Prediction of bone marrow fibrosis from complete blood count in myeloproliferative neoplasms (FIBOM-AI): a multicentre machine learning model development and validation study.

Date publication

juin 2026

Journal

The Lancet. Haematology

Auteurs

Membres identifiés du Cancéropôle Est :
Dr PAGLIUCA Simona

Tous les auteurs :
Donzel M, Khedimallah S, Barriere S, Gouband A, Aubert C, Bosselut N, Poullot E, Bezsera SM, Mansier O, Yilmaz N, Syrykh C, Hittinger X, Momenkhan S, Barraco F, Gilis L, Labussière-Wallet H, Brehon M, Chin-Yee B, Hsia C, Wang L, Zouaghi S, Sujobert P, Eveillard M, De Mas V, Tavitian S, Legros L, Parrens M, Flandrin-Gresta P, Meunier M, Freynet N, Roy L, Meignin V, Drevon L, Ranta D, Pagliuca S, Lippert E, Ianotto JC, Jallades L, Burroni B, Luque Paz D, Traverse-Glehen A, Chevalier S, Alcazer V

Lien Pubmed

https://www.ncbi.nlm.nih.gov/pubmed/42242261

Résumé

Bone marrow biopsy is essential for myeloproliferative neoplasms diagnosis, particularly for assessing bone marrow fibrosis. However, it is an invasive procedure that can be difficult to perform in some patients. This study aimed to develop an artificial intelligence (AI) model (FIBOM-AI) to predict grade 2-3 fibrosis using complete blood count (CBC) data and age.

Référence

Lancet Haematol. 2026 06;13(6):e396-e407