Dataset Information

Machine learning-aided risk stratification in Philadelphia chromosome-positive acute lymphoblastic leukemia.

ABSTRACT: We used the eXtreme Gradient Boosting algorithm, an optimized gradient boosting machine learning library, and established a model to predict events in Philadelphia chromosome-positive acute lymphoblastic leukemia using a machine learning-aided method. A model was constructed using a training set (80%) and prediction was tested using a test set (20%). According to the feature importance score, BCR-ABL lineage, polymerase chain reaction value, age, and white blood cell count were identified as important features. These features were also confirmed by the permutation feature importance for the prediction using the test set. Both event-free survival and overall survival were clearly stratified according to risk groups categorized using these features: 80 and 100% in low risk (two or less factors), 42 and 47% in intermediate risk (three factors), and 0 and 10% in high risk (four factors) at 4?years. Machine learning-aided analysis was able to identify clinically useful prognostic factors using data from a relatively small number of patients.

SUBMITTER: Nishiwaki S

PROVIDER: S-EPMC7890949 | biostudies-literature | 2021 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning-aided risk stratification in Philadelphia chromosome-positive acute lymphoblastic leukemia.

Nishiwaki Satoshi S Sugiura Isamu I Koyama Daisuke D Ozawa Yukiyasu Y Osaki Masahide M Ishikawa Yuichi Y Kiyoi Hitoshi H

Biomarker research 20210218 1

We used the eXtreme Gradient Boosting algorithm, an optimized gradient boosting machine learning library, and established a model to predict events in Philadelphia chromosome-positive acute lymphoblastic leukemia using a machine learning-aided method. A model was constructed using a training set (80%) and prediction was tested using a test set (20%). According to the feature importance score, BCR-ABL lineage, polymerase chain reaction value, age, and white blood cell count were identified as imp ...[more]

PMID: 33602341

Similar Datasets

Project description:Promising results have been shown with the combination of ponatinib and chemotherapy in adults with Philadelphia chromosome-positive acute lymphoblastic leukemia (Ph+ ALL). The PONALFIL (Ponatinib With Chemotherapy for Young Adults Ph Positive Acute Lymphoblastic Leukemia) trial combined ponatinib (30 mg/d) with standard induction and consolidation chemotherapy followed by allogeneic hematopoietic stem cell transplant (alloHSCT) in newly diagnosed Ph+ ALL patients aged 18 to 60 years. Ponatinib was only given pre-emptively after alloHSCT. Primary end points were hematologic and molecular response before alloHSCT and event-free survival (EFS), including molecular relapse as event. Thirty patients (median age, 49 years; range, 19-59 years) entered the trial. All exhibited hematologic response, and alloHSCT was performed in 26 patients (20 in complete molecular response and 6 in major molecular response). Only 1 patient died (of graft-versus-host disease), and 5 patients exhibited molecular relapse after alloHSCT. No tyrosine kinase inhibitor was given after HSCT in 18 of 26 patients. Twenty-nine patients are alive (median follow-up, 2.1 years; range, 0.2-4.0 years), with 3-year EFS and overall survival (OS) of 70% (95% confidence interval, 51-89) and 96% (95% confidence interval, 89-100), respectively. Comparison of the PONALFIL and the ALLPh08 (Chemotherapy and Imatinib in Young Adults With Acute Lymphoblastic Leukemia Ph [BCR-ABL] Positive; same schedule, using imatinib as the tyrosine kinase inhibitor) trials by propensity score showed significant improvement in OS for patients in PONALFIL (3-year OS, 96% vs 53%; P = .002). The most frequent grade 3 to 4 adverse events were hematologic (42%), infectious (17%), and hepatic (22%), with only one vascular occlusive event. The combination of chemotherapy with ponatinib followed by alloHSCT is well tolerated, with encouraging EFS in adults with newly diagnosed Ph+ ALL. Cross-trial comparison suggests improvement vs imatinib (clinicaltrials.gov identifier #NCT02776605).

Dataset Information

Machine learning-aided risk stratification in Philadelphia chromosome-positive acute lymphoblastic leukemia.

Publications

Machine learning-aided risk stratification in Philadelphia chromosome-positive acute lymphoblastic leukemia.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets