Artificial intelligence-based prediction models for acute myeloid leukemia using real-life data: A DATAML registry study.
Acute myeloid leukemia
Artificial intelligence
Gradient boosting
Neural network
Prediction model
Journal
Leukemia research
ISSN: 1873-5835
Titre abrégé: Leuk Res
Pays: England
ID NLM: 7706787
Informations de publication
Date de publication:
09 Jan 2024
09 Jan 2024
Historique:
received:
29
08
2023
revised:
19
12
2023
accepted:
05
01
2024
medline:
13
1
2024
pubmed:
13
1
2024
entrez:
12
1
2024
Statut:
aheadofprint
Résumé
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.
Identifiants
pubmed: 38215555
pii: S0145-2126(24)00003-1
doi: 10.1016/j.leukres.2024.107437
pii:
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
107437Informations de copyright
Copyright © 2024. Published by Elsevier Ltd.
Déclaration de conflit d'intérêts
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.