Artificial intelligence-based prediction models for acute myeloid leukemia using real-life data: A DATAML registry study.

Autor: Didi I; École Polytechnique, Palaiseau, France., Alliot JM; Centre Hospitalo-Universitaire de Toulouse, Toulouse, France., Dumas PY; Centre Hospitalier Universitaire de Bordeaux, Service d'Hématologie Clinique et de Thérapie Cellulaire, Bordeaux, France; Université de Bordeaux, Bordeaux, France; Institut National de la Santé et de la Recherche Médicale, U1035 Bordeaux, France., Vergez F; Centre Hospitalo-Universitaire de Toulouse, Institut Universitaire du Cancer Toulouse-Oncopole, Laboratoire d'hématologie, Toulouse, France; Centre de Recherches en Cancérologie de Toulouse, Université Toulouse 3 Paul Sabatier, Toulouse, France., Tavitian S; Centre Hospitalo-Universitaire de Toulouse, Institut Universitaire du Cancer de Toulouse-Oncopole, Service d'hématologie, Toulouse, France., Largeaud L; Centre Hospitalo-Universitaire de Toulouse, Institut Universitaire du Cancer Toulouse-Oncopole, Laboratoire d'hématologie, Toulouse, France; Centre de Recherches en Cancérologie de Toulouse, Université Toulouse 3 Paul Sabatier, Toulouse, France., Bidet A; CHU Bordeaux, Laboratoire d'Hématologie Biologique, F-33000 Bordeaux, France., Rieu JB; Centre Hospitalo-Universitaire de Toulouse, Institut Universitaire du Cancer Toulouse-Oncopole, Laboratoire d'hématologie, Toulouse, France., Luquet I; Centre Hospitalo-Universitaire de Toulouse, Institut Universitaire du Cancer Toulouse-Oncopole, Laboratoire d'hématologie, Toulouse, France., Lechevalier N; CHU Bordeaux, Laboratoire d'Hématologie Biologique, F-33000 Bordeaux, France., Delabesse E; Centre Hospitalo-Universitaire de Toulouse, Institut Universitaire du Cancer Toulouse-Oncopole, Laboratoire d'hématologie, Toulouse, France; Centre de Recherches en Cancérologie de Toulouse, Université Toulouse 3 Paul Sabatier, Toulouse, France., Sarry A; Centre Hospitalo-Universitaire de Toulouse, Institut Universitaire du Cancer de Toulouse-Oncopole, Service d'hématologie, Toulouse, France., De Grande AC; Centre Hospitalier Universitaire de Bordeaux, Service d'Hématologie Clinique et de Thérapie Cellulaire, Bordeaux, France., Bérard E; Department of Epidemiology, Health Economics and Public Health, UMR 1295 CERPOP, University of Toulouse, INSERM, UPS, Toulouse University Hospital (CHU), Toulouse, France., Pigneux A; Centre Hospitalier Universitaire de Bordeaux, Service d'Hématologie Clinique et de Thérapie Cellulaire, Bordeaux, France; Université de Bordeaux, Bordeaux, France., Récher C; Centre de Recherches en Cancérologie de Toulouse, Université Toulouse 3 Paul Sabatier, Toulouse, France; Centre Hospitalo-Universitaire de Toulouse, Institut Universitaire du Cancer de Toulouse-Oncopole, Service d'hématologie, Toulouse, France., Simoncini D; IRIT UMR 5505-CNRS, Université Toulouse I Capitole, Toulouse, France., Bertoli S; Centre de Recherches en Cancérologie de Toulouse, Université Toulouse 3 Paul Sabatier, Toulouse, France; Centre Hospitalo-Universitaire de Toulouse, Institut Universitaire du Cancer de Toulouse-Oncopole, Service d'hématologie, Toulouse, France. Electronic address: bertoli.sarah@iuct-oncopole.fr.
Jazyk: angličtina
Zdroj: Leukemia research [Leuk Res] 2024 Jan; Vol. 136, pp. 107437. Date of Electronic Publication: 2024 Jan 09.
DOI: 10.1016/j.leukres.2024.107437
Abstrakt: We designed artificial intelligence-based prediction models (AIPM) using 52 diagnostic variables from 3687 patients included in the DATAML registry treated with intensive chemotherapy (IC, N = 3030) or azacitidine (AZA, N = 657) for an acute myeloid leukemia (AML). A neural network called multilayer perceptron (MLP) achieved a prediction accuracy for overall survival (OS) of 68.5% and 62.1% in the IC and AZA cohorts, respectively. The Boruta algorithm could select the most important variables for prediction without decreasing accuracy. Thirteen features were retained with this algorithm in the IC cohort: age, cytogenetic risk, white blood cells count, LDH, platelet count, albumin, MPO expression, mean corpuscular volume, CD117 expression, NPM1 mutation, AML status (de novo or secondary), multilineage dysplasia and ASXL1 mutation; and 7 variables in the AZA cohort: blood blasts, serum ferritin, CD56, LDH, hemoglobin, CD13 and disseminated intravascular coagulation (DIC). We believe that AIPM could help hematologists to deal with the huge amount of data available at diagnosis, enabling them to have an OS estimation and guide their treatment choice. Our registry-based AIPM could offer a large real-life dataset with original and exhaustive features and select a low number of diagnostic features with an equivalent accuracy of prediction, more appropriate to routine practice.
Competing Interests: Declaration of Competing Interest Pierre-Yves Dumas: Daiichi-Sankyo, Jazz Pharmaceutical, Astellas, Abbvie, Celgene, Janssen. Arnaud Pigneux: Grant/Research Support: Astellas, Roche; Speaker’s Bureau: Astellas, AbbVie, Gilead, Pfizer, Roche, Sanofi; Consultant: Jazz, AbbVie, Agios, BMS, Gilead, Novartis, Pfizer, Roche, Takeda. Christian Récher: Research grants from AbbVie, Amgen, Novartis, BMS-Celgene, Jazz Pharmaceuticals, Agios, Chugai, MaaT Pharma, Astellas, Roche, Daiichi-Sankyo and Iqvia; an advisory role for AbbVie, Janssen, Jazz Pharmaceuticals, Novartis, Celgene, Otsuka, Astellas, Daiichi-Sankyo, Macrogenics, Pfizer. Roche, Servier and Takeda. Sarah Bertoli: Abbvie, Jazz Pharmaceuticals, Daiichi-Sankyo, Sanofi, Astellas, Pfizer, Servier and BMS.
(Copyright © 2024 The Authors. Published by Elsevier Ltd.. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: