Machine Learning Improves Risk Stratification in Myelofibrosis: An Analysis of the Spanish Registry of Myelofibrosis
| Autor: | Mosquera Orgueira, Adrián, Pérez Encinas, Manuel, Hernández Sánchez, Alberto, González Martínez, Teresa, Arellano Rodrigo, Eduardo, Martínez Elicegui, Javier, Villaverde Ramiro, Ángela, Raya, José María, Ayala, Rosa, Ferrer Marín, Francisca, Fox, María Laura, Velez, Patricia, Mora, Elvira, Xicoy, Blanca, Mata Vázquez, María Isabel, García Fortes, María, Angona, Anna, Cuevas, Beatriz, Senín, María Alicia, Ramírez Payer, Angel, Ramírez, María José, Pérez López, Raúl, González de Villambrosía, Sonia, Martínez Valverde, Clara, Gómez Casares, María Teresa, García Hernández, Carmen, Gasior, Mercedes, Bellosillo Paricio, Beatriz, Steegmann, Juan Luis, Álvarez Larrán, Alberto, Hernández Rivas, Jesús María, Hernández Boluda, Juan Carlos, The Spanish MPN Group (GEMFIN). |
|---|---|
| Přispěvatelé: | Institut Català de la Salut, [Mosquera-Orgueira A, Pérez-Encinas M] Hospital Clínico Universitario, Santiago de Compostela, Spain. [Hernández-Sánchez A, González-Martínez T, Martínez-Elicegui J] Hospital Clínico, Salamanca, Spain. [Arellano-Rodrigo E] Hospital Clínic, Institut d’Investigacions Biomèdiques August Pi i Sunyer, Barcelona, Spain. [Fox ML] Vall d’Hebron Institute of Oncology (VHIO), Barcelona, Spain. Vall d’Hebron Hospital Universitari, Barcelona, Spain, Vall d'Hebron Barcelona Hospital Campus |
| Jazyk: | angličtina |
| Rok vydání: | 2023 |
| Předmět: |
Intel·ligència artificial - Aplicacions a la medicina
Pronòstic mèdic Mielofibrosi Immunology Myelofibrosis Neoplasms::Neoplasms by Histologic Type::Leukemia::Leukemia Myeloid::Leukemia Myeloid Acute [DISEASES] enfermedades hematológicas y linfáticas::enfermedades hematológicas::enfermedades de la médula ósea::trastornos mieloproliferativos [ENFERMEDADES] Cell Biology Hematology Prognosis Biochemistry Ciencias de la información::metodologías computacionales::algoritmos::inteligencia artificial::aprendizaje automático [CIENCIA DE LA INFORMACIÓN] neoplasias::neoplasias por tipo histológico::leucemia::leucemia mieloide::leucemia mieloide aguda [ENFERMEDADES] Aprenentatge automàtic Machine learning Sang - Malalties Hemic and Lymphatic Diseases::Hematologic Diseases::Bone Marrow Diseases::Myeloproliferative Disorders [DISEASES] Information Science::Computing Methodologies::Algorithms::Artificial Intelligence::Machine Learning [INFORMATION SCIENCE] |
| Zdroj: | Scientia |
| Popis: | Aprendizaje automático; Mielofibrosis Aprenentatge automàtic; Mielofibrosi Machine learning; Myelofibrosis Myelofibrosis (MF) is a myeloproliferative neoplasm (MPN) with heterogeneous clinical course. Allogeneic hematopoietic cell transplantation remains the only curative therapy, but its morbidity and mortality require careful candidate selection. Therefore, accurate disease risk prognostication is critical for treatment decision-making. We obtained registry data from patients diagnosed with MF in 60 Spanish institutions (N = 1386). These were randomly divided into a training set (80%) and a test set (20%). A machine learning (ML) technique (random forest) was used to model overall survival (OS) and leukemia-free survival (LFS) in the training set, and the results were validated in the test set. We derived the AIPSS-MF (Artificial Intelligence Prognostic Scoring System for Myelofibrosis) model, which was based on 8 clinical variables at diagnosis and achieved high accuracy in predicting OS (training set c-index, 0.750; test set c-index, 0.744) and LFS (training set c-index, 0.697; test set c-index, 0.703). No improvement was obtained with the inclusion of MPN driver mutations in the model. We were unable to adequately assess the potential benefit of including adverse cytogenetics or high-risk mutations due to the lack of these data in many patients. AIPSS-MF was superior to the IPSS regardless of MF subtype and age range and outperformed the MYSEC-PM in patients with secondary MF. In conclusion, we have developed a prediction model based exclusively on clinical variables that provides individualized prognostic estimates in patients with primary and secondary MF. The use of AIPSS-MF in combination with predictive models that incorporate genetic information may improve disease risk stratification. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|