorithm, predictive performance plateaued on a population size of 6,611–8,814 patients, reaching a maximal area under the receiver operator characteristic curve (AUC) of 0.67. AUCs’ of models developed on specific subpopulation ranged from 0.59 to 0.67 for patients in second complete remission and receiving reduced intensity conditioning, respectively. Only 3–5 variables were necessary to achieve near maximal AUCs. The top 3 ranking variables, shared by all algorithms were disease stage, donor type, and conditioning regimen. Our findings empirically demonstrate that with regards to NRM prediction, few variables “carry the weight” and that traditional HSCT data has been “worn out”. “Breaking through” the predictive boundaries will likely require additional types of inputs.

Validation of the acute leukemia-EBMT score for prediction of mortality following allogeneic stem cell transplantation in a multi-center GITMO cohort

Predictive models may help in determining the risk/benefit ratio of allogeneic hematopoietic stem cell transplantation (HSCT) in acute leukemia (AL). Using a machine‐learning algorithm we have previously developed the AL‐ European Society for Blood and Marrow Transplantation (EBMT) score for prediction of mortality following transplantation. We report here the first external validation of the AL‐EBMT score in a cohort of AL patients from the Italian national transplantation network. A total of 1848 patients transplanted between the years 2000‐2014 were analyzed. The median age was 45.9. Indications for HSCT were Acute Myeloid Leukemia (68.1%) and Acute Lymphoblastic Leukemia (31.9%). The majority of patients were in first complete remission (60.4%), and received myeloablative conditioning (81.3%). Median follow‐up was 2 years. The score was well‐calibrated for prediction of day 100 mortality and 2‐year overall survival (OS), leukemia free survival (LFS), and nonrelapse related mortality, with corresponding area under the receiver‐operator curves of 0.698, 0.651, 0.653, and 0.651, respectively. Increasing score intervals were associated with a decreasing probability of 2‐year OS and LFS. The highest scoring group was associated with a hazard ratio of 3.16, 2.8, and 2.27 for 2‐year OS, LFS, and NRM, respectively. In conclusion, the AL‐EBMT score identified three distinct risk groups and was predictive of OS. It is a valid tool for stratifying the risk of acute leukemia patients undergoing allogeneic HSCT.

Immunological effects of nilotinib prophylaxis after allogeneic stem cell transplantation in patients with advanced chronic myeloid leukemia or philadelphia chromosome-positive acute lymphoblastic leukemia

Allogeneic stem cell transplantation remains the standard treatment for resistant advanced chronic myeloid leukemia and Philadelphia chromosome–positive acute lymphoblastic leukemia. Relapse is the major cause of treatment failure in both diseases. Post-allo-SCT administration of TKIs could potentially reduce relapse rates, but concerns regarding their effect on immune reconstitution have been raised. We aimed to assess immune functions of 12 advanced CML and Ph+ ALL patients who received post-allo-SCT nilotinib. Lymphocyte subpopulations and their functional activities including T-cell response to mitogens, NK cytotoxic activity and thymic function, determined by quantification of the T cell receptor (TCR) excision circles (TREC) and TCR repertoire, were evaluated at several time points, including pre-nilotib-post-allo-SCT, and up to 365 days on nilotinib treatment. NK cells were the first to recover post allo-SCT. Concomitant to nilotinib administration, total lymphocyte counts and subpopulations gradually increased. CD8 T cells were rapidly reconstituted and continued to increase until day 180 post SCT, while CD4 T cells counts were low until 180−270 days post nilotinib treatment. T-cell response to mitogenic stimulation was not inhibited by nilotinib administration. Thymic activity, measured by TREC copies and surface membrane expression of 24 different TCR Vβ families, was evident in all patients at the end of follow-up after allo-SCT and nilotinib treatment. Finally, nilotinib did not inhibit NK cytotoxic activity. In conclusion, administration of nilotinib post allo-SCT, in attempt to reduce relapse rates or progression of Ph+ ALL and CML, did not jeopardize immune reconstitution or function following transplantation.

An integrative scoring system for survival prediction following umbilical cord blood transplantation in acute leukemia

Purpose: Survival of acute leukemia (AL) patients following umbilical cord blood transplantation (UCBT) is dependent on an array of individual features. Integrative models for risk assessment are lacking. We sought to develop a scoring system for prediction of overall survival (OS) and leukemia-free survival (LFS) at 2 years following UCBT in AL patients. Experimental Design: The study cohort included 3,140 pediatric and adult AL UCBT patients from the European Society of Blood and Marrow Transplantation and Eurocord registries. Patients received single or double cord blood units. The dataset was geographically split into a derivation (n = 2,362, 65%) and validation set (n = 778, 35%). Top predictors of OS were identified using the Random Survival Forest algorithm and introduced into a Cox regression model, which served for the construction of the UCBT risk score. Results: The score includes nine variables: disease status, diagnosis, cell dose, age, center experience, cytomegalovirus serostatus, degree of HLA mismatch, previous autograft, and anti-thymocyte globulin administration. Over the validation set an increasing score was associated with decreasing probabilities for 2 years OS and LFS, ranging from 70.21% [68.89–70.71, 95% confidence interval (CI)] and 64.76% (64.33–65.86, 95% CI) to 14.78% (10.91–17.41) and 18.11% (14.40–22.30), respectively. It stratified patients into six distinct risk groups. The scores discrimination (AUC) over multiple imputations of the validation set was 68.76 (68.19–69.04, range) and 65.78 (65.20–66.28) for 2 years OS and LFS, respectively. Conclusions: The UCBT score is a simple tool for risk stratification of AL patients undergoing UCBT. Widespread application of the score will require further independent validation. Clin Cancer Res; 23(21); 6478–86. ©2017 AACR.

Prognostic Scoring Systems in Allogeneic Hematopoietic Stem Cell Transplantation: Where Do We Stand?

Allogeneic hematopoietic stem cell transplantation is a potentially curative treatment for many hematologic disorders. Maximizing the benefit of transplantation for disease control while minimizing the risk for associated complications remains the fields leading challenge. This challenge has prompted the development of multiple prognostic scoring systems over the last 2 decades. Prognostic scores can be used for informed decision making, better patient counseling, design of interventional trials, and analysis of prospective and retrospective data. They are also helpful in treatment allocation and personalization according to predicted risk. A better understanding of the molecular and cytogenetic features of the disease, along with the advent of novel therapies, has increased the need for reliable prognostication of which patients will benefit most from transplantation. Here we review the clinical role of the prognostic systems currently in clinical use, examining both their strengths and their limitations.

Autologous Hematopoietic Stem Cell Transplantation for Systemic Sclerosis: A Systematic Review and Meta-Analysis

Autologous hematopoietic stem cell transplantation (AHSCT) has been proposed as a therapeutic modality for severe systemic sclerosis (SSc). We set out to systematically review and meta-analyze the efficacy and safety of AHSCT in SSc. Randomized controlled trials (RCTs) and retrospective studies comparing AHSCT with standard immunosuppressive therapy were included. Of 363 titles screened from multiple databases, 15 were extracted for further investigation, and 4 met inclusion criteria (3 RCTs and 1 retrospective analysis). The control arm was monthly cyclophosphamide in all the RCTs and the majority of patients in the retrospective analysis (69%). Compared with the control, AHSCT reduced all-cause mortality (risk ratio [RR], .5 [95% confidence interval, .33 to .75]) and improved skin thickness (modified Rodnan skin score mean difference [MD], 10.62 [95% CI, -14.21 to 7.03]), forced vital capacity (MD, 9.58 [95% CI, 3.89 to 15.18]), total lung capacity (MD, 6.36 [95% CI, 1.23 to 11.49]), and quality of life (physical 36-Item Short Form Health Survey [MD, 6.99 (95% CI, 2.79 to 11.18)]). Treatment-related mortality considerably varied between trials but was overall higher with AHSCT (RR, 9.00 [95% CI, 1.57 to 51.69]). The risk of bias for studies included in the analysis was low. Overall, AHSCT reduces the risk of all-cause mortality and has properties of a disease-modifying antirheumatic treatment in SSc. Further investigation is warranted for refining patient selection and timing of transplantation.

Interpretable Boosted Decision Trees for Prediction of Mortality Following Allogeneic Hematopoietic Stem Cell Transplantation

J Data Mining Genomics Proteomics ISSN: 2153-0602 JDMGP, an open access journal Volume 7 • Issue 1 • 1000184 Allogeneic (allo) hematopoietic stem transplantation (HSCT) is a potentially curative procedure for selected patients with hematological disease. Despite a reduction in transplant risk in recent years, morbidity and mortality remains substantial, making the decision of whom, how and when to transplant, of great importance [1].

Gender disparities in the functional significance of anemia among apparently healthy adults

Data on the functional impact of anemia on cardiorespiratory fitness (CRF) and survival in healthy individuals are limited. Our aim was to evaluate the association between anemia thresholds, low CRF, and survival in otherwise healthy adults.