Dataset Information

The LEukemia Artificial Intelligence Program (LEAP) in chronic myeloid leukemia in chronic phase: A model to improve patient outcomes.

ABSTRACT: Extreme gradient boosting methods outperform conventional machine-learning models. Here, we have developed the LEukemia Artificial intelligence Program (LEAP) with the extreme gradient boosting decision tree method for the optimal treatment recommendation of tyrosine kinase inhibitors (TKIs) in patients with chronic myeloid leukemia in chronic phase (CML-CP). A cohort of CML-CP patients was randomly divided into training/validation (N = 504) and test cohorts (N = 126). The training/validation cohort was used for 3-fold cross validation to develop the LEAP CML-CP model using 101 variables at diagnosis. The test cohort was then applied to the LEAP CML-CP model and an optimum TKI treatment was suggested for each patient. The area under the curve in the test cohort was 0.81899.Backward multivariate analysis identified age at diagnosis, the degree of comorbidities, and TKI recommended therapy by the LEAP CML-CP model as independent prognostic factors for overall survival. The bootstrapping method internally validated the association of the LEAP CML-CP recommendation with overall survival as an independent prognostic for overall survival. Selecting treatment according to the LEAP CML-CP personalized recommendations, in this model, is associated with better survival probability compared to treatment with a LEAP CML-CP non-recommended therapy. This approach may pave a way of new era of personalized treatment recommendations for patients with cancer.

SUBMITTER: Sasaki K

PROVIDER: S-EPMC9022629 | biostudies-literature | 2021 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

The LEukemia Artificial Intelligence Program (LEAP) in chronic myeloid leukemia in chronic phase: A model to improve patient outcomes.

Sasaki Koji K Jabbour Elias J EJ Ravandi Farhad F Konopleva Marina M Borthakur Gautam G Wierda William G WG Daver Naval N Takahashi Koichi K Naqvi Kiran K DiNardo Courtney C Montalban-Bravo Guillermo G Kanagal-Shamanna Rashmi R Issa Ghayas G Jain Preetesh P Skinner Jeffrey J Rios Mary B MB Pierce Sherry S Soltysiak Kelly A KA Sato Junya J Garcia-Manero Guillermo G Cortes Jorge E JE

American journal of hematology 20201203 2

Extreme gradient boosting methods outperform conventional machine-learning models. Here, we have developed the LEukemia Artificial intelligence Program (LEAP) with the extreme gradient boosting decision tree method for the optimal treatment recommendation of tyrosine kinase inhibitors (TKIs) in patients with chronic myeloid leukemia in chronic phase (CML-CP). A cohort of CML-CP patients was randomly divided into training/validation (N = 504) and test cohorts (N = 126). The training/validation co ...[more]

PMID: 33180322

Similar Datasets

Project description:BackgroundNavigating the complexity of chronic myeloid leukemia (CML) diagnosis and management poses significant challenges, including the need for accurate prediction of disease progression and response to treatment. Artificial intelligence (AI) presents a transformative approach that enables the development of sophisticated predictive models and personalized treatment strategies that enhance early detection and improve therapeutic interventions for better patient outcomes.MethodsAn extensive search was conducted to retrieve relevant articles from PubMed, Scopus, and Web of Science databases up to April 24, 2023. Data were collected using a standardized extraction form, and the results are presented in tables and graphs, showing frequencies and percentages. The authors adhered to the PRISMA-ScR checklist to ensure transparent reporting of the study.ResultsOf the 176 articles initially identified, 12 were selected for our study after removing duplicates and applying the inclusion and exclusion criteria. AI's primary applications of AI in managing CML included tumor diagnosis/classification (n = 9, 75%), prediction/prognosis (n = 2, 17%), and treatment (n = 1, 8%). For tumor diagnosis, AI is categorized into blood smear image-based (n = 5), clinical parameter-based (n = 2), and gene profiling-based (n = 2) approaches. The most commonly employed AI models include Support Vector Machine (SVM) (n = 5), eXtreme Gradient Boosting (XGBoost) (n = 4), and various neural network methods, such as Artificial Neural Network (ANN) (n = 3). Furthermore, Hybrid Convolutional Neural Network with Interactive Autodidactic School (HCNN-IAS) achieved 100% accuracy and sensitivity in organizing leukemia data types, whereas MayGAN attained 99.8% accuracy and high performance in diagnosing CML from blood smear images.ConclusionsAI offers groundbreaking insights and tools for enhancing prediction, prognosis, and personalized treatment in chronic myeloid leukemia. Integrated AI systems empower healthcare practitioners with advanced analytics, optimizing patient care and improving clinical outcomes in CML management.

Dataset Information

The LEukemia Artificial Intelligence Program (LEAP) in chronic myeloid leukemia in chronic phase: A model to improve patient outcomes.

Publications

The LEukemia Artificial Intelligence Program (LEAP) in chronic myeloid leukemia in chronic phase: A model to improve patient outcomes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets